On Tue, Aug 17, 2021 at 12:10:16PM -0700, Shakeel Butt wrote: > On Tue, Aug 17, 2021 at 11:03 AM Johannes Weiner <hannes@xxxxxxxxxxx> wrote: > > > > We've noticed occasional OOM killing when memory.low settings are in > > effect for cgroups. This is unexpected and undesirable as memory.low > > is supposed to express non-OOMing memory priorities between cgroups. > > > > The reason for this is proportional memory.low reclaim. When cgroups > > are below their memory.low threshold, reclaim passes them over in the > > first round, and then retries if it couldn't find pages anywhere else. > > But when cgroups are slighly above their memory.low setting, page scan > > *slightly > > > force is scaled down and diminished in proportion to the overage, to > > the point where it can cause reclaim to fail as well - only in that > > case we currently don't retry, and instead trigger OOM. > > > > To fix this, hook proportional reclaim into the same retry logic we > > have in place for when cgroups are skipped entirely. This way if > > reclaim fails and some cgroups were scanned with dimished pressure, > > *diminished Oops. Andrew, would you mind folding these into the checkpatch fixlet? > > we'll try another full-force cycle before giving up and OOMing. > > > > Reported-by: Leon Yang <lnyng@xxxxxx> > > Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> > > Should this be considered for stable? Yes, I think so after all. Please see my reply to Roman. > Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx> Thanks Shakeel!
