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 */
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
#ifndef INT_BLK_MQ_H
|
|
|
|
|
#define INT_BLK_MQ_H
|
|
|
|
|
|
2016-11-08 12:32:37 +08:00
|
|
|
#include "blk-stat.h"
|
2017-11-05 02:39:57 +08:00
|
|
|
#include "blk-mq-tag.h"
|
2016-11-08 12:32:37 +08:00
|
|
|
|
2014-04-16 04:14:00 +08:00
|
|
|
struct blk_mq_tag_set;
|
|
|
|
|
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
struct blk_mq_ctx {
|
|
|
|
|
struct {
|
|
|
|
|
spinlock_t lock;
|
|
|
|
|
struct list_head rq_list;
|
|
|
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
|
|
|
|
|
|
unsigned int cpu;
|
|
|
|
|
unsigned int index_hw;
|
|
|
|
|
|
|
|
|
|
/* incremented at dispatch time */
|
|
|
|
|
unsigned long rq_dispatched[2];
|
|
|
|
|
unsigned long rq_merged;
|
|
|
|
|
|
|
|
|
|
/* incremented at completion time */
|
|
|
|
|
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
|
|
|
|
|
|
|
|
|
|
struct request_queue *queue;
|
|
|
|
|
struct kobject kobj;
|
2014-05-09 23:36:49 +08:00
|
|
|
} ____cacheline_aligned_in_smp;
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
|
blk-mq: replace timeout synchronization with a RCU and generation based scheme
Currently, blk-mq timeout path synchronizes against the usual
issue/completion path using a complex scheme involving atomic
bitflags, REQ_ATOM_*, memory barriers and subtle memory coherence
rules. Unfortunately, it contains quite a few holes.
There's a complex dancing around REQ_ATOM_STARTED and
REQ_ATOM_COMPLETE between issue/completion and timeout paths; however,
they don't have a synchronization point across request recycle
instances and it isn't clear what the barriers add.
blk_mq_check_expired() can easily read STARTED from N-2'th iteration,
deadline from N-1'th, blk_mark_rq_complete() against Nth instance.
In fact, it's pretty easy to make blk_mq_check_expired() terminate a
later instance of a request. If we induce 5 sec delay before
time_after_eq() test in blk_mq_check_expired(), shorten the timeout to
2s, and issue back-to-back large IOs, blk-mq starts timing out
requests spuriously pretty quickly. Nothing actually timed out. It
just made the call on a recycle instance of a request and then
terminated a later instance long after the original instance finished.
The scenario isn't theoretical either.
This patch replaces the broken synchronization mechanism with a RCU
and generation number based one.
1. Each request has a u64 generation + state value, which can be
updated only by the request owner. Whenever a request becomes
in-flight, the generation number gets bumped up too. This provides
the basis for the timeout path to distinguish different recycle
instances of the request.
Also, marking a request in-flight and setting its deadline are
protected with a seqcount so that the timeout path can fetch both
values coherently.
2. The timeout path fetches the generation, state and deadline. If
the verdict is timeout, it records the generation into a dedicated
request abortion field and does RCU wait.
3. The completion path is also protected by RCU (from the previous
patch) and checks whether the current generation number and state
match the abortion field. If so, it skips completion.
4. The timeout path, after RCU wait, scans requests again and
terminates the ones whose generation and state still match the ones
requested for abortion.
By now, the timeout path knows that either the generation number
and state changed if it lost the race or the completion will yield
to it and can safely timeout the request.
While it's more lines of code, it's conceptually simpler, doesn't
depend on direct use of subtle memory ordering or coherence, and
hopefully doesn't terminate the wrong instance.
While this change makes REQ_ATOM_COMPLETE synchronization unnecessary
between issue/complete and timeout paths, REQ_ATOM_COMPLETE isn't
removed yet as it's still used in other places. Future patches will
move all state tracking to the new mechanism and remove all bitops in
the hot paths.
Note that this patch adds a comment explaining a race condition in
BLK_EH_RESET_TIMER path. The race has always been there and this
patch doesn't change it. It's just documenting the existing race.
v2: - Fixed BLK_EH_RESET_TIMER handling as pointed out by Jianchao.
- s/request->gstate_seqc/request->gstate_seq/ as suggested by Peter.
- READ_ONCE() added in blk_mq_rq_update_state() as suggested by Peter.
v3: - Fixed possible extended seqcount / u64_stats_sync read looping
spotted by Peter.
