linux-sg2042/kernel/sched/debug.c

662 lines
15 KiB
C
Raw Normal View History

/*
* kernel/sched/debug.c
*
* Print the CFS rbtree
*
* Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
#include <linux/utsname.h>
#include <linux/mempolicy.h>
#include "sched.h"
static DEFINE_SPINLOCK(sched_debug_lock);
/*
* This allows printing both to /proc/sched_debug and
* to the console
*/
#define SEQ_printf(m, x...) \
do { \
if (m) \
seq_printf(m, x); \
else \
printk(x); \
} while (0)
/*
* Ease the printing of nsec fields:
*/
static long long nsec_high(unsigned long long nsec)
{
if ((long long)nsec < 0) {
nsec = -nsec;
do_div(nsec, 1000000);
return -nsec;
}
do_div(nsec, 1000000);
return nsec;
}
static unsigned long nsec_low(unsigned long long nsec)
{
if ((long long)nsec < 0)
nsec = -nsec;
return do_div(nsec, 1000000);
}
#define SPLIT_NS(x) nsec_high(x), nsec_low(x)
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
#ifdef CONFIG_FAIR_GROUP_SCHED
sched: Add 'autogroup' scheduling feature: automated per session task groups A recurring complaint from CFS users is that parallel kbuild has a negative impact on desktop interactivity. This patch implements an idea from Linus, to automatically create task groups. Currently, only per session autogroups are implemented, but the patch leaves the way open for enhancement. Implementation: each task's signal struct contains an inherited pointer to a refcounted autogroup struct containing a task group pointer, the default for all tasks pointing to the init_task_group. When a task calls setsid(), a new task group is created, the process is moved into the new task group, and a reference to the preveious task group is dropped. Child processes inherit this task group thereafter, and increase it's refcount. When the last thread of a process exits, the process's reference is dropped, such that when the last process referencing an autogroup exits, the autogroup is destroyed. At runqueue selection time, IFF a task has no cgroup assignment, its current autogroup is used. Autogroup bandwidth is controllable via setting it's nice level through the proc filesystem: cat /proc/<pid>/autogroup Displays the task's group and the group's nice level. echo <nice level> > /proc/<pid>/autogroup Sets the task group's shares to the weight of nice <level> task. Setting nice level is rate limited for !admin users due to the abuse risk of task group locking. The feature is enabled from boot by default if CONFIG_SCHED_AUTOGROUP=y is selected, but can be disabled via the boot option noautogroup, and can also be turned on/off on the fly via: echo [01] > /proc/sys/kernel/sched_autogroup_enabled ... which will automatically move tasks to/from the root task group. Signed-off-by: Mike Galbraith <efault@gmx.de> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Paul Turner <pjt@google.com> Cc: Oleg Nesterov <oleg@redhat.com> [ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ] Signed-off-by: Ingo Molnar <mingo@elte.hu> LKML-Reference: <1290281700.28711.9.camel@maggy.simson.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-30 21:18:03 +08:00
static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
{
struct sched_entity *se = tg->se[cpu];
#define P(F) \
SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F)
#define PN(F) \
SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
if (!se)
return;
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
PN(se->exec_start);
PN(se->vruntime);
PN(se->sum_exec_runtime);
#ifdef CONFIG_SCHEDSTATS
PN(se->statistics.wait_start);
PN(se->statistics.sleep_start);
PN(se->statistics.block_start);
PN(se->statistics.sleep_max);
PN(se->statistics.block_max);
PN(se->statistics.exec_max);
PN(se->statistics.slice_max);
PN(se->statistics.wait_max);
PN(se->statistics.wait_sum);
P(se->statistics.wait_count);
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
#endif
P(se->load.weight);
#ifdef CONFIG_SMP
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 08:04:37 +08:00
P(se->avg.load_avg);
P(se->avg.util_avg);
#endif
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
#undef PN
#undef P
}
#endif
#ifdef CONFIG_CGROUP_SCHED
static char group_path[PATH_MAX];
static char *task_group_path(struct task_group *tg)
{
if (autogroup_path(tg, group_path, PATH_MAX))
return group_path;
