Messages in this thread | | | Date | Fri, 12 Jul 2013 11:28:19 +0100 | From | Mel Gorman <> | Subject | Re: [PATCH 08/16] sched: Reschedule task on preferred NUMA node once selected |
| |
On Fri, Jul 12, 2013 at 12:14:08PM +0200, Peter Zijlstra wrote: > On Thu, Jul 11, 2013 at 03:09:14PM +0100, Mel Gorman wrote: > > That might be necessary when the machine is overloaded. As a > > starting point the following should retry the migrate a number of times > > until success. The retry is checked on every fault but should not fire > > more than once every 100ms. > > Yeah, something like that might work. But getting a working imbalance bound is > important. The current very weak direct migration is the only thing that keeps > the system from massively skewing load.
I've corrected a flaw in that proposed patch, pulled in the check for dst load vs src load, and am adding another patch that will fallback to less preferred nodes if task_numa_find_cpu fails to find a suitable CPU.
-- Mel Gorman SUSE Labs
| |