License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* Deadline Scheduling Class (SCHED_DEADLINE)
|
|
|
|
*
|
|
|
|
* Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
|
|
|
|
*
|
|
|
|
* Tasks that periodically executes their instances for less than their
|
|
|
|
* runtime won't miss any of their deadlines.
|
|
|
|
* Tasks that are not periodic or sporadic or that tries to execute more
|
|
|
|
* than their reserved bandwidth will be slowed down (and may potentially
|
|
|
|
* miss some of their deadlines), and won't affect any other task.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
* Juri Lelli <juri.lelli@gmail.com>,
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
* Michael Trimarchi <michael@amarulasolutions.com>,
|
|
|
|
* Fabio Checconi <fchecconi@gmail.com>
|
|
|
|
*/
|
|
|
|
|
2023-05-08 15:58:51 +08:00
|
|
|
#include <linux/cpuset.h>
|
|
|
|
|
2022-02-15 19:46:00 +08:00
|
|
|
/*
|
|
|
|
* Default limits for DL period; on the top end we guard against small util
|
|
|
|
* tasks still getting ridiculously long effective runtimes, on the bottom end we
|
|
|
|
* guard against timer DoS.
|
|
|
|
*/
|
|
|
|
static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
|
|
|
|
static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
static struct ctl_table sched_dl_sysctls[] = {
|
|
|
|
{
|
|
|
|
.procname = "sched_deadline_period_max_us",
|
|
|
|
.data = &sysctl_sched_dl_period_max,
|
|
|
|
.maxlen = sizeof(unsigned int),
|
|
|
|
.mode = 0644,
|
2022-06-07 18:18:07 +08:00
|
|
|
.proc_handler = proc_douintvec_minmax,
|
|
|
|
.extra1 = (void *)&sysctl_sched_dl_period_min,
|
2022-02-15 19:46:00 +08:00
|
|
|
},
|
|
|
|
{
|
|
|
|
.procname = "sched_deadline_period_min_us",
|
|
|
|
.data = &sysctl_sched_dl_period_min,
|
|
|
|
.maxlen = sizeof(unsigned int),
|
|
|
|
.mode = 0644,
|
2022-06-07 18:18:07 +08:00
|
|
|
.proc_handler = proc_douintvec_minmax,
|
|
|
|
.extra2 = (void *)&sysctl_sched_dl_period_max,
|
2022-02-15 19:46:00 +08:00
|
|
|
},
|
|
|
|
{}
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init sched_dl_sysctl_init(void)
|
|
|
|
{
|
|
|
|
register_sysctl_init("kernel", sched_dl_sysctls);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
late_initcall(sched_dl_sysctl_init);
|
|
|
|
#endif
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return container_of(dl_se, struct task_struct, dl);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
return container_of(dl_rq, struct rq, dl);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
struct rq *rq = task_rq(p);
|
|
|
|
|
|
|
|
return &rq->dl;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int on_dl_rq(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return !RB_EMPTY_NODE(&dl_se->rb_node);
|
|
|
|
}
|
|
|
|
|
2020-11-17 14:14:32 +08:00
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
|
|
static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return dl_se->pi_se;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return pi_of(dl_se) != dl_se;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline struct sched_dl_entity *pi_of(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return dl_se;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
static inline struct dl_bw *dl_bw_of(int i)
|
|
|
|
{
|
|
|
|
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
|
|
|
|
"sched RCU must be held");
|
|
|
|
return &cpu_rq(i)->rd->dl_bw;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int dl_bw_cpus(int i)
|
|
|
|
{
|
|
|
|
struct root_domain *rd = cpu_rq(i)->rd;
|
2020-05-20 21:42:39 +08:00
|
|
|
int cpus;
|
2017-06-22 02:22:01 +08:00
|
|
|
|
|
|
|
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
|
|
|
|
"sched RCU must be held");
|
2020-05-20 21:42:39 +08:00
|
|
|
|
|
|
|
if (cpumask_subset(rd->span, cpu_active_mask))
|
|
|
|
return cpumask_weight(rd->span);
|
|
|
|
|
|
|
|
cpus = 0;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
for_each_cpu_and(i, rd->span, cpu_active_mask)
|
|
|
|
cpus++;
|
|
|
|
|
|
|
|
return cpus;
|
|
|
|
}
|
2020-05-20 21:42:40 +08:00
|
|
|
|
2022-07-29 19:13:04 +08:00
|
|
|
static inline unsigned long __dl_bw_capacity(const struct cpumask *mask)
|
2020-05-20 21:42:40 +08:00
|
|
|
{
|
|
|
|
unsigned long cap = 0;
|
2022-07-29 19:13:04 +08:00
|
|
|
int i;
|
2020-05-20 21:42:40 +08:00
|
|
|
|
2022-07-29 19:13:04 +08:00
|
|
|
for_each_cpu_and(i, mask, cpu_active_mask)
|
2020-05-20 21:42:40 +08:00
|
|
|
cap += capacity_orig_of(i);
|
|
|
|
|
|
|
|
return cap;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX Fix: If 'rq->rd == def_root_domain' perform AC against capacity
|
|
|
|
* of the CPU the task is running on rather rd's \Sum CPU capacity.
|
|
|
|
*/
|
|
|
|
static inline unsigned long dl_bw_capacity(int i)
|
|
|
|
{
|
2022-07-29 19:13:03 +08:00
|
|
|
if (!sched_asym_cpucap_active() &&
|
2020-05-20 21:42:40 +08:00
|
|
|
capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
|
|
|
|
return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
|
|
|
|
} else {
|
2022-07-29 19:13:04 +08:00
|
|
|
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
|
|
|
|
"sched RCU must be held");
|
|
|
|
|
|
|
|
return __dl_bw_capacity(cpu_rq(i)->rd->span);
|
2020-05-20 21:42:40 +08:00
|
|
|
}
|
|
|
|
}
|
2020-10-08 23:48:46 +08:00
|
|
|
|
|
|
|
static inline bool dl_bw_visited(int cpu, u64 gen)
|
|
|
|
{
|
|
|
|
struct root_domain *rd = cpu_rq(cpu)->rd;
|
|
|
|
|
|
|
|
if (rd->visit_gen == gen)
|
|
|
|
return true;
|
|
|
|
|
|
|
|
rd->visit_gen = gen;
|
|
|
|
return false;
|
|
|
|
}
|
2022-03-03 02:34:29 +08:00
|
|
|
|
|
|
|
static inline
|
|
|
|
void __dl_update(struct dl_bw *dl_b, s64 bw)
|
|
|
|
{
|
|
|
|
struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
|
|
|
|
int i;
|
|
|
|
|
|
|
|
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
|
|
|
|
"sched RCU must be held");
|
|
|
|
for_each_cpu_and(i, rd->span, cpu_active_mask) {
|
|
|
|
struct rq *rq = cpu_rq(i);
|
|
|
|
|
|
|
|
rq->dl.extra_bw += bw;
|
|
|
|
}
|
|
|
|
}
|
2017-06-22 02:22:01 +08:00
|
|
|
#else
|
|
|
|
static inline struct dl_bw *dl_bw_of(int i)
|
|
|
|
{
|
|
|
|
return &cpu_rq(i)->dl.dl_bw;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int dl_bw_cpus(int i)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
2020-05-20 21:42:40 +08:00
|
|
|
|
|
|
|
static inline unsigned long dl_bw_capacity(int i)
|
|
|
|
{
|
|
|
|
return SCHED_CAPACITY_SCALE;
|
|
|
|
}
|
2020-10-08 23:48:46 +08:00
|
|
|
|
|
|
|
static inline bool dl_bw_visited(int cpu, u64 gen)
|
|
|
|
{
|
|
|
|
return false;
|
|
|
|
}
|
2022-03-03 02:34:29 +08:00
|
|
|
|
|
|
|
static inline
|
|
|
|
void __dl_update(struct dl_bw *dl_b, s64 bw)
|
|
|
|
{
|
|
|
|
struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
|
|
|
|
|
|
|
|
dl->extra_bw += bw;
|
|
|
|
}
|
2017-06-22 02:22:01 +08:00
|
|
|
#endif
|
|
|
|
|
2022-03-03 02:34:29 +08:00
|
|
|
static inline
|
|
|
|
void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
|
|
|
|
{
|
|
|
|
dl_b->total_bw -= tsk_bw;
|
|
|
|
__dl_update(dl_b, (s32)tsk_bw / cpus);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
|
|
|
|
{
|
|
|
|
dl_b->total_bw += tsk_bw;
|
|
|
|
__dl_update(dl_b, -((s32)tsk_bw / cpus));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool
|
|
|
|
__dl_overflow(struct dl_bw *dl_b, unsigned long cap, u64 old_bw, u64 new_bw)
|
|
|
|
{
|
|
|
|
return dl_b->bw != -1 &&
|
|
|
|
cap_scale(dl_b->bw, cap) < dl_b->total_bw - old_bw + new_bw;
|
|
|
|
}
|
|
|
|
|
2017-05-19 04:13:28 +08:00
|
|
|
static inline
|
2017-12-04 18:23:20 +08:00
|
|
|
void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
2017-05-19 04:13:28 +08:00
|
|
|
{
|
|
|
|
u64 old = dl_rq->running_bw;
|
|
|
|
|
2020-11-18 07:19:31 +08:00
|
|
|
lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
|
2017-05-19 04:13:28 +08:00
|
|
|
dl_rq->running_bw += dl_bw;
|
|
|
|
SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
|
2017-05-19 04:13:34 +08:00
|
|
|
SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
|
2017-12-04 18:23:19 +08:00
|
|
|
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
|
2017-12-20 22:37:26 +08:00
|
|
|
cpufreq_update_util(rq_of_dl_rq(dl_rq), 0);
|
2017-05-19 04:13:28 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
2017-12-04 18:23:20 +08:00
|
|
|
void __sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
2017-05-19 04:13:28 +08:00
|
|
|
{
|
|
|
|
u64 old = dl_rq->running_bw;
|
|
|
|
|
2020-11-18 07:19:31 +08:00
|
|
|
lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
|
2017-05-19 04:13:28 +08:00
|
|
|
dl_rq->running_bw -= dl_bw;
|
|
|
|
SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
|
|
|
|
if (dl_rq->running_bw > old)
|
|
|
|
dl_rq->running_bw = 0;
|
2017-12-04 18:23:19 +08:00
|
|
|
/* kick cpufreq (see the comment in kernel/sched/sched.h). */
|
2017-12-20 22:37:26 +08:00
|
|
|
cpufreq_update_util(rq_of_dl_rq(dl_rq), 0);
|
2017-05-19 04:13:28 +08:00
|
|
|
}
|
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
static inline
|
2017-12-04 18:23:20 +08:00
|
|
|
void __add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
2017-05-19 04:13:34 +08:00
|
|
|
{
|
|
|
|
u64 old = dl_rq->this_bw;
|
|
|
|
|
2020-11-18 07:19:31 +08:00
|
|
|
lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
|
2017-05-19 04:13:34 +08:00
|
|
|
dl_rq->this_bw += dl_bw;
|
|
|
|
SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
2017-12-04 18:23:20 +08:00
|
|
|
void __sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
|
2017-05-19 04:13:34 +08:00
|
|
|
{
|
|
|
|
u64 old = dl_rq->this_bw;
|
|
|
|
|
2020-11-18 07:19:31 +08:00
|
|
|
lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
|
2017-05-19 04:13:34 +08:00
|
|
|
dl_rq->this_bw -= dl_bw;
|
|
|
|
SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */
|
|
|
|
if (dl_rq->this_bw > old)
|
|
|
|
dl_rq->this_bw = 0;
|
|
|
|
SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
|
|
|
|
}
|
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
static inline
|
|
|
|
void add_rq_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
if (!dl_entity_is_special(dl_se))
|
|
|
|
__add_rq_bw(dl_se->dl_bw, dl_rq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void sub_rq_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
if (!dl_entity_is_special(dl_se))
|
|
|
|
__sub_rq_bw(dl_se->dl_bw, dl_rq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void add_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
if (!dl_entity_is_special(dl_se))
|
|
|
|
__add_running_bw(dl_se->dl_bw, dl_rq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
if (!dl_entity_is_special(dl_se))
|
|
|
|
__sub_running_bw(dl_se->dl_bw, dl_rq);
|
|
|
|
}
|
|
|
|
|
2020-02-28 18:03:29 +08:00
|
|
|
static void dl_change_utilization(struct task_struct *p, u64 new_bw)
|
2017-05-19 04:13:29 +08:00
|
|
|
{
|
2017-05-19 04:13:34 +08:00
|
|
|
struct rq *rq;
|
2017-05-19 04:13:29 +08:00
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
|
2017-12-04 18:23:20 +08:00
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
if (task_on_rq_queued(p))
|
2017-05-19 04:13:29 +08:00
|
|
|
return;
|
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
rq = task_rq(p);
|
|
|
|
if (p->dl.dl_non_contending) {
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(&p->dl, &rq->dl);
|
2017-05-19 04:13:34 +08:00
|
|
|
p->dl.dl_non_contending = 0;
|
|
|
|
/*
|
|
|
|
* If the timer handler is currently running and the
|
2021-03-18 20:38:50 +08:00
|
|
|
* timer cannot be canceled, inactive_task_timer()
|
2017-05-19 04:13:34 +08:00
|
|
|
* will see that dl_not_contending is not set, and
|
|
|
|
* will not touch the rq's active utilization,
|
|
|
|
* so we are still safe.
|
|
|
|
*/
|
|
|
|
if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
|
|
|
|
put_task_struct(p);
|
|
|
|
}
|
2017-12-04 18:23:20 +08:00
|
|
|
__sub_rq_bw(p->dl.dl_bw, &rq->dl);
|
|
|
|
__add_rq_bw(new_bw, &rq->dl);
|
2017-05-19 04:13:29 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The utilization of a task cannot be immediately removed from
|
|
|
|
* the rq active utilization (running_bw) when the task blocks.
|
|
|
|
* Instead, we have to wait for the so called "0-lag time".
|
|
|
|
*
|
|
|
|
* If a task blocks before the "0-lag time", a timer (the inactive
|
|
|
|
* timer) is armed, and running_bw is decreased when the timer
|
|
|
|
* fires.
|
|
|
|
*
|
|
|
|
* If the task wakes up again before the inactive timer fires,
|
2021-03-18 20:38:50 +08:00
|
|
|
* the timer is canceled, whereas if the task wakes up after the
|
2017-05-19 04:13:29 +08:00
|
|
|
* inactive timer fired (and running_bw has been decreased) the
|
|
|
|
* task's utilization has to be added to running_bw again.
|
|
|
|
* A flag in the deadline scheduling entity (dl_non_contending)
|
|
|
|
* is used to avoid race conditions between the inactive timer handler
|
|
|
|
* and task wakeups.
|
|
|
|
*
|
|
|
|
* The following diagram shows how running_bw is updated. A task is
|
|
|
|
* "ACTIVE" when its utilization contributes to running_bw; an
|
|
|
|
* "ACTIVE contending" task is in the TASK_RUNNING state, while an
|
|
|
|
* "ACTIVE non contending" task is a blocked task for which the "0-lag time"
|
|
|
|
* has not passed yet. An "INACTIVE" task is a task for which the "0-lag"
|
|
|
|
* time already passed, which does not contribute to running_bw anymore.
|
|
|
|
* +------------------+
|
|
|
|
* wakeup | ACTIVE |
|
|
|
|
* +------------------>+ contending |
|
|
|
|
* | add_running_bw | |
|
|
|
|
* | +----+------+------+
|
|
|
|
* | | ^
|
|
|
|
* | dequeue | |
|
|
|
|
* +--------+-------+ | |
|
|
|
|
* | | t >= 0-lag | | wakeup
|
|
|
|
* | INACTIVE |<---------------+ |
|
|
|
|
* | | sub_running_bw | |
|
|
|
|
* +--------+-------+ | |
|
|
|
|
* ^ | |
|
|
|
|
* | t < 0-lag | |
|
|
|
|
* | | |
|
|
|
|
* | V |
|
|
|
|
* | +----+------+------+
|
|
|
|
* | sub_running_bw | ACTIVE |
|
|
|
|
* +-------------------+ |
|
|
|
|
* inactive timer | non contending |
|
|
|
|
* fired +------------------+
|
|
|
|
*
|
|
|
|
* The task_non_contending() function is invoked when a task
|
|
|
|
* blocks, and checks if the 0-lag time already passed or
|
|
|
|
* not (in the first case, it directly updates running_bw;
|
|
|
|
* in the second case, it arms the inactive timer).
|
|
|
|
*
|
|
|
|
* The task_contending() function is invoked when a task wakes
|
|
|
|
* up, and checks if the task is still in the "ACTIVE non contending"
|
|
|
|
* state or not (in the second case, it updates running_bw).
|
|
|
|
*/
|
|
|
|
static void task_non_contending(struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
struct hrtimer *timer = &dl_se->inactive_timer;
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
s64 zerolag_time;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If this is a non-deadline task that has been boosted,
|
|
|
|
* do nothing
|
|
|
|
*/
|
|
|
|
if (dl_se->dl_runtime == 0)
|
|
|
|
return;
|
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
if (dl_entity_is_special(dl_se))
|
|
|
|
return;
|
|
|
|
|
2017-05-19 04:13:29 +08:00
|
|
|
WARN_ON(dl_se->dl_non_contending);
|
|
|
|
|
|
|
|
zerolag_time = dl_se->deadline -
|
|
|
|
div64_long((dl_se->runtime * dl_se->dl_period),
|
|
|
|
dl_se->dl_runtime);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Using relative times instead of the absolute "0-lag time"
|
|
|
|
* allows to simplify the code
|
|
|
|
*/
|
|
|
|
zerolag_time -= rq_clock(rq);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If the "0-lag time" already passed, decrease the active
|
|
|
|
* utilization now, instead of starting a timer
|
|
|
|
*/
|
2019-03-25 21:15:30 +08:00
|
|
|
if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
|
2017-05-19 04:13:29 +08:00
|
|
|
if (dl_task(p))
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(dl_se, dl_rq);
|
2021-06-11 16:28:17 +08:00
|
|
|
if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
|
2017-05-19 04:13:30 +08:00
|
|
|
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
|
|
|
|
|
2021-06-11 16:28:17 +08:00
|
|
|
if (READ_ONCE(p->__state) == TASK_DEAD)
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
2017-05-19 04:13:30 +08:00
|
|
|
raw_spin_lock(&dl_b->lock);
|
2017-09-07 18:09:30 +08:00
|
|
|
__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
|
2017-05-19 04:13:30 +08:00
|
|
|
raw_spin_unlock(&dl_b->lock);
|
2022-08-27 10:09:11 +08:00
|
|
|
__dl_clear_params(p);
|
2017-05-19 04:13:30 +08:00
|
|
|
}
|
2017-05-19 04:13:29 +08:00
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
dl_se->dl_non_contending = 1;
|
|
|
|
get_task_struct(p);
|
2019-07-31 18:37:15 +08:00
|
|
|
hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
|
2017-05-19 04:13:29 +08:00
|
|
|
}
|
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
static void task_contending(struct sched_dl_entity *dl_se, int flags)
|
2017-05-19 04:13:29 +08:00
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If this is a non-deadline task that has been boosted,
|
|
|
|
* do nothing
|
|
|
|
*/
|
|
|
|
if (dl_se->dl_runtime == 0)
|
|
|
|
return;
|
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
if (flags & ENQUEUE_MIGRATED)
|
2017-12-04 18:23:20 +08:00
|
|
|
add_rq_bw(dl_se, dl_rq);
|
2017-05-19 04:13:34 +08:00
|
|
|
|
2017-05-19 04:13:29 +08:00
|
|
|
if (dl_se->dl_non_contending) {
|
|
|
|
dl_se->dl_non_contending = 0;
|
|
|
|
/*
|
|
|
|
* If the timer handler is currently running and the
|
2021-03-18 20:38:50 +08:00
|
|
|
* timer cannot be canceled, inactive_task_timer()
|
2017-05-19 04:13:29 +08:00
|
|
|
* will see that dl_not_contending is not set, and
|
|
|
|
* will not touch the rq's active utilization,
|
|
|
|
* so we are still safe.
|
|
|
|
*/
|
|
|
|
if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
|
|
|
|
put_task_struct(dl_task_of(dl_se));
|
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Since "dl_non_contending" is not set, the
|
|
|
|
* task's utilization has already been removed from
|
|
|
|
* active utilization (either when the task blocked,
|
|
|
|
* when the "inactive timer" fired).
|
|
|
|
* So, add it back.
|
|
|
|
*/
|
2017-12-04 18:23:20 +08:00
|
|
|
add_running_bw(dl_se, dl_rq);
|
2017-05-19 04:13:29 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
|
2022-03-03 02:34:31 +08:00
|
|
|
return rb_first_cached(&dl_rq->root) == &dl_se->rb_node;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2020-02-28 18:03:29 +08:00
|
|
|
static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
|
|
|
|
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
void init_dl_bw(struct dl_bw *dl_b)
|
|
|
|
{
|
|
|
|
raw_spin_lock_init(&dl_b->lock);
|
2013-12-17 19:44:49 +08:00
|
|
|
if (global_rt_runtime() == RUNTIME_INF)
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
dl_b->bw = -1;
|
|
|
|
else
|
2013-12-17 19:44:49 +08:00
|
|
|
dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
dl_b->total_bw = 0;
|
|
|
|
}
|
|
|
|
|
2015-03-03 19:50:27 +08:00
|
|
|
void init_dl_rq(struct dl_rq *dl_rq)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2017-09-09 07:14:58 +08:00
|
|
|
dl_rq->root = RB_ROOT_CACHED;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/* zero means no -deadline tasks */
|
|
|
|
dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
|
|
|
|
|
|
|
|
dl_rq->dl_nr_migratory = 0;
|
|
|
|
dl_rq->overloaded = 0;
|
2017-09-09 07:14:58 +08:00
|
|
|
dl_rq->pushable_dl_tasks_root = RB_ROOT_CACHED;
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
#else
|
|
|
|
init_dl_bw(&dl_rq->dl_bw);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#endif
|
2017-05-19 04:13:28 +08:00
|
|
|
|
|
|
|
dl_rq->running_bw = 0;
|
2017-05-19 04:13:34 +08:00
|
|
|
dl_rq->this_bw = 0;
|
2017-05-19 04:13:32 +08:00
|
|
|
init_dl_rq_bw_ratio(dl_rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
|
|
|
static inline int dl_overloaded(struct rq *rq)
|
|
|
|
{
|
|
|
|
return atomic_read(&rq->rd->dlo_count);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void dl_set_overload(struct rq *rq)
|
|
|
|
{
|
|
|
|
if (!rq->online)
|
|
|
|
return;
|
|
|
|
|
|
|
|
cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
|
|
|
|
/*
|
|
|
|
* Must be visible before the overload count is
|
|
|
|
* set (as in sched_rt.c).
|
|
|
|
*
|
|
|
|
* Matched by the barrier in pull_dl_task().
|
|
|
|
*/
|
|
|
|
smp_wmb();
|
|
|
|
atomic_inc(&rq->rd->dlo_count);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void dl_clear_overload(struct rq *rq)
|
|
|
|
{
|
|
|
|
if (!rq->online)
|
|
|
|
return;
|
|
|
|
|
|
|
|
atomic_dec(&rq->rd->dlo_count);
|
|
|
|
cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void update_dl_migration(struct dl_rq *dl_rq)
|
|
|
|
{
|
2014-02-18 06:24:13 +08:00
|
|
|
if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
if (!dl_rq->overloaded) {
|
|
|
|
dl_set_overload(rq_of_dl_rq(dl_rq));
|
|
|
|
dl_rq->overloaded = 1;
|
|
|
|
}
|
|
|
|
} else if (dl_rq->overloaded) {
|
|
|
|
dl_clear_overload(rq_of_dl_rq(dl_rq));
|
|
|
|
dl_rq->overloaded = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
|
2017-02-05 22:41:03 +08:00
|
|
|
if (p->nr_cpus_allowed > 1)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dl_rq->dl_nr_migratory++;
|
|
|
|
|
|
|
|
update_dl_migration(dl_rq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
|
2017-02-05 22:41:03 +08:00
|
|
|
if (p->nr_cpus_allowed > 1)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dl_rq->dl_nr_migratory--;
|
|
|
|
|
|
|
|
update_dl_migration(dl_rq);
|
|
|
|
}
|
|
|
|
|
2020-04-29 23:04:41 +08:00
|
|
|
#define __node_2_pdl(node) \
|
|
|
|
rb_entry((node), struct task_struct, pushable_dl_tasks)
|
|
|
|
|
|
|
|
static inline bool __pushable_less(struct rb_node *a, const struct rb_node *b)
|
|
|
|
{
|
|
|
|
return dl_entity_preempt(&__node_2_pdl(a)->dl, &__node_2_pdl(b)->dl);
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* The list of pushable -deadline task is not a plist, like in
|
|
|
|
* sched_rt.c, it is an rb-tree with tasks ordered by deadline.
|
|
|
|
*/
|
|
|
|
static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
2020-04-29 23:04:41 +08:00
|
|
|
struct rb_node *leftmost;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2020-04-29 23:04:41 +08:00
|
|
|
leftmost = rb_add_cached(&p->pushable_dl_tasks,
|
|
|
|
&rq->dl.pushable_dl_tasks_root,
|
|
|
|
__pushable_less);
|
2017-09-09 07:14:58 +08:00
|
|
|
if (leftmost)
|
2020-04-29 23:04:41 +08:00
|
|
|
rq->dl.earliest_dl.next = p->dl.deadline;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = &rq->dl;
|
2020-04-29 23:04:41 +08:00
|
|
|
struct rb_root_cached *root = &dl_rq->pushable_dl_tasks_root;
|
|
|
|
struct rb_node *leftmost;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
|
|
|
|
return;
|
|
|
|
|
2020-04-29 23:04:41 +08:00
|
|
|
leftmost = rb_erase_cached(&p->pushable_dl_tasks, root);
|
|
|
|
if (leftmost)
|
|
|
|
dl_rq->earliest_dl.next = __node_2_pdl(leftmost)->dl.deadline;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
RB_CLEAR_NODE(&p->pushable_dl_tasks);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int has_pushable_dl_tasks(struct rq *rq)
|
|
|
|
{
|
2017-09-09 07:14:58 +08:00
|
|
|
return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root.rb_root);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int push_dl_task(struct rq *rq);
|
|
|
|
|
2014-02-12 22:47:29 +08:00
|
|
|
static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
|
|
|
|
{
|
2020-09-25 22:42:31 +08:00
|
|
|
return rq->online && dl_task(prev);
|
2014-02-12 22:47:29 +08:00
|
|
|
}
|
|
|
|
|
2022-10-08 08:07:58 +08:00
|
|
|
static DEFINE_PER_CPU(struct balance_callback, dl_push_head);
|
|
|
|
static DEFINE_PER_CPU(struct balance_callback, dl_pull_head);
|
2015-06-11 20:46:37 +08:00
|
|
|
|
|
|
|
static void push_dl_tasks(struct rq *);
|
2015-06-11 20:46:43 +08:00
|
|
|
static void pull_dl_task(struct rq *);
|
2015-06-11 20:46:37 +08:00
|
|
|
|
2018-03-03 23:27:54 +08:00
|
|
|
static inline void deadline_queue_push_tasks(struct rq *rq)
|
2014-02-12 22:47:29 +08:00
|
|
|
{
|
2015-06-11 20:46:37 +08:00
|
|
|
if (!has_pushable_dl_tasks(rq))
|
|
|
|
return;
|
|
|
|
|
2015-06-11 20:46:43 +08:00
|
|
|
queue_balance_callback(rq, &per_cpu(dl_push_head, rq->cpu), push_dl_tasks);
|
|
|
|
}
|
|
|
|
|
2018-03-03 23:27:54 +08:00
|
|
|
static inline void deadline_queue_pull_task(struct rq *rq)
|
2015-06-11 20:46:43 +08:00
|
|
|
{
|
|
|
|
queue_balance_callback(rq, &per_cpu(dl_pull_head, rq->cpu), pull_dl_task);
|
2014-02-12 22:47:29 +08:00
|
|
|
}
|
|
|
|
|
2015-03-27 07:08:35 +08:00
|
|
|
static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
|
|
|
|
|
2015-06-11 20:46:49 +08:00
|
|
|
static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p)
|
2015-03-27 07:08:35 +08:00
|
|
|
{
|
|
|
|
struct rq *later_rq = NULL;
|
2019-07-19 21:59:56 +08:00
|
|
|
struct dl_bw *dl_b;
|
2015-03-27 07:08:35 +08:00
|
|
|
|
|
|
|
later_rq = find_lock_later_rq(p, rq);
|
|
|
|
if (!later_rq) {
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we cannot preempt any rq, fall back to pick any
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* online CPU:
|
2015-03-27 07:08:35 +08:00
|
|
|
*/
|
2019-04-23 22:26:36 +08:00
|
|
|
cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr);
|
2015-03-27 07:08:35 +08:00
|
|
|
if (cpu >= nr_cpu_ids) {
|
|
|
|
/*
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* Failed to find any suitable CPU.
