Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Fri, Feb 3, 2017 at 8:29 PM, Michal Hocko wrote: > On Fri 03-02-17 10:56:42, vinayak menon wrote: >> On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: >> > >> > Why would you like to chose and kill a task when the slab reclaim can >> > still make

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Fri, Feb 3, 2017 at 8:29 PM, Michal Hocko wrote: > On Fri 03-02-17 10:56:42, vinayak menon wrote: >> On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: >> > >> > Why would you like to chose and kill a task when the slab reclaim can >> > still make sufficient progres? Are you sure that the

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Fri 03-02-17 10:56:42, vinayak menon wrote: > On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: > > > > Why would you like to chose and kill a task when the slab reclaim can > > still make sufficient progres? Are you sure that the slab contribution > > to the stats makes

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Fri 03-02-17 10:56:42, vinayak menon wrote: > On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: > > > > Why would you like to chose and kill a task when the slab reclaim can > > still make sufficient progres? Are you sure that the slab contribution > > to the stats makes all the above

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 02, 2017 at 11:44:22AM +0100, Michal Hocko wrote: > On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > > During global reclaim, the nr_reclaimed passed to vmpressure > > includes the pages reclaimed from slab. But the corresponding > > scanned slab pages is not passed. This can cause

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 02, 2017 at 11:44:22AM +0100, Michal Hocko wrote: > On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > > During global reclaim, the nr_reclaimed passed to vmpressure > > includes the pages reclaimed from slab. But the corresponding > > scanned slab pages is not passed. This can cause

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: > > Why would you like to chose and kill a task when the slab reclaim can > still make sufficient progres? Are you sure that the slab contribution > to the stats makes all the above happening? > I agree that a task need not be

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 9:31 PM, Michal Hocko wrote: > > Why would you like to chose and kill a task when the slab reclaim can > still make sufficient progres? Are you sure that the slab contribution > to the stats makes all the above happening? > I agree that a task need not be killed if

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 21:00:10, vinayak menon wrote: > On Thu, Feb 2, 2017 at 5:22 PM, Michal Hocko wrote: > > On Thu 02-02-17 16:55:49, vinayak menon wrote: > >> On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > >> > On Thu 02-02-17 11:44:22, Michal Hocko

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 21:00:10, vinayak menon wrote: > On Thu, Feb 2, 2017 at 5:22 PM, Michal Hocko wrote: > > On Thu 02-02-17 16:55:49, vinayak menon wrote: > >> On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > >> > On Thu 02-02-17 11:44:22, Michal Hocko wrote: > >> >> On Tue 31-01-17 14:32:08,

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 5:22 PM, Michal Hocko wrote: > On Thu 02-02-17 16:55:49, vinayak menon wrote: >> On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: >> > On Thu 02-02-17 11:44:22, Michal Hocko wrote: >> >> On Tue 31-01-17 14:32:08, Vinayak Menon

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 5:22 PM, Michal Hocko wrote: > On Thu 02-02-17 16:55:49, vinayak menon wrote: >> On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: >> > On Thu 02-02-17 11:44:22, Michal Hocko wrote: >> >> On Tue 31-01-17 14:32:08, Vinayak Menon wrote: >> >> > During global reclaim, the

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 16:55:49, vinayak menon wrote: > On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > > On Thu 02-02-17 11:44:22, Michal Hocko wrote: > >> On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > >> > During global reclaim, the nr_reclaimed passed to vmpressure > >> >

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 16:55:49, vinayak menon wrote: > On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > > On Thu 02-02-17 11:44:22, Michal Hocko wrote: > >> On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > >> > During global reclaim, the nr_reclaimed passed to vmpressure > >> > includes the pages

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 4:14 PM, Michal Hocko wrote: > > We usually refer to the culprit comment as > Fixes: 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") > Thanks for pointing that out Michal. I see that added to the version of patch in mmotm. > To

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 4:14 PM, Michal Hocko wrote: > > We usually refer to the culprit comment as > Fixes: 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") > Thanks for pointing that out Michal. I see that added to the version of patch in mmotm. > To unsubscribe, send a

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > On Thu 02-02-17 11:44:22, Michal Hocko wrote: >> On Tue 31-01-17 14:32:08, Vinayak Menon wrote: >> > During global reclaim, the nr_reclaimed passed to vmpressure >> > includes the pages reclaimed from slab. But the

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu, Feb 2, 2017 at 4:18 PM, Michal Hocko wrote: > On Thu 02-02-17 11:44:22, Michal Hocko wrote: >> On Tue 31-01-17 14:32:08, Vinayak Menon wrote: >> > During global reclaim, the nr_reclaimed passed to vmpressure >> > includes the pages reclaimed from slab. But the corresponding >> > scanned

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 11:44:22, Michal Hocko wrote: > On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > > During global reclaim, the nr_reclaimed passed to vmpressure > > includes the pages reclaimed from slab. But the corresponding > > scanned slab pages is not passed. This can cause total reclaimed > >

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Thu 02-02-17 11:44:22, Michal Hocko wrote: > On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > > During global reclaim, the nr_reclaimed passed to vmpressure > > includes the pages reclaimed from slab. But the corresponding > > scanned slab pages is not passed. This can cause total reclaimed > >

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > During global reclaim, the nr_reclaimed passed to vmpressure > includes the pages reclaimed from slab. But the corresponding > scanned slab pages is not passed. This can cause total reclaimed > pages to be greater than scanned, causing an unsigned

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Tue 31-01-17 14:32:08, Vinayak Menon wrote: > During global reclaim, the nr_reclaimed passed to vmpressure > includes the pages reclaimed from slab. But the corresponding > scanned slab pages is not passed. This can cause total reclaimed > pages to be greater than scanned, causing an unsigned

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Tue, Jan 31, 2017 at 02:32:08PM +0530, Vinayak Menon wrote: > During global reclaim, the nr_reclaimed passed to vmpressure > includes the pages reclaimed from slab. But the corresponding > scanned slab pages is not passed. This can cause total reclaimed > pages to be greater than scanned,

Re: [PATCH 1/2 v3] mm: vmscan: do not pass reclaimed slab to vmpressure

On Tue, Jan 31, 2017 at 02:32:08PM +0530, Vinayak Menon wrote: > During global reclaim, the nr_reclaimed passed to vmpressure > includes the pages reclaimed from slab. But the corresponding > scanned slab pages is not passed. This can cause total reclaimed > pages to be greater than scanned,