cgroup: remove cgroup->name cgroup->name handling became quite complicated over time involving dedicated struct cgroup_name for RCU protection. Now that cgroup is on kernfs, we can drop all of it and simply use kernfs_name/path() and friends. Replace cgroup->name and all related code with kernfs name/path constructs. * Reimplement cgroup_name() and cgroup_path() as thin wrappers on top of kernfs counterparts, which involves semantic changes. pr_cont_cgroup_name() and pr_cont_cgroup_path() added. * cgroup->name handling dropped from cgroup_rename(). * All users of cgroup_name/path() updated to the new semantics. Users which were formatting the string just to printk them are converted to use pr_cont_cgroup_name/path() instead, which simplifies things quite a bit. As cgroup_name() no longer requires RCU read lock around it, RCU lockings which were protecting only cgroup_name() are removed. v2: Comment above oom_info_lock updated as suggested by Michal. v3: dummy_top doesn't have a kn associated and pr_cont_cgroup_name/path() ended up calling the matching kernfs functions with NULL kn leading to oops. Test for NULL kn and print "/" if so. This issue was reported by Fengguang Wu. v4: Rebased on top of 0ab02ca8f887 ("cgroup: protect modifications to cgroup_idr with cgroup_mutex"). Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Li Zefan <lizefan@huawei.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
2014-02-12 22:29:50 +08:00
return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
}
#endif
static void
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
if (rq->curr == p)
SEQ_printf(m, "R");
else
SEQ_printf(m, " ");
SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
p->comm, task_pid_nr(p),
SPLIT_NS(p->se.vruntime),
(long long)(p->nvcsw + p->nivcsw),
p->prio);
#ifdef CONFIG_SCHEDSTATS
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
SPLIT_NS(p->se.statistics.wait_sum),
SPLIT_NS(p->se.sum_exec_runtime),
SPLIT_NS(p->se.statistics.sum_sleep_runtime));
#else
SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
0LL, 0L,
SPLIT_NS(p->se.sum_exec_runtime),
0LL, 0L);
#endif
#ifdef CONFIG_NUMA_BALANCING
SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
#endif
#ifdef CONFIG_CGROUP_SCHED
SEQ_printf(m, " %s", task_group_path(task_group(p)));
#endif
SEQ_printf(m, "\n");
}
static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
{
struct task_struct *g, *p;
SEQ_printf(m,
"\nrunnable tasks:\n"
" task PID tree-key switches prio"
" wait-time sum-exec sum-sleep\n"
"------------------------------------------------------"
"----------------------------------------------------\n");
rcu_read_lock();
for_each_process_thread(g, p) {
if (task_cpu(p) != rq_cpu)
continue;
print_task(m, rq, p);
}
rcu_read_unlock();
}
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
spread, rq0_min_vruntime, spread0;
struct rq *rq = cpu_rq(cpu);
struct sched_entity *last;
unsigned long flags;
#ifdef CONFIG_FAIR_GROUP_SCHED
SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
#else
SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
#endif
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock",
SPLIT_NS(cfs_rq->exec_clock));
raw_spin_lock_irqsave(&rq->lock, flags);
if (cfs_rq->rb_leftmost)
MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
last = __pick_last_entity(cfs_rq);
if (last)
max_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
raw_spin_unlock_irqrestore(&rq->lock, flags);
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "MIN_vruntime",
SPLIT_NS(MIN_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
SPLIT_NS(min_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "max_vruntime",
SPLIT_NS(max_vruntime));
spread = max_vruntime - MIN_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread",
SPLIT_NS(spread));
spread0 = min_vruntime - rq0_min_vruntime;
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread0",
SPLIT_NS(spread0));
SEQ_printf(m, " .%-30s: %d\n", "nr_spread_over",
cfs_rq->nr_spread_over);
SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
#ifdef CONFIG_SMP
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 08:04:37 +08:00
SEQ_printf(m, " .%-30s: %lu\n", "load_avg",
cfs_rq->avg.load_avg);
SEQ_printf(m, " .%-30s: %lu\n", "runnable_load_avg",
cfs_rq->runnable_load_avg);
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 08:04:37 +08:00
SEQ_printf(m, " .%-30s: %lu\n", "util_avg",
cfs_rq->avg.util_avg);
SEQ_printf(m, " .%-30s: %ld\n", "removed_load_avg",
atomic_long_read(&cfs_rq->removed_load_avg));
