| blob | e295835fc1164ecc543e4faea2cd7e501f7233d0 |
1 =========
2 Workqueue
3 =========
5 :Date: September, 2010
6 :Author: Tejun Heo <tj@kernel.org>
7 :Author: Florian Mickler <florian@mickler.org>
10 Introduction
11 ============
13 There are many cases where an asynchronous process execution context
14 is needed and the workqueue (wq) API is the most commonly used
15 mechanism for such cases.
17 When such an asynchronous execution context is needed, a work item
18 describing which function to execute is put on a queue. An
19 independent thread serves as the asynchronous execution context. The
20 queue is called workqueue and the thread is called worker.
22 While there are work items on the workqueue the worker executes the
23 functions associated with the work items one after the other. When
24 there is no work item left on the workqueue the worker becomes idle.
25 When a new work item gets queued, the worker begins executing again.
28 Why Concurrency Managed Workqueue?
29 ==================================
31 In the original wq implementation, a multi threaded (MT) wq had one
32 worker thread per CPU and a single threaded (ST) wq had one worker
33 thread system-wide. A single MT wq needed to keep around the same
34 number of workers as the number of CPUs. The kernel grew a lot of MT
35 wq users over the years and with the number of CPU cores continuously
36 rising, some systems saturated the default 32k PID space just booting
37 up.
39 Although MT wq wasted a lot of resource, the level of concurrency
40 provided was unsatisfactory. The limitation was common to both ST and
41 MT wq albeit less severe on MT. Each wq maintained its own separate
42 worker pool. An MT wq could provide only one execution context per CPU
43 while an ST wq one for the whole system. Work items had to compete for
44 those very limited execution contexts leading to various problems
45 including proneness to deadlocks around the single execution context.
47 The tension between the provided level of concurrency and resource
48 usage also forced its users to make unnecessary tradeoffs like libata
49 choosing to use ST wq for polling PIOs and accepting an unnecessary
50 limitation that no two polling PIOs can progress at the same time. As
51 MT wq don't provide much better concurrency, users which require
52 higher level of concurrency, like async or fscache, had to implement
53 their own thread pool.
55 Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with
56 focus on the following goals.
58 * Maintain compatibility with the original workqueue API.
60 * Use per-CPU unified worker pools shared by all wq to provide
61 flexible level of concurrency on demand without wasting a lot of
62 resource.
64 * Automatically regulate worker pool and level of concurrency so that
65 the API users don't need to worry about such details.
68 The Design
69 ==========
71 In order to ease the asynchronous execution of functions a new
72 abstraction, the work item, is introduced.
74 A work item is a simple struct that holds a pointer to the function
75 that is to be executed asynchronously. Whenever a driver or subsystem
76 wants a function to be executed asynchronously it has to set up a work
77 item pointing to that function and queue that work item on a
78 workqueue.
80 A work item can be executed in either a thread or the BH (softirq) context.
82 For threaded workqueues, special purpose threads, called [k]workers, execute
83 the functions off of the queue, one after the other. If no work is queued,
84 the worker threads become idle. These worker threads are managed in
85 worker-pools.
87 The cmwq design differentiates between the user-facing workqueues that
88 subsystems and drivers queue work items on and the backend mechanism
89 which manages worker-pools and processes the queued work items.
91 There are two worker-pools, one for normal work items and the other
92 for high priority ones, for each possible CPU and some extra
93 worker-pools to serve work items queued on unbound workqueues - the
94 number of these backing pools is dynamic.
96 BH workqueues use the same framework. However, as there can only be one
97 concurrent execution context, there's no need to worry about concurrency.
98 Each per-CPU BH worker pool contains only one pseudo worker which represents
99 the BH execution context. A BH workqueue can be considered a convenience
100 interface to softirq.
102 Subsystems and drivers can create and queue work items through special
103 workqueue API functions as they see fit. They can influence some
104 aspects of the way the work items are executed by setting flags on the
105 workqueue they are putting the work item on. These flags include
106 things like CPU locality, concurrency limits, priority and more. To
107 get a detailed overview refer to the API description of
108 ``alloc_workqueue()`` below.