|
2015-03-27 07:08:35 +08:00
|
|
|
* The task will never come back!
|
|
|
|
*/
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(dl_bandwidth_enabled());
|
2015-03-27 07:08:35 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If admission control is disabled we
|
|
|
|
* try a little harder to let the task
|
|
|
|
* run.
|
|
|
|
*/
|
|
|
|
cpu = cpumask_any(cpu_active_mask);
|
|
|
|
}
|
|
|
|
later_rq = cpu_rq(cpu);
|
|
|
|
double_lock_balance(rq, later_rq);
|
|
|
|
}
|
|
|
|
|
2019-07-19 21:59:56 +08:00
|
|
|
if (p->dl.dl_non_contending || p->dl.dl_throttled) {
|
|
|
|
/*
|
|
|
|
* Inactive timer is armed (or callback is running, but
|
|
|
|
* waiting for us to release rq locks). In any case, when it
|
|
|
|
* will fire (or continue), it will see running_bw of this
|
|
|
|
* task migrated to later_rq (and correctly handle it).
|
|
|
|
*/
|
|
|
|
sub_running_bw(&p->dl, &rq->dl);
|
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
|
|
|
|
|
|
|
add_rq_bw(&p->dl, &later_rq->dl);
|
|
|
|
add_running_bw(&p->dl, &later_rq->dl);
|
|
|
|
} else {
|
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
|
|
|
add_rq_bw(&p->dl, &later_rq->dl);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* And we finally need to fixup root_domain(s) bandwidth accounting,
|
|
|
|
* since p is still hanging out in the old (now moved to default) root
|
|
|
|
* domain.
|
|
|
|
*/
|
|
|
|
dl_b = &rq->rd->dl_bw;
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
|
|
|
__dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
|
|
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
|
|
|
|
dl_b = &later_rq->rd->dl_bw;
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
|
|
|
__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span));
|
|
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
|
2015-03-27 07:08:35 +08:00
|
|
|
set_task_cpu(p, later_rq->cpu);
|
2015-06-11 20:46:49 +08:00
|
|
|
double_unlock_balance(later_rq, rq);
|
|
|
|
|
|
|
|
return later_rq;
|
2015-03-27 07:08:35 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#else
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2018-03-03 23:27:54 +08:00
|
|
|
static inline void deadline_queue_push_tasks(struct rq *rq)
|
2014-02-12 22:47:29 +08:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2018-03-03 23:27:54 +08:00
|
|
|
static inline void deadline_queue_pull_task(struct rq *rq)
|
2014-02-12 22:47:29 +08:00
|
|
|
{
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
|
|
|
|
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, int flags);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2022-08-26 18:00:37 +08:00
|
|
|
static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
|
|
|
|
struct rq *rq)
|
|
|
|
{
|
|
|
|
/* for non-boosted task, pi_of(dl_se) == dl_se */
|
|
|
|
dl_se->deadline = rq_clock(rq) + pi_of(dl_se)->dl_deadline;
|
|
|
|
dl_se->runtime = pi_of(dl_se)->dl_runtime;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* We are being explicitly informed that a new instance is starting,
|
|
|
|
* and this means that:
|
|
|
|
* - the absolute deadline of the entity has to be placed at
|
|
|
|
* current time + relative deadline;
|
|
|
|
* - the runtime of the entity has to be set to the maximum value.
|
|
|
|
*
|
|
|
|
* The capability of specifying such event is useful whenever a -deadline
|
|
|
|
* entity wants to (try to!) synchronize its behaviour with the scheduler's
|
|
|
|
* one, and to (try to!) reconcile itself with its own scheduling
|
|
|
|
* parameters.
|
|
|
|
*/
|
sched/deadline: Remove useless parameter from setup_new_dl_entity()
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-05 23:07:55 +08:00
|
|
|
static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
|
2020-11-17 14:14:32 +08:00
|
|
|
WARN_ON(is_dl_boosted(dl_se));
|
2016-03-07 19:27:04 +08:00
|
|
|
WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline));
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We are racing with the deadline timer. So, do nothing because
|
|
|
|
* the deadline timer handler will take care of properly recharging
|
|
|
|
* the runtime and postponing the deadline
|
|
|
|
*/
|
|
|
|
if (dl_se->dl_throttled)
|
|
|
|
return;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We use the regular wall clock time to set deadlines in the
|
|
|
|
* future; in fact, we must consider execution overheads (time
|
|
|
|
* spent on hardirq context, etc.).
|
|
|
|
*/
|
2022-08-26 18:00:37 +08:00
|
|
|
replenish_dl_new_period(dl_se, rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Pure Earliest Deadline First (EDF) scheduling does not deal with the
|
|
|
|
* possibility of a entity lasting more than what it declared, and thus
|
|
|
|
* exhausting its runtime.
|
|
|
|
*
|
|
|
|
* Here we are interested in making runtime overrun possible, but we do
|
|
|
|
* not want a entity which is misbehaving to affect the scheduling of all
|
|
|
|
* other entities.
|
|
|
|
* Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
|
|
|
|
* is used, in order to confine each entity within its own bandwidth.
|
|
|
|
*
|
|
|
|
* This function deals exactly with that, and ensures that when the runtime
|
|
|
|
* of a entity is replenished, its deadline is also postponed. That ensures
|
|
|
|
* the overrunning entity can't interfere with other entity in the system and
|
|
|
|
* can't make them miss their deadlines. Reasons why this kind of overruns
|
|
|
|
* could happen are, typically, a entity voluntarily trying to overcome its
|
2014-07-07 13:59:04 +08:00
|
|
|
* runtime, or it just underestimated it during sched_setattr().
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*/
|
2020-11-17 14:14:32 +08:00
|
|
|
static void replenish_dl_entity(struct sched_dl_entity *dl_se)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(pi_of(dl_se)->dl_runtime <= 0);
|
sched/deadline: Add SCHED_DEADLINE inheritance logic
Some method to deal with rt-mutexes and make sched_dl interact with
the current PI-coded is needed, raising all but trivial issues, that
needs (according to us) to be solved with some restructuring of
the pi-code (i.e., going toward a proxy execution-ish implementation).
This is under development, in the meanwhile, as a temporary solution,
what this commits does is:
- ensure a pi-lock owner with waiters is never throttled down. Instead,
when it runs out of runtime, it immediately gets replenished and it's
deadline is postponed;
- the scheduling parameters (relative deadline and default runtime)
used for that replenishments --during the whole period it holds the
pi-lock-- are the ones of the waiting task with earliest deadline.
Acting this way, we provide some kind of boosting to the lock-owner,
still by using the existing (actually, slightly modified by the previous
commit) pi-architecture.
We would stress the fact that this is only a surely needed, all but
clean solution to the problem. In the end it's only a way to re-start
discussion within the community. So, as always, comments, ideas, rants,
etc.. are welcome! :-)
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Added !RT_MUTEXES build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-11-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:44 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This could be the case for a !-dl task that is boosted.
|
|
|
|
* Just go with full inherited parameters.
|
|
|
|
*/
|
2022-08-26 18:00:37 +08:00
|
|
|
if (dl_se->dl_deadline == 0)
|
|
|
|
replenish_dl_new_period(dl_se, rq);
|
sched/deadline: Add SCHED_DEADLINE inheritance logic
Some method to deal with rt-mutexes and make sched_dl interact with
the current PI-coded is needed, raising all but trivial issues, that
needs (according to us) to be solved with some restructuring of
the pi-code (i.e., going toward a proxy execution-ish implementation).
This is under development, in the meanwhile, as a temporary solution,
what this commits does is:
- ensure a pi-lock owner with waiters is never throttled down. Instead,
when it runs out of runtime, it immediately gets replenished and it's
deadline is postponed;
- the scheduling parameters (relative deadline and default runtime)
used for that replenishments --during the whole period it holds the
pi-lock-- are the ones of the waiting task with earliest deadline.
Acting this way, we provide some kind of boosting to the lock-owner,
still by using the existing (actually, slightly modified by the previous
commit) pi-architecture.
We would stress the fact that this is only a surely needed, all but
clean solution to the problem. In the end it's only a way to re-start
discussion within the community. So, as always, comments, ideas, rants,
etc.. are welcome! :-)
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Added !RT_MUTEXES build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-11-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:44 +08:00
|
|
|
|
2016-02-23 20:28:22 +08:00
|
|
|
if (dl_se->dl_yielded && dl_se->runtime > 0)
|
|
|
|
dl_se->runtime = 0;
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* We keep moving the deadline away until we get some
|
|
|
|
* available runtime for the entity. This ensures correct
|
|
|
|
* handling of situations where the runtime overrun is
|
|
|
|
* arbitrary large.
|
|
|
|
*/
|
|
|
|
while (dl_se->runtime <= 0) {
|
2020-11-17 14:14:32 +08:00
|
|
|
dl_se->deadline += pi_of(dl_se)->dl_period;
|
|
|
|
dl_se->runtime += pi_of(dl_se)->dl_runtime;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* At this point, the deadline really should be "in
|
|
|
|
* the future" with respect to rq->clock. If it's
|
|
|
|
* not, we are, for some reason, lagging too much!
|
|
|
|
* Anyway, after having warn userspace abut that,
|
|
|
|
* we still try to keep the things running by
|
|
|
|
* resetting the deadline and the budget of the
|
|
|
|
* entity.
|
|
|
|
*/
|
|
|
|
if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
|
2016-02-11 01:04:22 +08:00
|
|
|
printk_deferred_once("sched: DL replenish lagged too much\n");
|
2022-08-26 18:00:37 +08:00
|
|
|
replenish_dl_new_period(dl_se, rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
2014-11-26 08:44:03 +08:00
|
|
|
|
|
|
|
if (dl_se->dl_yielded)
|
|
|
|
dl_se->dl_yielded = 0;
|
|
|
|
if (dl_se->dl_throttled)
|
|
|
|
dl_se->dl_throttled = 0;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we check if --at time t-- an entity (which is probably being
|
|
|
|
* [re]activated or, in general, enqueued) can use its remaining runtime
|
|
|
|
* and its current deadline _without_ exceeding the bandwidth it is
|
|
|
|
* assigned (function returns true if it can't). We are in fact applying
|
|
|
|
* one of the CBS rules: when a task wakes up, if the residual runtime
|
|
|
|
* over residual deadline fits within the allocated bandwidth, then we
|
|
|
|
* can keep the current (absolute) deadline and residual budget without
|
|
|
|
* disrupting the schedulability of the system. Otherwise, we should
|
|
|
|
* refill the runtime and set the deadline a period in the future,
|
|
|
|
* because keeping the current (absolute) deadline of the task would
|
2014-01-27 19:20:15 +08:00
|
|
|
* result in breaking guarantees promised to other tasks (refer to
|
2019-06-13 01:53:03 +08:00
|
|
|
* Documentation/scheduler/sched-deadline.rst for more information).
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*
|
|
|
|
* This function returns true if:
|
|
|
|
*
|
sched/deadline: Use deadline instead of period when calculating overflow
I was testing Daniel's changes with his test case, and tweaked it a
little. Instead of having the runtime equal to the deadline, I
increased the deadline ten fold.
Daniel's test case had:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
To make it more interesting, I changed it to:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
The results were rather surprising. The behavior that Daniel's patch
was fixing came back. The task started using much more than .1% of the
CPU. More like 20%.
Looking into this I found that it was due to the dl_entity_overflow()
constantly returning true. That's because it uses the relative period
against relative runtime vs the absolute deadline against absolute
runtime.
runtime / (deadline - t) > dl_runtime / dl_period
There's even a comment mentioning this, and saying that when relative
deadline equals relative period, that the equation is the same as using
deadline instead of period. That comment is backwards! What we really
want is:
runtime / (deadline - t) > dl_runtime / dl_deadline
We care about if the runtime can make its deadline, not its period. And
then we can say "when the deadline equals the period, the equation is
the same as using dl_period instead of dl_deadline".
After correcting this, now when the task gets enqueued, it can throttle
correctly, and Daniel's fix to the throttling of sleeping deadline
tasks works even when the runtime and deadline are not the same.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/02135a27f1ae3fe5fd032568a5a2f370e190e8d7.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:59 +08:00
|
|
|
* runtime / (deadline - t) > dl_runtime / dl_deadline ,
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*
|
|
|
|
* IOW we can't recycle current parameters.
|
2013-11-07 21:43:40 +08:00
|
|
|
*
|
sched/deadline: Use deadline instead of period when calculating overflow
I was testing Daniel's changes with his test case, and tweaked it a
little. Instead of having the runtime equal to the deadline, I
increased the deadline ten fold.
Daniel's test case had:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
To make it more interesting, I changed it to:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
The results were rather surprising. The behavior that Daniel's patch
was fixing came back. The task started using much more than .1% of the
CPU. More like 20%.
Looking into this I found that it was due to the dl_entity_overflow()
constantly returning true. That's because it uses the relative period
against relative runtime vs the absolute deadline against absolute
runtime.
runtime / (deadline - t) > dl_runtime / dl_period
There's even a comment mentioning this, and saying that when relative
deadline equals relative period, that the equation is the same as using
deadline instead of period. That comment is backwards! What we really
want is:
runtime / (deadline - t) > dl_runtime / dl_deadline
We care about if the runtime can make its deadline, not its period. And
then we can say "when the deadline equals the period, the equation is
the same as using dl_period instead of dl_deadline".
After correcting this, now when the task gets enqueued, it can throttle
correctly, and Daniel's fix to the throttling of sleeping deadline
tasks works even when the runtime and deadline are not the same.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/02135a27f1ae3fe5fd032568a5a2f370e190e8d7.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:59 +08:00
|
|
|
* Notice that the bandwidth check is done against the deadline. For
|
2013-11-07 21:43:40 +08:00
|
|
|
* task with deadline equal to period this is the same of using
|
sched/deadline: Use deadline instead of period when calculating overflow
I was testing Daniel's changes with his test case, and tweaked it a
little. Instead of having the runtime equal to the deadline, I
increased the deadline ten fold.
Daniel's test case had:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
To make it more interesting, I changed it to:
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 20 * 1000 * 1000; /* 20 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
The results were rather surprising. The behavior that Daniel's patch
was fixing came back. The task started using much more than .1% of the
CPU. More like 20%.
Looking into this I found that it was due to the dl_entity_overflow()
constantly returning true. That's because it uses the relative period
against relative runtime vs the absolute deadline against absolute
runtime.
runtime / (deadline - t) > dl_runtime / dl_period
There's even a comment mentioning this, and saying that when relative
deadline equals relative period, that the equation is the same as using
deadline instead of period. That comment is backwards! What we really
want is:
runtime / (deadline - t) > dl_runtime / dl_deadline
We care about if the runtime can make its deadline, not its period. And
then we can say "when the deadline equals the period, the equation is
the same as using dl_period instead of dl_deadline".
After correcting this, now when the task gets enqueued, it can throttle
correctly, and Daniel's fix to the throttling of sleeping deadline
tasks works even when the runtime and deadline are not the same.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/02135a27f1ae3fe5fd032568a5a2f370e190e8d7.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:59 +08:00
|
|
|
* dl_period instead of dl_deadline in the equation above.
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*/
|
2020-11-17 14:14:32 +08:00
|
|
|
static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
|
|
|
u64 left, right;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* left and right are the two sides of the equation above,
|
|
|
|
* after a bit of shuffling to use multiplications instead
|
|
|
|
* of divisions.
|
|
|
|
*
|
|
|
|
* Note that none of the time values involved in the two
|
|
|
|
* multiplications are absolute: dl_deadline and dl_runtime
|
|
|
|
* are the relative deadline and the maximum runtime of each
|
|
|
|
* instance, runtime is the runtime left for the last instance
|
|
|
|
* and (deadline - t), since t is rq->clock, is the time left
|
|
|
|
* to the (absolute) deadline. Even if overflowing the u64 type
|
|
|
|
* is very unlikely to occur in both cases, here we scale down
|
|
|
|
* as we want to avoid that risk at all. Scaling down by 10
|
|
|
|
* means that we reduce granularity to 1us. We are fine with it,
|
|
|
|
* since this is only a true/false check and, anyway, thinking
|
|
|
|
* of anything below microseconds resolution is actually fiction
|
|
|
|
* (but still we want to give the user that illusion >;).
|
|
|
|
*/
|
2020-11-17 14:14:32 +08:00
|
|
|
left = (pi_of(dl_se)->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
right = ((dl_se->deadline - t) >> DL_SCALE) *
|
2020-11-17 14:14:32 +08:00
|
|
|
(pi_of(dl_se)->dl_runtime >> DL_SCALE);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
return dl_time_before(right, left);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks
We have been facing some problems with self-suspending constrained
deadline tasks. The main reason is that the original CBS was not
designed for such sort of tasks.
One problem reported by Xunlei Pang takes place when a task
suspends, and then is awakened before the deadline, but so close
to the deadline that its remaining runtime can cause the task
to have an absolute density higher than allowed. In such situation,
the original CBS assumes that the task is facing an early activation,
and so it replenishes the task and set another deadline, one deadline
in the future. This rule works fine for implicit deadline tasks.
Moreover, it allows the system to adapt the period of a task in which
the external event source suffered from a clock drift.
However, this opens the window for bandwidth leakage for constrained
deadline tasks. For instance, a task with the following parameters:
runtime = 5 ms
deadline = 7 ms
[density] = 5 / 7 = 0.71
period = 1000 ms
If the task runs for 1 ms, and then suspends for another 1ms,
it will be awakened with the following parameters:
remaining runtime = 4
laxity = 5
presenting a absolute density of 4 / 5 = 0.80.
In this case, the original CBS would assume the task had an early
wakeup. Then, CBS will reset the runtime, and the absolute deadline will
be postponed by one relative deadline, allowing the task to run.
The problem is that, if the task runs this pattern forever, it will keep
receiving bandwidth, being able to run 1ms every 2ms. Following this
behavior, the task would be able to run 500 ms in 1 sec. Thus running
more than the 5 ms / 1 sec the admission control allowed it to run.
Trying to address the self-suspending case, Luca Abeni, Giuseppe
Lipari, and Juri Lelli [1] revisited the CBS in order to deal with
self-suspending tasks. In the new approach, rather than
replenishing/postponing the absolute deadline, the revised wakeup rule
adjusts the remaining runtime, reducing it to fit into the allowed
density.
A revised version of the idea is:
At a given time t, the maximum absolute density of a task cannot be
higher than its relative density, that is:
runtime / (deadline - t) <= dl_runtime / dl_deadline
Knowing the laxity of a task (deadline - t), it is possible to move
it to the other side of the equality, thus enabling to define max
remaining runtime a task can use within the absolute deadline, without
over-running the allowed density:
runtime = (dl_runtime / dl_deadline) * (deadline - t)
For instance, in our previous example, the task could still run:
runtime = ( 5 / 7 ) * 5
runtime = 3.57 ms
Without causing damage for other deadline tasks. It is note worthy
that the laxity cannot be negative because that would cause a negative
runtime. Thus, this patch depends on the patch:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline")
Which throttles a constrained deadline task activated after the
deadline.
Finally, it is also possible to use the revised wakeup rule for
all other tasks, but that would require some more discussions
about pros and cons.
Reported-by: Xunlei Pang <xpang@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
[peterz: replaced dl_is_constrained with dl_is_implicit]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/5c800ab3a74a168a84ee5f3f84d12a02e11383be.1495803804.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-29 22:24:03 +08:00
|
|
|
* Revised wakeup rule [1]: For self-suspending tasks, rather then
|
|
|
|
* re-initializing task's runtime and deadline, the revised wakeup
|
|
|
|
* rule adjusts the task's runtime to avoid the task to overrun its
|
|
|
|
* density.
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*
|
sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks
We have been facing some problems with self-suspending constrained
deadline tasks. The main reason is that the original CBS was not
designed for such sort of tasks.
One problem reported by Xunlei Pang takes place when a task
suspends, and then is awakened before the deadline, but so close
to the deadline that its remaining runtime can cause the task
to have an absolute density higher than allowed. In such situation,
the original CBS assumes that the task is facing an early activation,
and so it replenishes the task and set another deadline, one deadline
in the future. This rule works fine for implicit deadline tasks.
Moreover, it allows the system to adapt the period of a task in which
the external event source suffered from a clock drift.
However, this opens the window for bandwidth leakage for constrained
deadline tasks. For instance, a task with the following parameters:
runtime = 5 ms
deadline = 7 ms
[density] = 5 / 7 = 0.71
period = 1000 ms
If the task runs for 1 ms, and then suspends for another 1ms,
it will be awakened with the following parameters:
remaining runtime = 4
laxity = 5
presenting a absolute density of 4 / 5 = 0.80.
In this case, the original CBS would assume the task had an early
wakeup. Then, CBS will reset the runtime, and the absolute deadline will
be postponed by one relative deadline, allowing the task to run.
The problem is that, if the task runs this pattern forever, it will keep
receiving bandwidth, being able to run 1ms every 2ms. Following this
behavior, the task would be able to run 500 ms in 1 sec. Thus running
more than the 5 ms / 1 sec the admission control allowed it to run.
Trying to address the self-suspending case, Luca Abeni, Giuseppe
Lipari, and Juri Lelli [1] revisited the CBS in order to deal with
self-suspending tasks. In the new approach, rather than
replenishing/postponing the absolute deadline, the revised wakeup rule
adjusts the remaining runtime, reducing it to fit into the allowed
density.
A revised version of the idea is:
At a given time t, the maximum absolute density of a task cannot be
higher than its relative density, that is:
runtime / (deadline - t) <= dl_runtime / dl_deadline
Knowing the laxity of a task (deadline - t), it is possible to move
it to the other side of the equality, thus enabling to define max
remaining runtime a task can use within the absolute deadline, without
over-running the allowed density:
runtime = (dl_runtime / dl_deadline) * (deadline - t)
For instance, in our previous example, the task could still run:
runtime = ( 5 / 7 ) * 5
runtime = 3.57 ms
Without causing damage for other deadline tasks. It is note worthy
that the laxity cannot be negative because that would cause a negative
runtime. Thus, this patch depends on the patch:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline")
Which throttles a constrained deadline task activated after the
deadline.
Finally, it is also possible to use the revised wakeup rule for
all other tasks, but that would require some more discussions
about pros and cons.
Reported-by: Xunlei Pang <xpang@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
[peterz: replaced dl_is_constrained with dl_is_implicit]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/5c800ab3a74a168a84ee5f3f84d12a02e11383be.1495803804.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-29 22:24:03 +08:00
|
|
|
* Reasoning: a task may overrun the density if:
|
|
|
|
* runtime / (deadline - t) > dl_runtime / dl_deadline
|
|
|
|
*
|
|
|
|
* Therefore, runtime can be adjusted to:
|
|
|
|
* runtime = (dl_runtime / dl_deadline) * (deadline - t)
|
|
|
|
*
|
|
|
|
* In such way that runtime will be equal to the maximum density
|
|
|
|
* the task can use without breaking any rule.
|
|
|
|
*
|
|
|
|
* [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant
|
|
|
|
* bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24.
|
|
|
|
*/
|
|
|
|
static void
|
|
|
|
update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
|
|
|
|
{
|
|
|
|
u64 laxity = dl_se->deadline - rq_clock(rq);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If the task has deadline < period, and the deadline is in the past,
|
|
|
|
* it should already be throttled before this check.
|
|
|
|
*
|
|
|
|
* See update_dl_entity() comments for further details.
|
|
|
|
*/
|
|
|
|
WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq)));
|
|
|
|
|
|
|
|
dl_se->runtime = (dl_se->dl_density * laxity) >> BW_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Regarding the deadline, a task with implicit deadline has a relative
|
|
|
|
* deadline == relative period. A task with constrained deadline has a
|
|
|
|
* relative deadline <= relative period.
|
|
|
|
*
|
|
|
|
* We support constrained deadline tasks. However, there are some restrictions
|
|
|
|
* applied only for tasks which do not have an implicit deadline. See
|
|
|
|
* update_dl_entity() to know more about such restrictions.
|
|
|
|
*
|
|
|
|
* The dl_is_implicit() returns true if the task has an implicit deadline.
|
|
|
|
*/
|
|
|
|
static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return dl_se->dl_deadline == dl_se->dl_period;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When a deadline entity is placed in the runqueue, its runtime and deadline
|
|
|
|
* might need to be updated. This is done by a CBS wake up rule. There are two
|
|
|
|
* different rules: 1) the original CBS; and 2) the Revisited CBS.
|
|
|
|
*
|
|
|
|
* When the task is starting a new period, the Original CBS is used. In this
|
|
|
|
* case, the runtime is replenished and a new absolute deadline is set.
|
|
|
|
*
|
|
|
|
* When a task is queued before the begin of the next period, using the
|
|
|
|
* remaining runtime and deadline could make the entity to overflow, see
|
|
|
|
* dl_entity_overflow() to find more about runtime overflow. When such case
|
|
|
|
* is detected, the runtime and deadline need to be updated.
|
|
|
|
*
|
|
|
|
* If the task has an implicit deadline, i.e., deadline == period, the Original
|
|
|
|
* CBS is applied. the runtime is replenished and a new absolute deadline is
|
|
|
|
* set, as in the previous cases.
|
|
|
|
*
|
|
|
|
* However, the Original CBS does not work properly for tasks with
|
|
|
|
* deadline < period, which are said to have a constrained deadline. By
|
|
|
|
* applying the Original CBS, a constrained deadline task would be able to run
|
|
|
|
* runtime/deadline in a period. With deadline < period, the task would
|
|
|
|
* overrun the runtime/period allowed bandwidth, breaking the admission test.
|
|
|
|
*
|
|
|
|
* In order to prevent this misbehave, the Revisited CBS is used for
|
|
|
|
* constrained deadline tasks when a runtime overflow is detected. In the
|
|
|
|
* Revisited CBS, rather than replenishing & setting a new absolute deadline,
|
|
|
|
* the remaining runtime of the task is reduced to avoid runtime overflow.
|
|
|
|
* Please refer to the comments update_dl_revised_wakeup() function to find
|
|
|
|
* more about the Revised CBS rule.
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*/
|
2020-11-17 14:14:32 +08:00
|
|
|
static void update_dl_entity(struct sched_dl_entity *dl_se)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
|
|
|
|
if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
|
2020-11-17 14:14:32 +08:00
|
|
|
dl_entity_overflow(dl_se, rq_clock(rq))) {
|
sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks
We have been facing some problems with self-suspending constrained
deadline tasks. The main reason is that the original CBS was not
designed for such sort of tasks.
