Re: [PATCH] mm, compaction: Make sure we isolate a valid PFN

2019-05-26 Thread Anshuman Khandual
On 05/24/2019 09:01 PM, Suzuki K Poulose wrote: > When we have holes in a normal memory zone, we could endup having > cached_migrate_pfns which may not necessarily be valid, under heavy memory > pressure with swapping enabled ( via __reset_isolation_suitable(), triggered > by kswapd). > >

Re: [PATCH] mm, compaction: Make sure we isolate a valid PFN

2019-05-24 Thread Mel Gorman
On Fri, May 24, 2019 at 04:31:48PM +0100, Suzuki K Poulose wrote: > When we have holes in a normal memory zone, we could endup having > cached_migrate_pfns which may not necessarily be valid, under heavy memory > pressure with swapping enabled ( via __reset_isolation_suitable(), triggered > by

[PATCH] mm, compaction: Make sure we isolate a valid PFN

2019-05-24 Thread Suzuki K Poulose
When we have holes in a normal memory zone, we could endup having cached_migrate_pfns which may not necessarily be valid, under heavy memory pressure with swapping enabled ( via __reset_isolation_suitable(), triggered by kswapd). Later if we fail to find a page via fast_isolate_freepages(), we