SEQ_printf(m, " .%-30s: %ld\n", "removed_util_avg",
atomic_long_read(&cfs_rq->removed_util_avg));
#ifdef CONFIG_FAIR_GROUP_SCHED
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 08:04:37 +08:00
SEQ_printf(m, " .%-30s: %lu\n", "tg_load_avg_contrib",
cfs_rq->tg_load_avg_contrib);
SEQ_printf(m, " .%-30s: %ld\n", "tg_load_avg",
atomic_long_read(&cfs_rq->tg->load_avg));
#endif
#endif
#ifdef CONFIG_CFS_BANDWIDTH
SEQ_printf(m, " .%-30s: %d\n", "throttled",
cfs_rq->throttled);
SEQ_printf(m, " .%-30s: %d\n", "throttle_count",
cfs_rq->throttle_count);
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
sched: include group statistics in /proc/sched_debug Impact: extend /proc/sched_debug info Since the statistics of a group entity isn't exported directly from the kernel, it becomes difficult to obtain some of the group statistics. For example, the current method to obtain exec time of a group entity is not always accurate. One has to read the exec times of all the tasks(/proc/<pid>/sched) in the group and add them. This method fails (or becomes difficult) if we want to collect stats of a group over a duration where tasks get created and terminated. This patch makes it easier to obtain group stats by directly including them in /proc/sched_debug. Stats like group exec time would help user programs (like LTP) to accurately measure the group fairness. An example output of group stats from /proc/sched_debug: cfs_rq[3]:/3/a/1 .exec_clock : 89.598007 .MIN_vruntime : 0.000001 .min_vruntime : 256300.970506 .max_vruntime : 0.000001 .spread : 0.000000 .spread0 : -25373.372248 .nr_running : 0 .load : 0 .yld_exp_empty : 0 .yld_act_empty : 0 .yld_both_empty : 0 .yld_count : 4474 .sched_switch : 0 .sched_count : 40507 .sched_goidle : 12686 .ttwu_count : 15114 .ttwu_local : 11950 .bkl_count : 67 .nr_spread_over : 0 .shares : 0 .se->exec_start : 113676.727170 .se->vruntime : 1592.612714 .se->sum_exec_runtime : 89.598007 .se->wait_start : 0.000000 .se->sleep_start : 0.000000 .se->block_start : 0.000000 .se->sleep_max : 0.000000 .se->block_max : 0.000000 .se->exec_max : 1.000282 .se->slice_max : 1.999750 .se->wait_max : 54.981093 .se->wait_sum : 217.610521 .se->wait_count : 50 .se->load.weight : 2 Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com> Acked-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-11 00:04:09 +08:00
print_cfs_group_stats(m, cpu, cfs_rq->tg);
#endif
}
void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
{
#ifdef CONFIG_RT_GROUP_SCHED
SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
#else
SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
#endif
#define P(x) \
SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
#define PN(x) \
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
P(rt_nr_running);
P(rt_throttled);
PN(rt_time);
PN(rt_runtime);
#undef PN
#undef P
}
void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
{
SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
}
extern __read_mostly int sched_clock_running;
static void print_cpu(struct seq_file *m, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
#ifdef CONFIG_X86
{
unsigned int freq = cpu_khz ? : 1;
SEQ_printf(m, "cpu#%d, %u.%03u MHz\n",
cpu, freq / 1000, (freq % 1000));
}
#else
SEQ_printf(m, "cpu#%d\n", cpu);
#endif
#define P(x) \
do { \
if (sizeof(rq->x) == 4) \
SEQ_printf(m, " .%-30s: %ld\n", #x, (long)(rq->x)); \
else \
SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rq->x));\
} while (0)
#define PN(x) \
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
P(nr_running);
SEQ_printf(m, " .%-30s: %lu\n", "load",
rq->load.weight);
P(nr_switches);
P(nr_load_updates);
P(nr_uninterruptible);
PN(next_balance);
SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
PN(clock);
PN(clock_task);
P(cpu_load[0]);
P(cpu_load[1]);
P(cpu_load[2]);
P(cpu_load[3]);
P(cpu_load[4]);
#undef P
#undef PN
#ifdef CONFIG_SCHEDSTATS
#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n);
#define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n);
P(yld_count);
P(sched_count);
P(sched_goidle);
#ifdef CONFIG_SMP
P64(avg_idle);
P64(max_idle_balance_cost);
#endif
P(ttwu_count);
P(ttwu_local);
#undef P
#undef P64
#endif
spin_lock_irqsave(&sched_debug_lock, flags);
print_cfs_stats(m, cpu);
print_rt_stats(m, cpu);
print_dl_stats(m, cpu);
print_rq(m, rq, cpu);
spin_unlock_irqrestore(&sched_debug_lock, flags);
SEQ_printf(m, "\n");
}
static const char *sched_tunable_scaling_names[] = {
