mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-12-29 17:25:38 +00:00
d6b6d39054
- Maximum concurrency limit of 512 which was set a long time ago is too low now. A legitimate use (BPF cgroup release) of system_wq could saturate it under stress test conditions leading to false dependencies and deadlocks. While the offending use was switched to a dedicated workqueue, use the opportunity to bump WQ_MAX_ACTIVE four fold and document that system workqueue shouldn't be saturated. Workqueue should add at least a warning mechanism for cases where system workqueues are saturated. - Recent workqueue updates to support more flexible execution topology made unbound workqueues use per-cpu worker pool frontends which pushed up workqueue flush overhead. As consecutive CPUs are likely to be pointing to the same worker pool, reduce overhead by switching locks only when necessary. -----BEGIN PGP SIGNATURE----- iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCZztfbQ4cdGpAa2VybmVs Lm9yZwAKCRCxYfJx3gVYGcaOAP9nlm5gKnY4pqQeohxfE9uRoUJY/isbuk0z2ZbB +u2AXQD/ZX16MZm1WOdJ3kcj9bxEbJerW1twus951X6+2tSnRAQ= =mBeG -----END PGP SIGNATURE----- Merge tag 'wq-for-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq Pull workqueue updates from Tejun Heo: - The maximum concurrency limit of 512 which was set a long time ago is too low now. A legitimate use (BPF cgroup release) of system_wq could saturate it under stress test conditions leading to false dependencies and deadlocks. While the offending use was switched to a dedicated workqueue, use the opportunity to bump WQ_MAX_ACTIVE four fold and document that system workqueue shouldn't be saturated. Workqueue should add at least a warning mechanism for cases where system workqueues are saturated. - Recent workqueue updates to support more flexible execution topology made unbound workqueues use per-cpu worker pool frontends which pushed up workqueue flush overhead. As consecutive CPUs are likely to be pointing to the same worker pool, reduce overhead by switching locks only when necessary. * tag 'wq-for-6.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq: workqueue: Reduce expensive locks for unbound workqueue workqueue: Adjust WQ_MAX_ACTIVE from 512 to 2048 workqueue: doc: Add a note saturating the system_wq is not permitted |
||
|---|---|---|
| .. | ||
| irq | ||
| wrappers | ||
| asm-annotations.rst | ||
| assoc_array.rst | ||
| boot-time-mm.rst | ||
| cachetlb.rst | ||
| circular-buffers.rst | ||
| cleanup.rst | ||
| cpu_hotplug.rst | ||
| debug-objects.rst | ||
| debugging-via-ohci1394.rst | ||
| dma-api-howto.rst | ||
| dma-api.rst | ||
| dma-attributes.rst | ||
| dma-isa-lpc.rst | ||
| entry.rst | ||
| errseq.rst | ||
| floating-point.rst | ||
| folio_queue.rst | ||
| genalloc.rst | ||
| generic-radix-tree.rst | ||
| genericirq.rst | ||
| gfp_mask-from-fs-io.rst | ||
| idr.rst | ||
| index.rst | ||
| kernel-api.rst | ||
| kobject.rst | ||
| kref.rst | ||
| librs.rst | ||
| local_ops.rst | ||
| maple_tree.rst | ||
| memory-allocation.rst | ||
| memory-hotplug.rst | ||
| mm-api.rst | ||
| netlink.rst | ||
| packing.rst | ||
| padata.rst | ||
| pin_user_pages.rst | ||
| printk-basics.rst | ||
| printk-formats.rst | ||
| printk-index.rst | ||
| protection-keys.rst | ||
| rbtree.rst | ||
| refcount-vs-atomic.rst | ||
| swiotlb.rst | ||
| symbol-namespaces.rst | ||
| this_cpu_ops.rst | ||
| timekeeping.rst | ||
| tracepoint.rst | ||
| unaligned-memory-access.rst | ||
| union_find.rst | ||
| watch_queue.rst | ||
| workqueue.rst | ||
| xarray.rst | ||