On Tue 29-10-19 16:25:17, David Rientjes wrote: > On Tue, 29 Oct 2019, Andrew Morton wrote: > > > On Tue, 29 Oct 2019 16:15:49 +0100 Michal Hocko <mhocko@xxxxxxxxxx> wrote: > > > > > > > > > > 1. local node only THP allocation with no reclaim, just compaction. > > > > 2. for madvised VMA's or when synchronous compaction is enabled always - THP > > > > allocation from any node with effort determined by global defrag setting > > > > and VMA madvise > > > > 3. fallback to base pages on any node > > > > > > > > Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx> > > > > > > I've given this a try and here are the results of my previous testcase > > > (memory full of page cache). > > > > Thanks, I'll queue this for some more testing. At some point we should > > decide on a suitable set of Fixes: tags and a backporting strategy, if any? > > > > I'd strongly suggest that Andrea test this patch out on his workload on > hosts where all nodes are low on memory because based on my understanding > of his reported issue this would result in swap storms reemerging but > worse this time because they wouldn't be constrained only locally. (This > patch causes us to no longer circumvent excessive reclaim when using > MADV_HUGEPAGE.) Could you be more specific on why this would be the case? My testing is doesn't show any such signs and I am effectivelly testing memory low situation. The amount of reclaimed memory matches the amount of requested memory. -- Michal Hocko SUSE Labs