- MQ_RQ_IDLE was incorrectly being set in complete_request instead
of free_request. Fixed.
v4: - Rebased on top of hctx_lock() refactoring patch.
- Added comment explaining the use of hctx_lock() in completion path.
v5: - Added comments requested by Bart.
- Note the addition of BLK_EH_RESET_TIMER race condition in the
commit message.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: "jianchao.wang" <jianchao.w.wang@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <Bart.VanAssche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-10 00:29:48 +08:00
|
|
|
/*
|
|
|
|
|
* Bits for request->gstate. The lower two bits carry MQ_RQ_* state value
|
|
|
|
|
* and the upper bits the generation number.
|
|
|
|
|
*/
|
|
|
|
|
enum mq_rq_state {
|
|
|
|
|
MQ_RQ_IDLE = 0,
|
|
|
|
|
MQ_RQ_IN_FLIGHT = 1,
|
2018-01-10 00:29:52 +08:00
|
|
|
MQ_RQ_COMPLETE = 2,
|
blk-mq: replace timeout synchronization with a RCU and generation based scheme
Currently, blk-mq timeout path synchronizes against the usual
issue/completion path using a complex scheme involving atomic
bitflags, REQ_ATOM_*, memory barriers and subtle memory coherence
rules. Unfortunately, it contains quite a few holes.
There's a complex dancing around REQ_ATOM_STARTED and
REQ_ATOM_COMPLETE between issue/completion and timeout paths; however,
they don't have a synchronization point across request recycle
instances and it isn't clear what the barriers add.
blk_mq_check_expired() can easily read STARTED from N-2'th iteration,
deadline from N-1'th, blk_mark_rq_complete() against Nth instance.
In fact, it's pretty easy to make blk_mq_check_expired() terminate a
later instance of a request. If we induce 5 sec delay before
time_after_eq() test in blk_mq_check_expired(), shorten the timeout to
2s, and issue back-to-back large IOs, blk-mq starts timing out
requests spuriously pretty quickly. Nothing actually timed out. It
just made the call on a recycle instance of a request and then
terminated a later instance long after the original instance finished.
The scenario isn't theoretical either.
This patch replaces the broken synchronization mechanism with a RCU
and generation number based one.
1. Each request has a u64 generation + state value, which can be
updated only by the request owner. Whenever a request becomes
in-flight, the generation number gets bumped up too. This provides
the basis for the timeout path to distinguish different recycle
instances of the request.
Also, marking a request in-flight and setting its deadline are
protected with a seqcount so that the timeout path can fetch both
values coherently.
2. The timeout path fetches the generation, state and deadline. If
the verdict is timeout, it records the generation into a dedicated
request abortion field and does RCU wait.
3. The completion path is also protected by RCU (from the previous
patch) and checks whether the current generation number and state
match the abortion field. If so, it skips completion.
4. The timeout path, after RCU wait, scans requests again and
terminates the ones whose generation and state still match the ones
requested for abortion.
By now, the timeout path knows that either the generation number
and state changed if it lost the race or the completion will yield
to it and can safely timeout the request.
While it's more lines of code, it's conceptually simpler, doesn't
depend on direct use of subtle memory ordering or coherence, and
hopefully doesn't terminate the wrong instance.
While this change makes REQ_ATOM_COMPLETE synchronization unnecessary
between issue/complete and timeout paths, REQ_ATOM_COMPLETE isn't
removed yet as it's still used in other places. Future patches will
move all state tracking to the new mechanism and remove all bitops in
the hot paths.
Note that this patch adds a comment explaining a race condition in
BLK_EH_RESET_TIMER path. The race has always been there and this
patch doesn't change it. It's just documenting the existing race.
v2: - Fixed BLK_EH_RESET_TIMER handling as pointed out by Jianchao.
- s/request->gstate_seqc/request->gstate_seq/ as suggested by Peter.
- READ_ONCE() added in blk_mq_rq_update_state() as suggested by Peter.
v3: - Fixed possible extended seqcount / u64_stats_sync read looping
spotted by Peter.
- MQ_RQ_IDLE was incorrectly being set in complete_request instead
of free_request. Fixed.
v4: - Rebased on top of hctx_lock() refactoring patch.
- Added comment explaining the use of hctx_lock() in completion path.
v5: - Added comments requested by Bart.
