Messages in this thread |  | | Date | Thu, 12 Dec 2013 15:34:22 +0000 | From | Mel Gorman <> | Subject | Re: [RFC PATCH 0/4] Configurable fair allocation zone policy |
| |
On Thu, Dec 12, 2013 at 03:06:15PM +0000, Mel Gorman wrote: > Commit 81c0a2bb ("mm: page_alloc: fair zone allocator policy") solved a > bug whereby new pages could be reclaimed before old pages because of how > the page allocator and kswapd interacted on the per-zone LRU lists. > > Unfortunately a side-effect missed during review was that it's now very > easy to allocate remote memory on NUMA machines. The problem is that > it is not a simple case of just restoring local allocation policies as > there are genuine reasons why global page aging may be prefereable. It's > still a major change to default behaviour so this patch makes the policy > configurable and sets what I think is a sensible default. > > The patches are on top of some NUMA balancing patches currently in -mm. > The first patch in the series is a patch posted by Johannes that must be > taken into account before any of my patches on top. The last patch of the > series is what alters default behaviour and makes the fair zone allocator > policy configurable. > > Sniff test results based on following kernels > > vanilla 3.13-rc3 stock > instrument-v5r1 NUMA balancing patches just to rule out any conflicts there > lruslabonly-v1r2 Patch 1 only > local-v1r2 Full series >
These figures need to be redone. The instrument-v5r1 and later kernels included a debugging patch that increases migration rates to trigger another bug. The figures of local-v1r2 relative to instrument-v5r1 are fine but not relative to 3.13.0-rc3-vanilla
-- Mel Gorman SUSE Labs
|  |