Re: [PATCH 1/2] mm, oom: make sure that the oom victim uses memory reserves

2017-05-22 Thread Roman Gushchin
On Fri, May 19, 2017 at 02:46:32PM +0200, Michal Hocko wrote: > On Fri 19-05-17 21:12:36, Tetsuo Handa wrote: > > >From 41b663d0324bbaa29c01d7fee01e897b8b3b7397 Mon Sep 17 00:00:00 2001 > > From: Tetsuo Handa > > Date: Fri, 19 May 2017 21:06:49 +0900 > > Subject: [PATCH] mm,page_alloc: Make sure O

Re: [PATCH 1/2] mm, oom: make sure that the oom victim uses memory reserves

2017-05-19 Thread Michal Hocko
On Fri 19-05-17 21:12:36, Tetsuo Handa wrote: > >From 41b663d0324bbaa29c01d7fee01e897b8b3b7397 Mon Sep 17 00:00:00 2001 > From: Tetsuo Handa > Date: Fri, 19 May 2017 21:06:49 +0900 > Subject: [PATCH] mm,page_alloc: Make sure OOM victim can try allocations with > no watermarks once > > Roman Gush

Re: [PATCH 1/2] mm, oom: make sure that the oom victim uses memory reserves

2017-05-19 Thread Tetsuo Handa
>From 41b663d0324bbaa29c01d7fee01e897b8b3b7397 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 19 May 2017 21:06:49 +0900 Subject: [PATCH] mm,page_alloc: Make sure OOM victim can try allocations with no watermarks once Roman Gushchin has reported that the OOM killer can trivially selects

[PATCH 1/2] mm, oom: make sure that the oom victim uses memory reserves

2017-05-19 Thread Michal Hocko
From: Michal Hocko Roman Gushchin has noticed that we kill two tasks when the memory hog killed from page fault path: [ 25.721494] allocate invoked oom-killer: gfp_mask=0x14280ca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), nodemask=(null), order=0, oom_score_adj=0 [ 25.725658] allocate cpuset=/ mems