From c006fac556e401a62054d065da168099ea5a5b10 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Fri, 16 Apr 2021 14:29:36 -0700 Subject: sched: Warn on long periods of pending need_resched CPU scheduler marks need_resched flag to signal a schedule() on a particular CPU. But, schedule() may not happen immediately in cases where the current task is executing in the kernel mode (no preemption state) for extended periods of time. This patch adds a warn_on if need_resched is pending for more than the time specified in sysctl resched_latency_warn_ms. If it goes off, it is likely that there is a missing cond_resched() somewhere. Monitoring is done via the tick and the accuracy is hence limited to jiffy scale. This also means that we won't trigger the warning if the tick is disabled. This feature (LATENCY_WARN) is default disabled. Signed-off-by: Paul Turner Signed-off-by: Josh Don Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210416212936.390566-1-joshdon@google.com --- kernel/sched/debug.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 461342f598ef8..7251fc477a118 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -309,6 +309,9 @@ static __init int sched_init_debug(void) debugfs_create_u32("min_granularity_ns", 0644, debugfs_sched, &sysctl_sched_min_granularity); debugfs_create_u32("wakeup_granularity_ns", 0644, debugfs_sched, &sysctl_sched_wakeup_granularity); + debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms); + debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once); + #ifdef CONFIG_SMP debugfs_create_file("tunable_scaling", 0644, debugfs_sched, NULL, &sched_scaling_fops); debugfs_create_u32("migration_cost_ns", 0644, debugfs_sched, &sysctl_sched_migration_cost); @@ -1027,3 +1030,13 @@ void proc_sched_set_task(struct task_struct *p) memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif } + +void resched_latency_warn(int cpu, u64 latency) +{ + static DEFINE_RATELIMIT_STATE(latency_check_ratelimit, 60 * 60 * HZ, 1); + + WARN(__ratelimit(&latency_check_ratelimit), + "sched: CPU %d need_resched set for > %llu ns (%d ticks) " + "without schedule\n", + cpu, latency, cpu_rq(cpu)->ticks_without_resched); +} -- cgit v1.2.3