Re: [PATCH] mm: writeback: ratelimit stat flush from mem_cgroup_wb_stats

[Michal Koutný]

Hello.

On Thu, Jan 18, 2024 at 06:42:35PM +0000, Shakeel Butt <shakeelb@xxxxxxxxxx> wrote:
> One of our workloads (Postgres 14) has regressed when migrated from 5.10
> to 6.1 upstream kernel. The regression can be reproduced by sysbench's
> oltp_write_only benchmark.
> It seems like the always on rstat flush in
> mem_cgroup_wb_stats() is causing the regression.

Is the affected benchmark running in a non-root cgroup?

I'm asking whether this would warrant a 
  Fixes: fd25a9e0e23b ("memcg: unify memcg stat flushing") 
that introduced the global flush (in v6.1) but it was removed later in 
  7d7ef0a4686a ("mm: memcg: restore subtree stats flushing") 
(so v6.8 could be possibly unaffected).

Thanks,
Michal

Attachment: signature.asc
Description: PGP signature