Messages in this thread | | | Subject | Re: [PATCH] timers/nohz: Update nohz load even if tick already stopped | From | Scott Wood <> | Date | Fri, 01 Nov 2019 00:11:09 -0500 |
| |
On Wed, 2019-10-30 at 14:31 +0100, Peter Zijlstra wrote: > On Wed, Oct 30, 2019 at 03:48:26AM -0500, Scott Wood wrote: > > On Tue, 2019-10-29 at 11:05 +0100, Peter Zijlstra wrote: > > > @@ -3686,6 +3688,7 @@ static void sched_tick_remote(struct work_struct > > > *work) > > > curr->sched_class->task_tick(rq, curr, 0); > > > > > > out_unlock: > > > + calc_load_nohz_remote(cpu); > > > rq_unlock_irq(rq, &rf); > > > > This gets skipped when the cpu is idle, so it still misses the update. > > Oh argh! that's a bit radical of the remote tick. The normal tick runs > just fine on idle CPUs, so lets mirror that. > > How's this then? > > --- > diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h > index 1abe91ff6e4a..6d67e9a5af6b 100644 > --- a/include/linux/sched/nohz.h > +++ b/include/linux/sched/nohz.h > @@ -15,9 +15,11 @@ static inline void nohz_balance_enter_idle(int cpu) { } > > #ifdef CONFIG_NO_HZ_COMMON > void calc_load_nohz_start(void); > +void calc_load_nohz_remote(struct rq *rq); > void calc_load_nohz_stop(void); > #else > static inline void calc_load_nohz_start(void) { } > +static inline void calc_load_nohz_remote(struct rq *rq) { } > static inline void calc_load_nohz_stop(void) { } > #endif /* CONFIG_NO_HZ_COMMON */ > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index eb42b71faab9..d02d1b8f40af 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -3660,21 +3660,17 @@ static void sched_tick_remote(struct work_struct > *work) > u64 delta; > int os; > > - /* > - * Handle the tick only if it appears the remote CPU is running in > full > - * dynticks mode. The check is racy by nature, but missing a tick or > - * having one too much is no big deal because the scheduler tick > updates > - * statistics and checks timeslices in a time-independent way, > regardless > - * of when exactly it is running. > - */ > - if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) > + if (!tick_nohz_tick_stopped_cpu(cpu)) > goto out_requeue; > > rq_lock_irq(rq, &rf); > - curr = rq->curr; > - if (is_idle_task(curr) || cpu_is_offline(cpu)) > + /* > + * We must not call calc_load_nohz_remote() when not in NOHZ mode. > + */ > + if (cpu_is_offline(cpu) || !tick_nohz_tick_stopped(cpu)) > goto out_unlock;
Needs to be tick_nohz_tick_stopped_cpu(cpu)
After fixing that, I get:
[ 7.439068] WARNING: CPU: 20 PID: 7 at /home/root/linux/kernel/sched/core.c:3681 sched_tick_remote+0x132/0x150 [ 7.439068] Modules linked in: [ 7.439068] CPU: 20 PID: 7 Comm: kworker/u209:0 Not tainted 5.4.0-rc5.std+ #15 [ 7.439068] Hardware name: Intel Corporation S2600BT/S2600BT, BIOS SE5C620.86B.01.00.0763.022420181017 02/24/2018 [ 7.439068] Workqueue: events_unbound sched_tick_remote [ 7.446308] pci_bus 0000:9f: resource 1 [mem 0xe6a00000-0xe6bfffff] [ 7.455068] RIP: 0010:sched_tick_remote+0x132/0x150 [ 7.455068] Code: 00 e9 b2 fd fe ff 0f 0b e9 46 ff ff ff 83 f8 02 89 c2 74 d3 8d 4a ff 89 d0 f0 0f b1 0e 0f 94 c1 84 c9 0f 85 23 ff ff ff eb e3 <0f> 0b eb 9a 80 3d 9c d6 2c 01 00 0f 1f 00 0f 85 71 ff ff ff e8 05 [ 7.455068] RSP: 0000:ffffc9000c683e58 EFLAGS: 00010002 [ 7.455068] RAX: 00000000e7061da1 RBX: ffff8897e026e688 RCX: 0000000181f93295 [ 7.455068] RDX: 00000000b2d05e00 RSI: ffff8897e0269e50 RDI: 0000000000000004 [ 7.455068] RBP: ffff8881004c0000 R08: ffff8e8191a2b423 R09: 0000000000000000 [ 7.455068] R10: 0000000000000010 R11: 0000000000000018 R12: ffff8897e0269240 [ 7.455068] R13: ffff8897e0240000 R14: 0000000000000000 R15: ffff888107edc2e8 [ 7.455068] FS: 0000000000000000(0000) GS:ffff8897e0700000(0000) knlGS:0000000000000000 [ 7.455068] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7.455068] CR2: 0000000000000000 CR3: 000000303e60a001 CR4: 00000000007606e0 [ 7.455068] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 7.459338] pci_bus 0000:9f: resource 2 [mem 0x3a0000000000-0x3a00001fffff 64bit pref] [ 7.465068] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 7.465068] PKRU: 55555554 [ 7.465068] Call Trace: [ 7.465068] process_one_work+0x165/0x3c0 [ 7.465068] worker_thread+0x46/0x3d0 [ 7.465068] kthread+0xf8/0x130 [ 7.465068] ? process_one_work+0x3c0/0x3c0 [ 7.476788] pci_bus 0000:a0: resource 1 [mem 0xe6c00000-0xe6dfffff] [ 7.465068] ? kthread_bind+0x10/0x10 [ 7.465068] ret_from_fork+0x35/0x40
-Scott
| |