On Tue, 18 Jan 2011, Mel Gorman wrote: > > It may be the preferred zone even if it isn't allowed by current's cpuset > > such as if the allocation is __GFP_WAIT or the task has been oom killed > > and has the TIF_MEMDIE bit set, so the preferred zone in the fastpath is > > accurate in these cases. In the slowpath, the former is protected by > > checking for ALLOC_CPUSET and the latter is usually only set after the > > page allocator has looped at least once and triggered the oom killer to be > > killed. > > > > Ok, this is reasonable and is a notable distinction from nodemasks. It's > worth including this in the changelog. > Agreed, and please do s/__GFP_WAIT/!__GFP_WAIT/ for it, too :) > > I didn't want to add a branch to test for these possibilities in the > > fastpath, however, since preferred_zone isn't of critical importance until > > it's used in the slowpath (ignoring the statistical usage). > > > > With these two paragraphs included in the changelog; > > Acked-by: Mel Gorman <mel@xxxxxxxxx> > Thanks, and as Andrew noted: Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx> I'd also suggest this for the -stable tree for 2.6.37.x. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>