Messages in this thread | | | Date | Tue, 31 Jul 2012 17:56:11 -0400 | From | Rik van Riel <> | Subject | Re: [PATCH 18/19] sched, numa: Per task memory placement for big processes |
| |
On 07/31/2012 03:12 PM, Peter Zijlstra wrote: > Probability says that the task faulting on a page after we protect it, > is most likely to be the task that uses that page most. > > To decrease the likelyhood of acting on a false relation, we only > migrate a page when two consecutive samples are from the same task. > > I'm still not entirely convinced this scheme is sound, esp. for things > like virtualization and n:m threading solutions in general the > compute<->task relation is fundamentally untrue.
Again, we may need some additional code on top in the future, eg. something like Andrea's policy that tries grouping related tasks/threads together, but this looks like a very good way to start.
We can introduce complexity if it is needed. Simplicity is good.
Acked-by: Rik van Riel
-- All rights reversed
| |