Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-25 Thread Joonsoo Kim
On Fri, Oct 14, 2016 at 12:52:26PM +0200, Vlastimil Babka wrote: > On 10/14/2016 03:26 AM, Joonsoo Kim wrote: > >On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: > >>On 10/13/2016 10:08 AM, js1...@gmail.com wrote: > >>>From: Joonsoo Kim > >>> > >>>When we

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-25 Thread Joonsoo Kim
On Fri, Oct 14, 2016 at 12:52:26PM +0200, Vlastimil Babka wrote: > On 10/14/2016 03:26 AM, Joonsoo Kim wrote: > >On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: > >>On 10/13/2016 10:08 AM, js1...@gmail.com wrote: > >>>From: Joonsoo Kim > >>> > >>>When we try to find freepage in

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-14 Thread Vlastimil Babka
On 10/14/2016 03:26 AM, Joonsoo Kim wrote: On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: On 10/13/2016 10:08 AM, js1...@gmail.com wrote: >From: Joonsoo Kim > >When we try to find freepage in fallback buddy list, we always serach >the largest one. This

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-14 Thread Vlastimil Babka
On 10/14/2016 03:26 AM, Joonsoo Kim wrote: On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: On 10/13/2016 10:08 AM, js1...@gmail.com wrote: >From: Joonsoo Kim > >When we try to find freepage in fallback buddy list, we always serach >the largest one. This would help for

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread Joonsoo Kim
On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: > On 10/13/2016 10:08 AM, js1...@gmail.com wrote: > >From: Joonsoo Kim > > > >When we try to find freepage in fallback buddy list, we always serach > >the largest one. This would help for fragmentation if we

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread Joonsoo Kim
On Thu, Oct 13, 2016 at 11:12:10AM +0200, Vlastimil Babka wrote: > On 10/13/2016 10:08 AM, js1...@gmail.com wrote: > >From: Joonsoo Kim > > > >When we try to find freepage in fallback buddy list, we always serach > >the largest one. This would help for fragmentation if we process >

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread Vlastimil Babka
On 10/13/2016 10:08 AM, js1...@gmail.com wrote: From: Joonsoo Kim When we try to find freepage in fallback buddy list, we always serach the largest one. This would help for fragmentation if we process unmovable/reclaimable allocation request because it could cause

Re: [RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread Vlastimil Babka
On 10/13/2016 10:08 AM, js1...@gmail.com wrote: From: Joonsoo Kim When we try to find freepage in fallback buddy list, we always serach the largest one. This would help for fragmentation if we process unmovable/reclaimable allocation request because it could cause permanent fragmentation on

[RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread js1304
From: Joonsoo Kim When we try to find freepage in fallback buddy list, we always serach the largest one. This would help for fragmentation if we process unmovable/reclaimable allocation request because it could cause permanent fragmentation on movable pageblock and spread

[RFC PATCH 2/5] mm/page_alloc: use smallest fallback page first in movable allocation

2016-10-13 Thread js1304
From: Joonsoo Kim When we try to find freepage in fallback buddy list, we always serach the largest one. This would help for fragmentation if we process unmovable/reclaimable allocation request because it could cause permanent fragmentation on movable pageblock and spread out such allocations