"none",
"logaritmic",
"linear"
};
static void sched_debug_header(struct seq_file *m)
{
u64 ktime, sched_clk, cpu_clk;
unsigned long flags;
local_irq_save(flags);
ktime = ktime_to_ns(ktime_get());
sched_clk = sched_clock();
cpu_clk = local_clock();
local_irq_restore(flags);
SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n",
init_utsname()->release,
(int)strcspn(init_utsname()->version, " "),
init_utsname()->version);
#define P(x) \
SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x))
#define PN(x) \
SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
PN(ktime);
PN(sched_clk);
PN(cpu_clk);
P(jiffies);
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
P(sched_clock_stable());
#endif
#undef PN
#undef P
SEQ_printf(m, "\n");
SEQ_printf(m, "sysctl_sched\n");
#define P(x) \
SEQ_printf(m, " .%-40s: %Ld\n", #x, (long long)(x))
#define PN(x) \
SEQ_printf(m, " .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
PN(sysctl_sched_latency);
PN(sysctl_sched_min_granularity);
PN(sysctl_sched_wakeup_granularity);
P(sysctl_sched_child_runs_first);
P(sysctl_sched_features);
#undef PN
#undef P
SEQ_printf(m, " .%-40s: %d (%s)\n",
"sysctl_sched_tunable_scaling",
sysctl_sched_tunable_scaling,
sched_tunable_scaling_names[sysctl_sched_tunable_scaling]);
SEQ_printf(m, "\n");
}
static int sched_debug_show(struct seq_file *m, void *v)
{
int cpu = (unsigned long)(v - 2);
if (cpu != -1)
print_cpu(m, cpu);
else
sched_debug_header(m);
return 0;
}
void sysrq_sched_debug_show(void)
{
int cpu;
sched_debug_header(NULL);
for_each_online_cpu(cpu)
print_cpu(NULL, cpu);
}
/*
* This itererator needs some explanation.
* It returns 1 for the header position.
* This means 2 is cpu 0.
* In a hotplugged system some cpus, including cpu 0, may be missing so we have
* to use cpumask_* to iterate over the cpus.
*/
static void *sched_debug_start(struct seq_file *file, loff_t *offset)
{
unsigned long n = *offset;
if (n == 0)
return (void *) 1;
n--;
if (n > 0)
n = cpumask_next(n - 1, cpu_online_mask);
else
n = cpumask_first(cpu_online_mask);
*offset = n + 1;
if (n < nr_cpu_ids)
return (void *)(unsigned long)(n + 2);
return NULL;
}
static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset)
{
(*offset)++;
return sched_debug_start(file, offset);
}
static void sched_debug_stop(struct seq_file *file, void *data)
{
}
static const struct seq_operations sched_debug_sops = {
.start = sched_debug_start,
.next = sched_debug_next,
.stop = sched_debug_stop,
.show = sched_debug_show,
};
static int sched_debug_release(struct inode *inode, struct file *file)
{
seq_release(inode, file);
return 0;
}
static int sched_debug_open(struct inode *inode, struct file *filp)
{
int ret = 0;
ret = seq_open(filp, &sched_debug_sops);
return ret;
}
static const struct file_operations sched_debug_fops = {
.open = sched_debug_open,
.read = seq_read,
.llseek = seq_lseek,
.release = sched_debug_release,
};
static int __init init_sched_debug_procfs(void)
{
struct proc_dir_entry *pe;
pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
if (!pe)
return -ENOMEM;
return 0;
}
__initcall(init_sched_debug_procfs);
#define __P(F) \
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
#define P(F) \
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
#define __PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
#define PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
sched/numa: Fix numa balancing stats in /proc/pid/sched Commit 44dba3d5d6a1 ("sched: Refactor task_struct to use numa_faults instead of numa_* pointers") modified the way tsk->numa_faults stats are accounted. However that commit never touched show_numa_stats() that is displayed in /proc/pid/sched and thus the numbers displayed in /proc/pid/sched don't match the actual numbers. Fix it by making sure that /proc/pid/sched reflects the task fault numbers. Also add group fault stats too. Also couple of more modifications are added here: 1. Format changes: - Previously we would list two entries per node, one for private and one for shared. Also the home node info was listed in each entry. - Now preferred node, total_faults and current node are displayed separately. - Now there is one entry per node, that lists private,shared task and group faults. 2. Unit changes: - p->numa_pages_migrated was getting reset after every read of /proc/pid/sched. It's more useful to have absolute numbers since differential migrations between two accesses can be more easily calculated. Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Iulia Manda <iulia.manda21@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1435252903-1081-4-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-26 01:21:43 +08:00