- Note the addition of BLK_EH_RESET_TIMER race condition in the
commit message.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: "jianchao.wang" <jianchao.w.wang@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <Bart.VanAssche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-10 00:29:48 +08:00
|
|
|
|
|
|
|
|
MQ_RQ_STATE_BITS = 2,
|
|
|
|
|
MQ_RQ_STATE_MASK = (1 << MQ_RQ_STATE_BITS) - 1,
|
|
|
|
|
MQ_RQ_GEN_INC = 1 << MQ_RQ_STATE_BITS,
|
|
|
|
|
};
|
|
|
|
|
|
2014-07-02 00:31:13 +08:00
|
|
|
void blk_mq_freeze_queue(struct request_queue *q);
|
2013-12-26 21:31:38 +08:00
|
|
|
void blk_mq_free_queue(struct request_queue *q);
|
2014-05-21 01:49:02 +08:00
|
|
|
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
|
2014-12-23 05:04:42 +08:00
|
|
|
void blk_mq_wake_waiters(struct request_queue *q);
|
2017-10-14 17:22:29 +08:00
|
|
|
bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
|
2016-12-15 05:34:47 +08:00
|
|
|
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
|
2017-01-27 16:00:47 +08:00
|
|
|
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
|
|
|
|
|
bool wait);
|
blk-mq-sched: improve dispatching from sw queue
SCSI devices use host-wide tagset, and the shared driver tag space is
often quite big. However, there is also a queue depth for each lun(
.cmd_per_lun), which is often small, for example, on both lpfc and
qla2xxx, .cmd_per_lun is just 3.
So lots of requests may stay in sw queue, and we always flush all
belonging to same hw queue and dispatch them all to driver.
Unfortunately it is easy to cause queue busy because of the small
.cmd_per_lun. Once these requests are flushed out, they have to stay in
hctx->dispatch, and no bio merge can happen on these requests, and
sequential IO performance is harmed.
This patch introduces blk_mq_dequeue_from_ctx for dequeuing a request
from a sw queue, so that we can dispatch them in scheduler's way. We can
then avoid dequeueing too many requests from sw queue, since we don't
flush ->dispatch completely.
This patch improves dispatching from sw queue by using the .get_budget
and .put_budget callbacks.
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-10-14 17:22:30 +08:00
|
|
|
struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
|
|
|
|
|
struct blk_mq_ctx *start);
|
2016-12-15 05:34:47 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Internal helpers for allocating/freeing the request map
|
|
|
|
|
*/
|
2017-01-12 05:29:56 +08:00
|
|
|
void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
|
|
|
|
|
unsigned int hctx_idx);
|
|
|
|
|
void blk_mq_free_rq_map(struct blk_mq_tags *tags);
|
|
|
|
|
struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
|
|
|
|
|
unsigned int hctx_idx,
|
|
|
|
|
unsigned int nr_tags,
|
|
|
|
|
unsigned int reserved_tags);
|
|
|
|
|
int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
|
|
|
|
|
unsigned int hctx_idx, unsigned int depth);
|
2016-12-15 05:34:47 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Internal helpers for request insertion into sw queues
|
|
|
|
|
*/
|
|
|
|
|
void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
|
|
|
|
|
bool at_head);
|
2017-11-02 23:24:34 +08:00
|
|
|
void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
|
2017-01-17 21:03:22 +08:00
|
|
|
void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
|
|
|
|
|
struct list_head *list);
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
|
2018-01-18 00:25:57 +08:00
|
|
|
/* Used by blk_insert_cloned_request() to issue request directly */
|
2018-01-20 00:58:54 +08:00
|
|
|
blk_status_t blk_mq_request_issue_directly(struct request *rq);
|
2018-01-18 00:25:57 +08:00
|
|
|
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
/*
|
|
|
|
|
* CPU -> queue mappings
|
|
|
|
|
*/
|
2014-05-28 02:06:53 +08:00
|
|
|
extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int);
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
|
2016-09-14 22:18:54 +08:00
|
|
|
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
|
|
|
|
|
int cpu)
|
|
|
|
|
{
|
|
|
|
|
return q->queue_hw_ctx[q->mq_map[cpu]];
|
|
|
|
|
}
|
|
|
|
|
|
2014-05-30 22:25:36 +08:00
|
|
|
/*
|
|
|
|
|
* sysfs helpers
|
|
|
|
|
*/
|
2017-02-22 18:13:59 +08:00
|
|
|
extern void blk_mq_sysfs_init(struct request_queue *q);
|
2017-02-22 18:14:00 +08:00
|
|
|
extern void blk_mq_sysfs_deinit(struct request_queue *q);
|
2017-04-27 04:47:48 +08:00
|
|
|
extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
|
2014-05-30 22:25:36 +08:00
|
|
|
extern int blk_mq_sysfs_register(struct request_queue *q);
|
|
|
|
|
extern void blk_mq_sysfs_unregister(struct request_queue *q);
|
2015-12-18 08:08:14 +08:00
|
|
|
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
|
2014-05-30 22:25:36 +08:00
|
|
|
|
2015-01-29 20:17:27 +08:00
|
|
|
void blk_mq_release(struct request_queue *q);
|
|
|
|
|
|
blk-mq: replace timeout synchronization with a RCU and generation based scheme
Currently, blk-mq timeout path synchronizes against the usual
issue/completion path using a complex scheme involving atomic
bitflags, REQ_ATOM_*, memory barriers and subtle memory coherence
rules. Unfortunately, it contains quite a few holes.