One problem reported by Xunlei Pang takes place when a task
suspends, and then is awakened before the deadline, but so close
to the deadline that its remaining runtime can cause the task
to have an absolute density higher than allowed. In such situation,
the original CBS assumes that the task is facing an early activation,
and so it replenishes the task and set another deadline, one deadline
in the future. This rule works fine for implicit deadline tasks.
Moreover, it allows the system to adapt the period of a task in which
the external event source suffered from a clock drift.
However, this opens the window for bandwidth leakage for constrained
deadline tasks. For instance, a task with the following parameters:
runtime = 5 ms
deadline = 7 ms
[density] = 5 / 7 = 0.71
period = 1000 ms
If the task runs for 1 ms, and then suspends for another 1ms,
it will be awakened with the following parameters:
remaining runtime = 4
laxity = 5
presenting a absolute density of 4 / 5 = 0.80.
In this case, the original CBS would assume the task had an early
wakeup. Then, CBS will reset the runtime, and the absolute deadline will
be postponed by one relative deadline, allowing the task to run.
The problem is that, if the task runs this pattern forever, it will keep
receiving bandwidth, being able to run 1ms every 2ms. Following this
behavior, the task would be able to run 500 ms in 1 sec. Thus running
more than the 5 ms / 1 sec the admission control allowed it to run.
Trying to address the self-suspending case, Luca Abeni, Giuseppe
Lipari, and Juri Lelli [1] revisited the CBS in order to deal with
self-suspending tasks. In the new approach, rather than
replenishing/postponing the absolute deadline, the revised wakeup rule
adjusts the remaining runtime, reducing it to fit into the allowed
density.
A revised version of the idea is:
At a given time t, the maximum absolute density of a task cannot be
higher than its relative density, that is:
runtime / (deadline - t) <= dl_runtime / dl_deadline
Knowing the laxity of a task (deadline - t), it is possible to move
it to the other side of the equality, thus enabling to define max
remaining runtime a task can use within the absolute deadline, without
over-running the allowed density:
runtime = (dl_runtime / dl_deadline) * (deadline - t)
For instance, in our previous example, the task could still run:
runtime = ( 5 / 7 ) * 5
runtime = 3.57 ms
Without causing damage for other deadline tasks. It is note worthy
that the laxity cannot be negative because that would cause a negative
runtime. Thus, this patch depends on the patch:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline")
Which throttles a constrained deadline task activated after the
deadline.
Finally, it is also possible to use the revised wakeup rule for
all other tasks, but that would require some more discussions
about pros and cons.
Reported-by: Xunlei Pang <xpang@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
[peterz: replaced dl_is_constrained with dl_is_implicit]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/5c800ab3a74a168a84ee5f3f84d12a02e11383be.1495803804.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-29 22:24:03 +08:00
|
|
|
|
|
|
|
if (unlikely(!dl_is_implicit(dl_se) &&
|
|
|
|
!dl_time_before(dl_se->deadline, rq_clock(rq)) &&
|
2020-11-17 14:14:32 +08:00
|
|
|
!is_dl_boosted(dl_se))) {
|
sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks
We have been facing some problems with self-suspending constrained
deadline tasks. The main reason is that the original CBS was not
designed for such sort of tasks.
One problem reported by Xunlei Pang takes place when a task
suspends, and then is awakened before the deadline, but so close
to the deadline that its remaining runtime can cause the task
to have an absolute density higher than allowed. In such situation,
the original CBS assumes that the task is facing an early activation,
and so it replenishes the task and set another deadline, one deadline
in the future. This rule works fine for implicit deadline tasks.
Moreover, it allows the system to adapt the period of a task in which
the external event source suffered from a clock drift.
However, this opens the window for bandwidth leakage for constrained
deadline tasks. For instance, a task with the following parameters:
runtime = 5 ms
deadline = 7 ms
[density] = 5 / 7 = 0.71
period = 1000 ms
If the task runs for 1 ms, and then suspends for another 1ms,
it will be awakened with the following parameters:
remaining runtime = 4
laxity = 5
presenting a absolute density of 4 / 5 = 0.80.
In this case, the original CBS would assume the task had an early
wakeup. Then, CBS will reset the runtime, and the absolute deadline will
be postponed by one relative deadline, allowing the task to run.
The problem is that, if the task runs this pattern forever, it will keep
receiving bandwidth, being able to run 1ms every 2ms. Following this
behavior, the task would be able to run 500 ms in 1 sec. Thus running
more than the 5 ms / 1 sec the admission control allowed it to run.
Trying to address the self-suspending case, Luca Abeni, Giuseppe
Lipari, and Juri Lelli [1] revisited the CBS in order to deal with
self-suspending tasks. In the new approach, rather than
replenishing/postponing the absolute deadline, the revised wakeup rule
adjusts the remaining runtime, reducing it to fit into the allowed
density.
A revised version of the idea is:
At a given time t, the maximum absolute density of a task cannot be
higher than its relative density, that is:
runtime / (deadline - t) <= dl_runtime / dl_deadline
Knowing the laxity of a task (deadline - t), it is possible to move
it to the other side of the equality, thus enabling to define max
remaining runtime a task can use within the absolute deadline, without
over-running the allowed density:
runtime = (dl_runtime / dl_deadline) * (deadline - t)
For instance, in our previous example, the task could still run:
runtime = ( 5 / 7 ) * 5
runtime = 3.57 ms
Without causing damage for other deadline tasks. It is note worthy
that the laxity cannot be negative because that would cause a negative
runtime. Thus, this patch depends on the patch:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline")
Which throttles a constrained deadline task activated after the
deadline.
Finally, it is also possible to use the revised wakeup rule for
all other tasks, but that would require some more discussions
about pros and cons.
Reported-by: Xunlei Pang <xpang@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
[peterz: replaced dl_is_constrained with dl_is_implicit]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/5c800ab3a74a168a84ee5f3f84d12a02e11383be.1495803804.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-29 22:24:03 +08:00
|
|
|
update_dl_revised_wakeup(dl_se, rq);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2022-08-26 18:00:37 +08:00
|
|
|
replenish_dl_new_period(dl_se, rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sched/deadline: Make sure the replenishment timer fires in the next period
Currently, the replenishment timer is set to fire at the deadline
of a task. Although that works for implicit deadline tasks because the
deadline is equals to the begin of the next period, that is not correct
for constrained deadline tasks (deadline < period).
For instance:
f.c:
--------------- %< ---------------
int main (void)
{
for(;;);
}
--------------- >% ---------------
# gcc -o f f.c
# trace-cmd record -e sched:sched_switch \
-e syscalls:sys_exit_sched_setattr \
chrt -d --sched-runtime 490000000 \
--sched-deadline 500000000 \
--sched-period 1000000000 0 ./f
# trace-cmd report | grep "{pid of ./f}"
After setting parameters, the task is replenished and continue running
until being throttled:
f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0
The task is throttled after running 492318 ms, as expected:
f-11295 [003] 13322.606094: sched_switch: f:11295 [-1] R ==> watchdog/3:32 [0]
But then, the task is replenished 500719 ms after the first
replenishment:
<idle>-0 [003] 13322.614495: sched_switch: swapper/3:0 [120] R ==> f:11295 [-1]
Running for 490277 ms:
f-11295 [003] 13323.104772: sched_switch: f:11295 [-1] R ==> swapper/3:0 [120]
Hence, in the first period, the task runs 2 * runtime, and that is a bug.
During the first replenishment, the next deadline is set one period away.
So the runtime / period starts to be respected. However, as the second
replenishment took place in the wrong instant, the next replenishment
will also be held in a wrong instant of time. Rather than occurring in
the nth period away from the first activation, it is taking place
in the (nth period - relative deadline).
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@santannapisa.it>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/ac50d89887c25285b47465638354b63362f8adff.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:57 +08:00
|
|
|
static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* If the entity depleted all its runtime, and if we want it to sleep
|
|
|
|
* while waiting for some new execution time to become available, we
|
sched/deadline: Make sure the replenishment timer fires in the next period
Currently, the replenishment timer is set to fire at the deadline
of a task. Although that works for implicit deadline tasks because the
deadline is equals to the begin of the next period, that is not correct
for constrained deadline tasks (deadline < period).
For instance:
f.c:
--------------- %< ---------------
int main (void)
{
for(;;);
}
--------------- >% ---------------
# gcc -o f f.c
# trace-cmd record -e sched:sched_switch \
-e syscalls:sys_exit_sched_setattr \
chrt -d --sched-runtime 490000000 \
--sched-deadline 500000000 \
--sched-period 1000000000 0 ./f
# trace-cmd report | grep "{pid of ./f}"
After setting parameters, the task is replenished and continue running
until being throttled:
f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0
The task is throttled after running 492318 ms, as expected:
f-11295 [003] 13322.606094: sched_switch: f:11295 [-1] R ==> watchdog/3:32 [0]
But then, the task is replenished 500719 ms after the first
replenishment:
<idle>-0 [003] 13322.614495: sched_switch: swapper/3:0 [120] R ==> f:11295 [-1]
Running for 490277 ms:
f-11295 [003] 13323.104772: sched_switch: f:11295 [-1] R ==> swapper/3:0 [120]
Hence, in the first period, the task runs 2 * runtime, and that is a bug.
During the first replenishment, the next deadline is set one period away.
So the runtime / period starts to be respected. However, as the second
replenishment took place in the wrong instant, the next replenishment
will also be held in a wrong instant of time. Rather than occurring in
the nth period away from the first activation, it is taking place
in the (nth period - relative deadline).
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@santannapisa.it>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/ac50d89887c25285b47465638354b63362f8adff.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:57 +08:00
|
|
|
* set the bandwidth replenishment timer to the replenishment instant
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
* and try to activate it.
|
|
|
|
*
|
|
|
|
* Notice that it is important for the caller to know if the timer
|
|
|
|
* actually started or not (i.e., the replenishment instant is in
|
|
|
|
* the future or in the past).
|
|
|
|
*/
|
2015-06-11 20:46:49 +08:00
|
|
|
static int start_dl_timer(struct task_struct *p)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2015-06-11 20:46:49 +08:00
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
struct hrtimer *timer = &dl_se->dl_timer;
|
|
|
|
struct rq *rq = task_rq(p);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
ktime_t now, act;
|
|
|
|
s64 delta;
|
|
|
|
|
2020-11-18 07:19:31 +08:00
|
|
|
lockdep_assert_rq_held(rq);
|
2015-06-11 20:46:49 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* We want the timer to fire at the deadline, but considering
|
|
|
|
* that it is actually coming from rq->clock and not from
|
|
|
|
* hrtimer's time base reading.
|
|
|
|
*/
|
sched/deadline: Make sure the replenishment timer fires in the next period
Currently, the replenishment timer is set to fire at the deadline
of a task. Although that works for implicit deadline tasks because the
deadline is equals to the begin of the next period, that is not correct
for constrained deadline tasks (deadline < period).
For instance:
f.c:
--------------- %< ---------------
int main (void)
{
for(;;);
}
--------------- >% ---------------
# gcc -o f f.c
# trace-cmd record -e sched:sched_switch \
-e syscalls:sys_exit_sched_setattr \
chrt -d --sched-runtime 490000000 \
--sched-deadline 500000000 \
--sched-period 1000000000 0 ./f
# trace-cmd report | grep "{pid of ./f}"
After setting parameters, the task is replenished and continue running
until being throttled:
f-11295 [003] 13322.113776: sys_exit_sched_setattr: 0x0
The task is throttled after running 492318 ms, as expected:
f-11295 [003] 13322.606094: sched_switch: f:11295 [-1] R ==> watchdog/3:32 [0]
But then, the task is replenished 500719 ms after the first
replenishment:
<idle>-0 [003] 13322.614495: sched_switch: swapper/3:0 [120] R ==> f:11295 [-1]
Running for 490277 ms:
f-11295 [003] 13323.104772: sched_switch: f:11295 [-1] R ==> swapper/3:0 [120]
Hence, in the first period, the task runs 2 * runtime, and that is a bug.
During the first replenishment, the next deadline is set one period away.
So the runtime / period starts to be respected. However, as the second
replenishment took place in the wrong instant, the next replenishment
will also be held in a wrong instant of time. Rather than occurring in
the nth period away from the first activation, it is taking place
in the (nth period - relative deadline).
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@santannapisa.it>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/ac50d89887c25285b47465638354b63362f8adff.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:57 +08:00
|
|
|
act = ns_to_ktime(dl_next_period(dl_se));
|
2015-06-11 20:46:49 +08:00
|
|
|
now = hrtimer_cb_get_time(timer);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
delta = ktime_to_ns(now) - rq_clock(rq);
|
|
|
|
act = ktime_add_ns(act, delta);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If the expiry time already passed, e.g., because the value
|
|
|
|
* chosen as the deadline is too small, don't even try to
|
|
|
|
* start the timer in the past!
|
|
|
|
*/
|
|
|
|
if (ktime_us_delta(act, now) < 0)
|
|
|
|
return 0;
|
|
|
|
|
2015-06-11 20:46:49 +08:00
|
|
|
/*
|
|
|
|
* !enqueued will guarantee another callback; even if one is already in
|
|
|
|
* progress. This ensures a balanced {get,put}_task_struct().
|
|
|
|
*
|
|
|
|
* The race against __run_timer() clearing the enqueued state is
|
|
|
|
* harmless because we're holding task_rq()->lock, therefore the timer
|
|
|
|
* expiring after we've done the check will wait on its task_rq_lock()
|
|
|
|
* and observe our state.
|
|
|
|
*/
|
|
|
|
if (!hrtimer_is_queued(timer)) {
|
|
|
|
get_task_struct(p);
|
2019-07-27 02:30:52 +08:00
|
|
|
hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD);
|
2015-06-11 20:46:49 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2015-04-15 05:09:06 +08:00
|
|
|
return 1;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is the bandwidth enforcement timer callback. If here, we know
|
|
|
|
* a task is not on its dl_rq, since the fact that the timer was running
|
|
|
|
* means the task is throttled and needs a runtime replenishment.
|
|
|
|
*
|
|
|
|
* However, what we actually do depends on the fact the task is active,
|
|
|
|
* (it is on its rq) or has been removed from there by a call to
|
|
|
|
* dequeue_task_dl(). In the former case we must issue the runtime
|
|
|
|
* replenishment and add the task back to the dl_rq; in the latter, we just
|
|
|
|
* do nothing but clearing dl_throttled, so that runtime and deadline
|
|
|
|
* updating (and the queueing back to dl_rq) will be done by the
|
|
|
|
* next call to enqueue_task_dl().
|
|
|
|
*/
|
|
|
|
static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = container_of(timer,
|
|
|
|
struct sched_dl_entity,
|
|
|
|
dl_timer);
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
2015-08-01 03:28:18 +08:00
|
|
|
struct rq_flags rf;
|
2014-05-20 17:33:42 +08:00
|
|
|
struct rq *rq;
|
2015-02-17 20:22:25 +08:00
|
|
|
|
2015-08-01 03:28:18 +08:00
|
|
|
rq = task_rq_lock(p, &rf);
|
2014-05-20 17:33:42 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
2015-06-11 20:46:49 +08:00
|
|
|
* The task might have changed its scheduling policy to something
|
2016-11-08 18:15:23 +08:00
|
|
|
* different than SCHED_DEADLINE (through switched_from_dl()).
|
2015-06-11 20:46:49 +08:00
|
|
|
*/
|
2017-05-19 04:13:29 +08:00
|
|
|
if (!dl_task(p))
|
2015-06-11 20:46:49 +08:00
|
|
|
goto unlock;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The task might have been boosted by someone else and might be in the
|
|
|
|
* boosting/deboosting path, its not throttled.
|
|
|
|
*/
|
2020-11-17 14:14:32 +08:00
|
|
|
if (is_dl_boosted(dl_se))
|
2015-06-11 20:46:49 +08:00
|
|
|
goto unlock;
|
2015-02-16 20:38:34 +08:00
|
|
|
|
2015-03-27 07:08:35 +08:00
|
|
|
/*
|
2015-06-11 20:46:49 +08:00
|
|
|
* Spurious timer due to start_dl_timer() race; or we already received
|
|
|
|
* a replenishment from rt_mutex_setprio().
|
2015-03-27 07:08:35 +08:00
|
|
|
*/
|
2015-06-11 20:46:49 +08:00
|
|
|
if (!dl_se->dl_throttled)
|
2015-03-27 07:08:35 +08:00
|
|
|
goto unlock;
|
2015-06-11 20:46:49 +08:00
|
|
|
|
|
|
|
sched_clock_tick();
|
|
|
|
update_rq_clock(rq);
|
2015-03-27 07:08:35 +08:00
|
|
|
|
2015-02-16 20:38:34 +08:00
|
|
|
/*
|
|
|
|
* If the throttle happened during sched-out; like:
|
|
|
|
*
|
|
|
|
* schedule()
|
|
|
|
* deactivate_task()
|
|
|
|
* dequeue_task_dl()
|
|
|
|
* update_curr_dl()
|
|
|
|
* start_dl_timer()
|
|
|
|
* __dequeue_task_dl()
|
|
|
|
* prev->on_rq = 0;
|
|
|
|
*
|
|
|
|
* We can be both throttled and !queued. Replenish the counter
|
|
|
|
* but do not enqueue -- wait for our wakeup to do that.
|
|
|
|
*/
|
|
|
|
if (!task_on_rq_queued(p)) {
|
2020-11-17 14:14:32 +08:00
|
|
|
replenish_dl_entity(dl_se);
|
2015-02-16 20:38:34 +08:00
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2016-08-04 09:42:20 +08:00
|
|
|
if (unlikely(!rq->online)) {
|
2016-08-31 18:27:44 +08:00
|
|
|
/*
|
|
|
|
* If the runqueue is no longer available, migrate the
|
|
|
|
* task elsewhere. This necessarily changes rq.
|
|
|
|
*/
|
2021-03-03 23:45:41 +08:00
|
|
|
lockdep_unpin_lock(__rq_lockp(rq), rf.cookie);
|
2015-06-11 20:46:49 +08:00
|
|
|
rq = dl_task_offline_migration(rq, p);
|
2021-03-03 23:45:41 +08:00
|
|
|
rf.cookie = lockdep_pin_lock(__rq_lockp(rq));
|
2017-03-07 13:51:28 +08:00
|
|
|
update_rq_clock(rq);
|
2016-08-31 18:27:44 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Now that the task has been migrated to the new RQ and we
|
|
|
|
* have that locked, proceed as normal and enqueue the task
|
|
|
|
* there.
|
|
|
|
*/
|
2016-08-04 09:42:20 +08:00
|
|
|
}
|
2016-08-31 18:27:44 +08:00
|
|
|
#endif
|
2015-06-11 20:46:49 +08:00
|
|
|
|
2016-08-31 18:27:44 +08:00
|
|
|
enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
|
|
|
|
if (dl_task(rq->curr))
|
|
|
|
check_preempt_curr_dl(rq, p, 0);
|
|
|
|
else
|
|
|
|
resched_curr(rq);
|
2015-06-11 20:46:49 +08:00
|
|
|
|
2016-08-31 18:27:44 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2015-06-11 20:46:49 +08:00
|
|
|
/*
|
|
|
|
* Queueing this task back might have overloaded rq, check if we need
|
|
|
|
* to kick someone away.
|
2014-11-26 08:44:03 +08:00
|
|
|
*/
|
2015-10-23 17:50:08 +08:00
|
|
|
if (has_pushable_dl_tasks(rq)) {
|
|
|
|
/*
|
|
|
|
* Nothing relies on rq->lock after this, so its safe to drop
|
|
|
|
* rq->lock.
|
|
|
|
*/
|
2016-09-21 21:38:10 +08:00
|
|
|
rq_unpin_lock(rq, &rf);
|
2014-11-26 08:44:03 +08:00
|
|
|
push_dl_task(rq);
|
2016-09-21 21:38:10 +08:00
|
|
|
rq_repin_lock(rq, &rf);
|
2015-10-23 17:50:08 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#endif
|
2015-06-11 20:46:49 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
unlock:
|
2015-08-01 03:28:18 +08:00
|
|
|
task_rq_unlock(rq, p, &rf);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2015-06-11 20:46:49 +08:00
|
|
|
/*
|
|
|
|
* This can free the task_struct, including this hrtimer, do not touch
|
|
|
|
* anything related to that after this.
|
|
|
|
*/
|
|
|
|
put_task_struct(p);
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
return HRTIMER_NORESTART;
|
|
|
|
}
|
|
|
|
|
|
|
|
void init_dl_task_timer(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct hrtimer *timer = &dl_se->dl_timer;
|
|
|
|
|
2019-07-27 02:30:52 +08:00
|
|
|
hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
timer->function = dl_task_timer;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
/*
|
|
|
|
* During the activation, CBS checks if it can reuse the current task's
|
|
|
|
* runtime and period. If the deadline of the task is in the past, CBS
|
|
|
|
* cannot use the runtime, and so it replenishes the task. This rule
|
|
|
|
* works fine for implicit deadline tasks (deadline == period), and the
|
|
|
|
* CBS was designed for implicit deadline tasks. However, a task with
|
2020-06-03 03:50:02 +08:00
|
|
|
* constrained deadline (deadline < period) might be awakened after the
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
* deadline, but before the next period. In this case, replenishing the
|
|
|
|
* task would allow it to run for runtime / deadline. As in this case
|
|
|
|
* deadline < period, CBS enables a task to run for more than the
|
|
|
|
* runtime / period. In a very loaded system, this can cause a domino
|
|
|
|
* effect, making other tasks miss their deadlines.
|
|
|
|
*
|
|
|
|
* To avoid this problem, in the activation of a constrained deadline
|
|
|
|
* task after the deadline but before the next period, throttle the
|
|
|
|
* task and set the replenishing timer to the begin of the next period,
|
|
|
|
* unless it is boosted.
|
|
|
|
*/
|
|
|
|
static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
|
|
|
|
|
|
|
|
if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
|
|
|
|
dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
|
2020-11-17 14:14:32 +08:00
|
|
|
if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(p)))
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
return;
|
|
|
|
dl_se->dl_throttled = 1;
|
2017-05-10 21:03:37 +08:00
|
|
|
if (dl_se->runtime > 0)
|
|
|
|
dl_se->runtime = 0;
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static
|
2015-06-15 11:15:20 +08:00
|
|
|
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2014-12-17 18:50:32 +08:00
|
|
|
return (dl_se->runtime <= 0);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2017-05-19 04:13:31 +08:00
|
|
|
/*
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
* This function implements the GRUB accounting rule. According to the
|
|
|
|
* GRUB reclaiming algorithm, the runtime is not decreased as "dq = -dt",
|
|
|
|
* but as "dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt",
|
2017-05-19 04:13:36 +08:00
|
|
|
* where u is the utilization of the task, Umax is the maximum reclaimable
|
|
|
|
* utilization, Uinact is the (per-runqueue) inactive utilization, computed
|
|
|
|
* as the difference between the "total runqueue utilization" and the
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
* "runqueue active utilization", and Uextra is the (per runqueue) extra
|
2017-05-19 04:13:36 +08:00
|
|
|
* reclaimable utilization.
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
* Since rq->dl.running_bw and rq->dl.this_bw contain utilizations multiplied
|
|
|
|
* by 2^BW_SHIFT, the result has to be shifted right by BW_SHIFT.
|
|
|
|
* Since rq->dl.bw_ratio contains 1 / Umax multiplied by 2^RATIO_SHIFT, dl_bw
|
|
|
|
* is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT.
|
|
|
|
* Since delta is a 64 bit variable, to have an overflow its value should be
|
|
|
|
* larger than 2^(64 - 20 - 8), which is more than 64 seconds. So, overflow is
|
|
|
|
* not an issue here.
|
2017-05-19 04:13:31 +08:00
|
|
|
*/
|
2018-05-17 04:09:02 +08:00
|
|
|
static u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
|
2017-05-19 04:13:31 +08:00
|
|
|
{
|
2017-05-19 04:13:35 +08:00
|
|
|
u64 u_act;
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
|
2017-05-19 04:13:31 +08:00
|
|
|
|
2017-05-19 04:13:35 +08:00
|
|
|
/*
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
* Instead of computing max{u, (u_max - u_inact - u_extra)}, we
|
|
|
|
* compare u_inact + u_extra with u_max - u, because u_inact + u_extra
|
|
|
|
* can be larger than u_max. So, u_max - u_inact - u_extra would be
|
|
|
|
* negative leading to wrong results.
|
2017-05-19 04:13:35 +08:00
|
|
|
*/
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
if (u_inact + rq->dl.extra_bw > rq->dl.max_bw - dl_se->dl_bw)
|
|
|
|
u_act = dl_se->dl_bw;
|
2017-05-19 04:13:35 +08:00
|
|
|
else
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
u_act = rq->dl.max_bw - u_inact - rq->dl.extra_bw;
|
2017-05-19 04:13:35 +08:00
|
|
|
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
u_act = (u_act * rq->dl.bw_ratio) >> RATIO_SHIFT;
|
2017-05-19 04:13:35 +08:00
|
|
|
return (delta * u_act) >> BW_SHIFT;
|
2017-05-19 04:13:31 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* Update the current task's runtime statistics (provided it is still
|
|
|
|
* a -deadline task and has not been removed from the dl_rq).
|
|
|
|
*/
|
|
|
|
static void update_curr_dl(struct rq *rq)
|
|
|
|
{
|
|
|
|
struct task_struct *curr = rq->curr;
|
|
|
|
struct sched_dl_entity *dl_se = &curr->dl;
|
2017-12-04 18:23:25 +08:00
|
|
|
u64 delta_exec, scaled_delta_exec;
|
|
|
|
int cpu = cpu_of(rq);
|
2018-02-06 09:55:48 +08:00
|
|
|
u64 now;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
if (!dl_task(curr) || !on_dl_rq(dl_se))
|
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Consumed budget is computed considering the time as
|
|
|
|
* observed by schedulable tasks (excluding time spent
|
|
|
|
* in hardirq context, etc.). Deadlines are instead
|
|
|
|
* computed using hard walltime. This seems to be the more
|
|
|
|
* natural solution, but the full ramifications of this
|
|
|
|
* approach need further study.
|
|
|
|
*/
|
2018-02-06 09:55:48 +08:00
|
|
|
now = rq_clock_task(rq);
|
|
|
|
delta_exec = now - curr->se.exec_start;
|
2016-02-23 20:28:22 +08:00
|
|
|
if (unlikely((s64)delta_exec <= 0)) {
|
|
|
|
if (unlikely(dl_se->dl_yielded))
|
|
|
|
goto throttle;
|
2014-03-04 23:25:46 +08:00
|
|
|
return;
|
2016-02-23 20:28:22 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
sched: Make struct sched_statistics independent of fair sched class
If we want to use the schedstats facility to trace other sched classes, we
should make it independent of fair sched class. The struct sched_statistics
is the schedular statistics of a task_struct or a task_group. So we can
move it into struct task_struct and struct task_group to achieve the goal.
After the patch, schestats are orgnized as follows,
struct task_struct {
...
struct sched_entity se;
struct sched_rt_entity rt;
struct sched_dl_entity dl;
...
struct sched_statistics stats;
...
};
Regarding the task group, schedstats is only supported for fair group
sched, and a new struct sched_entity_stats is introduced, suggested by
Peter -
struct sched_entity_stats {
struct sched_entity se;
struct sched_statistics stats;
} __no_randomize_layout;
Then with the se in a task_group, we can easily get the stats.
The sched_statistics members may be frequently modified when schedstats is
enabled, in order to avoid impacting on random data which may in the same
cacheline with them, the struct sched_statistics is defined as cacheline
aligned.
As this patch changes the core struct of scheduler, so I verified the
performance it may impact on the scheduler with 'perf bench sched
pipe', suggested by Mel. Below is the result, in which all the values
are in usecs/op.
Before After
kernel.sched_schedstats=0 5.2~5.4 5.2~5.4
kernel.sched_schedstats=1 5.3~5.5 5.3~5.5
[These data is a little difference with the earlier version, that is
because my old test machine is destroyed so I have to use a new
different test machine.]