#ifdef CONFIG_NUMA_BALANCING
void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
unsigned long tpf, unsigned long gsf, unsigned long gpf)
{
SEQ_printf(m, "numa_faults node=%d ", node);
SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
}
#endif
static void sched_show_numa(struct task_struct *p, struct seq_file *m)
{
#ifdef CONFIG_NUMA_BALANCING
struct mempolicy *pol;
if (p->mm)
P(mm->numa_scan_seq);
task_lock(p);
pol = p->mempolicy;
if (pol && !(pol->flags & MPOL_F_MORON))
pol = NULL;
mpol_get(pol);
task_unlock(p);
sched/numa: Fix numa balancing stats in /proc/pid/sched Commit 44dba3d5d6a1 ("sched: Refactor task_struct to use numa_faults instead of numa_* pointers") modified the way tsk->numa_faults stats are accounted. However that commit never touched show_numa_stats() that is displayed in /proc/pid/sched and thus the numbers displayed in /proc/pid/sched don't match the actual numbers. Fix it by making sure that /proc/pid/sched reflects the task fault numbers. Also add group fault stats too. Also couple of more modifications are added here: 1. Format changes: - Previously we would list two entries per node, one for private and one for shared. Also the home node info was listed in each entry. - Now preferred node, total_faults and current node are displayed separately. - Now there is one entry per node, that lists private,shared task and group faults. 2. Unit changes: - p->numa_pages_migrated was getting reset after every read of /proc/pid/sched. It's more useful to have absolute numbers since differential migrations between two accesses can be more easily calculated. Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: Iulia Manda <iulia.manda21@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1435252903-1081-4-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-26 01:21:43 +08:00
P(numa_pages_migrated);
P(numa_preferred_nid);
P(total_numa_faults);
SEQ_printf(m, "current_node=%d, numa_group_id=%d\n",
task_node(p), task_numa_group_id(p));
show_numa_stats(p, m);
mpol_put(pol);
#endif
}
void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
unsigned long nr_switches;
SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
get_nr_threads(p));
SEQ_printf(m,
"---------------------------------------------------------"
"----------\n");
#define __P(F) \
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
#define P(F) \
SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
#define __PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
#define PN(F) \
SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
PN(se.exec_start);
PN(se.vruntime);
PN(se.sum_exec_runtime);
nr_switches = p->nvcsw + p->nivcsw;
#ifdef CONFIG_SCHEDSTATS
PN(se.statistics.sum_sleep_runtime);
PN(se.statistics.wait_start);
PN(se.statistics.sleep_start);
PN(se.statistics.block_start);
PN(se.statistics.sleep_max);
PN(se.statistics.block_max);
PN(se.statistics.exec_max);
PN(se.statistics.slice_max);
PN(se.statistics.wait_max);
PN(se.statistics.wait_sum);
P(se.statistics.wait_count);
PN(se.statistics.iowait_sum);
P(se.statistics.iowait_count);
P(se.nr_migrations);
P(se.statistics.nr_migrations_cold);
P(se.statistics.nr_failed_migrations_affine);
P(se.statistics.nr_failed_migrations_running);
P(se.statistics.nr_failed_migrations_hot);
P(se.statistics.nr_forced_migrations);
P(se.statistics.nr_wakeups);
P(se.statistics.nr_wakeups_sync);
P(se.statistics.nr_wakeups_migrate);
P(se.statistics.nr_wakeups_local);
P(se.statistics.nr_wakeups_remote);
P(se.statistics.nr_wakeups_affine);
P(se.statistics.nr_wakeups_affine_attempts);
P(se.statistics.nr_wakeups_passive);
P(se.statistics.nr_wakeups_idle);
{
u64 avg_atom, avg_per_cpu;
avg_atom = p->se.sum_exec_runtime;
if (nr_switches)
avg_atom = div64_ul(avg_atom, nr_switches);
else
avg_atom = -1LL;
avg_per_cpu = p->se.sum_exec_runtime;
if (p->se.nr_migrations) {
avg_per_cpu = div64_u64(avg_per_cpu,
p->se.nr_migrations);
} else {
avg_per_cpu = -1LL;
}
__PN(avg_atom);
__PN(avg_per_cpu);
}
#endif
__P(nr_switches);
SEQ_printf(m, "%-45s:%21Ld\n",
"nr_voluntary_switches", (long long)p->nvcsw);
SEQ_printf(m, "%-45s:%21Ld\n",
"nr_involuntary_switches", (long long)p->nivcsw);
