diff options
author | Chengming Zhou <zhouchengming@bytedance.com> | 2022-08-25 18:41:02 +0200 |
---|---|---|
committer | Peter Zijlstra <peterz@infradead.org> | 2022-09-09 11:08:30 +0200 |
commit | c530a3c716b963625e43aa915e0de6b4d1ce8ad9 (patch) | |
tree | 36178fdc2e2b651e20ba30085becd55da0ed31f7 /kernel | |
parent | Merge branch 'driver-core/driver-core-next' (diff) | |
download | linux-c530a3c716b963625e43aa915e0de6b4d1ce8ad9.tar.xz linux-c530a3c716b963625e43aa915e0de6b4d1ce8ad9.zip |
sched/psi: Fix periodic aggregation shut off
We don't want to wake periodic aggregation work back up if the
task change is the aggregation worker itself going to sleep, or
we'll ping-pong forever.
Previously, we would use psi_task_change() in psi_dequeue() when
task going to sleep, so this check was put in psi_task_change().
But commit 4117cebf1a9f ("psi: Optimize task switch inside shared cgroups")
defer task sleep handling to psi_task_switch(), won't go through
psi_task_change() anymore.
So this patch move this check to psi_task_switch().
Fixes: 4117cebf1a9f ("psi: Optimize task switch inside shared cgroups")
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20220825164111.29534-2-zhouchengming@bytedance.com
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/sched/psi.c | 28 |
1 files changed, 14 insertions, 14 deletions
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ecb4b4ff4ce0..39463dcc16bb 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -796,7 +796,6 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - bool wake_clock = true; void *iter = NULL; u64 now; @@ -806,19 +805,9 @@ void psi_task_change(struct task_struct *task, int clear, int set) psi_flags_change(task, clear, set); now = cpu_clock(cpu); - /* - * Periodic aggregation shuts off if there is a period of no - * task changes, so we wake it back up if necessary. However, - * don't do this if the task change is the aggregation worker - * itself going to sleep, or we'll ping-pong forever. - */ - if (unlikely((clear & TSK_RUNNING) && - (task->flags & PF_WQ_WORKER) && - wq_worker_last_func(task) == psi_avgs_work)) - wake_clock = false; while ((group = iterate_groups(task, &iter))) - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, now, true); } void psi_task_switch(struct task_struct *prev, struct task_struct *next, @@ -854,6 +843,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if (prev->pid) { int clear = TSK_ONCPU, set = 0; + bool wake_clock = true; /* * When we're going to sleep, psi_dequeue() lets us @@ -867,13 +857,23 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((prev->flags & PF_WQ_WORKER) && + wq_worker_last_func(prev) == psi_avgs_work)) + wake_clock = false; } psi_flags_change(prev, clear, set); iter = NULL; while ((group = iterate_groups(prev, &iter)) && group != common) - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, now, wake_clock); /* * TSK_ONCPU is handled up to the common ancestor. If we're tasked @@ -882,7 +882,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if (sleep) { clear &= ~TSK_ONCPU; for (; group; group = iterate_groups(prev, &iter)) - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, now, wake_clock); } } } |