The Linux kernel Workqueue (WQ) is used for handling asynchronous process execution. For the past many years there has been an upper limit on the number of workqueue execution contexts per CPU at 512, but with Linux 6.13 that is being quadrupled to a limit of 2048.
Sent out today was the workqueue pull request for Linux 6.13 and of the two changes this cycle, most notable is increasing the maximum concurrency limit:
“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.”
That 512 limit was set a decade and a half ago. But with the vastly increasing sizes of today’s servers, it’s time to increase that limit.
The other workqueue change for Linux 6.13 is also notable in that it’s reducing expensive locking around unbound workqueues:
“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.”
These WQ changes are now pending for the Linux 6.13 merge window.
