Messages in this thread | | | Subject | Re: [RFC PATCH 0/3] Fix SLQB on memoryless configurations V2 | From | Pekka Enberg <> | Date | Tue, 22 Sep 2009 13:21:15 +0300 |
| |
Hi Mel,
On Tue, 2009-09-22 at 11:05 +0100, Mel Gorman wrote: > I'm going to punt the decision on this one to Pekka or Nick. My feeling > is leave it enabled for NUMA so it can be identified if it gets fixed > for some other reason - e.g. the stalls are due to a per-cpu problem as > stated by Sachin and SLQB happens to exasperate the problem.
Can I have a tested patch that uses MAX_NUMNODES to allocate the structs, please? We can convert SLQB over to per-cpu allocator if the memoryless node issue is resolved.
Pekka
| |