P(se.load.weight);
#ifdef CONFIG_SMP
sched/fair: Rewrite runnable load and utilization average tracking The idea of runnable load average (let runnable time contribute to weight) was proposed by Paul Turner and Ben Segall, and it is still followed by this rewrite. This rewrite aims to solve the following issues: 1. cfs_rq's load average (namely runnable_load_avg and blocked_load_avg) is updated at the granularity of an entity at a time, which results in the cfs_rq's load average is stale or partially updated: at any time, only one entity is up to date, all other entities are effectively lagging behind. This is undesirable. To illustrate, if we have n runnable entities in the cfs_rq, as time elapses, they certainly become outdated: t0: cfs_rq { e1_old, e2_old, ..., en_old } and when we update: t1: update e1, then we have cfs_rq { e1_new, e2_old, ..., en_old } t2: update e2, then we have cfs_rq { e1_old, e2_new, ..., en_old } ... We solve this by combining all runnable entities' load averages together in cfs_rq's avg, and update the cfs_rq's avg as a whole. This is based on the fact that if we regard the update as a function, then: w * update(e) = update(w * e) and update(e1) + update(e2) = update(e1 + e2), then w1 * update(e1) + w2 * update(e2) = update(w1 * e1 + w2 * e2) therefore, by this rewrite, we have an entirely updated cfs_rq at the time we update it: t1: update cfs_rq { e1_new, e2_new, ..., en_new } t2: update cfs_rq { e1_new, e2_new, ..., en_new } ... 2. cfs_rq's load average is different between top rq->cfs_rq and other task_group's per CPU cfs_rqs in whether or not blocked_load_average contributes to the load. The basic idea behind runnable load average (the same for utilization) is that the blocked state is taken into account as opposed to only accounting for the currently runnable state. Therefore, the average should include both the runnable/running and blocked load averages. This rewrite does that. In addition, we also combine runnable/running and blocked averages of all entities into the cfs_rq's average, and update it together at once. This is based on the fact that: update(runnable) + update(blocked) = update(runnable + blocked) This significantly reduces the code as we don't need to separately maintain/update runnable/running load and blocked load. 3. How task_group entities' share is calculated is complex and imprecise. We reduce the complexity in this rewrite to allow a very simple rule: the task_group's load_avg is aggregated from its per CPU cfs_rqs's load_avgs. Then group entity's weight is simply proportional to its own cfs_rq's load_avg / task_group's load_avg. To illustrate, if a task_group has { cfs_rq1, cfs_rq2, ..., cfs_rqn }, then, task_group_avg = cfs_rq1_avg + cfs_rq2_avg + ... + cfs_rqn_avg, then cfs_rqx's entity's share = cfs_rqx_avg / task_group_avg * task_group's share To sum up, this rewrite in principle is equivalent to the current one, but fixes the issues described above. Turns out, it significantly reduces the code complexity and hence increases clarity and efficiency. In addition, the new averages are more smooth/continuous (no spurious spikes and valleys) and updated more consistently and quickly to reflect the load dynamics. As a result, we have less load tracking overhead, better performance, and especially better power efficiency due to more balanced load. Signed-off-by: Yuyang Du <yuyang.du@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> 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: arjan@linux.intel.com Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: fengguang.wu@intel.com Cc: len.brown@intel.com Cc: morten.rasmussen@arm.com Cc: pjt@google.com Cc: rafael.j.wysocki@intel.com Cc: umgwanakikbuti@gmail.com Cc: vincent.guittot@linaro.org Link: http://lkml.kernel.org/r/1436918682-4971-3-git-send-email-yuyang.du@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-07-15 08:04:37 +08:00
P(se.avg.load_sum);
P(se.avg.util_sum);
P(se.avg.load_avg);
P(se.avg.util_avg);
P(se.avg.last_update_time);
#endif
P(policy);
P(prio);
#undef PN
#undef __PN
#undef P
#undef __P
{
unsigned int this_cpu = raw_smp_processor_id();
u64 t0, t1;
t0 = cpu_clock(this_cpu);
t1 = cpu_clock(this_cpu);
SEQ_printf(m, "%-45s:%21Ld\n",
"clock-delta", (long long)(t1-t0));
}
sched_show_numa(p, m);
}
void proc_sched_set_task(struct task_struct *p)
{
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
}