Re: [PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Mel Gorman
On Wed, Nov 21, 2018 at 03:18:28PM +0100, Vlastimil Babka wrote: > > 1-socket Skylake machine > > config-global-dhp__workload_thpfioscale XFS (no special madvise) > > 4 fio threads, 1 THP allocating thread > > -- > > > > 4.20-rc1 extfrag events < order 9:

Re: [PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Mel Gorman
On Wed, Nov 21, 2018 at 03:18:28PM +0100, Vlastimil Babka wrote: > > 1-socket Skylake machine > > config-global-dhp__workload_thpfioscale XFS (no special madvise) > > 4 fio threads, 1 THP allocating thread > > -- > > > > 4.20-rc1 extfrag events < order 9:

Re: [PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Vlastimil Babka
On 11/21/18 11:14 AM, Mel Gorman wrote: > The page allocator zone lists are iterated based on the watermarks > of each zone which does not take anti-fragmentation into account. On > x86, node 0 may have multiple zones while other nodes have one zone. A > consequence is that tasks running on node 0

Re: [PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Vlastimil Babka
On 11/21/18 11:14 AM, Mel Gorman wrote: > The page allocator zone lists are iterated based on the watermarks > of each zone which does not take anti-fragmentation into account. On > x86, node 0 may have multiple zones while other nodes have one zone. A > consequence is that tasks running on node 0

[PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Mel Gorman
The page allocator zone lists are iterated based on the watermarks of each zone which does not take anti-fragmentation into account. On x86, node 0 may have multiple zones while other nodes have one zone. A consequence is that tasks running on node 0 may fragment ZONE_NORMAL even though ZONE_DMA32

[PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-21 Thread Mel Gorman
The page allocator zone lists are iterated based on the watermarks of each zone which does not take anti-fragmentation into account. On x86, node 0 may have multiple zones while other nodes have one zone. A consequence is that tasks running on node 0 may fragment ZONE_NORMAL even though ZONE_DMA32

[PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-08 Thread Mel Gorman
The page allocator zone lists are iterated based on the watermarks of each zone which does not take anti-fragmentation into account. On x86, node 0 may have multiple zones while other nodes have one zone. A consequence is that tasks running on node 0 may fragment ZONE_NORMAL even though ZONE_DMA32

[PATCH 1/4] mm, page_alloc: Spread allocations across zones before introducing fragmentation

2018-11-08 Thread Mel Gorman
The page allocator zone lists are iterated based on the watermarks of each zone which does not take anti-fragmentation into account. On x86, node 0 may have multiple zones while other nodes have one zone. A consequence is that tasks running on node 0 may fragment ZONE_NORMAL even though ZONE_DMA32