110 When a work item is queued to a workqueue, the target worker-pool is
111 determined according to the queue parameters and workqueue attributes
112 and appended on the shared worklist of the worker-pool. For example,
113 unless specifically overridden, a work item of a bound workqueue will
114 be queued on the worklist of either normal or highpri worker-pool that
115 is associated to the CPU the issuer is running on.
117 For any thread pool implementation, managing the concurrency level
118 (how many execution contexts are active) is an important issue. cmwq
119 tries to keep the concurrency at a minimal but sufficient level.
120 Minimal to save resources and sufficient in that the system is used at
121 its full capacity.
123 Each worker-pool bound to an actual CPU implements concurrency
124 management by hooking into the scheduler. The worker-pool is notified
125 whenever an active worker wakes up or sleeps and keeps track of the
126 number of the currently runnable workers. Generally, work items are
127 not expected to hog a CPU and consume many cycles. That means
128 maintaining just enough concurrency to prevent work processing from
129 stalling should be optimal. As long as there are one or more runnable
130 workers on the CPU, the worker-pool doesn't start execution of a new
131 work, but, when the last running worker goes to sleep, it immediately
132 schedules a new worker so that the CPU doesn't sit idle while there
133 are pending work items. This allows using a minimal number of workers
134 without losing execution bandwidth.
136 Keeping idle workers around doesn't cost other than the memory space
137 for kthreads, so cmwq holds onto idle ones for a while before killing
138 them.
140 For unbound workqueues, the number of backing pools is dynamic.
141 Unbound workqueue can be assigned custom attributes using
142 ``apply_workqueue_attrs()`` and workqueue will automatically create
143 backing worker pools matching the attributes. The responsibility of
144 regulating concurrency level is on the users. There is also a flag to
145 mark a bound wq to ignore the concurrency management. Please refer to
146 the API section for details.
148 Forward progress guarantee relies on that workers can be created when
149 more execution contexts are necessary, which in turn is guaranteed
150 through the use of rescue workers. All work items which might be used
151 on code paths that handle memory reclaim are required to be queued on
152 wq's that have a rescue-worker reserved for execution under memory
153 pressure. Else it is possible that the worker-pool deadlocks waiting
154 for execution contexts to free up.
157 Application Programming Interface (API)
158 =======================================
160 ``alloc_workqueue()`` allocates a wq. The original
161 ``create_*workqueue()`` functions are deprecated and scheduled for
162 removal. ``alloc_workqueue()`` takes three arguments - ``@name``,
163 ``@flags`` and ``@max_active``. ``@name`` is the name of the wq and
164 also used as the name of the rescuer thread if there is one.
166 A wq no longer manages execution resources but serves as a domain for
167 forward progress guarantee, flush and work item attributes. ``@flags``
168 and ``@max_active`` control how work items are assigned execution
169 resources, scheduled and executed.
172 ``flags``
173 ---------
175 ``WQ_BH``
176 BH workqueues can be considered a convenience interface to softirq. BH
177 workqueues are always per-CPU and all BH work items are executed in the
178 queueing CPU's softirq context in the queueing order.
180 All BH workqueues must have 0 ``max_active`` and ``WQ_HIGHPRI`` is the
181 only allowed additional flag.
183 BH work items cannot sleep. All other features such as delayed queueing,
184 flushing and canceling are supported.
186 ``WQ_UNBOUND``
187 Work items queued to an unbound wq are served by the special
188 worker-pools which host workers which are not bound to any
189 specific CPU. This makes the wq behave as a simple execution
190 context provider without concurrency management. The unbound
191 worker-pools try to start execution of work items as soon as
192 possible. Unbound wq sacrifices locality but is useful for
193 the following cases.
195 * Wide fluctuation in the concurrency level requirement is
196 expected and using bound wq may end up creating large number
197 of mostly unused workers across different CPUs as the issuer
198 hops through different CPUs.
200 * Long running CPU intensive workloads which can be better
201 managed by the system scheduler.
203 ``WQ_FREEZABLE``
204 A freezable wq participates in the freeze phase of the system
205 suspend operations. Work items on the wq are drained and no
206 new work item starts execution until thawed.
208 ``WQ_MEM_RECLAIM``
209 All wq which might be used in the memory reclaim paths **MUST**
210 have this flag set. The wq is guaranteed to have at least one
211 execution context regardless of memory pressure.