Almost no impact on the sched performance.
No functional change.
[lkp@intel.com: reported build failure in earlier version]
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20210905143547.4668-3-laoar.shao@gmail.com
2021-09-05 22:35:41 +08:00
|
|
|
schedstat_set(curr->stats.exec_max,
|
|
|
|
max(curr->stats.exec_max, delta_exec));
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2021-09-05 22:35:46 +08:00
|
|
|
trace_sched_stat_runtime(curr, delta_exec, 0);
|
|
|
|
|
2022-08-24 16:28:56 +08:00
|
|
|
update_current_exec_runtime(curr, now, delta_exec);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
if (dl_entity_is_special(dl_se))
|
|
|
|
return;
|
|
|
|
|
2017-12-04 18:23:25 +08:00
|
|
|
/*
|
|
|
|
* For tasks that participate in GRUB, we implement GRUB-PA: the
|
|
|
|
* spare reclaimed bandwidth is used to clock down frequency.
|
|
|
|
*
|
|
|
|
* For the others, we still need to scale reservation parameters
|
|
|
|
* according to current frequency and CPU maximum capacity.
|
|
|
|
*/
|
|
|
|
if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM)) {
|
|
|
|
scaled_delta_exec = grub_reclaim(delta_exec,
|
|
|
|
rq,
|
|
|
|
&curr->dl);
|
|
|
|
} else {
|
|
|
|
unsigned long scale_freq = arch_scale_freq_capacity(cpu);
|
2019-06-17 23:00:17 +08:00
|
|
|
unsigned long scale_cpu = arch_scale_cpu_capacity(cpu);
|
2017-12-04 18:23:25 +08:00
|
|
|
|
|
|
|
scaled_delta_exec = cap_scale(delta_exec, scale_freq);
|
|
|
|
scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu);
|
|
|
|
}
|
|
|
|
|
|
|
|
dl_se->runtime -= scaled_delta_exec;
|
2016-02-23 20:28:22 +08:00
|
|
|
|
|
|
|
throttle:
|
|
|
|
if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
|
2014-11-26 08:44:03 +08:00
|
|
|
dl_se->dl_throttled = 1;
|
2017-12-12 19:10:24 +08:00
|
|
|
|
|
|
|
/* If requested, inform the user about runtime overruns. */
|
|
|
|
if (dl_runtime_exceeded(dl_se) &&
|
|
|
|
(dl_se->flags & SCHED_FLAG_DL_OVERRUN))
|
|
|
|
dl_se->dl_overrun = 1;
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
__dequeue_task_dl(rq, curr, 0);
|
2020-11-17 14:14:32 +08:00
|
|
|
if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(curr)))
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
|
|
|
|
|
|
|
|
if (!is_leftmost(curr, &rq->dl))
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
2013-12-17 19:44:49 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Because -- for now -- we share the rt bandwidth, we need to
|
|
|
|
* account our runtime there too, otherwise actual rt tasks
|
|
|
|
* would be able to exceed the shared quota.
|
|
|
|
*
|
|
|
|
* Account to the root rt group for now.
|
|
|
|
*
|
|
|
|
* The solution we're working towards is having the RT groups scheduled
|
|
|
|
* using deadline servers -- however there's a few nasties to figure
|
|
|
|
* out before that can happen.
|
|
|
|
*/
|
|
|
|
if (rt_bandwidth_enabled()) {
|
|
|
|
struct rt_rq *rt_rq = &rq->rt;
|
|
|
|
|
|
|
|
raw_spin_lock(&rt_rq->rt_runtime_lock);
|
|
|
|
/*
|
|
|
|
* We'll let actual RT tasks worry about the overflow here, we
|
sched/deadline: Prevent rt_time growth to infinity
Kirill Tkhai noted:
Since deadline tasks share rt bandwidth, we must care about
bandwidth timer set. Otherwise rt_time may grow up to infinity
in update_curr_dl(), if there are no other available RT tasks
on top level bandwidth.
RT task were in fact throttled right after they got enqueued,
and never executed again (rt_time never again went below rt_runtime).
Peter then proposed to accrue DL execution on rt_time only when
rt timer is active, and proposed a patch (this patch is a slight
modification of that) to implement that behavior. While this
solves Kirill problem, it has a drawback.
Indeed, Kirill noted again:
It looks we may get into a situation, when all CPU time is shared
between RT and DL tasks:
rt_runtime = n
rt_period = 2n
| RT working, DL sleeping | DL working, RT sleeping |
-----------------------------------------------------------
| (1) duration = n | (2) duration = n | (repeat)
|--------------------------|------------------------------|
| (rt_bw timer is running) | (rt_bw timer is not running) |
No time for fair tasks at all.
While this can happen during the first period, if rq is always backlogged,
RT tasks won't have the opportunity to execute anymore: rt_time reached
rt_runtime during (1), suppose after (2) RT is enqueued back, it gets
throttled since rt timer didn't fire, replenishment is from now on eaten up
by DL tasks that accrue their execution on rt_time (while rt timer is
active - we have an RT task waiting for replenishment). FAIR tasks are
not touched after this first period. Ok, this is not ideal, and the situation
is even worse!
What above (the nice case), practically never happens in reality, where
your rt timer is not aligned to tasks periods, tasks are in general not
periodic, etc.. Long story short, you always risk to overload your system.
This patch is based on Peter's idea, but exploits an additional fact:
if you don't have RT tasks enqueued, it makes little sense to continue
incrementing rt_time once you reached the upper limit (DL tasks have their
own mechanism for throttling).
This cures both problems:
- no matter how many DL instances in the past, you'll have an rt_time
slightly above rt_runtime when an RT task is enqueued, and from that
point on (after the first replenishment), the task will normally execute;
- you can still eat up all bandwidth during the first period, but not
anymore after that, remember that DL execution will increment rt_time
till the upper limit is reached.
The situation is still not perfect! But, we have a simple solution for now,
that limits how much you can jeopardize your system, as we keep working
towards the right answer: RT groups scheduled using deadline servers.
Reported-by: Kirill Tkhai <tkhai@yandex.ru>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140225151515.617714e2f2cd6c558531ba61@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-02-21 18:37:15 +08:00
|
|
|
* have our own CBS to keep us inline; only account when RT
|
|
|
|
* bandwidth is relevant.
|
2013-12-17 19:44:49 +08:00
|
|
|
*/
|
sched/deadline: Prevent rt_time growth to infinity
Kirill Tkhai noted:
Since deadline tasks share rt bandwidth, we must care about
bandwidth timer set. Otherwise rt_time may grow up to infinity
in update_curr_dl(), if there are no other available RT tasks
on top level bandwidth.
RT task were in fact throttled right after they got enqueued,
and never executed again (rt_time never again went below rt_runtime).
Peter then proposed to accrue DL execution on rt_time only when
rt timer is active, and proposed a patch (this patch is a slight
modification of that) to implement that behavior. While this
solves Kirill problem, it has a drawback.
Indeed, Kirill noted again:
It looks we may get into a situation, when all CPU time is shared
between RT and DL tasks:
rt_runtime = n
rt_period = 2n
| RT working, DL sleeping | DL working, RT sleeping |
-----------------------------------------------------------
| (1) duration = n | (2) duration = n | (repeat)
|--------------------------|------------------------------|
| (rt_bw timer is running) | (rt_bw timer is not running) |
No time for fair tasks at all.
While this can happen during the first period, if rq is always backlogged,
RT tasks won't have the opportunity to execute anymore: rt_time reached
rt_runtime during (1), suppose after (2) RT is enqueued back, it gets
throttled since rt timer didn't fire, replenishment is from now on eaten up
by DL tasks that accrue their execution on rt_time (while rt timer is
active - we have an RT task waiting for replenishment). FAIR tasks are
not touched after this first period. Ok, this is not ideal, and the situation
is even worse!
What above (the nice case), practically never happens in reality, where
your rt timer is not aligned to tasks periods, tasks are in general not
periodic, etc.. Long story short, you always risk to overload your system.
This patch is based on Peter's idea, but exploits an additional fact:
if you don't have RT tasks enqueued, it makes little sense to continue
incrementing rt_time once you reached the upper limit (DL tasks have their
own mechanism for throttling).
This cures both problems:
- no matter how many DL instances in the past, you'll have an rt_time
slightly above rt_runtime when an RT task is enqueued, and from that
point on (after the first replenishment), the task will normally execute;
- you can still eat up all bandwidth during the first period, but not
anymore after that, remember that DL execution will increment rt_time
till the upper limit is reached.
The situation is still not perfect! But, we have a simple solution for now,
that limits how much you can jeopardize your system, as we keep working
towards the right answer: RT groups scheduled using deadline servers.
Reported-by: Kirill Tkhai <tkhai@yandex.ru>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20140225151515.617714e2f2cd6c558531ba61@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-02-21 18:37:15 +08:00
|
|
|
if (sched_rt_bandwidth_account(rt_rq))
|
|
|
|
rt_rq->rt_time += delta_exec;
|
2013-12-17 19:44:49 +08:00
|
|
|
raw_spin_unlock(&rt_rq->rt_runtime_lock);
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2017-05-19 04:13:29 +08:00
|
|
|
static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = container_of(timer,
|
|
|
|
struct sched_dl_entity,
|
|
|
|
inactive_timer);
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
struct rq_flags rf;
|
|
|
|
struct rq *rq;
|
|
|
|
|
|
|
|
rq = task_rq_lock(p, &rf);
|
|
|
|
|
2018-05-31 00:08:09 +08:00
|
|
|
sched_clock_tick();
|
|
|
|
update_rq_clock(rq);
|
|
|
|
|
2021-06-11 16:28:17 +08:00
|
|
|
if (!dl_task(p) || READ_ONCE(p->__state) == TASK_DEAD) {
|
2017-05-19 04:13:30 +08:00
|
|
|
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
|
|
|
|
|
2021-06-11 16:28:17 +08:00
|
|
|
if (READ_ONCE(p->__state) == TASK_DEAD && dl_se->dl_non_contending) {
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(&p->dl, dl_rq_of_se(&p->dl));
|
|
|
|
sub_rq_bw(&p->dl, dl_rq_of_se(&p->dl));
|
2017-05-19 04:13:29 +08:00
|
|
|
dl_se->dl_non_contending = 0;
|
|
|
|
}
|
2017-05-19 04:13:30 +08:00
|
|
|
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
2017-09-07 18:09:30 +08:00
|
|
|
__dl_sub(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
|
2017-05-19 04:13:30 +08:00
|
|
|
raw_spin_unlock(&dl_b->lock);
|
2017-05-19 04:13:29 +08:00
|
|
|
__dl_clear_params(p);
|
|
|
|
|
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
if (dl_se->dl_non_contending == 0)
|
|
|
|
goto unlock;
|
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(dl_se, &rq->dl);
|
2017-05-19 04:13:29 +08:00
|
|
|
dl_se->dl_non_contending = 0;
|
|
|
|
unlock:
|
|
|
|
task_rq_unlock(rq, p, &rf);
|
|
|
|
put_task_struct(p);
|
|
|
|
|
|
|
|
return HRTIMER_NORESTART;
|
|
|
|
}
|
|
|
|
|
|
|
|
void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct hrtimer *timer = &dl_se->inactive_timer;
|
|
|
|
|
2019-07-31 18:37:15 +08:00
|
|
|
hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
|
2017-05-19 04:13:29 +08:00
|
|
|
timer->function = inactive_task_timer;
|
|
|
|
}
|
|
|
|
|
2022-03-03 02:34:31 +08:00
|
|
|
#define __node_2_dle(node) \
|
|
|
|
rb_entry((node), struct sched_dl_entity, rb_node)
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
|
|
|
static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
|
|
|
|
{
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
|
|
|
|
if (dl_rq->earliest_dl.curr == 0 ||
|
|
|
|
dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
|
2020-10-15 03:39:04 +08:00
|
|
|
if (dl_rq->earliest_dl.curr == 0)
|
|
|
|
cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_HIGHER);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dl_rq->earliest_dl.curr = deadline;
|
sched/deadline: Split cpudl_set() into cpudl_set() and cpudl_clear()
These 2 exercise independent code paths and need different arguments.
After this change, you call:
cpudl_clear(cp, cpu);
cpudl_set(cp, cpu, dl);
instead of:
cpudl_set(cp, cpu, 0 /* dl */, 0 /* is_valid */);
cpudl_set(cp, cpu, dl, 1 /* is_valid */);
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-dl@retis.sssup.it
Link: http://lkml.kernel.org/r/1471184828-12644-4-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-14 22:27:08 +08:00
|
|
|
cpudl_set(&rq->rd->cpudl, rq->cpu, deadline);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
|
|
|
|
{
|
|
|
|
struct rq *rq = rq_of_dl_rq(dl_rq);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since we may have removed our earliest (and/or next earliest)
|
|
|
|
* task we must recompute them.
|
|
|
|
*/
|
|
|
|
if (!dl_rq->dl_nr_running) {
|
|
|
|
dl_rq->earliest_dl.curr = 0;
|
|
|
|
dl_rq->earliest_dl.next = 0;
|
sched/deadline: Split cpudl_set() into cpudl_set() and cpudl_clear()
These 2 exercise independent code paths and need different arguments.
After this change, you call:
cpudl_clear(cp, cpu);
cpudl_set(cp, cpu, dl);
instead of:
cpudl_set(cp, cpu, 0 /* dl */, 0 /* is_valid */);
cpudl_set(cp, cpu, dl, 1 /* is_valid */);
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-dl@retis.sssup.it
Link: http://lkml.kernel.org/r/1471184828-12644-4-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-14 22:27:08 +08:00
|
|
|
cpudl_clear(&rq->rd->cpudl, rq->cpu);
|
2020-10-15 03:39:04 +08:00
|
|
|
cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
} else {
|
2022-03-03 02:34:31 +08:00
|
|
|
struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
|
|
|
|
struct sched_dl_entity *entry = __node_2_dle(leftmost);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
dl_rq->earliest_dl.curr = entry->deadline;
|
sched/deadline: Split cpudl_set() into cpudl_set() and cpudl_clear()
These 2 exercise independent code paths and need different arguments.
After this change, you call:
cpudl_clear(cp, cpu);
cpudl_set(cp, cpu, dl);
instead of:
cpudl_set(cp, cpu, 0 /* dl */, 0 /* is_valid */);
cpudl_set(cp, cpu, dl, 1 /* is_valid */);
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-dl@retis.sssup.it
Link: http://lkml.kernel.org/r/1471184828-12644-4-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-14 22:27:08 +08:00
|
|
|
cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#else
|
|
|
|
|
|
|
|
static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
|
|
|
|
static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
|
|
|
|
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
int prio = dl_task_of(dl_se)->prio;
|
|
|
|
u64 deadline = dl_se->deadline;
|
|
|
|
|
|
|
|
WARN_ON(!dl_prio(prio));
|
|
|
|
dl_rq->dl_nr_running++;
|
2014-05-09 07:00:14 +08:00
|
|
|
add_nr_running(rq_of_dl_rq(dl_rq), 1);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
inc_dl_deadline(dl_rq, deadline);
|
|
|
|
inc_dl_migration(dl_se, dl_rq);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline
|
|
|
|
void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
|
|
|
|
{
|
|
|
|
int prio = dl_task_of(dl_se)->prio;
|
|
|
|
|
|
|
|
WARN_ON(!dl_prio(prio));
|
|
|
|
WARN_ON(!dl_rq->dl_nr_running);
|
|
|
|
dl_rq->dl_nr_running--;
|
2014-05-09 07:00:14 +08:00
|
|
|
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
dec_dl_deadline(dl_rq, dl_se->deadline);
|
|
|
|
dec_dl_migration(dl_se, dl_rq);
|
|
|
|
}
|
|
|
|
|
2020-04-29 23:04:41 +08:00
|
|
|
static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
|
|
|
|
{
|
|
|
|
return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
|
|
|
|
}
|
|
|
|
|
2021-09-05 22:35:47 +08:00
|
|
|
static inline struct sched_statistics *
|
|
|
|
__schedstats_from_dl_se(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
return &dl_task_of(dl_se)->stats;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
update_stats_wait_start_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct sched_statistics *stats;
|
|
|
|
|
|
|
|
if (!schedstat_enabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
stats = __schedstats_from_dl_se(dl_se);
|
|
|
|
__update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
update_stats_wait_end_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct sched_statistics *stats;
|
|
|
|
|
|
|
|
if (!schedstat_enabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
stats = __schedstats_from_dl_se(dl_se);
|
|
|
|
__update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
update_stats_enqueue_sleeper_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct sched_statistics *stats;
|
|
|
|
|
|
|
|
if (!schedstat_enabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
stats = __schedstats_from_dl_se(dl_se);
|
|
|
|
__update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
update_stats_enqueue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
|
|
|
|
int flags)
|
|
|
|
{
|
|
|
|
if (!schedstat_enabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (flags & ENQUEUE_WAKEUP)
|
|
|
|
update_stats_enqueue_sleeper_dl(dl_rq, dl_se);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void
|
|
|
|
update_stats_dequeue_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se,
|
|
|
|
int flags)
|
|
|
|
{
|
|
|
|
struct task_struct *p = dl_task_of(dl_se);
|
|
|
|
|
|
|
|
if (!schedstat_enabled())
|
|
|
|
return;
|
|
|
|
|
|
|
|
if ((flags & DEQUEUE_SLEEP)) {
|
|
|
|
unsigned int state;
|
|
|
|
|
|
|
|
state = READ_ONCE(p->__state);
|
|
|
|
if (state & TASK_INTERRUPTIBLE)
|
|
|
|
__schedstat_set(p->stats.sleep_start,
|
|
|
|
rq_clock(rq_of_dl_rq(dl_rq)));
|
|
|
|
|
|
|
|
if (state & TASK_UNINTERRUPTIBLE)
|
|
|
|
__schedstat_set(p->stats.block_start,
|
|
|
|
rq_clock(rq_of_dl_rq(dl_rq)));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(!RB_EMPTY_NODE(&dl_se->rb_node));
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2020-04-29 23:04:41 +08:00
|
|
|
rb_add_cached(&dl_se->rb_node, &dl_rq->root, __dl_less);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
inc_dl_tasks(dl_se, dl_rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
|
|
|
|
|
|
|
|
if (RB_EMPTY_NODE(&dl_se->rb_node))
|
|
|
|
return;
|
|
|
|
|
2017-09-09 07:14:58 +08:00
|
|
|
rb_erase_cached(&dl_se->rb_node, &dl_rq->root);
|
2020-04-29 23:04:41 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
RB_CLEAR_NODE(&dl_se->rb_node);
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dec_dl_tasks(dl_se, dl_rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
2020-11-17 14:14:32 +08:00
|
|
|
enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(on_dl_rq(dl_se));
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2021-09-05 22:35:47 +08:00
|
|
|
update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* If this is a wakeup or a new instance, the scheduling
|
|
|
|
* parameters of the task might need updating. Otherwise,
|
|
|
|
* we want a replenishment of its runtime.
|
|
|
|
*/
|
2017-05-19 04:13:28 +08:00
|
|
|
if (flags & ENQUEUE_WAKEUP) {
|
2017-05-19 04:13:34 +08:00
|
|
|
task_contending(dl_se, flags);
|
2020-11-17 14:14:32 +08:00
|
|
|
update_dl_entity(dl_se);
|
2017-05-19 04:13:28 +08:00
|
|
|
} else if (flags & ENQUEUE_REPLENISH) {
|
2020-11-17 14:14:32 +08:00
|
|
|
replenish_dl_entity(dl_se);
|
2017-09-07 18:09:29 +08:00
|
|
|
} else if ((flags & ENQUEUE_RESTORE) &&
|
|
|
|
dl_time_before(dl_se->deadline,
|
|
|
|
rq_clock(rq_of_dl_rq(dl_rq_of_se(dl_se))))) {
|
|
|
|
setup_new_dl_entity(dl_se);
|
2017-05-19 04:13:28 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
__enqueue_dl_entity(dl_se);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
|
|
|
|
{
|
|
|
|
__dequeue_dl_entity(dl_se);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
|
|
|
|
{
|
2020-11-17 14:14:32 +08:00
|
|
|
if (is_dl_boosted(&p->dl)) {
|
2020-09-16 15:06:39 +08:00
|
|
|
/*
|
|
|
|
* Because of delays in the detection of the overrun of a
|
|
|
|
* thread's runtime, it might be the case that a thread
|
|
|
|
* goes to sleep in a rt mutex with negative runtime. As
|
|
|
|
* a consequence, the thread will be throttled.
|
|
|
|
*
|
|
|
|
* While waiting for the mutex, this thread can also be
|
|
|
|
* boosted via PI, resulting in a thread that is throttled
|
|
|
|
* and boosted at the same time.
|
|
|
|
*
|
|
|
|
* In this case, the boost overrides the throttle.
|
|
|
|
*/
|
|
|
|
if (p->dl.dl_throttled) {
|
|
|
|
/*
|
|
|
|
* The replenish timer needs to be canceled. No
|
|
|
|
* problem if it fires concurrently: boosted threads
|
|
|
|
* are ignored in dl_task_timer().
|
|
|
|
*/
|
|
|
|
hrtimer_try_to_cancel(&p->dl.dl_timer);
|
|
|
|
p->dl.dl_throttled = 0;
|
|
|
|
}
|
2014-10-24 17:16:37 +08:00
|
|
|
} else if (!dl_prio(p->normal_prio)) {
|
|
|
|
/*
|
2020-08-31 19:07:19 +08:00
|
|
|
* Special case in which we have a !SCHED_DEADLINE task that is going
|
|
|
|
* to be deboosted, but exceeds its runtime while doing so. No point in
|
|
|
|
* replenishing it, as it's going to return back to its original
|
|
|
|
* scheduling class after this. If it has been throttled, we need to
|
|
|
|
* clear the flag, otherwise the task may wake up as throttled after
|
|
|
|
* being boosted again with no means to replenish the runtime and clear
|
|
|
|
* the throttle.
|
2014-10-24 17:16:37 +08:00
|
|
|
*/
|
2020-08-31 19:07:19 +08:00
|
|
|
p->dl.dl_throttled = 0;
|
2022-07-14 23:19:08 +08:00
|
|
|
if (!(flags & ENQUEUE_REPLENISH))
|
|
|
|
printk_deferred_once("sched: DL de-boosted task PID %d: REPLENISH flag missing\n",
|
|
|
|
task_pid_nr(p));
|
|
|
|
|
2014-10-24 17:16:37 +08:00
|
|
|
return;
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE inheritance logic
Some method to deal with rt-mutexes and make sched_dl interact with
the current PI-coded is needed, raising all but trivial issues, that
needs (according to us) to be solved with some restructuring of
the pi-code (i.e., going toward a proxy execution-ish implementation).
This is under development, in the meanwhile, as a temporary solution,
what this commits does is:
- ensure a pi-lock owner with waiters is never throttled down. Instead,
when it runs out of runtime, it immediately gets replenished and it's
deadline is postponed;
- the scheduling parameters (relative deadline and default runtime)
used for that replenishments --during the whole period it holds the
pi-lock-- are the ones of the waiting task with earliest deadline.
Acting this way, we provide some kind of boosting to the lock-owner,
still by using the existing (actually, slightly modified by the previous
commit) pi-architecture.
We would stress the fact that this is only a surely needed, all but
clean solution to the problem. In the end it's only a way to re-start
discussion within the community. So, as always, comments, ideas, rants,
etc.. are welcome! :-)
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Added !RT_MUTEXES build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-11-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:44 +08:00
|
|
|
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
/*
|
|
|
|
* Check if a constrained deadline task was activated
|
|
|
|
* after the deadline but before the next period.
|
|
|
|
* If that is the case, the task will be throttled and
|
|
|
|
* the replenishment timer will be set to the next period.
|
|
|
|
*/
|
sched/deadline: Use the revised wakeup rule for suspending constrained dl tasks
We have been facing some problems with self-suspending constrained
deadline tasks. The main reason is that the original CBS was not
designed for such sort of tasks.
One problem reported by Xunlei Pang takes place when a task
suspends, and then is awakened before the deadline, but so close
to the deadline that its remaining runtime can cause the task
to have an absolute density higher than allowed. In such situation,
the original CBS assumes that the task is facing an early activation,
and so it replenishes the task and set another deadline, one deadline
in the future. This rule works fine for implicit deadline tasks.
Moreover, it allows the system to adapt the period of a task in which
the external event source suffered from a clock drift.
However, this opens the window for bandwidth leakage for constrained
deadline tasks. For instance, a task with the following parameters:
runtime = 5 ms
deadline = 7 ms
[density] = 5 / 7 = 0.71
period = 1000 ms
If the task runs for 1 ms, and then suspends for another 1ms,
it will be awakened with the following parameters:
remaining runtime = 4
laxity = 5
presenting a absolute density of 4 / 5 = 0.80.
In this case, the original CBS would assume the task had an early
wakeup. Then, CBS will reset the runtime, and the absolute deadline will
be postponed by one relative deadline, allowing the task to run.
The problem is that, if the task runs this pattern forever, it will keep
receiving bandwidth, being able to run 1ms every 2ms. Following this
behavior, the task would be able to run 500 ms in 1 sec. Thus running
more than the 5 ms / 1 sec the admission control allowed it to run.
Trying to address the self-suspending case, Luca Abeni, Giuseppe
Lipari, and Juri Lelli [1] revisited the CBS in order to deal with
self-suspending tasks. In the new approach, rather than
replenishing/postponing the absolute deadline, the revised wakeup rule
adjusts the remaining runtime, reducing it to fit into the allowed
density.
A revised version of the idea is:
At a given time t, the maximum absolute density of a task cannot be
higher than its relative density, that is:
runtime / (deadline - t) <= dl_runtime / dl_deadline
Knowing the laxity of a task (deadline - t), it is possible to move
it to the other side of the equality, thus enabling to define max
remaining runtime a task can use within the absolute deadline, without
over-running the allowed density:
runtime = (dl_runtime / dl_deadline) * (deadline - t)
For instance, in our previous example, the task could still run:
runtime = ( 5 / 7 ) * 5
runtime = 3.57 ms
Without causing damage for other deadline tasks. It is note worthy
that the laxity cannot be negative because that would cause a negative
runtime. Thus, this patch depends on the patch:
df8eac8cafce ("sched/deadline: Throttle a constrained deadline task activated after the deadline")
Which throttles a constrained deadline task activated after the
deadline.
Finally, it is also possible to use the revised wakeup rule for
all other tasks, but that would require some more discussions
about pros and cons.
Reported-by: Xunlei Pang <xpang@redhat.com>
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
[peterz: replaced dl_is_constrained with dl_is_implicit]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/5c800ab3a74a168a84ee5f3f84d12a02e11383be.1495803804.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-05-29 22:24:03 +08:00
|
|
|
if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
|
sched/deadline: Throttle a constrained deadline task activated after the deadline
During the activation, CBS checks if it can reuse the current task's
runtime and period. If the deadline of the task is in the past, CBS
cannot use the runtime, and so it replenishes the task. This rule
works fine for implicit deadline tasks (deadline == period), and the
CBS was designed for implicit deadline tasks. However, a task with
constrained deadline (deadine < period) might be awakened after the
deadline, but before the next period. In this case, replenishing the
task would allow it to run for runtime / deadline. As in this case
deadline < period, CBS enables a task to run for more than the
runtime / period. In a very loaded system, this can cause a domino
effect, making other tasks miss their deadlines.
To avoid this problem, in the activation of a constrained deadline
task after the deadline but before the next period, throttle the
task and set the replenishing timer to the begin of the next period,
unless it is boosted.
