Lines Matching +full:- +full:affinity
33 thread system-wide. A single MT wq needed to keep around the same
60 * Use per-CPU unified worker pools shared by all wq to provide
85 worker-pools.
87 The cmwq design differentiates between the user-facing workqueues that
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
93 worker-pools to serve work items queued on unbound workqueues - the
98 Each per-CPU BH worker pool contains only one pseudo worker which represents
110 When a work item is queued to a workqueue, the target worker-pool is
112 and appended on the shared worklist of the worker-pool. For example,
114 be queued on the worklist of either normal or highpri worker-pool that
123 Each worker-pool bound to an actual CPU implements concurrency
124 management by hooking into the scheduler. The worker-pool is notified
130 workers on the CPU, the worker-pool doesn't start execution of a new
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
162 removal. ``alloc_workqueue()`` takes three arguments - ``@name``,
173 ---------
177 workqueues are always per-CPU and all BH work items are executed in the
187 Work items queued to a per-cpu wq are bound to a specific CPU.
194 worker-pools which host workers which are not bound to any
197 worker-pools try to start execution of work items as soon as
221 worker-pool of the target cpu. Highpri worker-pools are
224 Note that normal and highpri worker-pools don't interact with
232 worker-pool from starting execution. This is useful for bound
239 non-CPU-intensive work items can delay execution of CPU
246 --------------
251 at the same time per CPU. This is always a per-CPU attribute, even for
376 Affinity Scopes
379 An unbound workqueue groups CPUs according to its affinity scope to improve
380 cache locality. For example, if a workqueue is using the default affinity
381 scope of "cache_shard", it will group CPUs into sub-LLC shards. A work item
387 Workqueue currently supports the following affinity scopes.
395 worker on the same CPU. This makes unbound workqueues behave as per-cpu
408 CPUs are grouped into sub-LLC shards of at most ``wq_cache_shard_size``
411 This is the default affinity scope.
420 The default affinity scope can be changed with the module parameter
421 ``workqueue.default_affinity_scope`` and a specific workqueue's affinity
424 If ``WQ_SYSFS`` is set, the workqueue will have the following affinity scope
429 Read to see the current affinity scope. Write to change.
435 0 by default indicating that affinity scopes are not strict. When a work
436 item starts execution, workqueue makes a best-effort attempt to ensure
437 that the worker is inside its affinity scope, which is called
444 scope. This may be useful when crossing affinity scopes has other
450 Affinity Scopes and Performance
455 kernel, there exists a pronounced trade-off between locality and utilization
461 enough across the affinity scopes by the issuers. The following performance
462 testing with dm-crypt clearly illustrates this trade-off.
464 The tests are run on a CPU with 12-cores/24-threads split across four L3
466 ``/dev/dm-0`` is a dm-crypt device created on NVME SSD (Samsung 990 PRO) and
471 -------------------------------------------------------------
475 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k --ioengine=libaio \
476 --iodepth=64 --runtime=60 --numjobs=24 --time_based --group_reporting \
477 --name=iops-test-job --verify=sha512
479 There are 24 issuers, each issuing 64 IOs concurrently. ``--verify=sha512``
482 are the read bandwidths and CPU utilizations depending on different affinity
486 .. list-table::
488 :header-rows: 1
490 * - Affinity
491 - Bandwidth (MiBps)
492 - CPU util (%)
494 * - system
495 - 1159.40 ±1.34
496 - 99.31 ±0.02
498 * - cache
499 - 1166.40 ±0.89
500 - 99.34 ±0.01
502 * - cache (strict)
503 - 1166.00 ±0.71
504 - 99.35 ±0.01
508 machine but the cache-affine ones outperform by 0.6% thanks to improved
513 -----------------------------------------------------
517 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
518 --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=8 \
519 --time_based --group_reporting --name=iops-test-job --verify=sha512
521 The only difference from the previous scenario is ``--numjobs=8``. There are
525 .. list-table::
527 :header-rows: 1
529 * - Affinity
530 - Bandwidth (MiBps)
531 - CPU util (%)
533 * - system
534 - 1155.40 ±0.89
535 - 97.41 ±0.05
537 * - cache
538 - 1154.40 ±1.14
539 - 96.15 ±0.09
541 * - cache (strict)
542 - 1112.00 ±4.64
543 - 93.26 ±0.35
556 -----------------------------------------------------------
560 $ fio --filename=/dev/dm-0 --direct=1 --rw=randrw --bs=32k \
561 --ioengine=libaio --iodepth=64 --runtime=60 --numjobs=4 \
562 --time_based --group_reporting --name=iops-test-job --verify=sha512
564 Again, the only difference is ``--numjobs=4``. With the number of issuers
568 .. list-table::
570 :header-rows: 1
572 * - Affinity
573 - Bandwidth (MiBps)
574 - CPU util (%)
576 * - system
577 - 993.60 ±1.82
578 - 75.49 ±0.06
580 * - cache
581 - 973.40 ±1.52
582 - 74.90 ±0.07
584 * - cache (strict)
585 - 828.20 ±4.49
586 - 66.84 ±0.29
593 ------------------------------
595 In the above experiments, the efficiency advantage of the "cache" affinity
600 While the loss of work-conservation in certain scenarios hurts, it is a lot
603 affinity scope for unbound pools.
610 * An unbound workqueue with strict "cpu" affinity scope behaves the same as
611 ``WQ_CPU_INTENSIVE`` per-cpu workqueue. There is no real advanage to the
614 * Affinity scopes are introduced in Linux v6.5. To emulate the previous
615 behavior, use strict "numa" affinity scope.
617 * The loss of work-conservation in non-strict affinity scopes is likely
620 work-conservation in most cases. As such, it is possible that future
627 Use tools/workqueue/wq_dump.py to examine unbound CPU affinity
631 Affinity Scopes
662 pod_node [0]=-1
668 pool[01] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 0
670 pool[03] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 1
672 pool[05] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 2
674 pool[07] ref= 1 nice=-20 idle/workers= 2/ 2 cpu= 3
678 pool[11] ref= 1 nice=-20 idle/workers= 1/ 1 cpus=0000000f
679 pool[12] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=00000003
680 pool[13] ref= 2 nice=-20 idle/workers= 1/ 1 cpus=0000000c
682 Workqueue CPU -> pool
708 events 18545 0 6.1 0 5 - -
709 events_highpri 8 0 0.0 0 0 - -
710 events_long 3 0 0.0 0 0 - -
711 events_unbound 38306 0 0.1 - 7 - -
712 events_freezable 0 0 0.0 0 0 - -
713 events_power_efficient 29598 0 0.2 0 0 - -
714 events_freezable_pwr_ef 10 0 0.0 0 0 - -
715 sock_diag_events 0 0 0.0 0 0 - -
718 events 18548 0 6.1 0 5 - -
719 events_highpri 8 0 0.0 0 0 - -
720 events_long 3 0 0.0 0 0 - -
721 events_unbound 38322 0 0.1 - 7 - -
722 events_freezable 0 0 0.0 0 0 - -
723 events_power_efficient 29603 0 0.2 0 0 - -
724 events_freezable_pwr_ef 10 0 0.0 0 0 - -
725 sock_diag_events 0 0 0.0 0 0 - -
772 Non-reentrance Conditions
775 Workqueue guarantees that a work item cannot be re-entrant if the following
783 executed by at most one worker system-wide at any given time.
793 .. kernel-doc:: include/linux/workqueue.h
795 .. kernel-doc:: kernel/workqueue.c