213 ``WQ_HIGHPRI``
214 Work items of a highpri wq are queued to the highpri
215 worker-pool of the target cpu. Highpri worker-pools are
216 served by worker threads with elevated nice level.
218 Note that normal and highpri worker-pools don't interact with
219 each other. Each maintains its separate pool of workers and
220 implements concurrency management among its workers.
222 ``WQ_CPU_INTENSIVE``
223 Work items of a CPU intensive wq do not contribute to the
224 concurrency level. In other words, runnable CPU intensive
225 work items will not prevent other work items in the same
226 worker-pool from starting execution. This is useful for bound
227 work items which are expected to hog CPU cycles so that their
228 execution is regulated by the system scheduler.
230 Although CPU intensive work items don't contribute to the
231 concurrency level, start of their executions is still
232 regulated by the concurrency management and runnable
233 non-CPU-intensive work items can delay execution of CPU
234 intensive work items.
236 This flag is meaningless for unbound wq.
239 ``max_active``
240 --------------
242 ``@max_active`` determines the maximum number of execution contexts per
243 CPU which can be assigned to the work items of a wq. For example, with
244 ``@max_active`` of 16, at most 16 work items of the wq can be executing
245 at the same time per CPU. This is always a per-CPU attribute, even for
246 unbound workqueues.
248 The maximum limit for ``@max_active`` is 2048 and the default value used
249 when 0 is specified is 1024. These values are chosen sufficiently high
250 such that they are not the limiting factor while providing protection in
251 runaway cases.
253 The number of active work items of a wq is usually regulated by the
254 users of the wq, more specifically, by how many work items the users
255 may queue at the same time. Unless there is a specific need for
256 throttling the number of active work items, specifying '0' is
257 recommended.
259 Some users depend on strict execution ordering where only one work item
260 is in flight at any given time and the work items are processed in
261 queueing order. While the combination of ``@max_active`` of 1 and
262 ``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
263 case. Use alloc_ordered_workqueue() instead.
266 Example Execution Scenarios
267 ===========================
269 The following example execution scenarios try to illustrate how cmwq
270 behave under different configurations.
272 Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU.
273 w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms
274 again before finishing. w1 and w2 burn CPU for 5ms then sleep for
275 10ms.
277 Ignoring all other tasks, works and processing overhead, and assuming
278 simple FIFO scheduling, the following is one highly simplified version
279 of possible sequences of events with the original wq. ::
281 TIME IN MSECS EVENT
282 0 w0 starts and burns CPU
283 5 w0 sleeps
284 15 w0 wakes up and burns CPU
285 20 w0 finishes
286 20 w1 starts and burns CPU
287 25 w1 sleeps
288 35 w1 wakes up and finishes
289 35 w2 starts and burns CPU
290 40 w2 sleeps
291 50 w2 wakes up and finishes
293 And with cmwq with ``@max_active`` >= 3, ::
295 TIME IN MSECS EVENT
296 0 w0 starts and burns CPU
297 5 w0 sleeps
298 5 w1 starts and burns CPU
299 10 w1 sleeps
300 10 w2 starts and burns CPU
301 15 w2 sleeps
302 15 w0 wakes up and burns CPU
303 20 w0 finishes
304 20 w1 wakes up and finishes
305 25 w2 wakes up and finishes
307 If ``@max_active`` == 2, ::
309 TIME IN MSECS EVENT
310 0 w0 starts and burns CPU
311 5 w0 sleeps
312 5 w1 starts and burns CPU
313 10 w1 sleeps
314 15 w0 wakes up and burns CPU
315 20 w0 finishes
316 20 w1 wakes up and finishes
317 20 w2 starts and burns CPU
318 25 w2 sleeps
319 35 w2 wakes up and finishes
321 Now, let's assume w1 and w2 are queued to a different wq q1 which has
322 ``WQ_CPU_INTENSIVE`` set, ::
324 TIME IN MSECS EVENT
325 0 w0 starts and burns CPU
326 5 w0 sleeps
327 5 w1 and w2 start and burn CPU
328 10 w1 sleeps
329 15 w2 sleeps
330 15 w0 wakes up and burns CPU
331 20 w0 finishes
332 20 w1 wakes up and finishes
333 25 w2 wakes up and finishes
336 Guidelines
337 ==========
339 * Do not forget to use ``WQ_MEM_RECLAIM`` if a wq may process work
340 items which are used during memory reclaim. Each wq with
341 ``WQ_MEM_RECLAIM`` set has an execution context reserved for it. If
342 there is dependency among multiple work items used during memory
343 reclaim, they should be queued to separate wq each with
344 ``WQ_MEM_RECLAIM``.