Reproducer:
--------------- %< ---------------
int main (int argc, char **argv)
{
int ret;
int flags = 0;
unsigned long l = 0;
struct timespec ts;
struct sched_attr attr;
memset(&attr, 0, sizeof(attr));
attr.size = sizeof(attr);
attr.sched_policy = SCHED_DEADLINE;
attr.sched_runtime = 2 * 1000 * 1000; /* 2 ms */
attr.sched_deadline = 2 * 1000 * 1000; /* 2 ms */
attr.sched_period = 2 * 1000 * 1000 * 1000; /* 2 s */
ts.tv_sec = 0;
ts.tv_nsec = 2000 * 1000; /* 2 ms */
ret = sched_setattr(0, &attr, flags);
if (ret < 0) {
perror("sched_setattr");
exit(-1);
}
for(;;) {
/* XXX: you may need to adjust the loop */
for (l = 0; l < 150000; l++);
/*
* The ideia is to go to sleep right before the deadline
* and then wake up before the next period to receive
* a new replenishment.
*/
nanosleep(&ts, NULL);
}
exit(0);
}
--------------- >% ---------------
On my box, this reproducer uses almost 50% of the CPU time, which is
obviously wrong for a task with 2/2000 reservation.
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@santannapisa.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Romulo Silva de Oliveira <romulo.deoliveira@ufsc.br>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/edf58354e01db46bf42df8d2dd32418833f68c89.1488392936.git.bristot@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-03-02 22:10:58 +08:00
|
|
|
dl_check_constrained_dl(&p->dl);
|
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
|
2017-12-04 18:23:20 +08:00
|
|
|
add_rq_bw(&p->dl, &rq->dl);
|
|
|
|
add_running_bw(&p->dl, &rq->dl);
|
2017-05-19 04:13:34 +08:00
|
|
|
}
|
2017-05-19 04:13:28 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
2017-05-19 04:13:28 +08:00
|
|
|
* If p is throttled, we do not enqueue it. In fact, if it exhausted
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
* its budget it needs a replenishment and, since it now is on
|
|
|
|
* its rq, the bandwidth timer callback (which clearly has not
|
|
|
|
* run yet) will take care of this.
|
2017-05-19 04:13:28 +08:00
|
|
|
* However, the active utilization does not depend on the fact
|
|
|
|
* that the task is on the runqueue or not (but depends on the
|
|
|
|
* task's state - in GRUB parlance, "inactive" vs "active contending").
|
|
|
|
* In other words, even if a task is throttled its utilization must
|
|
|
|
* be counted in the active utilization; hence, we need to call
|
|
|
|
* add_running_bw().
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*/
|
2017-05-19 04:13:28 +08:00
|
|
|
if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
|
2017-05-19 04:13:29 +08:00
|
|
|
if (flags & ENQUEUE_WAKEUP)
|
2017-05-19 04:13:34 +08:00
|
|
|
task_contending(&p->dl, flags);
|
2017-05-19 04:13:29 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
return;
|
2017-05-19 04:13:28 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
2021-09-05 22:35:47 +08:00
|
|
|
check_schedstat_required();
|
|
|
|
update_stats_wait_start_dl(dl_rq_of_se(&p->dl), &p->dl);
|
|
|
|
|
2020-11-17 14:14:32 +08:00
|
|
|
enqueue_dl_entity(&p->dl, flags);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2017-02-05 22:41:03 +08:00
|
|
|
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
enqueue_pushable_dl_task(rq, p);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
|
|
|
|
{
|
2021-09-05 22:35:47 +08:00
|
|
|
update_stats_dequeue_dl(&rq->dl, &p->dl, flags);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
dequeue_dl_entity(&p->dl);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dequeue_pushable_dl_task(rq, p);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
|
|
|
|
{
|
|
|
|
update_curr_dl(rq);
|
|
|
|
__dequeue_task_dl(rq, p, flags);
|
2017-05-19 04:13:28 +08:00
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(&p->dl, &rq->dl);
|
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
2017-05-19 04:13:34 +08:00
|
|
|
}
|
2017-05-19 04:13:28 +08:00
|
|
|
|
|
|
|
/*
|
2017-05-19 04:13:29 +08:00
|
|
|
* This check allows to start the inactive timer (or to immediately
|
|
|
|
* decrease the active utilization, if needed) in two cases:
|
2017-05-19 04:13:28 +08:00
|
|
|
* when the task blocks and when it is terminating
|
|
|
|
* (p->state == TASK_DEAD). We can handle the two cases in the same
|
|
|
|
* way, because from GRUB's point of view the same thing is happening
|
|
|
|
* (the task moves from "active contending" to "active non contending"
|
|
|
|
* or "inactive")
|
|
|
|
*/
|
|
|
|
if (flags & DEQUEUE_SLEEP)
|
2017-05-19 04:13:29 +08:00
|
|
|
task_non_contending(p);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Yield task semantic for -deadline tasks is:
|
|
|
|
*
|
|
|
|
* get off from the CPU until our next instance, with
|
|
|
|
* a new runtime. This is of little use now, since we
|
|
|
|
* don't have a bandwidth reclaiming mechanism. Anyway,
|
|
|
|
* bandwidth reclaiming is planned for the future, and
|
|
|
|
* yield_task_dl will indicate that some spare budget
|
|
|
|
* is available for other task instances to use it.
|
|
|
|
*/
|
|
|
|
static void yield_task_dl(struct rq *rq)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* We make the task go to sleep until its current deadline by
|
|
|
|
* forcing its runtime to zero. This way, update_curr_dl() stops
|
|
|
|
* it and the bandwidth timer will wake it up and will give it
|
2014-04-15 19:49:04 +08:00
|
|
|
* new scheduling parameters (thanks to dl_yielded=1).
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
*/
|
2016-02-23 20:28:22 +08:00
|
|
|
rq->curr->dl.dl_yielded = 1;
|
|
|
|
|
2015-02-04 17:09:32 +08:00
|
|
|
update_rq_clock(rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
update_curr_dl(rq);
|
2015-03-10 12:20:00 +08:00
|
|
|
/*
|
|
|
|
* Tell update_rq_clock() that we've just updated,
|
|
|
|
* so we don't do microscopic update in schedule()
|
|
|
|
* and double the fastpath cost.
|
|
|
|
*/
|
2018-04-05 00:15:39 +08:00
|
|
|
rq_clock_skip_update(rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
2022-08-26 16:34:53 +08:00
|
|
|
static inline bool dl_task_is_earliest_deadline(struct task_struct *p,
|
|
|
|
struct rq *rq)
|
|
|
|
{
|
|
|
|
return (!rq->dl.dl_nr_running ||
|
|
|
|
dl_time_before(p->dl.deadline,
|
|
|
|
rq->dl.earliest_dl.curr));
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
static int find_later_rq(struct task_struct *task);
|
|
|
|
|
|
|
|
static int
|
2020-11-03 02:45:13 +08:00
|
|
|
select_task_rq_dl(struct task_struct *p, int cpu, int flags)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
{
|
|
|
|
struct task_struct *curr;
|
2020-05-20 21:42:42 +08:00
|
|
|
bool select_rq;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
struct rq *rq;
|
|
|
|
|
2020-11-03 02:45:13 +08:00
|
|
|
if (!(flags & WF_TTWU))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
rq = cpu_rq(cpu);
|
|
|
|
|
|
|
|
rcu_read_lock();
|
2015-04-29 04:00:20 +08:00
|
|
|
curr = READ_ONCE(rq->curr); /* unlocked access */
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are dealing with a -deadline task, we must
|
|
|
|
* decide where to wake it up.
|
|
|
|
* If it has a later deadline and the current task
|
|
|
|
* on this rq can't move (provided the waking task
|
|
|
|
* can!) we prefer to send it somewhere else. On the
|
|
|
|
* other hand, if it has a shorter deadline, we
|
|
|
|
* try to make it stay here, it might be important.
|
|
|
|
*/
|
2020-05-20 21:42:42 +08:00
|
|
|
select_rq = unlikely(dl_task(curr)) &&
|
|
|
|
(curr->nr_cpus_allowed < 2 ||
|
|
|
|
!dl_entity_preempt(&p->dl, &curr->dl)) &&
|
|
|
|
p->nr_cpus_allowed > 1;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Take the capacity of the CPU into account to
|
|
|
|
* ensure it fits the requirement of the task.
|
|
|
|
*/
|
2022-07-29 19:13:03 +08:00
|
|
|
if (sched_asym_cpucap_active())
|
2020-05-20 21:42:42 +08:00
|
|
|
select_rq |= !dl_task_fits_capacity(p, cpu);
|
|
|
|
|
|
|
|
if (select_rq) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
int target = find_later_rq(p);
|
|
|
|
|
2015-05-13 14:01:03 +08:00
|
|
|
if (target != -1 &&
|
2022-08-26 16:34:53 +08:00
|
|
|
dl_task_is_earliest_deadline(p, cpu_rq(target)))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
cpu = target;
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
out:
|
|
|
|
return cpu;
|
|
|
|
}
|
|
|
|
|
sched/numa: Pass destination CPU as a parameter to migrate_task_rq
This additional parameter (new_cpu) is used later for identifying if
task migration is across nodes.
No functional change.
Specjbb2005 results (8 warehouses)
Higher bops are better
2 Socket - 2 Node Haswell - X86
JVMS Prev Current %Change
4 203353 200668 -1.32036
1 328205 321791 -1.95427
2 Socket - 4 Node Power8 - PowerNV
JVMS Prev Current %Change
1 214384 204848 -4.44809
2 Socket - 2 Node Power9 - PowerNV
JVMS Prev Current %Change
4 188553 188098 -0.241311
1 196273 200351 2.07772
4 Socket - 4 Node Power7 - PowerVM
JVMS Prev Current %Change
8 57581.2 58145.9 0.980702
1 103468 103798 0.318939
Brings out the variance between different specjbb2005 runs.
Some events stats before and after applying the patch.
perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86
Event Before After
cs 13,941,377 13,912,183
migrations 1,157,323 1,155,931
faults 382,175 367,139
cache-misses 54,993,823,500 54,240,196,814
sched:sched_move_numa 2,005 1,571
sched:sched_stick_numa 14 9
sched:sched_swap_numa 529 463
migrate:mm_migrate_pages 1,573 703
vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86
Event Before After
numa_hint_faults 67099 50155
numa_hint_faults_local 58456 45264
numa_hit 240416 239652
numa_huge_pte_updates 18 36
numa_interleave 65 68
numa_local 240339 239576
numa_other 77 76
numa_pages_migrated 1574 680
numa_pte_updates 77182 71146
perf stats 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86
Event Before After
cs 3,176,453 3,156,720
migrations 30,238 30,354
faults 87,869 97,261
cache-misses 12,544,479,391 12,400,026,826
sched:sched_move_numa 23 4
sched:sched_stick_numa 0 0
sched:sched_swap_numa 6 1
migrate:mm_migrate_pages 10 20
vmstat 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86
Event Before After
numa_hint_faults 236 272
numa_hint_faults_local 201 186
numa_hit 72293 71362
numa_huge_pte_updates 0 0
numa_interleave 26 23
numa_local 72233 71299
numa_other 60 63
numa_pages_migrated 8 2
numa_pte_updates 0 0
perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV
Event Before After
cs 8,478,820 8,606,824
migrations 171,323 155,352
faults 307,499 301,409
cache-misses 240,353,599 157,759,224
sched:sched_move_numa 214 168
sched:sched_stick_numa 0 0
sched:sched_swap_numa 4 3
migrate:mm_migrate_pages 89 125
vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV
Event Before After
numa_hint_faults 5301 4650
numa_hint_faults_local 4745 3946
numa_hit 92943 90489
numa_huge_pte_updates 0 0
numa_interleave 899 892
numa_local 92345 90034
numa_other 598 455
numa_pages_migrated 88 124
numa_pte_updates 5505 4818
perf stats 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV
Event Before After
cs 2,066,172 2,113,167
migrations 11,076 10,533
faults 149,544 142,727
cache-misses 10,398,067 5,594,192
sched:sched_move_numa 43 10
sched:sched_stick_numa 0 0
sched:sched_swap_numa 0 0
migrate:mm_migrate_pages 6 6
vmstat 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV
Event Before After
numa_hint_faults 3552 744
numa_hint_faults_local 3347 584
numa_hit 25611 25551
numa_huge_pte_updates 0 0
numa_interleave 213 263
numa_local 25583 25302
numa_other 28 249
numa_pages_migrated 6 6
numa_pte_updates 3535 744
perf stats 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM
Event Before After
cs 99,358,136 101,227,352
migrations 4,041,607 4,151,829
faults 749,653 745,233
cache-misses 225,562,543,251 224,669,561,766
sched:sched_move_numa 771 617
sched:sched_stick_numa 14 2
sched:sched_swap_numa 204 187
migrate:mm_migrate_pages 1,180 316
vmstat 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM
Event Before After
numa_hint_faults 27409 24195
numa_hint_faults_local 20677 21639
numa_hit 239988 238331
numa_huge_pte_updates 0 0
numa_interleave 0 0
numa_local 239983 238331
numa_other 5 0
numa_pages_migrated 1016 204
numa_pte_updates 27916 24561
perf stats 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM
Event Before After
cs 60,899,307 62,738,978
migrations 544,668 562,702
faults 270,834 228,465
cache-misses 74,543,455,635 75,778,067,952
sched:sched_move_numa 735 648
sched:sched_stick_numa 25 13
sched:sched_swap_numa 174 137
migrate:mm_migrate_pages 816 733
vmstat 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM
Event Before After
numa_hint_faults 11059 10281
numa_hint_faults_local 4733 3242
numa_hit 41384 36338
numa_huge_pte_updates 0 0
numa_interleave 0 0
numa_local 41383 36338
numa_other 1 0
numa_pages_migrated 815 706
numa_pte_updates 11323 10176
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jirka Hladky <jhladky@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1537552141-27815-3-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-09-22 01:48:57 +08:00
|
|
|
static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
|
2017-05-19 04:13:29 +08:00
|
|
|
{
|
sched/core: Avoid obvious double update_rq_clock warning
When we use raw_spin_rq_lock() to acquire the rq lock and have to
update the rq clock while holding the lock, the kernel may issue
a WARN_DOUBLE_CLOCK warning.
Since we directly use raw_spin_rq_lock() to acquire rq lock instead of
rq_lock(), there is no corresponding change to rq->clock_update_flags.
In particular, we have obtained the rq lock of other CPUs, the
rq->clock_update_flags of this CPU may be RQCF_UPDATED at this time, and
then calling update_rq_clock() will trigger the WARN_DOUBLE_CLOCK warning.
So we need to clear RQCF_UPDATED of rq->clock_update_flags to avoid
the WARN_DOUBLE_CLOCK warning.
For the sched_rt_period_timer() and migrate_task_rq_dl() cases
we simply replace raw_spin_rq_lock()/raw_spin_rq_unlock() with
rq_lock()/rq_unlock().
For the {pull,push}_{rt,dl}_task() cases, we add the
double_rq_clock_clear_update() function to clear RQCF_UPDATED of
rq->clock_update_flags, and call double_rq_clock_clear_update()
before double_lock_balance()/double_rq_lock() returns to avoid the
WARN_DOUBLE_CLOCK warning.
Some call trace reports:
Call Trace 1:
<IRQ>
sched_rt_period_timer+0x10f/0x3a0
? enqueue_top_rt_rq+0x110/0x110
__hrtimer_run_queues+0x1a9/0x490
hrtimer_interrupt+0x10b/0x240
__sysvec_apic_timer_interrupt+0x8a/0x250
sysvec_apic_timer_interrupt+0x9a/0xd0
</IRQ>
<TASK>
asm_sysvec_apic_timer_interrupt+0x12/0x20
Call Trace 2:
<TASK>
activate_task+0x8b/0x110
push_rt_task.part.108+0x241/0x2c0
push_rt_tasks+0x15/0x30
finish_task_switch+0xaa/0x2e0
? __switch_to+0x134/0x420
__schedule+0x343/0x8e0
? hrtimer_start_range_ns+0x101/0x340
schedule+0x4e/0xb0
do_nanosleep+0x8e/0x160
hrtimer_nanosleep+0x89/0x120
? hrtimer_init_sleeper+0x90/0x90
__x64_sys_nanosleep+0x96/0xd0
do_syscall_64+0x34/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 3:
<TASK>
deactivate_task+0x93/0xe0
pull_rt_task+0x33e/0x400
balance_rt+0x7e/0x90
__schedule+0x62f/0x8e0
do_task_dead+0x3f/0x50
do_exit+0x7b8/0xbb0
do_group_exit+0x2d/0x90
get_signal+0x9df/0x9e0
? preempt_count_add+0x56/0xa0
? __remove_hrtimer+0x35/0x70
arch_do_signal_or_restart+0x36/0x720
? nanosleep_copyout+0x39/0x50
? do_nanosleep+0x131/0x160
? audit_filter_inodes+0xf5/0x120
exit_to_user_mode_prepare+0x10f/0x1e0
syscall_exit_to_user_mode+0x17/0x30
do_syscall_64+0x40/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 4:
update_rq_clock+0x128/0x1a0
migrate_task_rq_dl+0xec/0x310
set_task_cpu+0x84/0x1e4
try_to_wake_up+0x1d8/0x5c0
wake_up_process+0x1c/0x30
hrtimer_wakeup+0x24/0x3c
__hrtimer_run_queues+0x114/0x270
hrtimer_interrupt+0xe8/0x244
arch_timer_handler_phys+0x30/0x50
handle_percpu_devid_irq+0x88/0x140
generic_handle_domain_irq+0x40/0x60
gic_handle_irq+0x48/0xe0
call_on_irq_stack+0x2c/0x60
do_interrupt_handler+0x80/0x84
Steps to reproduce:
1. Enable CONFIG_SCHED_DEBUG when compiling the kernel
2. echo 1 > /sys/kernel/debug/clear_warn_once
echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
echo "NO_RT_PUSH_IPI" > /sys/kernel/debug/sched/features
3. Run some rt/dl tasks that periodically work and sleep, e.g.
Create 2*n rt or dl (90% running) tasks via rt-app (on a system
with n CPUs), and Dietmar Eggemann reports Call Trace 4 when running
on PREEMPT_RT kernel.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220430085843.62939-2-jiahao.os@bytedance.com
2022-04-30 16:58:42 +08:00
|
|
|
struct rq_flags rf;
|
2017-05-19 04:13:29 +08:00
|
|
|
struct rq *rq;
|
|
|
|
|
2021-06-11 16:28:17 +08:00
|
|
|
if (READ_ONCE(p->__state) != TASK_WAKING)
|
2017-05-19 04:13:29 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
rq = task_rq(p);
|
|
|
|
/*
|
|
|
|
* Since p->state == TASK_WAKING, set_task_cpu() has been called
|
|
|
|
* from try_to_wake_up(). Hence, p->pi_lock is locked, but
|
|
|
|
* rq->lock is not... So, lock it
|
|
|
|
*/
|
sched/core: Avoid obvious double update_rq_clock warning
When we use raw_spin_rq_lock() to acquire the rq lock and have to
update the rq clock while holding the lock, the kernel may issue
a WARN_DOUBLE_CLOCK warning.
Since we directly use raw_spin_rq_lock() to acquire rq lock instead of
rq_lock(), there is no corresponding change to rq->clock_update_flags.
In particular, we have obtained the rq lock of other CPUs, the
rq->clock_update_flags of this CPU may be RQCF_UPDATED at this time, and
then calling update_rq_clock() will trigger the WARN_DOUBLE_CLOCK warning.
So we need to clear RQCF_UPDATED of rq->clock_update_flags to avoid
the WARN_DOUBLE_CLOCK warning.
For the sched_rt_period_timer() and migrate_task_rq_dl() cases
we simply replace raw_spin_rq_lock()/raw_spin_rq_unlock() with
rq_lock()/rq_unlock().
For the {pull,push}_{rt,dl}_task() cases, we add the
double_rq_clock_clear_update() function to clear RQCF_UPDATED of
rq->clock_update_flags, and call double_rq_clock_clear_update()
before double_lock_balance()/double_rq_lock() returns to avoid the
WARN_DOUBLE_CLOCK warning.
Some call trace reports:
Call Trace 1:
<IRQ>
sched_rt_period_timer+0x10f/0x3a0
? enqueue_top_rt_rq+0x110/0x110
__hrtimer_run_queues+0x1a9/0x490
hrtimer_interrupt+0x10b/0x240
__sysvec_apic_timer_interrupt+0x8a/0x250
sysvec_apic_timer_interrupt+0x9a/0xd0
</IRQ>
<TASK>
asm_sysvec_apic_timer_interrupt+0x12/0x20
Call Trace 2:
<TASK>
activate_task+0x8b/0x110
push_rt_task.part.108+0x241/0x2c0
push_rt_tasks+0x15/0x30
finish_task_switch+0xaa/0x2e0
? __switch_to+0x134/0x420
__schedule+0x343/0x8e0
? hrtimer_start_range_ns+0x101/0x340
schedule+0x4e/0xb0
do_nanosleep+0x8e/0x160
hrtimer_nanosleep+0x89/0x120
? hrtimer_init_sleeper+0x90/0x90
__x64_sys_nanosleep+0x96/0xd0
do_syscall_64+0x34/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 3:
<TASK>
deactivate_task+0x93/0xe0
pull_rt_task+0x33e/0x400
balance_rt+0x7e/0x90
__schedule+0x62f/0x8e0
do_task_dead+0x3f/0x50
do_exit+0x7b8/0xbb0
do_group_exit+0x2d/0x90
get_signal+0x9df/0x9e0
? preempt_count_add+0x56/0xa0
? __remove_hrtimer+0x35/0x70
arch_do_signal_or_restart+0x36/0x720
? nanosleep_copyout+0x39/0x50
? do_nanosleep+0x131/0x160
? audit_filter_inodes+0xf5/0x120
exit_to_user_mode_prepare+0x10f/0x1e0
syscall_exit_to_user_mode+0x17/0x30
do_syscall_64+0x40/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 4:
update_rq_clock+0x128/0x1a0
migrate_task_rq_dl+0xec/0x310
set_task_cpu+0x84/0x1e4
try_to_wake_up+0x1d8/0x5c0
wake_up_process+0x1c/0x30
hrtimer_wakeup+0x24/0x3c
__hrtimer_run_queues+0x114/0x270
hrtimer_interrupt+0xe8/0x244
arch_timer_handler_phys+0x30/0x50
handle_percpu_devid_irq+0x88/0x140
generic_handle_domain_irq+0x40/0x60
gic_handle_irq+0x48/0xe0
call_on_irq_stack+0x2c/0x60
do_interrupt_handler+0x80/0x84
Steps to reproduce:
1. Enable CONFIG_SCHED_DEBUG when compiling the kernel
2. echo 1 > /sys/kernel/debug/clear_warn_once
echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
echo "NO_RT_PUSH_IPI" > /sys/kernel/debug/sched/features
3. Run some rt/dl tasks that periodically work and sleep, e.g.
Create 2*n rt or dl (90% running) tasks via rt-app (on a system
with n CPUs), and Dietmar Eggemann reports Call Trace 4 when running
on PREEMPT_RT kernel.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220430085843.62939-2-jiahao.os@bytedance.com
2022-04-30 16:58:42 +08:00
|
|
|
rq_lock(rq, &rf);
|
2017-05-19 04:13:34 +08:00
|
|
|
if (p->dl.dl_non_contending) {
|
2021-08-04 21:59:25 +08:00
|
|
|
update_rq_clock(rq);
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_running_bw(&p->dl, &rq->dl);
|
2017-05-19 04:13:34 +08:00
|
|
|
p->dl.dl_non_contending = 0;
|
|
|
|
/*
|
|
|
|
* If the timer handler is currently running and the
|
2021-03-18 20:38:50 +08:00
|
|
|
* timer cannot be canceled, inactive_task_timer()
|
2017-05-19 04:13:34 +08:00
|
|
|
* will see that dl_not_contending is not set, and
|
|
|
|
* will not touch the rq's active utilization,
|
|
|
|
* so we are still safe.
|
|
|
|
*/
|
|
|
|
if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
|
|
|
|
put_task_struct(p);
|
|
|
|
}
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
sched/core: Avoid obvious double update_rq_clock warning
When we use raw_spin_rq_lock() to acquire the rq lock and have to
update the rq clock while holding the lock, the kernel may issue
a WARN_DOUBLE_CLOCK warning.
Since we directly use raw_spin_rq_lock() to acquire rq lock instead of
rq_lock(), there is no corresponding change to rq->clock_update_flags.
In particular, we have obtained the rq lock of other CPUs, the
rq->clock_update_flags of this CPU may be RQCF_UPDATED at this time, and
then calling update_rq_clock() will trigger the WARN_DOUBLE_CLOCK warning.
So we need to clear RQCF_UPDATED of rq->clock_update_flags to avoid
the WARN_DOUBLE_CLOCK warning.
For the sched_rt_period_timer() and migrate_task_rq_dl() cases
we simply replace raw_spin_rq_lock()/raw_spin_rq_unlock() with
rq_lock()/rq_unlock().
For the {pull,push}_{rt,dl}_task() cases, we add the
double_rq_clock_clear_update() function to clear RQCF_UPDATED of
rq->clock_update_flags, and call double_rq_clock_clear_update()
before double_lock_balance()/double_rq_lock() returns to avoid the
WARN_DOUBLE_CLOCK warning.
Some call trace reports:
Call Trace 1:
<IRQ>
sched_rt_period_timer+0x10f/0x3a0
? enqueue_top_rt_rq+0x110/0x110
__hrtimer_run_queues+0x1a9/0x490
hrtimer_interrupt+0x10b/0x240
__sysvec_apic_timer_interrupt+0x8a/0x250
sysvec_apic_timer_interrupt+0x9a/0xd0
</IRQ>
<TASK>
asm_sysvec_apic_timer_interrupt+0x12/0x20
Call Trace 2:
<TASK>
activate_task+0x8b/0x110
push_rt_task.part.108+0x241/0x2c0
push_rt_tasks+0x15/0x30
finish_task_switch+0xaa/0x2e0
? __switch_to+0x134/0x420
__schedule+0x343/0x8e0
? hrtimer_start_range_ns+0x101/0x340
schedule+0x4e/0xb0
do_nanosleep+0x8e/0x160
hrtimer_nanosleep+0x89/0x120
? hrtimer_init_sleeper+0x90/0x90
__x64_sys_nanosleep+0x96/0xd0
do_syscall_64+0x34/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 3:
<TASK>
deactivate_task+0x93/0xe0
pull_rt_task+0x33e/0x400
balance_rt+0x7e/0x90
__schedule+0x62f/0x8e0
do_task_dead+0x3f/0x50
do_exit+0x7b8/0xbb0
do_group_exit+0x2d/0x90
get_signal+0x9df/0x9e0
? preempt_count_add+0x56/0xa0
? __remove_hrtimer+0x35/0x70
arch_do_signal_or_restart+0x36/0x720
? nanosleep_copyout+0x39/0x50
? do_nanosleep+0x131/0x160
? audit_filter_inodes+0xf5/0x120
exit_to_user_mode_prepare+0x10f/0x1e0
syscall_exit_to_user_mode+0x17/0x30
do_syscall_64+0x40/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 4:
update_rq_clock+0x128/0x1a0
migrate_task_rq_dl+0xec/0x310
set_task_cpu+0x84/0x1e4
try_to_wake_up+0x1d8/0x5c0
wake_up_process+0x1c/0x30
hrtimer_wakeup+0x24/0x3c
__hrtimer_run_queues+0x114/0x270
hrtimer_interrupt+0xe8/0x244
arch_timer_handler_phys+0x30/0x50
handle_percpu_devid_irq+0x88/0x140
generic_handle_domain_irq+0x40/0x60
gic_handle_irq+0x48/0xe0
call_on_irq_stack+0x2c/0x60
do_interrupt_handler+0x80/0x84
Steps to reproduce:
1. Enable CONFIG_SCHED_DEBUG when compiling the kernel
2. echo 1 > /sys/kernel/debug/clear_warn_once
echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
echo "NO_RT_PUSH_IPI" > /sys/kernel/debug/sched/features
3. Run some rt/dl tasks that periodically work and sleep, e.g.
Create 2*n rt or dl (90% running) tasks via rt-app (on a system
with n CPUs), and Dietmar Eggemann reports Call Trace 4 when running
on PREEMPT_RT kernel.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220430085843.62939-2-jiahao.os@bytedance.com
2022-04-30 16:58:42 +08:00
|
|
|
rq_unlock(rq, &rf);
|
2017-05-19 04:13:29 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Current can't be migrated, useless to reschedule,
|
|
|
|
* let's hope p can move out.
|
|
|
|
*/
|
2017-02-05 22:41:03 +08:00
|
|
|
if (rq->curr->nr_cpus_allowed == 1 ||
|
2017-05-23 10:00:57 +08:00
|
|
|
!cpudl_find(&rq->rd->cpudl, rq->curr, NULL))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* p is migratable, so let's not schedule it and
|
|
|
|
* see if it is pushed or pulled somewhere else.
|
|
|
|
*/
|
2017-02-05 22:41:03 +08:00
|
|
|
if (p->nr_cpus_allowed != 1 &&
|
2017-05-23 10:00:57 +08:00
|
|
|
cpudl_find(&rq->rd->cpudl, p, NULL))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return;
|
|
|
|
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
2019-11-08 18:11:52 +08:00
|
|
|
static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
|
|
|
|
{
|
|
|
|
if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
|
|
|
|
/*
|
|
|
|
* This is OK, because current is on_cpu, which avoids it being
|
|
|
|
* picked for load-balance and preemption/IRQs are still
|
|
|
|
* disabled avoiding further scheduler activity on it and we've
|
|
|
|
* not yet started the picking loop.
|
|
|
|
*/
|
|
|
|
rq_unpin_lock(rq, rf);
|
|
|
|
pull_dl_task(rq);
|
|
|
|
rq_repin_lock(rq, rf);
|
|
|
|
}
|
|
|
|
|
|
|
|
return sched_stop_runnable(rq) || sched_dl_runnable(rq);
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
/*
|
|
|
|
* Only called when both the current and waking task are -deadline
|
|
|
|
* tasks.
|
|
|
|
*/
|
|
|
|
static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
|
|
|
|
int flags)
|
|
|
|
{
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
/*
|
|
|
|
* In the unlikely case current and p have the same deadline
|
|
|
|
* let us try to decide what's the best thing to do...
|
|
|
|
*/
|
sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks
In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.
Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).
Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.
However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).
Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.
This patch, therefore:
- adds system wide deadline bandwidth management by means of:
* /proc/sys/kernel/sched_dl_runtime_us,
* /proc/sys/kernel/sched_dl_period_us,
that determine (i.e., runtime / period) the total bandwidth
available on each CPU of each root_domain for -deadline tasks;
- couples the RT and deadline bandwidth management, i.e., enforces
that the sum of how much bandwidth is being devoted to -rt
-deadline tasks to stay below 100%.
This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:
M * (sched_dl_runtime_us / sched_dl_period_us)
It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:45 +08:00
|
|
|
if ((p->dl.deadline == rq->curr->dl.deadline) &&
|
|
|
|
!test_tsk_need_resched(rq->curr))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
check_preempt_equal_dl(rq, p);
|
|
|
|
#endif /* CONFIG_SMP */
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_SCHED_HRTICK
|
|
|
|
static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
2014-08-26 11:15:41 +08:00
|
|
|
hrtick_start(rq, p->dl.runtime);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
2014-11-11 09:52:26 +08:00
|
|
|
#else /* !CONFIG_SCHED_HRTICK */
|
|
|
|
static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
#endif
|
|
|
|
|
2019-11-08 21:16:00 +08:00
|
|
|
static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
|
sched/core: Introduce set_next_task() helper for better code readability
When we pick the next task, we will do the following for the task:
1) p->se.exec_start = rq_clock_task(rq);
2) dequeue_pushable(_dl)_task(rq, p);
When we call set_curr_task(), we also need to do the same thing
above. In rt.c, the code at 1) is in the _pick_next_task_rt()
and the code at 2) is in the pick_next_task_rt(). If we put two
operations in one function, maybe better. So, we introduce a new
function set_next_task(), which is responsible for doing the above.
By introducing the function we can get rid of calling the
dequeue_pushable(_dl)_task() directly(We can call set_next_task())
in pick_next_task() and have better code readability and reuse.
In set_curr_task_rt(), we also can call set_next_task().
Do this things such that we end up with:
static struct task_struct *pick_next_task(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf)
{
/* do something else ... */
put_prev_task(rq, prev);
/* pick next task p */
set_next_task(rq, p);
/* do something else ... */
}
put_prev_task() can match set_next_task(), which can make the
code more readable.
Signed-off-by: Muchun Song <smuchun@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20181026131743.21786-1-smuchun@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-10-26 21:17:43 +08:00
|
|
|
{
|
2021-09-05 22:35:47 +08:00
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
struct dl_rq *dl_rq = &rq->dl;
|
|
|
|
|
sched/core: Introduce set_next_task() helper for better code readability
When we pick the next task, we will do the following for the task:
1) p->se.exec_start = rq_clock_task(rq);
2) dequeue_pushable(_dl)_task(rq, p);
When we call set_curr_task(), we also need to do the same thing
above. In rt.c, the code at 1) is in the _pick_next_task_rt()
and the code at 2) is in the pick_next_task_rt(). If we put two
operations in one function, maybe better. So, we introduce a new
function set_next_task(), which is responsible for doing the above.
By introducing the function we can get rid of calling the
dequeue_pushable(_dl)_task() directly(We can call set_next_task())
in pick_next_task() and have better code readability and reuse.
In set_curr_task_rt(), we also can call set_next_task().
Do this things such that we end up with:
static struct task_struct *pick_next_task(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf)
{
/* do something else ... */
put_prev_task(rq, prev);
/* pick next task p */
set_next_task(rq, p);
/* do something else ... */
}
put_prev_task() can match set_next_task(), which can make the
code more readable.
Signed-off-by: Muchun Song <smuchun@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20181026131743.21786-1-smuchun@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-10-26 21:17:43 +08:00
|
|
|
p->se.exec_start = rq_clock_task(rq);
|
2021-09-05 22:35:47 +08:00
|
|
|
if (on_dl_rq(&p->dl))
|
|
|
|
update_stats_wait_end_dl(dl_rq, dl_se);
|
sched/core: Introduce set_next_task() helper for better code readability
When we pick the next task, we will do the following for the task:
1) p->se.exec_start = rq_clock_task(rq);
2) dequeue_pushable(_dl)_task(rq, p);
When we call set_curr_task(), we also need to do the same thing
above. In rt.c, the code at 1) is in the _pick_next_task_rt()
and the code at 2) is in the pick_next_task_rt(). If we put two
operations in one function, maybe better. So, we introduce a new
function set_next_task(), which is responsible for doing the above.
By introducing the function we can get rid of calling the
dequeue_pushable(_dl)_task() directly(We can call set_next_task())
in pick_next_task() and have better code readability and reuse.
In set_curr_task_rt(), we also can call set_next_task().
Do this things such that we end up with:
static struct task_struct *pick_next_task(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf)
{
/* do something else ... */
put_prev_task(rq, prev);
/* pick next task p */
set_next_task(rq, p);
/* do something else ... */
}
put_prev_task() can match set_next_task(), which can make the
code more readable.
Signed-off-by: Muchun Song <smuchun@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20181026131743.21786-1-smuchun@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-10-26 21:17:43 +08:00
|
|
|
|
|
|
|
/* You can't push away the running task */
|
|
|
|
dequeue_pushable_dl_task(rq, p);
|
2019-05-30 04:36:40 +08:00
|
|
|
|
2019-11-08 21:16:00 +08:00
|
|
|
if (!first)
|
|
|
|
return;
|
|
|
|
|
2021-02-08 15:35:54 +08:00
|
|
|
if (hrtick_enabled_dl(rq))
|
2019-05-30 04:36:40 +08:00
|
|
|
start_hrtick_dl(rq, p);
|
|
|
|
|
|
|
|
if (rq->curr->sched_class != &dl_sched_class)
|
|
|
|
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
|
|
|
|
|
|
|
|
deadline_queue_push_tasks(rq);
|
sched/core: Introduce set_next_task() helper for better code readability
When we pick the next task, we will do the following for the task:
1) p->se.exec_start = rq_clock_task(rq);
2) dequeue_pushable(_dl)_task(rq, p);
When we call set_curr_task(), we also need to do the same thing
above. In rt.c, the code at 1) is in the _pick_next_task_rt()
and the code at 2) is in the pick_next_task_rt(). If we put two
operations in one function, maybe better. So, we introduce a new
function set_next_task(), which is responsible for doing the above.
By introducing the function we can get rid of calling the
dequeue_pushable(_dl)_task() directly(We can call set_next_task())
in pick_next_task() and have better code readability and reuse.
In set_curr_task_rt(), we also can call set_next_task().
Do this things such that we end up with:
static struct task_struct *pick_next_task(struct rq *rq,
struct task_struct *prev,
struct rq_flags *rf)
{
/* do something else ... */
put_prev_task(rq, prev);
/* pick next task p */
set_next_task(rq, p);
/* do something else ... */
}
put_prev_task() can match set_next_task(), which can make the
code more readable.
Signed-off-by: Muchun Song <smuchun@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20181026131743.21786-1-smuchun@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-10-26 21:17:43 +08:00
|
|
|
}
|
|
|
|
|
2022-03-03 02:34:33 +08:00
|
|
|
static struct sched_dl_entity *pick_next_dl_entity(struct dl_rq *dl_rq)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2017-09-09 07:14:58 +08:00
|
|
|
struct rb_node *left = rb_first_cached(&dl_rq->root);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
if (!left)
|
|
|
|
return NULL;
|
|
|
|
|
2022-03-03 02:34:31 +08:00
|
|
|
return __node_2_dle(left);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2020-11-18 07:19:32 +08:00
|
|
|
static struct task_struct *pick_task_dl(struct rq *rq)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se;
|
2019-11-08 18:11:52 +08:00
|
|
|
struct dl_rq *dl_rq = &rq->dl;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
struct task_struct *p;
|
|
|
|
|
2019-11-08 18:11:52 +08:00
|
|
|
if (!sched_dl_runnable(rq))
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
return NULL;
|
|
|
|
|
2022-03-03 02:34:33 +08:00
|
|
|
dl_se = pick_next_dl_entity(dl_rq);
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(!dl_se);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
p = dl_task_of(dl_se);
|
2020-11-18 07:19:32 +08:00
|
|
|
|
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct task_struct *pick_next_task_dl(struct rq *rq)
|
|
|
|
{
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
p = pick_task_dl(rq);
|
|
|
|
if (p)
|
|
|
|
set_next_task_dl(rq, p, true);
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
2019-11-08 18:11:52 +08:00
|
|
|
static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
{
|
2021-09-05 22:35:47 +08:00
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
struct dl_rq *dl_rq = &rq->dl;
|
|
|
|
|
|
|
|
if (on_dl_rq(&p->dl))
|
|
|
|
update_stats_wait_start_dl(dl_rq, dl_se);
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
update_curr_dl(rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
sched/fair: Update scale invariance of PELT
The current implementation of load tracking invariance scales the
contribution with current frequency and uarch performance (only for
utilization) of the CPU. One main result of this formula is that the
figures are capped by current capacity of CPU. Another one is that the
load_avg is not invariant because not scaled with uarch.
The util_avg of a periodic task that runs r time slots every p time slots
varies in the range :
U * (1-y^r)/(1-y^p) * y^i < Utilization < U * (1-y^r)/(1-y^p)
with U is the max util_avg value = SCHED_CAPACITY_SCALE
At a lower capacity, the range becomes:
U * C * (1-y^r')/(1-y^p) * y^i' < Utilization < U * C * (1-y^r')/(1-y^p)
with C reflecting the compute capacity ratio between current capacity and
max capacity.
so C tries to compensate changes in (1-y^r') but it can't be accurate.
Instead of scaling the contribution value of PELT algo, we should scale the
running time. The PELT signal aims to track the amount of computation of
tasks and/or rq so it seems more correct to scale the running time to
reflect the effective amount of computation done since the last update.
In order to be fully invariant, we need to apply the same amount of
running time and idle time whatever the current capacity. Because running
at lower capacity implies that the task will run longer, we have to ensure
that the same amount of idle time will be applied when system becomes idle
and no idle time has been "stolen". But reaching the maximum utilization
value (SCHED_CAPACITY_SCALE) means that the task is seen as an
always-running task whatever the capacity of the CPU (even at max compute
capacity). In this case, we can discard this "stolen" idle times which
becomes meaningless.
In order to achieve this time scaling, a new clock_pelt is created per rq.
The increase of this clock scales with current capacity when something
is running on rq and synchronizes with clock_task when rq is idle. With
this mechanism, we ensure the same running and idle time whatever the
current capacity. This also enables to simplify the pelt algorithm by
removing all references of uarch and frequency and applying the same
contribution to utilization and loads. Furthermore, the scaling is done
only once per update of clock (update_rq_clock_task()) instead of during
each update of sched_entities and cfs/rt/dl_rq of the rq like the current
implementation. This is interesting when cgroup are involved as shown in
the results below:
On a hikey (octo Arm64 platform).
Performance cpufreq governor and only shallowest c-state to remove variance
generated by those power features so we only track the impact of pelt algo.
each test runs 16 times:
./perf bench sched pipe
(higher is better)
kernel tip/sched/core + patch
ops/seconds ops/seconds diff
cgroup
root 59652(+/- 0.18%) 59876(+/- 0.24%) +0.38%
level1 55608(+/- 0.27%) 55923(+/- 0.24%) +0.57%
level2 52115(+/- 0.29%) 52564(+/- 0.22%) +0.86%
hackbench -l 1000
(lower is better)
kernel tip/sched/core + patch
duration(sec) duration(sec) diff
cgroup
root 4.453(+/- 2.37%) 4.383(+/- 2.88%) -1.57%
level1 4.859(+/- 8.50%) 4.830(+/- 7.07%) -0.60%
level2 5.063(+/- 9.83%) 4.928(+/- 9.66%) -2.66%
Then, the responsiveness of PELT is improved when CPU is not running at max
capacity with this new algorithm. I have put below some examples of
duration to reach some typical load values according to the capacity of the
CPU with current implementation and with this patch. These values has been
computed based on the geometric series and the half period value:
Util (%) max capacity half capacity(mainline) half capacity(w/ patch)
972 (95%) 138ms not reachable 276ms
486 (47.5%) 30ms 138ms 60ms
256 (25%) 13ms 32ms 26ms
On my hikey (octo Arm64 platform) with schedutil governor, the time to
reach max OPP when starting from a null utilization, decreases from 223ms
with current scale invariance down to 121ms with the new algorithm.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: patrick.bellasi@arm.com
Cc: pjt@google.com
Cc: pkondeti@codeaurora.org
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: srinivas.pandruvada@linux.intel.com
Cc: thara.gopinath@linaro.org
Link: https://lkml.kernel.org/r/1548257214-13745-3-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-01-23 23:26:53 +08:00
|
|
|
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
|
2017-02-05 22:41:03 +08:00
|
|
|
if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
enqueue_pushable_dl_task(rq, p);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2018-02-21 12:17:27 +08:00
|
|
|
/*
|
|
|
|
* scheduler tick hitting a task of our scheduling class.
|
|
|
|
*
|
|
|
|
* NOTE: This function can be called remotely by the tick offload that
|
|
|
|
* goes along full dynticks. Therefore no local assumption can be made
|
|
|
|
* and everything must be accessed through the @rq and @curr passed in
|
|
|
|
* parameters.
|
|
|
|
*/
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
|
|
|
|
{
|
|
|
|
update_curr_dl(rq);
|
|
|
|
|
sched/fair: Update scale invariance of PELT
The current implementation of load tracking invariance scales the
contribution with current frequency and uarch performance (only for
utilization) of the CPU. One main result of this formula is that the
figures are capped by current capacity of CPU. Another one is that the
load_avg is not invariant because not scaled with uarch.
The util_avg of a periodic task that runs r time slots every p time slots
varies in the range :
U * (1-y^r)/(1-y^p) * y^i < Utilization < U * (1-y^r)/(1-y^p)
with U is the max util_avg value = SCHED_CAPACITY_SCALE
At a lower capacity, the range becomes:
U * C * (1-y^r')/(1-y^p) * y^i' < Utilization < U * C * (1-y^r')/(1-y^p)
with C reflecting the compute capacity ratio between current capacity and
max capacity.
so C tries to compensate changes in (1-y^r') but it can't be accurate.
Instead of scaling the contribution value of PELT algo, we should scale the
running time. The PELT signal aims to track the amount of computation of
tasks and/or rq so it seems more correct to scale the running time to
reflect the effective amount of computation done since the last update.
In order to be fully invariant, we need to apply the same amount of
running time and idle time whatever the current capacity. Because running
at lower capacity implies that the task will run longer, we have to ensure
that the same amount of idle time will be applied when system becomes idle
and no idle time has been "stolen". But reaching the maximum utilization
value (SCHED_CAPACITY_SCALE) means that the task is seen as an
always-running task whatever the capacity of the CPU (even at max compute
capacity). In this case, we can discard this "stolen" idle times which
becomes meaningless.
In order to achieve this time scaling, a new clock_pelt is created per rq.
The increase of this clock scales with current capacity when something
is running on rq and synchronizes with clock_task when rq is idle. With
this mechanism, we ensure the same running and idle time whatever the
current capacity. This also enables to simplify the pelt algorithm by
removing all references of uarch and frequency and applying the same
contribution to utilization and loads. Furthermore, the scaling is done
only once per update of clock (update_rq_clock_task()) instead of during
each update of sched_entities and cfs/rt/dl_rq of the rq like the current
implementation. This is interesting when cgroup are involved as shown in
the results below:
On a hikey (octo Arm64 platform).
Performance cpufreq governor and only shallowest c-state to remove variance
generated by those power features so we only track the impact of pelt algo.
each test runs 16 times:
./perf bench sched pipe
(higher is better)
kernel tip/sched/core + patch
ops/seconds ops/seconds diff
cgroup
root 59652(+/- 0.18%) 59876(+/- 0.24%) +0.38%
level1 55608(+/- 0.27%) 55923(+/- 0.24%) +0.57%
level2 52115(+/- 0.29%) 52564(+/- 0.22%) +0.86%
hackbench -l 1000
(lower is better)
kernel tip/sched/core + patch
duration(sec) duration(sec) diff
cgroup
root 4.453(+/- 2.37%) 4.383(+/- 2.88%) -1.57%
level1 4.859(+/- 8.50%) 4.830(+/- 7.07%) -0.60%
level2 5.063(+/- 9.83%) 4.928(+/- 9.66%) -2.66%
Then, the responsiveness of PELT is improved when CPU is not running at max
capacity with this new algorithm. I have put below some examples of
duration to reach some typical load values according to the capacity of the
CPU with current implementation and with this patch. These values has been
computed based on the geometric series and the half period value:
Util (%) max capacity half capacity(mainline) half capacity(w/ patch)
972 (95%) 138ms not reachable 276ms
486 (47.5%) 30ms 138ms 60ms
256 (25%) 13ms 32ms 26ms
On my hikey (octo Arm64 platform) with schedutil governor, the time to
reach max OPP when starting from a null utilization, decreases from 223ms
with current scale invariance down to 121ms with the new algorithm.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Cc: dietmar.eggemann@arm.com
Cc: patrick.bellasi@arm.com
Cc: pjt@google.com
Cc: pkondeti@codeaurora.org
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: srinivas.pandruvada@linux.intel.com
Cc: thara.gopinath@linaro.org
Link: https://lkml.kernel.org/r/1548257214-13745-3-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-01-23 23:26:53 +08:00
|
|
|
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
|
2014-11-26 08:44:01 +08:00
|
|
|
/*
|
|
|
|
* Even when we have runtime, update_curr_dl() might have resulted in us
|
|
|
|
* not being the leftmost task anymore. In that case NEED_RESCHED will
|
|
|
|
* be set and schedule() will start a new hrtick for the next task.
|
|
|
|
*/
|
2021-02-08 15:35:54 +08:00
|
|
|
if (hrtick_enabled_dl(rq) && queued && p->dl.runtime > 0 &&
|
2014-11-26 08:44:01 +08:00
|
|
|
is_leftmost(p, &rq->dl))
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
start_hrtick_dl(rq, p);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void task_fork_dl(struct task_struct *p)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* SCHED_DEADLINE tasks cannot fork and this is achieved through
|
|
|
|
* sched_fork()
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
|
|
|
|
/* Only try algorithms three times */
|
|
|
|
#define DL_MAX_TRIES 3
|
|
|
|
|
|
|
|
static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
|
|
|
|
{
|
2022-09-06 18:33:04 +08:00
|
|
|
if (!task_on_cpu(rq, p) &&
|
2020-10-01 22:05:39 +08:00
|
|
|
cpumask_test_cpu(cpu, &p->cpus_mask))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-05-13 14:01:01 +08:00
|
|
|
/*
|
|
|
|
* Return the earliest pushable rq's task, which is suitable to be executed
|
|
|
|
* on the CPU, NULL otherwise:
|
|
|
|
*/
|
|
|
|
static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu)
|
|
|
|
{
|
|
|
|
struct task_struct *p = NULL;
|
2022-03-03 02:34:31 +08:00
|
|
|
struct rb_node *next_node;
|
2015-05-13 14:01:01 +08:00
|
|
|
|
|
|
|
if (!has_pushable_dl_tasks(rq))
|
|
|
|
return NULL;
|
|
|
|
|
2022-03-03 02:34:31 +08:00
|
|
|
next_node = rb_first_cached(&rq->dl.pushable_dl_tasks_root);
|
|
|
|
|
2015-05-13 14:01:01 +08:00
|
|
|
next_node:
|
|
|
|
if (next_node) {
|
2022-03-03 02:34:31 +08:00
|
|
|
p = __node_2_pdl(next_node);
|
2015-05-13 14:01:01 +08:00
|
|
|
|
|
|
|
if (pick_dl_task(rq, p, cpu))
|
|
|
|
return p;
|
|
|
|
|
|
|
|
next_node = rb_next(next_node);
|
|
|
|
goto next_node;
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
|
|
|
|
|
|
|
|
static int find_later_rq(struct task_struct *task)
|
|
|
|
{
|
|
|
|
struct sched_domain *sd;
|
2014-08-27 08:12:21 +08:00
|
|
|
struct cpumask *later_mask = this_cpu_cpumask_var_ptr(local_cpu_mask_dl);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
int this_cpu = smp_processor_id();
|
2017-05-23 10:00:56 +08:00
|
|
|
int cpu = task_cpu(task);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/* Make sure the mask is initialized first */
|
|
|
|
if (unlikely(!later_mask))
|
|
|
|
return -1;
|
|
|
|
|
2017-02-05 22:41:03 +08:00
|
|
|
if (task->nr_cpus_allowed == 1)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return -1;
|
|
|
|
|
2014-09-19 17:22:41 +08:00
|
|
|
/*
|
|
|
|
* We have to consider system topology and task affinity
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* first, then we can look for a suitable CPU.
|
2014-09-19 17:22:41 +08:00
|
|
|
*/
|
2017-05-23 10:00:57 +08:00
|
|
|
if (!cpudl_find(&task_rq(task)->rd->cpudl, task, later_mask))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return -1;
|
|
|
|
|
|
|
|
/*
|
2017-05-23 10:00:56 +08:00
|
|
|
* If we are here, some targets have been found, including
|
|
|
|
* the most suitable which is, among the runqueues where the
|
|
|
|
* current tasks have later deadlines than the task's one, the
|
|
|
|
* rq with the latest possible one.
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
*
|
|
|
|
* Now we check how well this matches with task's
|
|
|
|
* affinity and system topology.
|
|
|
|
*
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* The last CPU where the task run is our first
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
* guess, since it is most likely cache-hot there.
|
|
|
|
*/
|
|
|
|
if (cpumask_test_cpu(cpu, later_mask))
|
|
|
|
return cpu;
|
|
|
|
/*
|
|
|
|
* Check if this_cpu is to be skipped (i.e., it is
|
|
|
|
* not in the mask) or not.
|
|
|
|
*/
|
|
|
|
if (!cpumask_test_cpu(this_cpu, later_mask))
|
|
|
|
this_cpu = -1;
|
|
|
|
|
|
|
|
rcu_read_lock();
|
|
|
|
for_each_domain(cpu, sd) {
|
|
|
|
if (sd->flags & SD_WAKE_AFFINE) {
|
2017-05-23 10:00:56 +08:00
|
|
|
int best_cpu;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If possible, preempting this_cpu is
|
|
|
|
* cheaper than migrating.
|
|
|
|
*/
|
|
|
|
if (this_cpu != -1 &&
|
|
|
|
cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
|
|
|
|
rcu_read_unlock();
|
|
|
|
return this_cpu;
|
|
|
|
}
|
|
|
|
|
2020-10-01 21:54:14 +08:00
|
|
|
best_cpu = cpumask_any_and_distribute(later_mask,
|
|
|
|
sched_domain_span(sd));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* Last chance: if a CPU being in both later_mask
|
2017-05-23 10:00:56 +08:00
|
|
|
* and current sd span is valid, that becomes our
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* choice. Of course, the latest possible CPU is
|
2017-05-23 10:00:56 +08:00
|
|
|
* already under consideration through later_mask.