There's a complex dancing around REQ_ATOM_STARTED and
REQ_ATOM_COMPLETE between issue/completion and timeout paths; however,
they don't have a synchronization point across request recycle
instances and it isn't clear what the barriers add.
blk_mq_check_expired() can easily read STARTED from N-2'th iteration,
deadline from N-1'th, blk_mark_rq_complete() against Nth instance.
In fact, it's pretty easy to make blk_mq_check_expired() terminate a
later instance of a request. If we induce 5 sec delay before
time_after_eq() test in blk_mq_check_expired(), shorten the timeout to
2s, and issue back-to-back large IOs, blk-mq starts timing out
requests spuriously pretty quickly. Nothing actually timed out. It
just made the call on a recycle instance of a request and then
terminated a later instance long after the original instance finished.
The scenario isn't theoretical either.
This patch replaces the broken synchronization mechanism with a RCU
and generation number based one.
1. Each request has a u64 generation + state value, which can be
updated only by the request owner. Whenever a request becomes
in-flight, the generation number gets bumped up too. This provides
the basis for the timeout path to distinguish different recycle
instances of the request.
Also, marking a request in-flight and setting its deadline are
protected with a seqcount so that the timeout path can fetch both
values coherently.
2. The timeout path fetches the generation, state and deadline. If
the verdict is timeout, it records the generation into a dedicated
request abortion field and does RCU wait.
3. The completion path is also protected by RCU (from the previous
patch) and checks whether the current generation number and state
match the abortion field. If so, it skips completion.
4. The timeout path, after RCU wait, scans requests again and
terminates the ones whose generation and state still match the ones
requested for abortion.
By now, the timeout path knows that either the generation number
and state changed if it lost the race or the completion will yield
to it and can safely timeout the request.
While it's more lines of code, it's conceptually simpler, doesn't
depend on direct use of subtle memory ordering or coherence, and
hopefully doesn't terminate the wrong instance.
While this change makes REQ_ATOM_COMPLETE synchronization unnecessary
between issue/complete and timeout paths, REQ_ATOM_COMPLETE isn't
removed yet as it's still used in other places. Future patches will
move all state tracking to the new mechanism and remove all bitops in
the hot paths.
Note that this patch adds a comment explaining a race condition in
BLK_EH_RESET_TIMER path. The race has always been there and this
patch doesn't change it. It's just documenting the existing race.
v2: - Fixed BLK_EH_RESET_TIMER handling as pointed out by Jianchao.
- s/request->gstate_seqc/request->gstate_seq/ as suggested by Peter.
- READ_ONCE() added in blk_mq_rq_update_state() as suggested by Peter.
v3: - Fixed possible extended seqcount / u64_stats_sync read looping
spotted by Peter.
- MQ_RQ_IDLE was incorrectly being set in complete_request instead
of free_request. Fixed.
v4: - Rebased on top of hctx_lock() refactoring patch.
- Added comment explaining the use of hctx_lock() in completion path.
v5: - Added comments requested by Bart.
