From 82607adcf9cdf40fb7b5331269780c8f70ec6e35 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Dec 2015 11:28:04 -0500 Subject: workqueue: implement lockup detector Workqueue stalls can happen from a variety of usage bugs such as missing WQ_MEM_RECLAIM flag or concurrency managed work item indefinitely staying RUNNING. These stalls can be extremely difficult to hunt down because the usual warning mechanisms can't detect workqueue stalls and the internal state is pretty opaque. To alleviate the situation, this patch implements workqueue lockup detector. It periodically monitors all worker_pools periodically and, if any pool failed to make forward progress longer than the threshold duration, triggers warning and dumps workqueue state as follows. BUG: workqueue lockup - pool cpus=0 node=0 flags=0x0 nice=0 stuck for 31s! Showing busy workqueues and worker pools: workqueue events: flags=0x0 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=17/256 pending: monkey_wrench_fn, e1000_watchdog, cache_reap, vmstat_shepherd, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, release_one_tty, cgroup_release_agent workqueue events_power_efficient: flags=0x80 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=2/256 pending: check_lifetime, neigh_periodic_work workqueue cgroup_pidlist_destroy: flags=0x0 pwq 0: cpus=0 node=0 flags=0x0 nice=0 active=1/1 pending: cgroup_pidlist_destroy_work_fn ... The detection mechanism is controller through kernel parameter workqueue.watchdog_thresh and can be updated at runtime through the sysfs module parameter file. v2: Decoupled from softlockup control knobs. Signed-off-by: Tejun Heo Acked-by: Don Zickus Cc: Ulrich Obergfell Cc: Michal Hocko Cc: Chris Mason Cc: Andrew Morton --- lib/Kconfig.debug | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8c15b29d5adc..3048bf5b729a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -812,6 +812,17 @@ config BOOTPARAM_HUNG_TASK_PANIC_VALUE default 0 if !BOOTPARAM_HUNG_TASK_PANIC default 1 if BOOTPARAM_HUNG_TASK_PANIC +config WQ_WATCHDOG + bool "Detect Workqueue Stalls" + depends on DEBUG_KERNEL + help + Say Y here to enable stall detection on workqueues. If a + worker pool doesn't make forward progress on a pending work + item for over a given amount of time, 30s by default, a + warning message is printed along with dump of workqueue + state. This can be configured through kernel parameter + "workqueue.watchdog_thresh" and its sysfs counterpart. + endmenu # "Debug lockups and hangs" config PANIC_ON_OOPS -- cgit v1.2.3