346 * Unless strict ordering is required, there is no need to use ST wq.
348 * Unless there is a specific need, using 0 for @max_active is
349 recommended. In most use cases, concurrency level usually stays
350 well under the default limit.
352 * A wq serves as a domain for forward progress guarantee
353 (``WQ_MEM_RECLAIM``, flush and work item attributes. Work items
354 which are not involved in memory reclaim and don't need to be
355 flushed as a part of a group of work items, and don't require any
356 special attribute, can use one of the system wq. There is no
357 difference in execution characteristics between using a dedicated wq
358 and a system wq.
360 Note: If something may generate more than @max_active outstanding
361 work items (do stress test your producers), it may saturate a system
362 wq and potentially lead to deadlock. It should utilize its own
363 dedicated workqueue rather than the system wq.
365 * Unless work items are expected to consume a huge amount of CPU
366 cycles, using a bound wq is usually beneficial due to the increased
367 level of locality in wq operations and work item execution.
370 Affinity Scopes
371 ===============
373 An unbound workqueue groups CPUs according to its affinity scope to improve
374 cache locality. For example, if a workqueue is using the default affinity
375 scope of "cache", it will group CPUs according to last level cache
376 boundaries. A work item queued on the workqueue will be assigned to a worker
377 on one of the CPUs which share the last level cache with the issuing CPU.
378 Once started, the worker may or may not be allowed to move outside the scope
379 depending on the ``affinity_strict`` setting of the scope.
381 Workqueue currently supports the following affinity scopes.
383 ``default``
384 Use the scope in module parameter ``workqueue.default_affinity_scope``
385 which is always set to one of the scopes below.
387 ``cpu``
388 CPUs are not grouped. A work item issued on one CPU is processed by a
389 worker on the same CPU. This makes unbound workqueues behave as per-cpu
390 workqueues without concurrency management.
392 ``smt``
393 CPUs are grouped according to SMT boundaries. This usually means that the
394 logical threads of each physical CPU core are grouped together.
396 ``cache``
397 CPUs are grouped according to cache boundaries. Which specific cache
398 boundary is used is determined by the arch code. L3 is used in a lot of
399 cases. This is the default affinity scope.
401 ``numa``
402 CPUs are grouped according to NUMA boundaries.
404 ``system``
405 All CPUs are put in the same group. Workqueue makes no effort to process a
406 work item on a CPU close to the issuing CPU.
408 The default affinity scope can be changed with the module parameter
409 ``workqueue.default_affinity_scope`` and a specific workqueue's affinity
410 scope can be changed using ``apply_workqueue_attrs()``.
412 If ``WQ_SYSFS`` is set, the workqueue will have the following affinity scope
413 related interface files under its ``/sys/devices/virtual/workqueue/WQ_NAME/``
414 directory.
416 ``affinity_scope``
417 Read to see the current affinity scope. Write to change.
419 When default is the current scope, reading this file will also show the
420 current effective scope in parentheses, for example, ``default (cache)``.
422 ``affinity_strict``
423 0 by default indicating that affinity scopes are not strict. When a work
424 item starts execution, workqueue makes a best-effort attempt to ensure
425 that the worker is inside its affinity scope, which is called
426 repatriation. Once started, the scheduler is free to move the worker
427 anywhere in the system as it sees fit. This enables benefiting from scope
428 locality while still being able to utilize other CPUs if necessary and
429 available.
431 If set to 1, all workers of the scope are guaranteed always to be in the
432 scope. This may be useful when crossing affinity scopes has other
433 implications, for example, in terms of power consumption or workload
434 isolation. Strict NUMA scope can also be used to match the workqueue
435 behavior of older kernels.
