On Wed, 24 Jan 2018, Michal Hocko wrote: > > The current implementation of memory.oom_group is based on top of a > > selection implementation that is broken in three ways I have listed for > > months: > > This doesn't lead to anywhere. You are not presenting any new arguments > and you are ignoring feedback you have received so far. We have tried > really hard. Considering different _independent_ people presented more or > less consistent view on these points I think you should deeply > reconsider how you take that feedback. >
I've responded to each email providing useful feedback on this patchset. I agreed with Tejun about not embedding the oom mechanism into memory.oom_policy. I was trying to avoid having two files in the mem cgroup v2 filesystem for oom policy and mechanism. I agreed that delegating the mechanism to the workload would be useful in some cases. I've solicited feedback on any other opinions on how that can be done better, but it appears another tunable is the most convenient way of allowing this behavior to be specified. As a result, this would remove patch 3/4 from the series. Do you have any other feedback regarding the remainder of this patch series before I rebase it? I will address the unfair root mem cgroup vs leaf mem cgroup comparison in a separate patchset to fix an issue where any user of oom_score_adj on a system that is not fully containerized gets very unusual, unexpected, and undocumented results. Thanks.