- Note the addition of BLK_EH_RESET_TIMER race condition in the
commit message.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: "jianchao.wang" <jianchao.w.wang@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <Bart.VanAssche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-01-10 00:29:48 +08:00
|
|
|
/**
|
|
|
|
|
* blk_mq_rq_state() - read the current MQ_RQ_* state of a request
|
|
|
|
|
* @rq: target request.
|
|
|
|
|
*/
|
|
|
|
|
static inline int blk_mq_rq_state(struct request *rq)
|
|
|
|
|
{
|
|
|
|
|
return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
|
|
|
|
|
* @rq: target request.
|
|
|
|
|
* @state: new state to set.
|
|
|
|
|
*
|
|
|
|
|
* Set @rq's state to @state. The caller is responsible for ensuring that
|
|
|
|
|
* there are no other updaters. A request can transition into IN_FLIGHT
|
|
|
|
|
* only from IDLE and doing so increments the generation number.
|
|
|
|
|
*/
|
|
|
|
|
static inline void blk_mq_rq_update_state(struct request *rq,
|
|
|
|
|
enum mq_rq_state state)
|
|
|
|
|
{
|
|
|
|
|
u64 old_val = READ_ONCE(rq->gstate);
|
|
|
|
|
u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
|
|
|
|
|
|
|
|
|
|
if (state == MQ_RQ_IN_FLIGHT) {
|
|
|
|
|
WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
|
|
|
|
|
new_val += MQ_RQ_GEN_INC;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* avoid exposing interim values */
|
|
|
|
|
WRITE_ONCE(rq->gstate, new_val);
|
|
|
|
|
}
|
|
|
|
|
|
2014-06-01 00:43:36 +08:00
|
|
|
static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
|
|
|
|
|
unsigned int cpu)
|
|
|
|
|
{
|
|
|
|
|
return per_cpu_ptr(q->queue_ctx, cpu);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This assumes per-cpu software queueing queues. They could be per-node
|
|
|
|
|
* as well, for instance. For now this is hardcoded as-is. Note that we don't
|
|
|
|
|
* care about preemption, since we know the ctx's are persistent. This does
|
|
|
|
|
* mean that we can't rely on ctx always matching the currently running CPU.
|
|
|
|
|
*/
|
|
|
|
|
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
|
|
|
|
|
{
|
|
|
|
|
return __blk_mq_get_ctx(q, get_cpu());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
|
|
|
|
|
{
|
|
|
|
|
put_cpu();
|
|
|
|
|
}
|
|
|
|
|
|
2014-06-01 00:43:37 +08:00
|
|
|
struct blk_mq_alloc_data {
|
|
|
|
|
/* input parameter */
|
|
|
|
|
struct request_queue *q;
|
2017-11-10 02:49:59 +08:00
|
|
|
blk_mq_req_flags_t flags;
|
2017-04-14 15:59:59 +08:00
|
|
|
unsigned int shallow_depth;
|
2014-06-01 00:43:37 +08:00
|
|
|
|
|
|
|
|
/* input & output parameter */
|
|
|
|
|
struct blk_mq_ctx *ctx;
|
|
|
|
|
struct blk_mq_hw_ctx *hctx;
|
|
|
|
|
};
|
|
|
|
|
|
2017-01-13 23:09:05 +08:00
|
|
|
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
|
|
|
|
|
{
|
2017-01-17 21:03:22 +08:00
|
|
|
if (data->flags & BLK_MQ_REQ_INTERNAL)
|
|
|
|
|
return data->hctx->sched_tags;
|
|
|
|
|
|
2017-01-13 23:09:05 +08:00
|
|
|
return data->hctx->tags;
|
|
|
|
|
}
|
|
|
|
|
|
2016-10-29 08:19:15 +08:00
|
|
|
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
|
|
|
|
|
{
|
|
|
|
|
return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
|
|
|
|
|
}
|
|
|
|
|
|
2014-12-03 19:38:04 +08:00
|
|
|
static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
|
|
|
|
|
{
|
|
|
|
|
return hctx->nr_ctx && hctx->tags;
|
|
|
|
|
}
|
|
|
|
|
|
2017-08-09 07:51:45 +08:00
|
|
|
void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
|
|
|
|
|
unsigned int inflight[2]);
|
|
|
|
|
|
2017-10-14 17:22:29 +08:00
|
|
|
static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
|
|
|
|
|
{
|
|
|
|
|
struct request_queue *q = hctx->queue;
|
|
|
|
|
|
|
|
|
|
if (q->mq_ops->put_budget)
|
|
|
|
|
q->mq_ops->put_budget(hctx);
|
|
|
|
|
}
|
|
|
|
|
|
2017-11-05 02:21:12 +08:00
|
|
|
static inline bool blk_mq_get_dispatch_budget(struct blk_mq_hw_ctx *hctx)
|
2017-10-14 17:22:29 +08:00
|
|
|
{
|
|
|
|
|
struct request_queue *q = hctx->queue;
|
|
|
|
|
|
|
|
|
|
if (q->mq_ops->get_budget)
|
|
|
|
|
return q->mq_ops->get_budget(hctx);
|
2017-11-05 02:21:12 +08:00
|
