* [PATCH] psi: Add PSI_CPU_FULL state
@ 2020-12-25 4:22 Chengming Zhou
0 siblings, 0 replies; 3+ messages in thread
From: Chengming Zhou @ 2020-12-25 4:22 UTC (permalink / raw)
To: linux-kernel
Cc: hannes, mingo, peterz, juri.lelli, vincent.guittot,
dietmar.eggemann, rostedt, bsegall, mgorman, bristot,
zhouchengming
From: zhouchengming <zhouchengming@bytedance.com>
When I run a simple "perf bench sched pipe" test in a cgroup on my
machine, the output of "watch -d -n 1 cpu.pressure" of this cgroup
will report some avg10 10%-20%.
It's strange because there is not any other process in the cgroup.
Then I found that cpu contention/wait percentage came from outside
of the cgroup and the cpu idle latency, not wait for threads in
the cgroup.
So I think adding PSI_CPU_FULL state will be useful for container
workloads to distinguish between outside cgroup resource contention
and inside cgroup resource contention.
What's more, the PSI_CPU_FULL state includes the latency of the cpu
idle itself, so we can see the system sum latency introduced by cpu
idle state.
Signed-off-by: zhouchengming <zhouchengming@bytedance.com>
---
include/linux/psi_types.h | 3 ++-
kernel/sched/psi.c | 9 +++++++--
2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index b95f3211566a..0a23300d49af 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -50,9 +50,10 @@ enum psi_states {
PSI_MEM_SOME,
PSI_MEM_FULL,
PSI_CPU_SOME,
+ PSI_CPU_FULL,
/* Only per-CPU, to weigh the CPU in the global average: */
PSI_NONIDLE,
- NR_PSI_STATES = 6,
+ NR_PSI_STATES = 7,
};
enum psi_aggregators {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 967732c0766c..234047e368a5 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -224,7 +224,9 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
case PSI_MEM_FULL:
return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
case PSI_CPU_SOME:
- return tasks[NR_RUNNING] > tasks[NR_ONCPU];
+ return tasks[NR_RUNNING] > tasks[NR_ONCPU] && tasks[NR_ONCPU];
+ case PSI_CPU_FULL:
+ return tasks[NR_RUNNING] && !tasks[NR_ONCPU];
case PSI_NONIDLE:
return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
tasks[NR_RUNNING];
@@ -681,6 +683,9 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
if (groupc->state_mask & (1 << PSI_CPU_SOME))
groupc->times[PSI_CPU_SOME] += delta;
+ if (groupc->state_mask & (1 << PSI_CPU_FULL))
+ groupc->times[PSI_CPU_FULL] += delta;
+
if (groupc->state_mask & (1 << PSI_NONIDLE))
groupc->times[PSI_NONIDLE] += delta;
}
@@ -1018,7 +1023,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
group->avg_next_update = update_averages(group, now);
mutex_unlock(&group->avgs_lock);
- for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+ for (full = 0; full < 2; full++) {
unsigned long avg[3];
u64 total;
int w;
--
2.11.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] psi: Add PSI_CPU_FULL state
2021-02-07 7:24 Chengming Zhou
@ 2021-02-08 18:18 ` Johannes Weiner
0 siblings, 0 replies; 3+ messages in thread
From: Johannes Weiner @ 2021-02-08 18:18 UTC (permalink / raw)
To: Chengming Zhou
Cc: mingo, peterz, juri.lelli, vincent.guittot, rostedt,
dietmar.eggemann, linux-kernel, songmuchun
On Sun, Feb 07, 2021 at 03:24:02PM +0800, Chengming Zhou wrote:
> The FULL state doesn't exist for the CPU resource at the system level,
> but exist at the cgroup level, means all non-idle tasks in a cgroup are
> delayed on the CPU resource which used by others outside of the cgroup.
>
> Co-developed-by: Muchun Song <songmuchun@bytedance.com>
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
That metric's come up in our production environment recently as well,
it makes a lot of sense.
In addition to outside competition, this also applies to downtimes
enforced by cpu.max - another cgroup usecase that is worth mentioning
in the changelog & code comment.
Thanks
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH] psi: Add PSI_CPU_FULL state
@ 2021-02-07 7:24 Chengming Zhou
2021-02-08 18:18 ` Johannes Weiner
0 siblings, 1 reply; 3+ messages in thread
From: Chengming Zhou @ 2021-02-07 7:24 UTC (permalink / raw)
To: hannes, mingo, peterz, juri.lelli, vincent.guittot, rostedt,
dietmar.eggemann
Cc: linux-kernel, songmuchun, zhouchengming
The FULL state doesn't exist for the CPU resource at the system level,
but exist at the cgroup level, means all non-idle tasks in a cgroup are
delayed on the CPU resource which used by others outside of the cgroup.
Co-developed-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
---
include/linux/psi_types.h | 3 ++-
kernel/sched/psi.c | 14 +++++++++++---
2 files changed, 13 insertions(+), 4 deletions(-)
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index b95f3211566a..0a23300d49af 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -50,9 +50,10 @@ enum psi_states {
PSI_MEM_SOME,
PSI_MEM_FULL,
PSI_CPU_SOME,
+ PSI_CPU_FULL,
/* Only per-CPU, to weigh the CPU in the global average: */
PSI_NONIDLE,
- NR_PSI_STATES = 6,
+ NR_PSI_STATES = 7,
};
enum psi_aggregators {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 39d758a15a57..c572ad529d87 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -34,7 +34,10 @@
* delayed on that resource such that nobody is advancing and the CPU
* goes idle. This leaves both workload and CPU unproductive.
*
- * (Naturally, the FULL state doesn't exist for the CPU resource.)
+ * Naturally, the FULL state doesn't exist for the CPU resource at the
+ * system level, but exist at the cgroup level, means all non-idle tasks
+ * in a cgroup are delayed on the CPU resource which used by others outside
+ * of the cgroup.
*
* SOME = nr_delayed_tasks != 0
* FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0
@@ -225,6 +228,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state)
return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING];
case PSI_CPU_SOME:
return tasks[NR_RUNNING] > tasks[NR_ONCPU];
+ case PSI_CPU_FULL:
+ return tasks[NR_RUNNING] && !tasks[NR_ONCPU];
case PSI_NONIDLE:
return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] ||
tasks[NR_RUNNING];
@@ -678,8 +683,11 @@ static void record_times(struct psi_group_cpu *groupc, int cpu,
}
}
- if (groupc->state_mask & (1 << PSI_CPU_SOME))
+ if (groupc->state_mask & (1 << PSI_CPU_SOME)) {
groupc->times[PSI_CPU_SOME] += delta;
+ if (groupc->state_mask & (1 << PSI_CPU_FULL))
+ groupc->times[PSI_CPU_FULL] += delta;
+ }
if (groupc->state_mask & (1 << PSI_NONIDLE))
groupc->times[PSI_NONIDLE] += delta;
@@ -1018,7 +1026,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
group->avg_next_update = update_averages(group, now);
mutex_unlock(&group->avgs_lock);
- for (full = 0; full < 2 - (res == PSI_CPU); full++) {
+ for (full = 0; full < 2; full++) {
unsigned long avg[3];
u64 total;
int w;
--
2.11.0
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2021-02-08 19:58 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-12-25 4:22 [PATCH] psi: Add PSI_CPU_FULL state Chengming Zhou
2021-02-07 7:24 Chengming Zhou
2021-02-08 18:18 ` Johannes Weiner
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.