438 Affinity Scopes and Performance
439 ===============================
441 It'd be ideal if an unbound workqueue's behavior is optimal for vast
442 majority of use cases without further tuning. Unfortunately, in the current
443 kernel, there exists a pronounced trade-off between locality and utilization
444 necessitating explicit configurations when workqueues are heavily used.
446 Higher locality leads to higher efficiency where more work is performed for
447 the same number of consumed CPU cycles. However, higher locality may also
448 cause lower overall system utilization if the work items are not spread
449 enough across the affinity scopes by the issuers. The following performance
450 testing with dm-crypt clearly illustrates this trade-off.
452 The tests are run on a CPU with 12-cores/24-threads split across four L3
453 caches (AMD Ryzen 9 3900x). CPU clock boost is turned off for consistency.
454 ``/dev/dm-0`` is a dm-crypt device created on NVME SSD (Samsung 990 PRO) and
455 opened with ``cryptsetup`` with default settings.
458 Scenario 1: Enough issuers and work spread across the machine
459 -------------------------------------------------------------
461 The command used: ::
463 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k --ioengine=libaio \
464 --iodepth=64 --runtime=60 --numjobs=24 --time_based --group_reporting \
465 --name=iops-test-job --verify=sha512
467 There are 24 issuers, each issuing 64 IOs concurrently. ``--verify=sha512``
468 makes ``fio`` generate and read back the content each time which makes
469 execution locality matter between the issuer and ``kcryptd``. The following
470 are the read bandwidths and CPU utilizations depending on different affinity
471 scope settings on ``kcryptd`` measured over five runs. Bandwidths are in
472 MiBps, and CPU util in percents.
474 .. list-table::
475 :widths: 16 20 20
476 :header-rows: 1
478 * - Affinity
479 - Bandwidth (MiBps)
480 - CPU util (%)
482 * - system
483 - 1159.40 ±1.34
484 - 99.31 ±0.02
486 * - cache
487 - 1166.40 ±0.89
488 - 99.34 ±0.01
490 * - cache (strict)
491 - 1166.00 ±0.71
492 - 99.35 ±0.01
494 With enough issuers spread across the system, there is no downside to
495 "cache", strict or otherwise. All three configurations saturate the whole
496 machine but the cache-affine ones outperform by 0.6% thanks to improved
497 locality.
500 Scenario 2: Fewer issuers, enough work for saturation
501 -----------------------------------------------------
503 The command used: ::
505 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
506 --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=8 \
507 --time_based --group_reporting --name=iops-test-job --verify=sha512
509 The only difference from the previous scenario is ``--numjobs=8``. There are
510 a third of the issuers but is still enough total work to saturate the
511 system.
513 .. list-table::
514 :widths: 16 20 20
515 :header-rows: 1
517 * - Affinity
518 - Bandwidth (MiBps)
519 - CPU util (%)
521 * - system
522 - 1155.40 ±0.89
523 - 97.41 ±0.05
525 * - cache
526 - 1154.40 ±1.14
527 - 96.15 ±0.09
529 * - cache (strict)
530 - 1112.00 ±4.64
531 - 93.26 ±0.35
533 This is more than enough work to saturate the system. Both "system" and
534 "cache" are nearly saturating the machine but not fully. "cache" is using
535 less CPU but the better efficiency puts it at the same bandwidth as
536 "system".
538 Eight issuers moving around over four L3 cache scope still allow "cache
539 (strict)" to mostly saturate the machine but the loss of work conservation
540 is now starting to hurt with 3.7% bandwidth loss.
543 Scenario 3: Even fewer issuers, not enough work to saturate
544 -----------------------------------------------------------
546 The command used: ::
548 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
549 --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=4 \
550 --time_based --group_reporting --name=iops-test-job --verify=sha512
552 Again, the only difference is ``--numjobs=4``. With the number of issuers
553 reduced to four, there now isn't enough work to saturate the whole system
554 and the bandwidth becomes dependent on completion latencies.
