Re: [regression v4.0-rc1] mm: IPIs from TLB flushes causing significant performance degradation.

[Dave Chinner <david@fromorbit.com>]

On Tue, Mar 03, 2015 at 01:43:46PM +0000, Mel Gorman wrote:
> On Tue, Mar 03, 2015 at 10:34:37PM +1100, Dave Chinner wrote:
> > On Mon, Mar 02, 2015 at 10:56:14PM -0800, Linus Torvalds wrote:
> > > On Mon, Mar 2, 2015 at 9:20 PM, Dave Chinner <david@fromorbit.com> wrote:
> > > >>
> > > >> But are those migrate-page calls really common enough to make these
> > > >> things happen often enough on the same pages for this all to matter?
> > > >
> > > > It's looking like that's a possibility.
> > > 
> > > Hmm. Looking closer, commit 10c1045f28e8 already should have
> > > re-introduced the "pte was already NUMA" case.
> > > 
> > > So that's not it either, afaik. Plus your numbers seem to say that
> > > it's really "migrate_pages()" that is done more. So it feels like the
> > > numa balancing isn't working right.
> > 
> > So that should show up in the vmstats, right? Oh, and there's a
> > tracepoint in migrate_pages, too. Same 6x10s samples in phase 3:
> > 
> 
> The stats indicate both more updates and more faults. Can you try this
> please? It's against 4.0-rc1.
> 
> ---8<---
> mm: numa: Reduce amount of IPI traffic due to automatic NUMA balancing

Makes no noticable difference to behaviour or performance. Stats:

359,857      migrate:mm_migrate_pages ( +-  5.54% )

numa_hit 36026802
numa_miss 14287
numa_foreign 14287
numa_interleave 18408
numa_local 36006052
numa_other 35037
numa_pte_updates 81803359
numa_huge_pte_updates 0
numa_hint_faults 79810798
numa_hint_faults_local 21227730
numa_pages_migrated 32037516
pgmigrate_success 32037516
pgmigrate_fail 0

-Dave.
-- 
Dave Chinner
david@fromorbit.com