Re: [PATCH] psi: remove CPU full metric at system level

[Johannes Weiner]

On Thu, Mar 03, 2022 at 01:58:14PM +0800, Chengming Zhou wrote:
> Martin find it confusing when look at the /proc/pressure/cpu output,
> and found no hint about that CPU "full" line in psi Documentation.
> 
> % cat /proc/pressure/cpu
> some avg10=0.92 avg60=0.91 avg300=0.73 total=933490489
> full avg10=0.22 avg60=0.23 avg300=0.16 total=358783277
> 
> The PSI_CPU_FULL state is introduced by commit e7fcd7622823
> ("psi: Add PSI_CPU_FULL state"), which mainly for cgroup level,
> but also counted at the system level as a side effect.
> 
> Naturally, the FULL state doesn't exist for the CPU resource at
> the system level. These "full" numbers can come from CPU idle
> schedule latency. For example, t1 is the time when task wakeup
> on an idle CPU, t2 is the time when CPU pick and switch to it.
> The delta of (t2 - t1) will be in CPU_FULL state.
> 
> Another case all processes can be stalled is when all cgroups
> have been throttled at the same time, which unlikely to happen.
> 
> Anyway, CPU_FULL metric is meaningless and confusing at the
> system level. So this patch removed CPU full metric at the
> system level, and removed it's monitor function too. The psi
> Documentation has also been updated accordingly.
> 
> Fixes: e7fcd7622823 ("psi: Add PSI_CPU_FULL state")
> Reported-by: Martin Steigerwald <Martin.Steigerwald@xxxxxxxxx>
> Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> ---
>  Documentation/accounting/psi.rst | 18 +++++++++++++++---
>  kernel/sched/psi.c               | 10 +++++++++-
>  2 files changed, 24 insertions(+), 4 deletions(-)
> 
> diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst
> index 860fe651d645..519652c06d7d 100644
> --- a/Documentation/accounting/psi.rst
> +++ b/Documentation/accounting/psi.rst
> @@ -178,8 +178,20 @@ Cgroup2 interface
>  In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem
>  mounted, pressure stall information is also tracked for tasks grouped
>  into cgroups. Each subdirectory in the cgroupfs mountpoint contains
> -cpu.pressure, memory.pressure, and io.pressure files; the format is
> -the same as the /proc/pressure/ files.
> +cpu.pressure, memory.pressure, and io.pressure files; the format of
> +memory.pressure and io.pressure is the same as the /proc/pressure/ files.
> +
> +But the format of cpu.pressure is as such::
> +	some avg10=0.00 avg60=0.00 avg300=0.00 total=0
> +	full avg10=0.00 avg60=0.00 avg300=0.00 total=0

It's the format of cpu.pressure, except when it's
/sys/fs/cgroup/cpu.pressure... I think this is getting maybe a tad too
difficult to write parsers for. Plus, we added the line over a year
ago so we might break somebody by removing it again.

How about reporting zeroes at the system level?

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index e14358178849..86824de404bc 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1062,14 +1062,17 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res)
 	mutex_unlock(&group->avgs_lock);
 
 	for (full = 0; full < 2; full++) {
-		unsigned long avg[3];
-		u64 total;
+		unsigned long avg[3] = { 0, };
+		u64 total = 0;
 		int w;
 
-		for (w = 0; w < 3; w++)
-			avg[w] = group->avg[res * 2 + full][w];
-		total = div_u64(group->total[PSI_AVGS][res * 2 + full],
-				NSEC_PER_USEC);
+		/* CPU FULL is undefined at the system level */
+		if (!(group == &psi_system && res == PSI_CPU && full)) {
+			for (w = 0; w < 3; w++)
+				avg[w] = group->avg[res * 2 + full][w];
+			total = div_u64(group->total[PSI_AVGS][res * 2 + full],
+					NSEC_PER_USEC);
+		}
 
 		seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n",
 			   full ? "full" : "some",