* [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs @ 2026-11-19 20:38 Valentin Schneider 2026-11-20 8:34 ` Peter Zijlstra 0 siblings, 1 reply; 4+ messages in thread From: Valentin Schneider @ 2026-11-19 20:38 UTC (permalink / raw) To: linux-kernel Cc: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman, K Prateek Nayak While testing some CPU isolation / NOHZ_FULL stuff I stumbled on something like so: kworker/u289:5-241489 [001] d..3. 2963.728734: ipi_send_cpu: cpu=6 callsite=task_work_add+0x84 callback=0x0 kworker/u289:5-241489 [001] d..3. 2963.728735: kernel_stack: <stack trace > => trace_event_raw_event_ipi_send_cpu (ffffffffa6d7ba45) => kick_process (ffffffffa6d827a2) => task_work_add (ffffffffa6d645c4) => task_tick_fair (ffffffffa6d9cfbe) => sched_tick_remote (ffffffffa6d84c69) => process_one_work (ffffffffa6d5d57b) => worker_thread (ffffffffa6d5e1af) => kthread (ffffffffa6d66e85) => ret_from_fork (ffffffffa6cb3f2b) => ret_from_fork_asm (ffffffffa6c7741a) In this case CPU6 is isolated via isolcpus=, and is executing a single pure userspace task, so should be fully leveraging dynticks. However, because that task is SCHED_OTHER, housekeeping CPUs periodically handle a sched_tick_remote() on its behalf, and end up kicking that task out of userspace to run the task_cache_work(). Let task_tick_cache() recognize when it is invoked via a remote tick, and bail out rather than disturb dyntick CPUs. Signed-off-by: Valentin Schneider <vschneid@redhat.com> --- kernel/sched/fair.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d4cc0caee6265..42394745a124b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1925,6 +1925,13 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p) !grp->pcpu_sched) return; + /* + * We got here from a sched_tick_remote(), meaning @p is making use of + * NOHZ_FULL. Don't disturb it with a task_work() IPI. + */ + if (cpu_of(rq) != smp_processor_id()) + return; + epoch = rq->cpu_epoch; /* avoid moving backwards */ if (time_after_eq(grp->epoch, epoch)) -- 2.56.1 ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs 2026-11-19 20:38 [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs Valentin Schneider @ 2026-11-20 8:34 ` Peter Zijlstra 2026-11-20 11:02 ` Valentin Schneider 0 siblings, 1 reply; 4+ messages in thread From: Peter Zijlstra @ 2026-11-20 8:34 UTC (permalink / raw) To: Valentin Schneider Cc: linux-kernel, Ingo Molnar, Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman, K Prateek Nayak On Thu, Nov 19, 2026 at 09:38:25PM +0100, Valentin Schneider wrote: > While testing some CPU isolation / NOHZ_FULL stuff I stumbled on something > like so: > > kworker/u289:5-241489 [001] d..3. 2963.728734: ipi_send_cpu: cpu=6 callsite=task_work_add+0x84 callback=0x0 > kworker/u289:5-241489 [001] d..3. 2963.728735: kernel_stack: <stack trace > > => trace_event_raw_event_ipi_send_cpu (ffffffffa6d7ba45) > => kick_process (ffffffffa6d827a2) > => task_work_add (ffffffffa6d645c4) > => task_tick_fair (ffffffffa6d9cfbe) > => sched_tick_remote (ffffffffa6d84c69) > => process_one_work (ffffffffa6d5d57b) > => worker_thread (ffffffffa6d5e1af) > => kthread (ffffffffa6d66e85) > => ret_from_fork (ffffffffa6cb3f2b) > => ret_from_fork_asm (ffffffffa6c7741a) > > In this case CPU6 is isolated via isolcpus=, and is executing a single pure > userspace task, so should be fully leveraging dynticks. > > However, because that task is SCHED_OTHER, housekeeping CPUs periodically > handle a sched_tick_remote() on its behalf, and end up kicking that task > out of userspace to run the task_cache_work(). > > Let task_tick_cache() recognize when it is invoked via a remote tick, and > bail out rather than disturb dyntick CPUs. > > Signed-off-by: Valentin Schneider <vschneid@redhat.com> > --- > kernel/sched/fair.c | 7 +++++++ > 1 file changed, 7 insertions(+) > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > index d4cc0caee6265..42394745a124b 100644 > --- a/kernel/sched/fair.c > +++ b/kernel/sched/fair.c > @@ -1925,6 +1925,13 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p) > !grp->pcpu_sched) > return; > > + /* > + * We got here from a sched_tick_remote(), meaning @p is making use of > + * NOHZ_FULL. Don't disturb it with a task_work() IPI. > + */ > + if (cpu_of(rq) != smp_processor_id()) > + return; > + > epoch = rq->cpu_epoch; > /* avoid moving backwards */ > if (time_after_eq(grp->epoch, epoch)) Its early, and I definitely need more wake-up juice, but how is task_tick_numa() different here? Also, I'm not sure sched_tick_remote() is the right condition here. But perhaps something like so? Does this make sense? --- diff --git a/arch/x86/include/asm/stop_machine.h