Hi Kame, On Tue, May 31, 2011 at 01:48:35PM +0900, KAMEZAWA Hiroyuki wrote: > On Mon, 30 May 2011 14:13:00 +0100 > Mel Gorman <[email protected]> wrote: > > > Asynchronous compaction is used when promoting to huge pages. This is > > all very nice but if there are a number of processes in compacting > > memory, a large number of pages can be isolated. An "asynchronous" > > process can stall for long periods of time as a result with a user > > reporting that firefox can stall for 10s of seconds. This patch aborts > > asynchronous compaction if too many pages are isolated as it's better to > > fail a hugepage promotion than stall a process. > > > > If accepted, this should also be considered for 2.6.39-stable. It should > > also be considered for 2.6.38-stable but ideally [11bc82d6: mm: > > compaction: Use async migration for __GFP_NO_KSWAPD and enforce no > > writeback] would be applied to 2.6.38 before consideration. > > > > Reported-and-Tested-by: Ury Stankevich <[email protected]> > > Signed-off-by: Mel Gorman <[email protected]> > > > > Reviewed-by: KAMEZAWA Hiroyuki <[email protected]> > > BTW, I'm surprised to see both of vmscan.c and compaction.c has > too_many_isolated().. > in different logic ;) > > BTW, compaction ignores UNEVICTABLE LRU ?
Good point. Yes. now compaction doesn't work with unevictable LRU but I think we have no reason to work well with unveictable pages. If we don't support unevictable lru, it would be a problem in lots of mlocked pages workload. It would be a good enhance point on compaction. > > Thanks, > -Kame -- Kind regards Minchan Kim _______________________________________________ stable mailing list [email protected] http://linux.kernel.org/mailman/listinfo/stable
