diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-08-07 23:07:12 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-08-07 23:07:12 +0300 |
commit | 14f9643dc90adea074a0ffb7a17d337eafc6a5cc (patch) | |
tree | d67dd9c778e7faea04c5891753ae457099edf80d | |
parent | 8043e2225aa2ef7c7a04aac129a7ded3b1771aba (diff) | |
parent | aa6fde93f3a49e42c0fe0490d7f3711bac0d162e (diff) | |
download | linux-14f9643dc90adea074a0ffb7a17d337eafc6a5cc.tar.xz |
Merge tag 'wq-for-6.5-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq
Pull workqueue fixes from Tejun Heo:
- The recently added cpu_intensive auto detection and warning mechanism
was spuriously triggered on slow CPUs.
While not causing serious issues, it's still a nuisance and can cause
unintended concurrency management behaviors.
Relax the threshold on machines with lower BogoMIPS. While BogoMIPS
is not an accurate measure of performance by most measures, we don't
have to be accurate and it has rough but strong enough correlation.
- A correction in Kconfig help text
* tag 'wq-for-6.5-rc5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
workqueue: Scale up wq_cpu_intensive_thresh_us if BogoMIPS is below 4000
workqueue: Fix cpu_intensive_thresh_us name in help text
-rw-r--r-- | kernel/workqueue.c | 43 | ||||
-rw-r--r-- | lib/Kconfig.debug | 2 |
2 files changed, 43 insertions, 2 deletions
diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 02a8f402eeb5..800b4208dba9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -52,6 +52,7 @@ #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> +#include <linux/delay.h> #include "workqueue_internal.h" @@ -338,8 +339,10 @@ static cpumask_var_t *wq_numa_possible_cpumask; * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. + * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. + * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ -static unsigned long wq_cpu_intensive_thresh_us = 10000; +static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); static bool wq_disable_numa; @@ -6513,6 +6516,42 @@ void __init workqueue_init_early(void) !system_freezable_power_efficient_wq); } +static void __init wq_cpu_intensive_thresh_init(void) +{ + unsigned long thresh; + unsigned long bogo; + + /* if the user set it to a specific value, keep it */ + if (wq_cpu_intensive_thresh_us != ULONG_MAX) + return; + + /* + * The default of 10ms is derived from the fact that most modern (as of + * 2023) processors can do a lot in 10ms and that it's just below what + * most consider human-perceivable. However, the kernel also runs on a + * lot slower CPUs including microcontrollers where the threshold is way + * too low. + * + * Let's scale up the threshold upto 1 second if BogoMips is below 4000. + * This is by no means accurate but it doesn't have to be. The mechanism + * is still useful even when the threshold is fully scaled up. Also, as + * the reports would usually be applicable to everyone, some machines + * operating on longer thresholds won't significantly diminish their + * usefulness. + */ + thresh = 10 * USEC_PER_MSEC; + + /* see init/calibrate.c for lpj -> BogoMIPS calculation */ + bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); + if (bogo < 4000) + thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); + + pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", + loops_per_jiffy, bogo, thresh); + + wq_cpu_intensive_thresh_us = thresh; +} + /** * workqueue_init - bring workqueue subsystem fully online * @@ -6528,6 +6567,8 @@ void __init workqueue_init(void) struct worker_pool *pool; int cpu, bkt; + wq_cpu_intensive_thresh_init(); + /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fbc89baf7de6..d6798513a8c2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1200,7 +1200,7 @@ config WQ_CPU_INTENSIVE_REPORT help Say Y here to enable reporting of concurrency-managed per-cpu work items that hog CPUs for longer than - workqueue.cpu_intensive_threshold_us. Workqueue automatically + workqueue.cpu_intensive_thresh_us. Workqueue automatically detects and excludes them from concurrency management to prevent them from stalling other per-cpu work items. Occassional triggering may not necessarily indicate a problem. Repeated |