556 .. list-table::
557 :widths: 16 20 20
558 :header-rows: 1
560 * - Affinity
561 - Bandwidth (MiBps)
562 - CPU util (%)
564 * - system
565 - 993.60 ±1.82
566 - 75.49 ±0.06
568 * - cache
569 - 973.40 ±1.52
570 - 74.90 ±0.07
572 * - cache (strict)
573 - 828.20 ±4.49
574 - 66.84 ±0.29
576 Now, the tradeoff between locality and utilization is clearer. "cache" shows
577 2% bandwidth loss compared to "system" and "cache (struct)" whopping 20%.
580 Conclusion and Recommendations
581 ------------------------------
583 In the above experiments, the efficiency advantage of the "cache" affinity
584 scope over "system" is, while consistent and noticeable, small. However, the
585 impact is dependent on the distances between the scopes and may be more
586 pronounced in processors with more complex topologies.
588 While the loss of work-conservation in certain scenarios hurts, it is a lot
589 better than "cache (strict)" and maximizing workqueue utilization is
590 unlikely to be the common case anyway. As such, "cache" is the default
591 affinity scope for unbound pools.
593 * As there is no one option which is great for most cases, workqueue usages
594 that may consume a significant amount of CPU are recommended to configure
595 the workqueues using ``apply_workqueue_attrs()`` and/or enable
596 ``WQ_SYSFS``.
598 * An unbound workqueue with strict "cpu" affinity scope behaves the same as
599 ``WQ_CPU_INTENSIVE`` per-cpu workqueue. There is no real advanage to the
600 latter and an unbound workqueue provides a lot more flexibility.
602 * Affinity scopes are introduced in Linux v6.5. To emulate the previous
603 behavior, use strict "numa" affinity scope.
605 * The loss of work-conservation in non-strict affinity scopes is likely
606 originating from the scheduler. There is no theoretical reason why the
607 kernel wouldn't be able to do the right thing and maintain
608 work-conservation in most cases. As such, it is possible that future
609 scheduler improvements may make most of these tunables unnecessary.
612 Examining Configuration
613 =======================
615 Use tools/workqueue/wq_dump.py to examine unbound CPU affinity
616 configuration, worker pools and how workqueues map to the pools: ::
618 $ tools/workqueue/wq_dump.py
619 Affinity Scopes
620 ===============
621 wq_unbound_cpumask=0000000f
623 CPU
624 nr_pods 4
625 pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008
626 pod_node [0]=0 [1]=0 [2]=1 [3]=1
627 cpu_pod [0]=0 [1]=1 [2]=2 [3]=3
629 SMT
630 nr_pods 4
631 pod_cpus [0]=00000001 [1]=00000002 [2]=00000004 [3]=00000008
632 pod_node [0]=0 [1]=0 [2]=1 [3]=1
633 cpu_pod [0]=0 [1]=1 [2]=2 [3]=3
635 CACHE (default)
636 nr_pods 2
637 pod_cpus [0]=00000003 [1]=0000000c
638 pod_node [0]=0 [1]=1
639 cpu_pod [0]=0 [1]=0 [2]=1 [3]=1
641 NUMA
642 nr_pods 2
643 pod_cpus [0]=00000003 [1]=0000000c
644 pod_node [0]=0 [1]=1
645 cpu_pod [0]=0 [1]=0 [2]=1 [3]=1
647 SYSTEM
648 nr_pods 1
649 pod_cpus [0]=0000000f
650 pod_node [0]=-1
651 cpu_pod [0]=0 [1]=0 [2]=0 [3]=0
653 Worker Pools
654 ============
655 pool[00] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 0
656 pool[01] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 0
657 pool[02] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 1
658 pool[03] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 1
659 pool[04] ref= 1 nice= 0 idle/workers= 4/ 4 cpu= 2
660 pool[05] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 2
661 pool[06] ref= 1 nice= 0 idle/workers= 3/ 3 cpu= 3
662 pool[07] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 3
663 pool[08] ref=42 nice= 0 idle/workers= 6/ 6 cpus=0000000f
664 pool[09] ref=28 nice= 0 idle/workers= 3/ 3 cpus=00000003
665 pool[10] ref=28 nice= 0 idle/workers= 17/ 17 cpus=0000000c
666 pool[11] ref= 1 nice=-20 idle/workers= 1/ 1 cpus=0000000f
667 pool[12] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=00000003
668 pool[13] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=0000000c
670 Workqueue CPU -> pool
671 =====================
672 [ workqueue \ CPU 0 1 2 3 dfl]
673 events percpu 0 2 4 6
674 events_highpri percpu 1 3 5 7
675 events_long percpu 0 2 4 6
676 events_unbound unbound 9 9 10 10 8
677 events_freezable percpu 0 2 4 6
678 events_power_efficient percpu 0 2 4 6
679 events_freezable_pwr_ef percpu 0 2 4 6
680 rcu_gp percpu 0 2 4 6
681 rcu_par_gp percpu 0 2 4 6
682 slub_flushwq percpu 0 2 4 6
683 netns ordered 8 8 8 8 8
684 ...