b/arch/x86/include/asm/stop_machine.h deleted file mode 100644 index e69de29bb2d1..000000000000 diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 731d78155e65..ddcfd82a9e8e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4588,6 +4588,9 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) struct callback_head *work = &curr->numa_work; u64 period, now; + if (!static_branch_unlikely(&sched_numa_balancing)) + return; + /* * We don't care about NUMA placement if we don't have memory. */ @@ -15401,15 +15404,20 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int hrtick) if (hrtick) return; - if (static_branch_unlikely(&sched_numa_balancing)) - task_tick_numa(rq, curr); + task_tick_core(rq, curr); + /* + * If there is no root domain; there is no balancing, and none of this + * matters. + */ + if (!rq->rd) + return; + + task_tick_numa(rq, curr); task_tick_cache(rq, curr); update_misfit_status(curr, rq); check_update_overutilized_status(task_rq(curr)); - - task_tick_core(rq, curr); } /* ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs 2026-11-20 8:34 ` Peter Zijlstra @ 2026-11-20 11:02 ` Valentin Schneider 2026-11-20 15:40 ` Peter Zijlstra 0 siblings, 1 reply; 4+ messages in thread From: Valentin Schneider @ 2026-11-20 11:02 UTC (permalink / raw) To: Peter Zijlstra Cc: linux-kernel, Ingo Molnar, Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman, K Prateek Nayak On 20/11/26 09:34, Peter Zijlstra wrote: > On Thu, Nov 19, 2026 at 09:38:25PM +0100, Valentin Schneider wrote: >> @@ -1925,6 +1925,13 @@ static void task_tick_cache(struct rq *rq, struct task_struct *p) >> !grp->pcpu_sched) >> return; >> >> + /* >> + * We got here from a sched_tick_remote(), meaning @p is making use of >> + * NOHZ_FULL. Don't disturb it with a task_work() IPI. >> + */ >> + if (cpu_of(rq) != smp_processor_id()) >> + return; >> + >> epoch = rq->cpu_epoch; >> /* avoid moving backwards */ >> if (time_after_eq(grp->epoch, epoch)) > > > Its early, and I definitely need more wake-up juice, but how is > task_tick_numa() different here? > It shouldn't be too different, I just can't get it to trigger on my QEMU setup; I'm done running stuff on the machine I caught this on so I can start digging there. > @@ -15401,15 +15404,20 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int hrtick) > if (hrtick) > return; > > - if (static_branch_unlikely(&sched_numa_balancing)) > - task_tick_numa(rq, curr); > + task_tick_core(rq, curr); > > + /* > + * If there is no root domain; there is no balancing, and none of this > + * matters. > + */ > + if (!rq->rd) > + return; > + What if the setup involves a separate root domain where all the CPUs are in dynticks mode? Methinks the signal we want is: is that task on a NOHZ_FULL CPU with the tick disabled? If so then we shouldn't do anything about it. Let the other CPUs in its LLC / RD run some balancing. If they're all dynticks, well then there is nothing to do is there? And that should also apply to the NUMA stuff like you pointed out. > + task_tick_numa(rq, curr); > task_tick_cache(rq, curr); > > update_misfit_status(curr, rq); > check_update_overutilized_status(task_rq(curr)); > - > - task_tick_core(rq, curr); > } > > /* ^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs 2026-11-20 11:02 ` Valentin Schneider @ 2026-11-20 15:40 ` Peter Zijlstra 0 siblings, 0 replies; 4+ messages in thread From: Peter Zijlstra @ 2026-11-20 15:40 UTC (permalink / raw) To: Valentin Schneider Cc: linux-kernel, Ingo Molnar, Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman, K Prateek Nayak On Fri, Nov 20, 2026 at 12:02:49PM +0100, Valentin Schneider wrote: > > + /* > > + * If there is no root domain; there is no balancing, and none of this > > + * matters. > > + */ > > + if (!rq->rd) > > + return; > > + > > What if the setup involves a separate root domain where all the CPUs are in > dynticks mode? > > Methinks the signal we want is: > > is that task on a NOHZ_FULL CPU with the tick disabled? > > If so then we shouldn't do anything about it. Let the other CPUs in its LLC > / RD run some balancing. If they're all dynticks, well then there is > nothing to do is there? > > And that should also apply to the NUMA stuff like you pointed out. If you have a root domain with more than 1 CPU in it, you get balancing, deal with it. ^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-11-20 15:40 UTC | newest] Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2026-11-19 20:38 [PATCH] sched/fair: Don't let task_tick_cache() IPI dyntick CPUs Valentin Schneider 2026-11-20 8:34 ` Peter Zijlstra 2026-11-20 11:02 ` Valentin Schneider 2026-11-20 15:40 ` Peter Zijlstra
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®