Re: [PATCH] mm, hugetlb: allow hugepage allocations to excessively reclaim

2019-10-08 Thread Vlastimil Babka
On 10/7/19 9:55 AM, Michal Hocko wrote: > From: David Rientjes Nit: the subject is still somewhat misleading IMHO, especially in light of Mike's responses. I would say "reclaim as needed" instead of "excessively reclaim". The excessive reclaim behavior in hugetlb nr_pages setting was a bug that wa

Re: [PATCH] mm, hugetlb: allow hugepage allocations to excessively reclaim

2019-10-08 Thread Michal Hocko
On Mon 07-10-19 12:03:30, Mike Kravetz wrote: > On 10/7/19 12:55 AM, Michal Hocko wrote: > > From: David Rientjes > > > > b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when compaction > > may not succeed") has chnaged the allocator to bail out from the > > allocator early to prevent from

Re: [PATCH] mm, hugetlb: allow hugepage allocations to excessively reclaim

2019-10-07 Thread Mike Kravetz
On 10/7/19 12:55 AM, Michal Hocko wrote: > From: David Rientjes > > b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when compaction > may not succeed") has chnaged the allocator to bail out from the > allocator early to prevent from a potentially excessive memory > reclaim. __GFP_RETRY_MAY

[PATCH] mm, hugetlb: allow hugepage allocations to excessively reclaim

2019-10-07 Thread Michal Hocko
From: David Rientjes b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when compaction may not succeed") has chnaged the allocator to bail out from the allocator early to prevent from a potentially excessive memory reclaim. __GFP_RETRY_MAYFAIL is designed to retry the allocation, reclaim and