On Tue, Jul 25, 2023 at 7:15 PM Roman Gushchin <roman.gushchin@xxxxxxxxx> wrote:
>
> On Wed, Jul 26, 2023 at 12:29:04AM +0000, Yosry Ahmed wrote:
> > Currently, memcg uses rstat to maintain hierarchical stats. Counters are
> > maintained for hierarchical stats at each memcg. Rstat tracks which
> > cgroups have updates on which cpus to keep those counters fresh on the
> > read-side.
> >
> > For non-hierarchical stats, we do not maintain counters. Instead, the
> global?
Do you mean "we do not maintain global counters"? I think "global" is
confusing, because it can be thought of as all cpus or as including
the subtree (as opposed to local for non-hierarchical stats).
> > percpu counters for a given stat need to be summed to get the
> > non-hierarchical stat value. The original implementation did the same.
> > At some point before rstat, non-hierarchical counters were introduced by
> > commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
> > memory.stat reporting"). However, those counters were updated on the
> > performance critical write-side, which caused regressions, so they were
> > later removed by commit 815744d75152 ("mm: memcontrol: don't batch
> > updates of local VM stats and events"). See [1] for more detailed
> > history.
> >
> > Kernel versions in between a983b5ebee57 & 815744d75152 (a year and a
> > half) enjoyed cheap reads of non-hierarchical stats, specifically on
> > cgroup v1. When moving to more recent kernels, a performance regression
> > for reading non-hierarchical stats is observed.
> >
> > Now that we have rstat, we know exactly which percpu counters have
> > updates for each stat. We can maintain non-hierarchical counters again,
> > making reads much more efficient, without affecting the performance
> > critical write-side. Hence, add non-hierarchical (i.e local) counters
> > for the stats, and extend rstat flushing to keep those up-to-date.
> >
> > A caveat is that we now a stats flush before reading
> need?
Ah yes. I am hoping Andrew can amend this but I am happy to send a v3 as well.
> > local/non-hierarchical stats through {memcg/lruvec}_page_state_local()
> > or memcg_events_local(), where we previously only needed a flush to
> > read hierarchical stats. Most contexts reading non-hierarchical stats
> > are already doing a flush, add a flush to the only missing context in
> > count_shadow_nodes().
> >
> > With this patch, reading memory.stat from 1000 memcgs is 3x faster on a
> > machine with 256 cpus on cgroup v1:
> > # for i in $(seq 1000); do mkdir /sys/fs/cgroup/memory/cg$i; done
> > # time cat /dev/cgroup/memory/cg*/memory.stat > /dev/null
> > real 0m0.125s
> > user 0m0.005s
> > sys 0m0.120s
> >
> > After:
> > real 0m0.032s
> > user 0m0.005s
> > sys 0m0.027s
> >
> > [1]https://lore.kernel.org/lkml/20230725201811.GA1231514@xxxxxxxxxxx/
> >
> > Signed-off-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
> > Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
>
> Acked-by: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Thanks!
>
> Thank you!
