Messages in this thread | | | Date | Tue, 10 Jun 2014 17:07:55 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH] sched,numa: always try to migrate to preferred node at task_numa_placement time |
| |
On Fri, Jun 06, 2014 at 02:23:41PM -0400, Rik van Riel wrote: > On 06/06/2014 01:18 PM, Peter Zijlstra wrote:
> > Clearly the retry thing didn't work, what happened? We got to the > > preferred nid, disabled the retry and got moved away again? > > > > Do we want to remove the retry logic in favour of this more aggressive > > form? > > I think we want both. When we have fresh statistics, and we discover > that we are not running on our preferred nid, is there any reason > not to relocate to a better node?
I got confused on the exact details, I thought we ended up calling task_numa_placement() far often than we actually do (well, we do call it as often, but bail early).
Yes this makes sense. [unhandled content-type:application/pgp-signature] | |