/linux-6.6.21/tools/workqueue/ |
D | wq_dump.py | 79 workqueues = prog['workqueues'] variable 156 for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
|
D | wq_monitor.py | 61 workqueues = prog['workqueues'] variable 161 for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
|
/linux-6.6.21/Documentation/admin-guide/ |
D | kernel-per-CPU-kthreads.rst | 149 2. Convert all drivers that you must use from tasklets to workqueues. 236 files. The set of WQ_SYSFS workqueues can be displayed using 237 "ls /sys/devices/virtual/workqueue". That said, the workqueues 239 sprinkling WQ_SYSFS across all the workqueues. The reason for 248 use of each CPU's workqueues to run its cache_reap()
|
D | xfs.rst | 507 XFS uses kernel workqueues to parallelize metadata update processes. This 516 The control knobs for a filesystem's workqueues are organized by task at hand 534 The interesting knobs for XFS workqueues are as follows:
|
D | kernel-parameters.txt | 2312 A residual 1Hz tick is offloaded to workqueues, which you 7088 to use in unbound workqueues. 7091 unbound workqueues. 7112 candidates for using WQ_UNBOUND workqueues instead. 7115 Per-cpu workqueues are generally preferred because 7117 locality; unfortunately, per-cpu workqueues tend to 7118 be more power hungry than unbound workqueues. 7120 Enabling this makes the per-cpu workqueues which 7131 workqueues. Can be one of "cpu", "smt", "cache", 7138 workqueues with the "default" affinity scope will be
|
/linux-6.6.21/Documentation/core-api/ |
D | workqueue.rst | 85 The cmwq design differentiates between the user-facing workqueues that 91 worker-pools to serve work items queued on unbound workqueues - the 132 For unbound workqueues, the number of backing pools is dynamic. 227 unbound workqueues. 369 worker on the same CPU. This makes unbound workqueues behave as per-cpu 370 workqueues without concurrency management. 424 necessitating explicit configurations when workqueues are heavily used. 575 the workqueues using ``apply_workqueue_attrs()`` and/or enable 596 configuration, worker pools and how workqueues map to the pools: ::
|
/linux-6.6.21/kernel/power/ |
D | Kconfig | 314 Per-cpu workqueues are generally preferred because they show 316 per-cpu workqueues tend to be more power hungry than unbound 317 workqueues. 320 per-cpu workqueues which were observed to contribute
|
/linux-6.6.21/kernel/ |
D | workqueue.c | 378 static LIST_HEAD(workqueues); /* PR: list of all workqueues */ 4742 list_add_tail_rcu(&wq->list, &workqueues); in alloc_workqueue() 5310 list_for_each_entry_rcu(wq, &workqueues, list) in show_all_workqueues() 5333 list_for_each_entry_rcu(wq, &workqueues, list) { in show_freezable_workqueues() 5563 list_for_each_entry(wq, &workqueues, list) { in workqueue_online_cpu() 5591 list_for_each_entry(wq, &workqueues, list) { in workqueue_offline_cpu() 5694 list_for_each_entry(wq, &workqueues, list) { in freeze_workqueues_begin() 5727 list_for_each_entry(wq, &workqueues, list) { in freeze_workqueues_busy() 5772 list_for_each_entry(wq, &workqueues, list) { in thaw_workqueues() 5793 list_for_each_entry(wq, &workqueues, list) { in workqueue_apply_unbound_cpumask() [all …]
|
/linux-6.6.21/Documentation/arch/x86/ |
D | sva.rst | 153 * Devices have a limited number (~10's to 1000's) of hardware workqueues. 154 The device driver manages allocating hardware workqueues. 184 * How are shared workqueues different?
|
/linux-6.6.21/Documentation/RCU/Design/Expedited-Grace-Periods/ |
D | Expedited-Grace-Periods.rst | 409 workqueues (see Documentation/core-api/workqueue.rst). 462 The use of workqueues has the advantage that the expedited grace-period 464 corresponding disadvantage that workqueues cannot be used until they are 472 the use of workqueues. However, the requesting task is only required to 475 workqueues are used.
|
/linux-6.6.21/Documentation/devicetree/bindings/media/ |
D | mediatek,vcodec-subdev-decoder.yaml | 38 There are two workqueues in parent device: lat workqueue and core workqueue. They are used
|
/linux-6.6.21/Documentation/networking/device_drivers/ethernet/freescale/ |
D | dpaa.rst | 163 range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with
|
/linux-6.6.21/Documentation/ABI/stable/ |
D | sysfs-driver-dma-idxd | 201 for dispatching work from multiple workqueues in the same group.
|
/linux-6.6.21/Documentation/RCU/ |
D | rcubarrier.rst | 79 If latency is of the essence, workqueues could be used to run these
|
D | checklist.rst | 530 If necessary, you can use something like workqueues to execute
|
/linux-6.6.21/tools/memory-model/Documentation/ |
D | simple.txt | 82 the list macros (for example, include/linux/{,rcu}list.h), workqueues,
|
/linux-6.6.21/Documentation/livepatch/ |
D | livepatch.rst | 190 The location is clear when using workqueues or the kthread worker
|
/linux-6.6.21/Documentation/spi/ |
D | spi-summary.rst | 615 execution contexts like IRQ handlers, tasklets, or workqueues (such
|
/linux-6.6.21/Documentation/RCU/Design/Requirements/ |
D | Requirements.rst | 1294 threads or (in the Linux kernel) workqueues. 1798 | on workqueues, but during the dead zone the requesting task itself | 1801 | dead zone ends, expedited grace periods go back to using workqueues, | 1915 | you can always use workqueues to invoke them concurrently. |
|
/linux-6.6.21/init/ |
D | Kconfig | 687 any source of "noise" such as unbound workqueues, timers, kthreads...
|
/linux-6.6.21/lib/ |
D | Kconfig.debug | 1195 Say Y here to enable stall detection on workqueues. If a
|
/linux-6.6.21/Documentation/filesystems/ |
D | xfs-online-fsck-design.rst | 4892 Thanks to Dave Chinner, bounded workqueues in userspace enable ``xfs_scrub`` to
|