[lkml]   [2012]   [Jun]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH v9] mm: compaction: handle incorrect MIGRATE_UNMOVABLE type pageblocks
On Tue, Jun 05, 2012 at 03:05:40PM +0900, Minchan Kim wrote:
> > Let's throw it away until the author send us data.
> >
> I guess it's hard to make such workload to prove it's useful normally.
> But we can't make sure there isn't such workload in the world.
> So I hope listen VOC. At least, Mel might require it.

I'm playing a lot of catch-up at the moment after being out for a few days
so sorry for my silence on this and other threads.

My initial support for this patch was based on an artifical load but one I
felt was plausible to trigger if CMA was being used. In a normal workload
I thought it might be possible to hit if a large process exited freeing
a lot of pagetable pages from MIGRATE_UNMOVABLE blocks at the same time
but that is a little unlikely and a test case would also look very artifical.

Hence, I believe that if you require a real workload to demonstrate the
benefit of the patch that it will be very difficult to find. The primary
decision is if CMA needs this or not. I was under the impression that it
was a help for CMA allocation success rates but I may be mistaken.

Mel Gorman

 \ /
  Last update: 2012-06-11 15:46    [W:0.039 / U:9.172 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site