On Wed, Aug 21, 2019 at 5:39 AM Roman Gushchin <guro@xxxxxx> wrote: > > On Sun, Aug 18, 2019 at 09:18:06PM -0400, Yafang Shao wrote: > > In the current memory.min design, the system is going to do OOM instead > > of reclaiming the reclaimable pages protected by memory.min if the > > system is lack of free memory. While under this condition, the OOM > > killer may kill the processes in the memcg protected by memory.min. > > This behavior is very weird. > > In order to make it more reasonable, I make some changes in the OOM > > killer. In this patch, the OOM killer will do two-round scan. It will > > skip the processes under memcg protection at the first scan, and if it > > can't kill any processes it will rescan all the processes. > > > > Regarding the overhead this change may takes, I don't think it will be a > > problem because this only happens under system memory pressure and > > the OOM killer can't find any proper victims which are not under memcg > > protection. > > Also, after the second thought, what your patch really does, > it basically guarantees that no processes out of memory cgroups > with memory.min set will be ever killed (unless there are any other > processes). In most cases (at least on our setups) it's basically > makes such processes immune to the OOM killer (similar to oom_score_adj > set to -1000). > Actually it is between -999 and -1000. > This is by far a too strong side effect of setting memory.min, > so I don't think the idea is acceptable at all. > More possible OOMs is also a strong side effect (and it prevent us from using it). Leave all other works to the userspace is not proper. We should improve it. Thanks Yafang
