Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-03-04 Thread Andrey Ryabinin
On 3/2/19 1:20 AM, Johannes Weiner wrote: > On Fri, Mar 01, 2019 at 10:46:34PM +0300, Andrey Ryabinin wrote: >> On 3/1/19 8:49 PM, Johannes Weiner wrote: >>> On Fri, Mar 01, 2019 at 01:38:26PM +0300, Andrey Ryabinin wrote: On 2/26/19 3:50 PM, Andrey Ryabinin wrote: > On 2/22/19 10:15

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-03-01 Thread Johannes Weiner
On Fri, Mar 01, 2019 at 10:46:34PM +0300, Andrey Ryabinin wrote: > On 3/1/19 8:49 PM, Johannes Weiner wrote: > > On Fri, Mar 01, 2019 at 01:38:26PM +0300, Andrey Ryabinin wrote: > >> On 2/26/19 3:50 PM, Andrey Ryabinin wrote: > >>> On 2/22/19 10:15 PM, Johannes Weiner wrote: > On Fri, Feb 22,

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-03-01 Thread Andrey Ryabinin
On 3/1/19 8:49 PM, Johannes Weiner wrote: > Hello Andrey, > > On Fri, Mar 01, 2019 at 01:38:26PM +0300, Andrey Ryabinin wrote: >> On 2/26/19 3:50 PM, Andrey Ryabinin wrote: >>> On 2/22/19 10:15 PM, Johannes Weiner wrote: On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote:

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-03-01 Thread Johannes Weiner
Hello Andrey, On Fri, Mar 01, 2019 at 01:38:26PM +0300, Andrey Ryabinin wrote: > On 2/26/19 3:50 PM, Andrey Ryabinin wrote: > > On 2/22/19 10:15 PM, Johannes Weiner wrote: > >> On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: > >>> In a presence of more than 1 memory cgroup in the

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-03-01 Thread Andrey Ryabinin
On 2/26/19 3:50 PM, Andrey Ryabinin wrote: > > > On 2/22/19 10:15 PM, Johannes Weiner wrote: >> On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: >>> In a presence of more than 1 memory cgroup in the system our reclaim >>> logic is just suck. When we hit memory limit (global or

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-26 Thread Roman Gushchin
On Tue, Feb 26, 2019 at 06:36:38PM +0300, Andrey Ryabinin wrote: > > > On 2/25/19 7:03 AM, Roman Gushchin wrote: > > On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: > >> In a presence of more than 1 memory cgroup in the system our reclaim > >> logic is just suck. When we hit

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-26 Thread Andrey Ryabinin
On 2/25/19 7:03 AM, Roman Gushchin wrote: > On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: >> In a presence of more than 1 memory cgroup in the system our reclaim >> logic is just suck. When we hit memory limit (global or a limit on >> cgroup with subgroups) we reclaim some

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-26 Thread Andrey Ryabinin
On 2/22/19 10:15 PM, Johannes Weiner wrote: > On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: >> In a presence of more than 1 memory cgroup in the system our reclaim >> logic is just suck. When we hit memory limit (global or a limit on >> cgroup with subgroups) we reclaim some

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-25 Thread Vlastimil Babka
On 2/22/19 6:58 PM, Andrey Ryabinin wrote: > In a presence of more than 1 memory cgroup in the system our reclaim > logic is just suck. When we hit memory limit (global or a limit on > cgroup with subgroups) we reclaim some memory from all cgroups. > This is sucks because, the cgroup that

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-24 Thread Roman Gushchin
On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: > In a presence of more than 1 memory cgroup in the system our reclaim > logic is just suck. When we hit memory limit (global or a limit on > cgroup with subgroups) we reclaim some memory from all cgroups. > This is sucks because,

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-22 Thread Johannes Weiner
On Fri, Feb 22, 2019 at 08:58:25PM +0300, Andrey Ryabinin wrote: > In a presence of more than 1 memory cgroup in the system our reclaim > logic is just suck. When we hit memory limit (global or a limit on > cgroup with subgroups) we reclaim some memory from all cgroups. > This is sucks because,

Re: [PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-22 Thread Rik van Riel
On Fri, 2019-02-22 at 20:58 +0300, Andrey Ryabinin wrote: > In a presence of more than 1 memory cgroup in the system our reclaim > logic is just suck. When we hit memory limit (global or a limit on > cgroup with subgroups) we reclaim some memory from all cgroups. > This is sucks because, the

[PATCH RFC] mm/vmscan: try to protect active working set of cgroup from reclaim.

2019-02-22 Thread Andrey Ryabinin
In a presence of more than 1 memory cgroup in the system our reclaim logic is just suck. When we hit memory limit (global or a limit on cgroup with subgroups) we reclaim some memory from all cgroups. This is sucks because, the cgroup that allocates more often always wins. E.g. job that allocates a