Messages in this thread | | | Date | Fri, 7 Nov 2008 10:42:42 +0000 | From | Mel Gorman <> | Subject | Re: [RFC][PATCH] mm: the page of MIGRATE_RESERVE don't insert into pcp |
| |
On Fri, Nov 07, 2008 at 10:42:24AM +0900, KAMEZAWA Hiroyuki wrote: > On Thu, 6 Nov 2008 16:46:45 +0000 > Mel Gorman <mel@csn.ul.ie> wrote: > > > otherwise, the system have unnecessary memory starvation risk > > > because other cpu can't use this emergency pages. > > > > > > > > > > > > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> > > > CC: Mel Gorman <mel@csn.ul.ie> > > > CC: Christoph Lameter <cl@linux-foundation.org> > > > > > > > This patch seems functionally sound but as Christoph points out, this > > adds another branch to the fast path. Now, I ran some tests and those that > > completed didn't show any problems but adding branches in the fast path can > > eventually lead to hard-to-detect performance problems. > > > dividing pcp-list into MIGRATE_TYPES is bad ?
I do not understand what your question is.
> If divided, we can get rid of scan. >
I don't know what you are saying here either. I think you are saying that we should avoid scanning the PCP lists for migrate types at all. That hurts anti-fragmentation as pages can be badly placed if any pcp page is used.
-- Mel Gorman Part-time Phd Student Linux Technology Center University of Limerick IBM Dublin Software Lab
| |