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
*/
|
2017-05-23 10:00:56 +08:00
|
|
|
if (best_cpu < nr_cpu_ids) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
rcu_read_unlock();
|
|
|
|
return best_cpu;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
rcu_read_unlock();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* At this point, all our guesses failed, we just return
|
|
|
|
* 'something', and let the caller sort the things out.
|
|
|
|
*/
|
|
|
|
if (this_cpu != -1)
|
|
|
|
return this_cpu;
|
|
|
|
|
2020-10-01 21:54:14 +08:00
|
|
|
cpu = cpumask_any_distribute(later_mask);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
if (cpu < nr_cpu_ids)
|
|
|
|
return cpu;
|
|
|
|
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Locks the rq it finds */
|
|
|
|
static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
|
|
|
|
{
|
|
|
|
struct rq *later_rq = NULL;
|
|
|
|
int tries;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
for (tries = 0; tries < DL_MAX_TRIES; tries++) {
|
|
|
|
cpu = find_later_rq(task);
|
|
|
|
|
|
|
|
if ((cpu == -1) || (cpu == rq->cpu))
|
|
|
|
break;
|
|
|
|
|
|
|
|
later_rq = cpu_rq(cpu);
|
|
|
|
|
2022-08-26 16:34:53 +08:00
|
|
|
if (!dl_task_is_earliest_deadline(task, later_rq)) {
|
2015-05-13 14:01:03 +08:00
|
|
|
/*
|
|
|
|
* Target rq has tasks of equal or earlier deadline,
|
|
|
|
* retrying does not release any lock and is unlikely
|
|
|
|
* to yield a different result.
|
|
|
|
*/
|
|
|
|
later_rq = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/* Retry if something changed. */
|
|
|
|
if (double_lock_balance(rq, later_rq)) {
|
|
|
|
if (unlikely(task_rq(task) != rq ||
|
2020-10-01 22:05:39 +08:00
|
|
|
!cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
|
2022-09-06 18:33:04 +08:00
|
|
|
task_on_cpu(rq, task) ||
|
2016-05-09 12:11:31 +08:00
|
|
|
!dl_task(task) ||
|
2022-08-29 01:03:02 +08:00
|
|
|
is_migration_disabled(task) ||
|
2014-08-20 17:47:32 +08:00
|
|
|
!task_on_rq_queued(task))) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
double_unlock_balance(rq, later_rq);
|
|
|
|
later_rq = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If the rq we found has no -deadline task, or
|
|
|
|
* its earliest one has a later deadline than our
|
|
|
|
* task, the rq is a good one.
|
|
|
|
*/
|
2022-08-26 16:34:53 +08:00
|
|
|
if (dl_task_is_earliest_deadline(task, later_rq))
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
break;
|
|
|
|
|
|
|
|
/* Otherwise we try again. */
|
|
|
|
double_unlock_balance(rq, later_rq);
|
|
|
|
later_rq = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return later_rq;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
|
|
|
|
{
|
|
|
|
struct task_struct *p;
|
|
|
|
|
|
|
|
if (!has_pushable_dl_tasks(rq))
|
|
|
|
return NULL;
|
|
|
|
|
2022-03-03 02:34:31 +08:00
|
|
|
p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(rq->cpu != task_cpu(p));
|
|
|
|
WARN_ON_ONCE(task_current(rq, p));
|
|
|
|
WARN_ON_ONCE(p->nr_cpus_allowed <= 1);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(!task_on_rq_queued(p));
|
|
|
|
WARN_ON_ONCE(!dl_task(p));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
return p;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* See if the non running -deadline tasks on this rq
|
|
|
|
* can be sent to some other CPU where they can preempt
|
|
|
|
* and start executing.
|
|
|
|
*/
|
|
|
|
static int push_dl_task(struct rq *rq)
|
|
|
|
{
|
|
|
|
struct task_struct *next_task;
|
|
|
|
struct rq *later_rq;
|
2014-11-06 15:22:44 +08:00
|
|
|
int ret = 0;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
if (!rq->dl.overloaded)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
next_task = pick_next_pushable_dl_task(rq);
|
|
|
|
if (!next_task)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
retry:
|
|
|
|
/*
|
|
|
|
* If next_task preempts rq->curr, and rq->curr
|
|
|
|
* can move away, it makes sense to just reschedule
|
|
|
|
* without going further in pushing next_task.
|
|
|
|
*/
|
|
|
|
if (dl_task(rq->curr) &&
|
|
|
|
dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
|
2017-02-05 22:41:03 +08:00
|
|
|
rq->curr->nr_cpus_allowed > 1) {
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-01-27 23:40:59 +08:00
|
|
|
if (is_migration_disabled(next_task))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (WARN_ON(next_task == rq->curr))
|
|
|
|
return 0;
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/* We might release rq lock */
|
|
|
|
get_task_struct(next_task);
|
|
|
|
|
|
|
|
/* Will lock the rq it'll find */
|
|
|
|
later_rq = find_lock_later_rq(next_task, rq);
|
|
|
|
if (!later_rq) {
|
|
|
|
struct task_struct *task;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We must check all this again, since
|
|
|
|
* find_lock_later_rq releases rq->lock and it is
|
|
|
|
* then possible that next_task has migrated.
|
|
|
|
*/
|
|
|
|
task = pick_next_pushable_dl_task(rq);
|
2017-05-12 09:05:59 +08:00
|
|
|
if (task == next_task) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* The task is still there. We don't try
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* again, some other CPU will pull it when ready.
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
*/
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!task)
|
|
|
|
/* No more tasks */
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
put_task_struct(next_task);
|
|
|
|
next_task = task;
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
|
|
|
|
deactivate_task(rq, next_task, 0);
|
|
|
|
set_task_cpu(next_task, later_rq->cpu);
|
2022-04-30 16:58:43 +08:00
|
|
|
activate_task(later_rq, next_task, 0);
|
2014-11-06 15:22:44 +08:00
|
|
|
ret = 1;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(later_rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
double_unlock_balance(rq, later_rq);
|
|
|
|
|
|
|
|
out:
|
|
|
|
put_task_struct(next_task);
|
|
|
|
|
2014-11-06 15:22:44 +08:00
|
|
|
return ret;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void push_dl_tasks(struct rq *rq)
|
|
|
|
{
|
2015-08-05 21:56:18 +08:00
|
|
|
/* push_dl_task() will return true if it moved a -deadline task */
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
while (push_dl_task(rq))
|
|
|
|
;
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2015-06-11 20:46:42 +08:00
|
|
|
static void pull_dl_task(struct rq *this_rq)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
{
|
2015-06-11 20:46:42 +08:00
|
|
|
int this_cpu = this_rq->cpu, cpu;
|
2020-09-28 23:06:07 +08:00
|
|
|
struct task_struct *p, *push_task;
|
2015-06-11 20:46:42 +08:00
|
|
|
bool resched = false;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
struct rq *src_rq;
|
|
|
|
u64 dmin = LONG_MAX;
|
|
|
|
|
|
|
|
if (likely(!dl_overloaded(this_rq)))
|
2015-06-11 20:46:42 +08:00
|
|
|
return;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Match the barrier from dl_set_overloaded; this guarantees that if we
|
|
|
|
* see overloaded we must also see the dlo_mask bit.
|
|
|
|
*/
|
|
|
|
smp_rmb();
|
|
|
|
|
|
|
|
for_each_cpu(cpu, this_rq->rd->dlo_mask) {
|
|
|
|
if (this_cpu == cpu)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
src_rq = cpu_rq(cpu);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* It looks racy, abd it is! However, as in sched_rt.c,
|
|
|
|
* we are fine with this.
|
|
|
|
*/
|
|
|
|
if (this_rq->dl.dl_nr_running &&
|
|
|
|
dl_time_before(this_rq->dl.earliest_dl.curr,
|
|
|
|
src_rq->dl.earliest_dl.next))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* Might drop this_rq->lock */
|
2020-09-28 23:06:07 +08:00
|
|
|
push_task = NULL;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
double_lock_balance(this_rq, src_rq);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If there are no more pullable tasks on the
|
|
|
|
* rq, we're done with it.
|
|
|
|
*/
|
|
|
|
if (src_rq->dl.dl_nr_running <= 1)
|
|
|
|
goto skip;
|
|
|
|
|
2015-05-13 14:01:01 +08:00
|
|
|
p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We found a task to be pulled if:
|
|
|
|
* - it preempts our current (if there's one),
|
|
|
|
* - it will preempt the last one we pulled (if any).
|
|
|
|
*/
|
|
|
|
if (p && dl_time_before(p->dl.deadline, dmin) &&
|
2022-08-26 16:34:53 +08:00
|
|
|
dl_task_is_earliest_deadline(p, this_rq)) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
WARN_ON(p == src_rq->curr);
|
2014-08-20 17:47:32 +08:00
|
|
|
WARN_ON(!task_on_rq_queued(p));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Then we pull iff p has actually an earlier
|
|
|
|
* deadline than the current task of its runqueue.
|
|
|
|
*/
|
|
|
|
if (dl_time_before(p->dl.deadline,
|
|
|
|
src_rq->curr->dl.deadline))
|
|
|
|
goto skip;
|
|
|
|
|
2020-09-28 23:06:07 +08:00
|
|
|
if (is_migration_disabled(p)) {
|
|
|
|
push_task = get_push_task(src_rq);
|
|
|
|
} else {
|
|
|
|
deactivate_task(src_rq, p, 0);
|
|
|
|
set_task_cpu(p, this_cpu);
|
|
|
|
activate_task(this_rq, p, 0);
|
|
|
|
dmin = p->dl.deadline;
|
|
|
|
resched = true;
|
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
|
|
|
/* Is there any other task even earlier? */
|
|
|
|
}
|
|
|
|
skip:
|
|
|
|
double_unlock_balance(this_rq, src_rq);
|
2020-09-28 23:06:07 +08:00
|
|
|
|
|
|
|
if (push_task) {
|
2023-10-11 02:57:39 +08:00
|
|
|
preempt_disable();
|
2020-11-18 07:19:31 +08:00
|
|
|
raw_spin_rq_unlock(this_rq);
|
2020-09-28 23:06:07 +08:00
|
|
|
stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
|
|
|
|
push_task, &src_rq->push_work);
|
2023-10-11 02:57:39 +08:00
|
|
|
preempt_enable();
|
2020-11-18 07:19:31 +08:00
|
|
|
raw_spin_rq_lock(this_rq);
|
2020-09-28 23:06:07 +08:00
|
|
|
}
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
2015-06-11 20:46:42 +08:00
|
|
|
if (resched)
|
|
|
|
resched_curr(this_rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since the task is not running and a reschedule is not going to happen
|
|
|
|
* anytime soon on its runqueue, we try pushing it away now.
|
|
|
|
*/
|
|
|
|
static void task_woken_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
2022-09-06 18:33:04 +08:00
|
|
|
if (!task_on_cpu(rq, p) &&
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
!test_tsk_need_resched(rq->curr) &&
|
2017-02-05 22:41:03 +08:00
|
|
|
p->nr_cpus_allowed > 1 &&
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
dl_task(rq->curr) &&
|
2017-02-05 22:41:03 +08:00
|
|
|
(rq->curr->nr_cpus_allowed < 2 ||
|
2014-10-31 06:39:34 +08:00
|
|
|
!dl_entity_preempt(&p->dl, &rq->curr->dl))) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
push_dl_tasks(rq);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void set_cpus_allowed_dl(struct task_struct *p,
|
2022-09-23 02:00:40 +08:00
|
|
|
struct affinity_context *ctx)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
{
|
2014-09-19 17:22:40 +08:00
|
|
|
struct root_domain *src_rd;
|
2015-05-15 23:43:36 +08:00
|
|
|
struct rq *rq;
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2022-08-11 14:54:52 +08:00
|
|
|
WARN_ON_ONCE(!dl_task(p));
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2014-09-19 17:22:40 +08:00
|
|
|
rq = task_rq(p);
|
|
|
|
src_rd = rq->rd;
|
|
|
|
/*
|
|
|
|
* Migrating a SCHED_DEADLINE task between exclusive
|
|
|
|
* cpusets (different root_domains) entails a bandwidth
|
|
|
|
* update. We already made space for us in the destination
|
|
|
|
* domain (see cpuset_can_attach()).
|
|
|
|
*/
|
2022-09-23 02:00:40 +08:00
|
|
|
if (!cpumask_intersects(src_rd->span, ctx->new_mask)) {
|
2014-09-19 17:22:40 +08:00
|
|
|
struct dl_bw *src_dl_b;
|
|
|
|
|
|
|
|
src_dl_b = dl_bw_of(cpu_of(rq));
|
|
|
|
/*
|
|
|
|
* We now free resources of the root_domain we are migrating
|
|
|
|
* off. In the worst case, sched_setattr() may temporary fail
|
|
|
|
* until we complete the update.
|
|
|
|
*/
|
|
|
|
raw_spin_lock(&src_dl_b->lock);
|
2017-09-07 18:09:30 +08:00
|
|
|
__dl_sub(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
|
2014-09-19 17:22:40 +08:00
|
|
|
raw_spin_unlock(&src_dl_b->lock);
|
|
|
|
}
|
|
|
|
|
2022-09-23 02:00:40 +08:00
|
|
|
set_cpus_allowed_common(p, ctx);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Assumes rq->lock is held */
|
|
|
|
static void rq_online_dl(struct rq *rq)
|
|
|
|
{
|
|
|
|
if (rq->dl.overloaded)
|
|
|
|
dl_set_overload(rq);
|
2013-11-07 21:43:47 +08:00
|
|
|
|
2015-01-19 12:49:36 +08:00
|
|
|
cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
|
2013-11-07 21:43:47 +08:00
|
|
|
if (rq->dl.dl_nr_running > 0)
|
sched/deadline: Split cpudl_set() into cpudl_set() and cpudl_clear()
These 2 exercise independent code paths and need different arguments.
After this change, you call:
cpudl_clear(cp, cpu);
cpudl_set(cp, cpu, dl);
instead of:
cpudl_set(cp, cpu, 0 /* dl */, 0 /* is_valid */);
cpudl_set(cp, cpu, dl, 1 /* is_valid */);
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-dl@retis.sssup.it
Link: http://lkml.kernel.org/r/1471184828-12644-4-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-14 22:27:08 +08:00
|
|
|
cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* Assumes rq->lock is held */
|
|
|
|
static void rq_offline_dl(struct rq *rq)
|
|
|
|
{
|
|
|
|
if (rq->dl.overloaded)
|
|
|
|
dl_clear_overload(rq);
|
2013-11-07 21:43:47 +08:00
|
|
|
|
sched/deadline: Split cpudl_set() into cpudl_set() and cpudl_clear()
These 2 exercise independent code paths and need different arguments.
After this change, you call:
cpudl_clear(cp, cpu);
cpudl_set(cp, cpu, dl);
instead of:
cpudl_set(cp, cpu, 0 /* dl */, 0 /* is_valid */);
cpudl_set(cp, cpu, dl, 1 /* is_valid */);
Signed-off-by: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luca Abeni <luca.abeni@unitn.it>
Reviewed-by: Juri Lelli <juri.lelli@arm.com>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-dl@retis.sssup.it
Link: http://lkml.kernel.org/r/1471184828-12644-4-git-send-email-tommaso.cucinotta@sssup.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-14 22:27:08 +08:00
|
|
|
cpudl_clear(&rq->rd->cpudl, rq->cpu);
|
2015-01-19 12:49:36 +08:00
|
|
|
cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
}
|
|
|
|
|
2015-05-13 14:01:02 +08:00
|
|
|
void __init init_sched_dl_class(void)
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
|
|
|
for_each_possible_cpu(i)
|
|
|
|
zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
|
|
|
|
GFP_KERNEL, cpu_to_node(i));
|
|
|
|
}
|
|
|
|
|
2019-07-19 21:59:55 +08:00
|
|
|
void dl_add_task_root_domain(struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct rq_flags rf;
|
|
|
|
struct rq *rq;
|
|
|
|
struct dl_bw *dl_b;
|
|
|
|
|
2021-01-19 16:35:42 +08:00
|
|
|
raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
|
|
|
|
if (!dl_task(p)) {
|
|
|
|
raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
rq = __task_rq_lock(p, &rf);
|
2019-07-19 21:59:55 +08:00
|
|
|
|
|
|
|
dl_b = &rq->rd->dl_bw;
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
|
|
|
|
|
|
|
__dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span));
|
|
|
|
|
|
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
|
|
|
|
task_rq_unlock(rq, p, &rf);
|
|
|
|
}
|
|
|
|
|
|
|
|
void dl_clear_root_domain(struct root_domain *rd)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
raw_spin_lock_irqsave(&rd->dl_bw.lock, flags);
|
|
|
|
rd->dl_bw.total_bw = 0;
|
|
|
|
raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags);
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void switched_from_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
2015-06-11 20:46:49 +08:00
|
|
|
/*
|
2017-05-19 04:13:29 +08:00
|
|
|
* task_non_contending() can start the "inactive timer" (if the 0-lag
|
|
|
|
* time is in the future). If the task switches back to dl before
|
|
|
|
* the "inactive timer" fires, it can continue to consume its current
|
|
|
|
* runtime using its current deadline. If it stays outside of
|
|
|
|
* SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer()
|
|
|
|
* will reset the task parameters.
|
2015-06-11 20:46:49 +08:00
|
|
|
*/
|
2017-05-19 04:13:29 +08:00
|
|
|
if (task_on_rq_queued(p) && p->dl.dl_runtime)
|
|
|
|
task_non_contending(p);
|
|
|
|
|
2023-05-08 15:58:51 +08:00
|
|
|
/*
|
|
|
|
* In case a task is setscheduled out from SCHED_DEADLINE we need to
|
|
|
|
* keep track of that on its cpuset (for correct bandwidth tracking).
|
|
|
|
*/
|
|
|
|
dec_dl_tasks_cs(p);
|
|
|
|
|
2018-07-11 15:29:48 +08:00
|
|
|
if (!task_on_rq_queued(p)) {
|
|
|
|
/*
|
|
|
|
* Inactive timer is armed. However, p is leaving DEADLINE and
|
|
|
|
* might migrate away from this rq while continuing to run on
|
|
|
|
* some other class. We need to remove its contribution from
|
|
|
|
* this rq running_bw now, or sub_rq_bw (below) will complain.
|
|
|
|
*/
|
|
|
|
if (p->dl.dl_non_contending)
|
|
|
|
sub_running_bw(&p->dl, &rq->dl);
|
2017-12-04 18:23:20 +08:00
|
|
|
sub_rq_bw(&p->dl, &rq->dl);
|
2018-07-11 15:29:48 +08:00
|
|
|
}
|
2017-05-19 04:13:34 +08:00
|
|
|
|
2017-05-19 04:13:29 +08:00
|
|
|
/*
|
|
|
|
* We cannot use inactive_task_timer() to invoke sub_running_bw()
|
|
|
|
* at the 0-lag time, because the task could have been migrated
|
|
|
|
* while SCHED_OTHER in the meanwhile.
|
|
|
|
*/
|
|
|
|
if (p->dl.dl_non_contending)
|
|
|
|
p->dl.dl_non_contending = 0;
|
2014-09-19 17:22:39 +08:00
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* Since this might be the only -deadline task on the rq,
|
|
|
|
* this is the right place to try to pull some other one
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
* from an overloaded CPU, if any.
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
*/
|
2014-10-31 06:39:35 +08:00
|
|
|
if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
|
|
|
|
return;
|
|
|
|
|
2018-03-03 23:27:54 +08:00
|
|
|
deadline_queue_pull_task(rq);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* When switching to -deadline, we may overload the rq, then
|
|
|
|
* we try to push someone off, if possible.
|
|
|
|
*/
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void switched_to_dl(struct rq *rq, struct task_struct *p)
|
|
|
|
{
|
2017-05-19 04:13:29 +08:00
|
|
|
if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
|
|
|
|
put_task_struct(p);
|
sched/deadline: Remove useless parameter from setup_new_dl_entity()
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-05 23:07:55 +08:00
|
|
|
|
2023-05-08 15:58:51 +08:00
|
|
|
/*
|
|
|
|
* In case a task is setscheduled to SCHED_DEADLINE we need to keep
|
|
|
|
* track of that on its cpuset (for correct bandwidth tracking).
|
|
|
|
*/
|
|
|
|
inc_dl_tasks_cs(p);
|
|
|
|
|
sched/deadline: Remove useless parameter from setup_new_dl_entity()
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-05 23:07:55 +08:00
|
|
|
/* If p is not queued we will update its parameters at next wakeup. */
|
2017-05-19 04:13:34 +08:00
|
|
|
if (!task_on_rq_queued(p)) {
|
2017-12-04 18:23:20 +08:00
|
|
|
add_rq_bw(&p->dl, &rq->dl);
|
sched/deadline: Remove useless parameter from setup_new_dl_entity()
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-05 23:07:55 +08:00
|
|
|
|
2017-05-19 04:13:34 +08:00
|
|
|
return;
|
|
|
|
}
|
2016-03-07 19:27:04 +08:00
|
|
|
|
sched/deadline: Remove useless parameter from setup_new_dl_entity()
setup_new_dl_entity() takes two parameters, but it only actually uses
one of them, under a different name, to setup a new dl_entity, after:
2f9f3fdc928 "sched/deadline: Remove dl_new from struct sched_dl_entity"
as we currently do:
setup_new_dl_entity(&p->dl, &p->dl)
However, before Luca's change we were doing:
setup_new_dl_entity(dl_se, pi_se)
in update_dl_entity() for a dl_se->new entity: we were using pi_se's
parameters (the potential PI donor) for setting up a new entity.
This change removes the useless second parameter of setup_new_dl_entity().
While we are at it we also optimize things further calling setup_new_dl_
entity() only for already queued tasks, since (as pointed out by Xunlei)
we already do the very same update at tasks wakeup time anyway. By doing
so, we don't need to worry about a potential PI donor anymore, as
rt_mutex_setprio() takes care of that already for us.
Signed-off-by: Juri Lelli <juri.lelli@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luca Abeni <luca.abeni@unitn.it>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Xunlei Pang <xpang@redhat.com>
Link: http://lkml.kernel.org/r/1470409675-20935-1-git-send-email-juri.lelli@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-05 23:07:55 +08:00
|
|
|
if (rq->curr != p) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2017-02-05 22:41:03 +08:00
|
|
|
if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
|
2018-03-03 23:27:54 +08:00
|
|
|
deadline_queue_push_tasks(rq);
|
2017-01-24 22:40:06 +08:00
|
|
|
#endif
|
2015-06-11 20:46:43 +08:00
|
|
|
if (dl_task(rq->curr))
|
|
|
|
check_preempt_curr_dl(rq, p, 0);
|
|
|
|
else
|
|
|
|
resched_curr(rq);
|
sched/rt: Fix Deadline utilization tracking during policy change
DL keeps track of the utilization on a per-rq basis with the structure
avg_dl. This utilization is updated during task_tick_dl(),
put_prev_task_dl() and set_next_task_dl(). However, when the current
running task changes its policy, set_next_task_dl() which would usually
take care of updating the utilization when the rq starts running DL
tasks, will not see a such change, leaving the avg_dl structure outdated.
When that very same task will be dequeued later, put_prev_task_dl() will
then update the utilization, based on a wrong last_update_time, leading to
a huge spike in the DL utilization signal.
The signal would eventually recover from this issue after few ms. Even
if no DL tasks are run, avg_dl is also updated in
__update_blocked_others(). But as the CPU capacity depends partly on the
avg_dl, this issue has nonetheless a significant impact on the scheduler.
Fix this issue by ensuring a load update when a running task changes
its policy to DL.
Fixes: 3727e0e ("sched/dl: Add dl_rq utilization tracking")
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/1624271872-211872-3-git-send-email-vincent.donnefort@arm.com
2021-06-21 18:37:52 +08:00
|
|
|
} else {
|
|
|
|
update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0);
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* If the scheduling parameters of a -deadline task changed,
|
|
|
|
* a push or pull operation might be needed.
|
|
|
|
*/
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
static void prio_changed_dl(struct rq *rq, struct task_struct *p,
|
|
|
|
int oldprio)
|
|
|
|
{
|
2023-02-06 22:06:12 +08:00
|
|
|
if (!task_on_rq_queued(p))
|
|
|
|
return;
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
#ifdef CONFIG_SMP
|
2023-02-06 22:06:12 +08:00
|
|
|
/*
|
|
|
|
* This might be too much, but unfortunately
|
|
|
|
* we don't have the old deadline value, and
|
|
|
|
* we can't argue if the task is increasing
|
|
|
|
* or lowering its prio, so...
|
|
|
|
*/
|
|
|
|
if (!rq->dl.overloaded)
|
|
|
|
deadline_queue_pull_task(rq);
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
|
2023-02-06 22:06:12 +08:00
|
|
|
if (task_current(rq, p)) {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
|
|
|
* If we now have a earlier deadline task than p,
|
|
|
|
* then reschedule, provided p is still on this
|
|
|
|
* runqueue.
|
|
|
|
*/
|
2015-06-11 20:46:43 +08:00
|
|
|
if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline))
|
2014-06-29 04:03:57 +08:00
|
|
|
resched_curr(rq);
|
2023-02-06 22:06:12 +08:00
|
|
|
} else {
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
/*
|
2023-02-06 22:06:12 +08:00
|
|
|
* Current may not be deadline in case p was throttled but we
|
|
|
|
* have just replenished it (e.g. rt_mutex_setprio()).
|
|
|
|
*
|
|
|
|
* Otherwise, if p was given an earlier deadline, reschedule.
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
*/
|
2023-02-06 22:06:12 +08:00
|
|
|
if (!dl_task(rq->curr) ||
|
|
|
|
dl_time_before(p->dl.deadline, rq->curr->dl.deadline))
|
|
|
|
resched_curr(rq);
|
2016-02-25 22:01:49 +08:00
|
|
|
}
|
2023-02-06 22:06:12 +08:00
|
|
|
#else
|
|
|
|
/*
|
|
|
|
* We don't know if p has a earlier or later deadline, so let's blindly
|
|
|
|
* set a (maybe not needed) rescheduling point.
|
|
|
|
*/
|
|
|
|
resched_curr(rq);
|
|
|
|
#endif
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
}
|
|
|
|
|
2023-03-16 16:18:06 +08:00
|
|
|
#ifdef CONFIG_SCHED_CORE
|
|
|
|
static int task_is_throttled_dl(struct task_struct *p, int cpu)
|
|
|
|
{
|
|
|
|
return p->dl.dl_throttled;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2020-10-21 21:45:33 +08:00
|
|
|
DEFINE_SCHED_CLASS(dl) = {
|
|
|
|
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
.enqueue_task = enqueue_task_dl,
|
|
|
|
.dequeue_task = dequeue_task_dl,
|
|
|
|
.yield_task = yield_task_dl,
|
|
|
|
|
|
|
|
.check_preempt_curr = check_preempt_curr_dl,
|
|
|
|
|
|
|
|
.pick_next_task = pick_next_task_dl,
|
|
|
|
.put_prev_task = put_prev_task_dl,
|
2019-05-30 04:36:41 +08:00
|
|
|
.set_next_task = set_next_task_dl,
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
2019-11-08 18:11:52 +08:00
|
|
|
.balance = balance_dl,
|
2020-11-18 07:19:32 +08:00
|
|
|
.pick_task = pick_task_dl,
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
.select_task_rq = select_task_rq_dl,
|
2017-05-19 04:13:29 +08:00
|
|
|
.migrate_task_rq = migrate_task_rq_dl,
|
sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.
Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.
The very same approach used in sched_rt is utilised:
- -deadline tasks are kept into CPU-specific runqueues,
- -deadline tasks are migrated among runqueues to achieve the
following:
* on an M-CPU system the M earliest deadline ready tasks
are always running;
* affinity/cpusets settings of all the -deadline tasks is
always respected.
Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.
To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.
In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:38 +08:00
|
|
|
.set_cpus_allowed = set_cpus_allowed_dl,
|
|
|
|
.rq_online = rq_online_dl,
|
|
|
|
.rq_offline = rq_offline_dl,
|
|
|
|
.task_woken = task_woken_dl,
|
2020-09-28 23:06:07 +08:00
|
|
|
.find_lock_rq = find_lock_later_rq,
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
.task_tick = task_tick_dl,
|
|
|
|
.task_fork = task_fork_dl,
|
|
|
|
|
|
|
|
.prio_changed = prio_changed_dl,
|
|
|
|
.switched_from = switched_from_dl,
|
|
|
|
.switched_to = switched_to_dl,
|
sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency
Commit d670ec13178d0 "posix-cpu-timers: Cure SMP wobbles" fixes one glibc
test case in cost of breaking another one. After that commit, calling
clock_nanosleep(TIMER_ABSTIME, X) and then clock_gettime(&Y) can result
of Y time being smaller than X time.
Reproducer/tester can be found further below, it can be compiled and ran by:
gcc -o tst-cpuclock2 tst-cpuclock2.c -pthread
while ./tst-cpuclock2 ; do : ; done
This reproducer, when running on a buggy kernel, will complain
about "clock_gettime difference too small".
Issue happens because on start in thread_group_cputimer() we initialize
sum_exec_runtime of cputimer with threads runtime not yet accounted and
then add the threads runtime to running cputimer again on scheduler
tick, making it's sum_exec_runtime bigger than actual threads runtime.
KOSAKI Motohiro posted a fix for this problem, but that patch was never
applied: https://lkml.org/lkml/2013/5/26/191 .
This patch takes different approach to cure the problem. It calls
update_curr() when cputimer starts, that assure we will have updated
stats of running threads and on the next schedule tick we will account
only the runtime that elapsed from cputimer start. That also assure we
have consistent state between cpu times of individual threads and cpu
time of the process consisted by those threads.
