On Wed 03-07-19 06:26:55, Tetsuo Handa wrote: > On 2019/07/02 22:51, Michal Hocko wrote: > >>> I do not see any strong reason to keep the current ordering. OOM victim > >>> check is trivial so it shouldn't add a visible overhead for few > >>> unkillable tasks that we might encounter. > >>> > >> > >> Yes if we can tolerate that there can be only one OOM victim for !memcg OOM events > >> (because an OOM victim in a different OOM context will hit "goto abort;" path). > > > > You are right. Considering that we now have a guarantee of a forward > > progress then this should be tolerateable (a victim in a disjoint > > numaset will go away and other one can go ahead and trigger its own > > OOM). > > But it might take very long period before MMF_OOM_SKIP is set by the OOM reaper > or exit_mmap(). Until MMF_OOM_SKIP is set, OOM events from disjoint numaset can't > make forward progress. If that is a concern then I would stick with the current status quo until we see the issue to be reported by real workloads. -- Michal Hocko SUSE Labs
