On Sun 22-04-18 21:22:07, Mike Kravetz wrote: > On 04/22/2018 05:09 PM, Michal Hocko wrote: [... > > Also do we want to check other usual suspects? E.g. PageReserved? And > > generally migrateable pages if page count > 0. Or do we want to leave > > everything to the alloc_contig_range? > > I think you proposed something like the above with limited checking at > some time in the past. In my testing, allocations were more likely to > succeed if we did limited testing here and let alloc_contig_range take > a shot at migration/allocation. There really are two ways to approach > this, do as much checking up front or let it be handled by alloc_contig_range. OK, it would be great to have a comment mentioning that. The discrepancy will just hit eyes [...] > Unless I am missing something, calls to alloc_contig range need to have > a size that is a multiple of page block. This is because isolation needs > to take place at a page block level. We can easily 'round up' and release > excess pages. I am not sure but can we simply leave a part of the page block behind? I mean it might have a misleading migrate type but that shouldn't matter much, no? Thanks! -- Michal Hocko SUSE Labs