Full reproducer (tst-cpuclock2.c):
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <stdio.h>
#include <time.h>
#include <pthread.h>
#include <stdint.h>
#include <inttypes.h>
/* Parameters for the Linux kernel ABI for CPU clocks. */
#define CPUCLOCK_SCHED 2
#define MAKE_PROCESS_CPUCLOCK(pid, clock) \
((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
static pthread_barrier_t barrier;
/* Help advance the clock. */
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1) ;
return NULL;
}
/* Don't use the glibc wrapper. */
static int do_nanosleep(int flags, const struct timespec *req)
{
clockid_t clock_id = MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED);
return syscall(SYS_clock_nanosleep, clock_id, flags, req, NULL);
}
static int64_t tsdiff(const struct timespec *before, const struct timespec *after)
{
int64_t before_i = before->tv_sec * 1000000000ULL + before->tv_nsec;
int64_t after_i = after->tv_sec * 1000000000ULL + after->tv_nsec;
return after_i - before_i;
}
int main(void)
{
int result = 0;
pthread_t th;
pthread_barrier_init(&barrier, NULL, 2);
if (pthread_create(&th, NULL, chew_cpu, NULL) != 0) {
perror("pthread_create");
return 1;
}
pthread_barrier_wait(&barrier);
/* The test. */
struct timespec before, after, sleeptimeabs;
int64_t sleepdiff, diffabs;
const struct timespec sleeptime = {.tv_sec = 0,.tv_nsec = 100000000 };
/* The relative nanosleep. Not sure why this is needed, but its presence
seems to make it easier to reproduce the problem. */
if (do_nanosleep(0, &sleeptime) != 0) {
perror("clock_nanosleep");
return 1;
}
/* Get the current time. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &before) < 0) {
perror("clock_gettime[2]");
return 1;
}
/* Compute the absolute sleep time based on the current time. */
uint64_t nsec = before.tv_nsec + sleeptime.tv_nsec;
sleeptimeabs.tv_sec = before.tv_sec + nsec / 1000000000;
sleeptimeabs.tv_nsec = nsec % 1000000000;
/* Sleep for the computed time. */
if (do_nanosleep(TIMER_ABSTIME, &sleeptimeabs) != 0) {
perror("absolute clock_nanosleep");
return 1;
}
/* Get the time after the sleep. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &after) < 0) {
perror("clock_gettime[3]");
return 1;
}
/* The time after sleep should always be equal to or after the absolute sleep
time passed to clock_nanosleep. */
sleepdiff = tsdiff(&sleeptimeabs, &after);
if (sleepdiff < 0) {
printf("absolute clock_nanosleep woke too early: %" PRId64 "\n", sleepdiff);
result = 1;
printf("Before %llu.%09llu\n", before.tv_sec, before.tv_nsec);
printf("After %llu.%09llu\n", after.tv_sec, after.tv_nsec);
printf("Sleep %llu.%09llu\n", sleeptimeabs.tv_sec, sleeptimeabs.tv_nsec);
}
/* The difference between the timestamps taken before and after the
clock_nanosleep call should be equal to or more than the duration of the
sleep. */
diffabs = tsdiff(&before, &after);
if (diffabs < sleeptime.tv_nsec) {
printf("clock_gettime difference too small: %" PRId64 "\n", diffabs);
result = 1;
}
pthread_cancel(th);
return result;
}
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141112155843.GA24803@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-11-12 23:58:44 +08:00
|
|
|
|
|
|
|
.update_curr = update_curr_dl,
|
2023-03-16 16:18:06 +08:00
|
|
|
#ifdef CONFIG_SCHED_CORE
|
|
|
|
.task_is_throttled = task_is_throttled_dl,
|
|
|
|
#endif
|
sched/deadline: Add SCHED_DEADLINE structures & implementation
Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.
Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.
Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.
The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.
The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.
To summarize, this patch:
- introduces the data structures, constants and symbols needed;
- implements the core logic of the scheduling algorithm in the new
scheduling class file;
- provides all the glue code between the new scheduling class and
the core scheduler and refines the interactions between sched/dl
and the other existing scheduling classes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-28 18:14:43 +08:00
|
|
|
};
|
2014-10-31 06:39:33 +08:00
|
|
|
|
2020-10-08 23:48:46 +08:00
|
|
|
/* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
|
|
|
|
static u64 dl_generation;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
int sched_dl_global_validate(void)
|
|
|
|
{
|
|
|
|
u64 runtime = global_rt_runtime();
|
|
|
|
u64 period = global_rt_period();
|
|
|
|
u64 new_bw = to_ratio(period, runtime);
|
2020-10-08 23:48:46 +08:00
|
|
|
u64 gen = ++dl_generation;
|
2017-06-22 02:22:01 +08:00
|
|
|
struct dl_bw *dl_b;
|
sched/deadline: Fix sched_dl_global_validate()
When change sched_rt_{runtime, period}_us, we validate that the new
settings should at least accommodate the currently allocated -dl
bandwidth:
sched_rt_handler()
--> sched_dl_bandwidth_validate()
{
new_bw = global_rt_runtime()/global_rt_period();
for_each_possible_cpu(cpu) {
dl_b = dl_bw_of(cpu);
if (new_bw < dl_b->total_bw) <-------
ret = -EBUSY;
}
}
But under CONFIG_SMP, dl_bw is per root domain , but not per CPU,
dl_b->total_bw is the allocated bandwidth of the whole root domain.
Instead, we should compare dl_b->total_bw against "cpus*new_bw",
where 'cpus' is the number of CPUs of the root domain.
Also, below annotation(in kernel/sched/sched.h) implied implementation
only appeared in SCHED_DEADLINE v2[1], then deadline scheduler kept
evolving till got merged(v9), but the annotation remains unchanged,
meaningless and misleading, update it.
* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
* - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
* - dl_total_bw array contains, in the i-eth element, the currently
* allocated bandwidth on the i-eth CPU.
[1]: https://lore.kernel.org/lkml/1267385230.13676.101.camel@Palantir/
Fixes: 332ac17ef5bf ("sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks")
Signed-off-by: Peng Liu <iwtbavbm@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/db6bbda316048cda7a1bbc9571defde193a8d67e.1602171061.git.iwtbavbm@gmail.com
2020-10-08 23:49:42 +08:00
|
|
|
int cpu, cpus, ret = 0;
|
2017-06-22 02:22:01 +08:00
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we want to check the bandwidth not being set to some
|
|
|
|
* value smaller than the currently allocated bandwidth in
|
|
|
|
* any of the root_domains.
|
|
|
|
*/
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
rcu_read_lock_sched();
|
2020-10-08 23:48:46 +08:00
|
|
|
|
|
|
|
if (dl_bw_visited(cpu, gen))
|
|
|
|
goto next;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
dl_b = dl_bw_of(cpu);
|
sched/deadline: Fix sched_dl_global_validate()
When change sched_rt_{runtime, period}_us, we validate that the new
settings should at least accommodate the currently allocated -dl
bandwidth:
sched_rt_handler()
--> sched_dl_bandwidth_validate()
{
new_bw = global_rt_runtime()/global_rt_period();
for_each_possible_cpu(cpu) {
dl_b = dl_bw_of(cpu);
if (new_bw < dl_b->total_bw) <-------
ret = -EBUSY;
}
}
But under CONFIG_SMP, dl_bw is per root domain , but not per CPU,
dl_b->total_bw is the allocated bandwidth of the whole root domain.
Instead, we should compare dl_b->total_bw against "cpus*new_bw",
where 'cpus' is the number of CPUs of the root domain.
Also, below annotation(in kernel/sched/sched.h) implied implementation
only appeared in SCHED_DEADLINE v2[1], then deadline scheduler kept
evolving till got merged(v9), but the annotation remains unchanged,
meaningless and misleading, update it.
* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
* - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
* - dl_total_bw array contains, in the i-eth element, the currently
* allocated bandwidth on the i-eth CPU.
[1]: https://lore.kernel.org/lkml/1267385230.13676.101.camel@Palantir/
Fixes: 332ac17ef5bf ("sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks")
Signed-off-by: Peng Liu <iwtbavbm@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/db6bbda316048cda7a1bbc9571defde193a8d67e.1602171061.git.iwtbavbm@gmail.com
2020-10-08 23:49:42 +08:00
|
|
|
cpus = dl_bw_cpus(cpu);
|
2017-06-22 02:22:01 +08:00
|
|
|
|
|
|
|
raw_spin_lock_irqsave(&dl_b->lock, flags);
|
sched/deadline: Fix sched_dl_global_validate()
When change sched_rt_{runtime, period}_us, we validate that the new
settings should at least accommodate the currently allocated -dl
bandwidth:
sched_rt_handler()
--> sched_dl_bandwidth_validate()
{
new_bw = global_rt_runtime()/global_rt_period();
for_each_possible_cpu(cpu) {
dl_b = dl_bw_of(cpu);
if (new_bw < dl_b->total_bw) <-------
ret = -EBUSY;
}
}
But under CONFIG_SMP, dl_bw is per root domain , but not per CPU,
dl_b->total_bw is the allocated bandwidth of the whole root domain.
Instead, we should compare dl_b->total_bw against "cpus*new_bw",
where 'cpus' is the number of CPUs of the root domain.
Also, below annotation(in kernel/sched/sched.h) implied implementation
only appeared in SCHED_DEADLINE v2[1], then deadline scheduler kept
evolving till got merged(v9), but the annotation remains unchanged,
meaningless and misleading, update it.
* With respect to SMP, the bandwidth is given on a per-CPU basis,
* meaning that:
* - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
* - dl_total_bw array contains, in the i-eth element, the currently
* allocated bandwidth on the i-eth CPU.
[1]: https://lore.kernel.org/lkml/1267385230.13676.101.camel@Palantir/
Fixes: 332ac17ef5bf ("sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks")
Signed-off-by: Peng Liu <iwtbavbm@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/db6bbda316048cda7a1bbc9571defde193a8d67e.1602171061.git.iwtbavbm@gmail.com
2020-10-08 23:49:42 +08:00
|
|
|
if (new_bw * cpus < dl_b->total_bw)
|
2017-06-22 02:22:01 +08:00
|
|
|
ret = -EBUSY;
|
|
|
|
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
|
|
|
|
|
2020-10-08 23:48:46 +08:00
|
|
|
next:
|
2017-06-22 02:22:01 +08:00
|
|
|
rcu_read_unlock_sched();
|
|
|
|
|
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-02-28 18:03:29 +08:00
|
|
|
static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
|
2017-06-22 02:22:01 +08:00
|
|
|
{
|
|
|
|
if (global_rt_runtime() == RUNTIME_INF) {
|
|
|
|
dl_rq->bw_ratio = 1 << RATIO_SHIFT;
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
dl_rq->max_bw = dl_rq->extra_bw = 1 << BW_SHIFT;
|
2017-06-22 02:22:01 +08:00
|
|
|
} else {
|
|
|
|
dl_rq->bw_ratio = to_ratio(global_rt_runtime(),
|
|
|
|
global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT);
|
sched/deadline: Fix bandwidth reclaim equation in GRUB
According to the GRUB[1] rule, the runtime is depreciated as:
"dq = -max{u, (1 - Uinact - Uextra)} dt" (1)
To guarantee that deadline tasks doesn't starve lower class tasks,
we do not allocate the full bandwidth of the cpu to deadline tasks.
Maximum bandwidth usable by deadline tasks is denoted by "Umax".
Considering Umax, equation (1) becomes:
"dq = -(max{u, (Umax - Uinact - Uextra)} / Umax) dt" (2)
Current implementation has a minor bug in equation (2), which this
patch fixes.
The reclamation logic is verified by a sample program which creates
multiple deadline threads and observing their utilization. The tests
were run on an isolated cpu(isolcpus=3) on a 4 cpu system.
Tests on 6.3.0
==============
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.33
TID[693]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 93.35
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
TID[708]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 16.69
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.67
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.37
TID[631]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 62.38
TID[632]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 6.23
As seen above, the reclamation doesn't reclaim the maximum allowed
bandwidth and as the bandwidth of tasks gets smaller, the reclaimed
bandwidth also comes down.
Tests with this patch applied
=============================
RUN 1: runtime=7ms, deadline=period=10ms, RT capacity = 95%
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.19
TID[608]: RECLAIM=1, (r=7ms, d=10ms, p=10ms), Util: 95.16
RUN 2: runtime=1ms, deadline=period=100ms, RT capacity = 95%
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.27
TID[616]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 95.21
RUN 3: 2 tasks
Task 1: runtime=1ms, deadline=period=10ms
Task 2: runtime=1ms, deadline=period=100ms
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.64
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.66
TID[620]: RECLAIM=1, (r=1ms, d=10ms, p=10ms), Util: 86.45
TID[621]: RECLAIM=1, (r=1ms, d=100ms, p=100ms), Util: 8.73
Running tasks on all cpus allowing for migration also showed that
the utilization is reclaimed to the maximum. Running 10 tasks on
3 cpus SCHED_FLAG_RECLAIM - top shows:
%Cpu0 : 94.6 us, 0.0 sy, 0.0 ni, 5.4 id, 0.0 wa
%Cpu1 : 95.2 us, 0.0 sy, 0.0 ni, 4.8 id, 0.0 wa
%Cpu2 : 95.8 us, 0.0 sy, 0.0 ni, 4.2 id, 0.0 wa
[1]: Abeni, Luca & Lipari, Giuseppe & Parri, Andrea & Sun, Youcheng.
(2015). Parallel and sequential reclaiming in multicore
real-time global scheduling.
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20230530135526.2385378-1-vineeth@bitbyteword.org
2023-05-30 21:55:25 +08:00
|
|
|
dl_rq->max_bw = dl_rq->extra_bw =
|
|
|
|
to_ratio(global_rt_period(), global_rt_runtime());
|
2017-06-22 02:22:01 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void sched_dl_do_global(void)
|
|
|
|
{
|
|
|
|
u64 new_bw = -1;
|
2020-10-08 23:48:46 +08:00
|
|
|
u64 gen = ++dl_generation;
|
2017-06-22 02:22:01 +08:00
|
|
|
struct dl_bw *dl_b;
|
|
|
|
int cpu;
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
if (global_rt_runtime() != RUNTIME_INF)
|
|
|
|
new_bw = to_ratio(global_rt_period(), global_rt_runtime());
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
rcu_read_lock_sched();
|
2020-10-08 23:48:46 +08:00
|
|
|
|
|
|
|
if (dl_bw_visited(cpu, gen)) {
|
|
|
|
rcu_read_unlock_sched();
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
dl_b = dl_bw_of(cpu);
|
|
|
|
|
|
|
|
raw_spin_lock_irqsave(&dl_b->lock, flags);
|
|
|
|
dl_b->bw = new_bw;
|
|
|
|
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
|
|
|
|
|
|
|
|
rcu_read_unlock_sched();
|
|
|
|
init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We must be sure that accepting a new task (or allowing changing the
|
|
|
|
* parameters of an existing one) is consistent with the bandwidth
|
|
|
|
* constraints. If yes, this function also accordingly updates the currently
|
|
|
|
* allocated bandwidth to reflect the new situation.
|
|
|
|
*
|
|
|
|
* This function is called while holding p's rq->lock.
|
|
|
|
*/
|
|
|
|
int sched_dl_overflow(struct task_struct *p, int policy,
|
|
|
|
const struct sched_attr *attr)
|
|
|
|
{
|
|
|
|
u64 period = attr->sched_period ?: attr->sched_deadline;
|
|
|
|
u64 runtime = attr->sched_runtime;
|
|
|
|
u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
|
2020-05-20 21:42:41 +08:00
|
|
|
int cpus, err = -1, cpu = task_cpu(p);
|
|
|
|
struct dl_bw *dl_b = dl_bw_of(cpu);
|
|
|
|
unsigned long cap;
|
2017-06-22 02:22:01 +08:00
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
if (attr->sched_flags & SCHED_FLAG_SUGOV)
|
|
|
|
return 0;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
/* !deadline task may carry old deadline bandwidth */
|
|
|
|
if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Either if a task, enters, leave, or stays -deadline but changes
|
|
|
|
* its parameters, we may need to update accordingly the total
|
|
|
|
* allocated bandwidth of the container.
|
|
|
|
*/
|
|
|
|
raw_spin_lock(&dl_b->lock);
|
2020-05-20 21:42:41 +08:00
|
|
|
cpus = dl_bw_cpus(cpu);
|
|
|
|
cap = dl_bw_capacity(cpu);
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
if (dl_policy(policy) && !task_has_dl_policy(p) &&
|
2020-05-20 21:42:41 +08:00
|
|
|
!__dl_overflow(dl_b, cap, 0, new_bw)) {
|
2017-06-22 02:22:01 +08:00
|
|
|
if (hrtimer_active(&p->dl.inactive_timer))
|
2017-09-07 18:09:30 +08:00
|
|
|
__dl_sub(dl_b, p->dl.dl_bw, cpus);
|
2017-06-22 02:22:01 +08:00
|
|
|
__dl_add(dl_b, new_bw, cpus);
|
|
|
|
err = 0;
|
|
|
|
} else if (dl_policy(policy) && task_has_dl_policy(p) &&
|
2020-05-20 21:42:41 +08:00
|
|
|
!__dl_overflow(dl_b, cap, p->dl.dl_bw, new_bw)) {
|
2017-06-22 02:22:01 +08:00
|
|
|
/*
|
|
|
|
* XXX this is slightly incorrect: when the task
|
|
|
|
* utilization decreases, we should delay the total
|
|
|
|
* utilization change until the task's 0-lag point.
|
|
|
|
* But this would require to set the task's "inactive
|
|
|
|
* timer" when the task is not inactive.
|
|
|
|
*/
|
2017-09-07 18:09:30 +08:00
|
|
|
__dl_sub(dl_b, p->dl.dl_bw, cpus);
|
2017-06-22 02:22:01 +08:00
|
|
|
__dl_add(dl_b, new_bw, cpus);
|
|
|
|
dl_change_utilization(p, new_bw);
|
|
|
|
err = 0;
|
|
|
|
} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
|
|
|
|
/*
|
|
|
|
* Do not decrease the total deadline utilization here,
|
|
|
|
* switched_from_dl() will take care to do it at the correct
|
|
|
|
* (0-lag) time.
|
|
|
|
*/
|
|
|
|
err = 0;
|
|
|
|
}
|
|
|
|
raw_spin_unlock(&dl_b->lock);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function initializes the sched_dl_entity of a newly becoming
|
|
|
|
* SCHED_DEADLINE task.
|
|
|
|
*
|
|
|
|
* Only the static values are considered here, the actual runtime and the
|
|
|
|
* absolute deadline will be properly calculated when the task is enqueued
|
|
|
|
* for the first time with its new policy.
|
|
|
|
*/
|
|
|
|
void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
|
|
|
|
dl_se->dl_runtime = attr->sched_runtime;
|
|
|
|
dl_se->dl_deadline = attr->sched_deadline;
|
|
|
|
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
|
2021-07-27 18:11:01 +08:00
|
|
|
dl_se->flags = attr->sched_flags & SCHED_DL_FLAGS;
|
2017-06-22 02:22:01 +08:00
|
|
|
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
|
|
|
|
dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
|
|
|
|
}
|
|
|
|
|
|
|
|
void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
|
|
|
|
attr->sched_priority = p->rt_priority;
|
|
|
|
attr->sched_runtime = dl_se->dl_runtime;
|
|
|
|
attr->sched_deadline = dl_se->dl_deadline;
|
|
|
|
attr->sched_period = dl_se->dl_period;
|
2021-07-27 18:11:01 +08:00
|
|
|
attr->sched_flags &= ~SCHED_DL_FLAGS;
|
|
|
|
attr->sched_flags |= dl_se->flags;
|
2017-06-22 02:22:01 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function validates the new parameters of a -deadline task.
|
|
|
|
* We ask for the deadline not being zero, and greater or equal
|
|
|
|
* than the runtime, as well as the period of being zero or
|
|
|
|
* greater than deadline. Furthermore, we have to be sure that
|
|
|
|
* user parameters are above the internal resolution of 1us (we
|
|
|
|
* check sched_runtime only since it is always the smaller one) and
|
|
|
|
* below 2^63 ns (we have to check both sched_deadline and
|
|
|
|
* sched_period, as the latter can be zero).
|
|
|
|
*/
|
|
|
|
bool __checkparam_dl(const struct sched_attr *attr)
|
|
|
|
{
|
2019-07-26 22:54:10 +08:00
|
|
|
u64 period, max, min;
|
|
|
|
|
2017-12-04 18:23:20 +08:00
|
|
|
/* special dl tasks don't actually use any parameter */
|
|
|
|
if (attr->sched_flags & SCHED_FLAG_SUGOV)
|
|
|
|
return true;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
/* deadline != 0 */
|
|
|
|
if (attr->sched_deadline == 0)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since we truncate DL_SCALE bits, make sure we're at least
|
|
|
|
* that big.
|
|
|
|
*/
|
|
|
|
if (attr->sched_runtime < (1ULL << DL_SCALE))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Since we use the MSB for wrap-around and sign issues, make
|
|
|
|
* sure it's not set (mind that period can be equal to zero).
|
|
|
|
*/
|
|
|
|
if (attr->sched_deadline & (1ULL << 63) ||
|
|
|
|
attr->sched_period & (1ULL << 63))
|
|
|
|
return false;
|
|
|
|
|
2019-07-26 22:54:10 +08:00
|
|
|
period = attr->sched_period;
|
|
|
|
if (!period)
|
|
|
|
period = attr->sched_deadline;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
/* runtime <= deadline <= period (if period != 0) */
|
2019-07-26 22:54:10 +08:00
|
|
|
if (period < attr->sched_deadline ||
|
2017-06-22 02:22:01 +08:00
|
|
|
attr->sched_deadline < attr->sched_runtime)
|
|
|
|
return false;
|
|
|
|
|
2019-07-26 22:54:10 +08:00
|
|
|
max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
|
|
|
|
min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
|
|
|
|
|
|
|
|
if (period < min || period > max)
|
|
|
|
return false;
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This function clears the sched_dl_entity static params.
|
|
|
|
*/
|
|
|
|
void __dl_clear_params(struct task_struct *p)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
dl_se->dl_runtime = 0;
|
|
|
|
dl_se->dl_deadline = 0;
|
|
|
|
dl_se->dl_period = 0;
|
|
|
|
dl_se->flags = 0;
|
|
|
|
dl_se->dl_bw = 0;
|
|
|
|
dl_se->dl_density = 0;
|
2017-06-22 02:22:01 +08:00
|
|
|
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
dl_se->dl_throttled = 0;
|
|
|
|
dl_se->dl_yielded = 0;
|
|
|
|
dl_se->dl_non_contending = 0;
|
|
|
|
dl_se->dl_overrun = 0;
|
2020-11-17 14:14:32 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_RT_MUTEXES
|
|
|
|
dl_se->pi_se = dl_se;
|
|
|
|
#endif
|
2017-06-22 02:22:01 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
|
|
|
|
{
|
|
|
|
struct sched_dl_entity *dl_se = &p->dl;
|
|
|
|
|
|
|
|
if (dl_se->dl_runtime != attr->sched_runtime ||
|
|
|
|
dl_se->dl_deadline != attr->sched_deadline ||
|
|
|
|
dl_se->dl_period != attr->sched_period ||
|
2021-07-27 18:11:01 +08:00
|
|
|
dl_se->flags != (attr->sched_flags & SCHED_DL_FLAGS))
|
2017-06-22 02:22:01 +08:00
|
|
|
return true;
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
|
|
|
|
const struct cpumask *trial)
|
|
|
|
{
|
2022-07-29 19:13:04 +08:00
|
|
|
unsigned long flags, cap;
|
2017-06-22 02:22:01 +08:00
|
|
|
struct dl_bw *cur_dl_b;
|
2022-07-29 19:13:04 +08:00
|
|
|
int ret = 1;
|
2017-06-22 02:22:01 +08:00
|
|
|
|
|
|
|
rcu_read_lock_sched();
|
|
|
|
cur_dl_b = dl_bw_of(cpumask_any(cur));
|
2022-07-29 19:13:04 +08:00
|
|
|
cap = __dl_bw_capacity(trial);
|
2017-06-22 02:22:01 +08:00
|
|
|
raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
|
2022-07-29 19:13:04 +08:00
|
|
|
if (__dl_overflow(cur_dl_b, cap, 0, 0))
|
2017-06-22 02:22:01 +08:00
|
|
|
ret = 0;
|
|
|
|
raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
|
|
|
|
rcu_read_unlock_sched();
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2023-05-08 15:58:53 +08:00
|
|
|
enum dl_bw_request {
|
|
|
|
dl_bw_req_check_overflow = 0,
|
|
|
|
dl_bw_req_alloc,
|
|
|
|
dl_bw_req_free
|
|
|
|
};
|
|
|
|
|
|
|
|
static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
|
2017-06-22 02:22:01 +08:00
|
|
|
{
|
2023-05-08 15:58:53 +08:00
|
|
|
unsigned long flags;
|
2017-06-22 02:22:01 +08:00
|
|
|
struct dl_bw *dl_b;
|
2023-05-08 15:58:53 +08:00
|
|
|
bool overflow = 0;
|
2017-06-22 02:22:01 +08:00
|
|
|
|
|
|
|
rcu_read_lock_sched();
|
|
|
|
dl_b = dl_bw_of(cpu);
|
|
|
|
raw_spin_lock_irqsave(&dl_b->lock, flags);
|
2022-03-03 02:34:30 +08:00
|
|
|
|
2023-05-08 15:58:53 +08:00
|
|
|
if (req == dl_bw_req_free) {
|
|
|
|
__dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
|
|
|
|
} else {
|
|
|
|
unsigned long cap = dl_bw_capacity(cpu);
|
|
|
|
|
|
|
|
overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
|
|
|
|
|
|
|
|
if (req == dl_bw_req_alloc && !overflow) {
|
|
|
|
/*
|
|
|
|
* We reserve space in the destination
|
|
|
|
* root_domain, as we can't fail after this point.
|
|
|
|
* We will free resources in the source root_domain
|
|
|
|
* later on (see set_cpus_allowed_dl()).
|
|
|
|
*/
|
|
|
|
__dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
|
|
|
|
}
|
2022-03-03 02:34:30 +08:00
|
|
|
}
|
|
|
|
|
2017-06-22 02:22:01 +08:00
|
|
|
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
|
|
|
|
rcu_read_unlock_sched();
|
sched: Clean up and harmonize the coding style of the scheduler code base
A good number of small style inconsistencies have accumulated
in the scheduler core, so do a pass over them to harmonize
all these details:
- fix speling in comments,
- use curly braces for multi-line statements,
- remove unnecessary parentheses from integer literals,
- capitalize consistently,
- remove stray newlines,
- add comments where necessary,
- remove invalid/unnecessary comments,
- align structure definitions and other data types vertically,
- add missing newlines for increased readability,
- fix vertical tabulation where it's misaligned,
- harmonize preprocessor conditional block labeling
and vertical alignment,
- remove line-breaks where they uglify the code,
- add newline after local variable definitions,
No change in functionality:
md5:
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.before.asm
1191fa0a890cfa8132156d2959d7e9e2 built-in.o.after.asm
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-03 21:01:12 +08:00
|
|
|
|
2022-03-03 02:34:30 +08:00
|
|
|
return overflow ? -EBUSY : 0;
|
2017-06-22 02:22:01 +08:00
|
|
|
}
|
2023-05-08 15:58:53 +08:00
|
|
|
|
|
|
|
int dl_bw_check_overflow(int cpu)
|
|
|
|
{
|
|
|
|
return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
int dl_bw_alloc(int cpu, u64 dl_bw)
|
|
|
|
{
|
|
|
|
return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw);
|
|
|
|
}
|
|
|
|
|
|
|
|
void dl_bw_free(int cpu, u64 dl_bw)
|
|
|
|
{
|
|
|
|
dl_bw_manage(dl_bw_req_free, cpu, dl_bw);
|
|
|
|
}
|
2017-06-22 02:22:01 +08:00
|
|
|
#endif
|
|
|
|
|
2014-10-31 06:39:33 +08:00
|
|
|
#ifdef CONFIG_SCHED_DEBUG
|
|
|
|
void print_dl_stats(struct seq_file *m, int cpu)
|
|
|
|
{
|
|
|
|
print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_SCHED_DEBUG */
|