|
|
return true;
|
2017-10-14 17:22:29 +08:00
|
|
|
}
|
|
|
|
|
|
2017-11-05 02:39:57 +08:00
|
|
|
static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
|
|
|
|
|
struct request *rq)
|
|
|
|
|
{
|
|
|
|
|
blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
|
|
|
|
|
rq->tag = -1;
|
|
|
|
|
|
|
|
|
|
if (rq->rq_flags & RQF_MQ_INFLIGHT) {
|
|
|
|
|
rq->rq_flags &= ~RQF_MQ_INFLIGHT;
|
|
|
|
|
atomic_dec(&hctx->nr_active);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
|
|
|
|
|
struct request *rq)
|
|
|
|
|
{
|
|
|
|
|
if (rq->tag == -1 || rq->internal_tag == -1)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
__blk_mq_put_driver_tag(hctx, rq);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void blk_mq_put_driver_tag(struct request *rq)
|
|
|
|
|
{
|
|
|
|
|
struct blk_mq_hw_ctx *hctx;
|
|
|
|
|
|
|
|
|
|
if (rq->tag == -1 || rq->internal_tag == -1)
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu);
|
|
|
|
|
__blk_mq_put_driver_tag(hctx, rq);
|
|
|
|
|
}
|
|
|
|
|
|
blk-mq: new multi-queue block IO queueing mechanism
Linux currently has two models for block devices:
- The classic request_fn based approach, where drivers use struct
request units for IO. The block layer provides various helper
functionalities to let drivers share code, things like tag
management, timeout handling, queueing, etc.
- The "stacked" approach, where a driver squeezes in between the
block layer and IO submitter. Since this bypasses the IO stack,
driver generally have to manage everything themselves.
With drivers being written for new high IOPS devices, the classic
request_fn based driver doesn't work well enough. The design dates
back to when both SMP and high IOPS was rare. It has problems with
scaling to bigger machines, and runs into scaling issues even on
smaller machines when you have IOPS in the hundreds of thousands
per device.
The stacked approach is then most often selected as the model
for the driver. But this means that everybody has to re-invent
everything, and along with that we get all the problems again
that the shared approach solved.
This commit introduces blk-mq, block multi queue support. The
design is centered around per-cpu queues for queueing IO, which
then funnel down into x number of hardware submission queues.
We might have a 1:1 mapping between the two, or it might be
an N:M mapping. That all depends on what the hardware supports.
blk-mq provides various helper functions, which include:
- Scalable support for request tagging. Most devices need to
be able to uniquely identify a request both in the driver and
to the hardware. The tagging uses per-cpu caches for freed
tags, to enable cache hot reuse.
- Timeout handling without tracking request on a per-device
basis. Basically the driver should be able to get a notification,
if a request happens to fail.
- Optional support for non 1:1 mappings between issue and
submission queues. blk-mq can redirect IO completions to the
desired location.
- Support for per-request payloads. Drivers almost always need
to associate a request structure with some driver private
command structure. Drivers can tell blk-mq this at init time,
and then any request handed to the driver will have the
required size of memory associated with it.
- Support for merging of IO, and plugging. The stacked model
gets neither of these. Even for high IOPS devices, merging
sequential IO reduces per-command overhead and thus
increases bandwidth.
For now, this is provided as a potential 3rd queueing model, with
the hope being that, as it matures, it can replace both the classic
and stacked model. That would get us back to having just 1 real
model for block devices, leaving the stacked approach to dm/md
devices (as it was originally intended).
Contributions in this patch from the following people:
Shaohua Li <shli@fusionio.com>
Alexander Gordeev <agordeev@redhat.com>
Christoph Hellwig <hch@infradead.org>
Mike Christie <michaelc@cs.wisc.edu>
Matias Bjorling <m@bjorling.me>
Jeff Moyer <jmoyer@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2013-10-24 16:20:05 +08:00
|
|
|
#endif
|