686 See the command's help message for more info.
689 Monitoring
690 ==========
692 Use tools/workqueue/wq_monitor.py to monitor workqueue operations: ::
694 $ tools/workqueue/wq_monitor.py events
695 total infl CPUtime CPUhog CMW/RPR mayday rescued
696 events 18545 0 6.1 0 5 - -
697 events_highpri 8 0 0.0 0 0 - -
698 events_long 3 0 0.0 0 0 - -
699 events_unbound 38306 0 0.1 - 7 - -
700 events_freezable 0 0 0.0 0 0 - -
701 events_power_efficient 29598 0 0.2 0 0 - -
702 events_freezable_pwr_ef 10 0 0.0 0 0 - -
703 sock_diag_events 0 0 0.0 0 0 - -
705 total infl CPUtime CPUhog CMW/RPR mayday rescued
706 events 18548 0 6.1 0 5 - -
707 events_highpri 8 0 0.0 0 0 - -
708 events_long 3 0 0.0 0 0 - -
709 events_unbound 38322 0 0.1 - 7 - -
710 events_freezable 0 0 0.0 0 0 - -
711 events_power_efficient 29603 0 0.2 0 0 - -
712 events_freezable_pwr_ef 10 0 0.0 0 0 - -
713 sock_diag_events 0 0 0.0 0 0 - -
715 ...
717 See the command's help message for more info.
720 Debugging
721 =========
723 Because the work functions are executed by generic worker threads
724 there are a few tricks needed to shed some light on misbehaving
725 workqueue users.
727 Worker threads show up in the process list as: ::
729 root 5671 0.0 0.0 0 0 ? S 12:07 0:00 [kworker/0:1]
730 root 5672 0.0 0.0 0 0 ? S 12:07 0:00 [kworker/1:2]
731 root 5673 0.0 0.0 0 0 ? S 12:12 0:00 [kworker/0:0]
732 root 5674 0.0 0.0 0 0 ? S 12:13 0:00 [kworker/1:0]
734 If kworkers are going crazy (using too much cpu), there are two types
735 of possible problems:
737 1. Something being scheduled in rapid succession
738 2. A single work item that consumes lots of cpu cycles
740 The first one can be tracked using tracing: ::
742 $ echo workqueue:workqueue_queue_work > /sys/kernel/tracing/set_event
743 $ cat /sys/kernel/tracing/trace_pipe > out.txt
744 (wait a few secs)
745 ^C
747 If something is busy looping on work queueing, it would be dominating
748 the output and the offender can be determined with the work item
749 function.
751 For the second type of problems it should be possible to just check
752 the stack trace of the offending worker thread. ::
754 $ cat /proc/THE_OFFENDING_KWORKER/stack
756 The work item's function should be trivially visible in the stack
757 trace.
760 Non-reentrance Conditions
761 =========================
763 Workqueue guarantees that a work item cannot be re-entrant if the following
764 conditions hold after a work item gets queued:
766 1. The work function hasn't been changed.
767 2. No one queues the work item to another workqueue.
768 3. The work item hasn't been reinitiated.
770 In other words, if the above conditions hold, the work item is guaranteed to be
771 executed by at most one worker system-wide at any given time.
773 Note that requeuing the work item (to the same queue) in the self function
774 doesn't break these conditions, so it's safe to do. Otherwise, caution is
775 required when breaking the conditions inside a work function.
778 Kernel Inline Documentations Reference
779 ======================================
781 .. kernel-doc:: include/linux/workqueue.h
783 .. kernel-doc:: kernel/workqueue.c