lkml.org 
[lkml]   [2011]   [May]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] mm: compaction: Abort compaction if too many pages are isolated and caller is asynchronous
On Tue, May 31, 2011 at 01:14:15AM +0900, Minchan Kim wrote:
> On Mon, May 30, 2011 at 02:13:00PM +0100, Mel Gorman 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 <urykhy@gmail.com>
> > Signed-off-by: Mel Gorman <mgorman@suse.de>
> Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
>

Thanks

> I have a nitpick below.
> Otherwise, looks good to me.
>
> > ---
> > mm/compaction.c | 32 ++++++++++++++++++++++++++------
> > 1 files changed, 26 insertions(+), 6 deletions(-)
> >
> > diff --git a/mm/compaction.c b/mm/compaction.c
> > index 021a296..331a2ee 100644
> > --- a/mm/compaction.c
> > +++ b/mm/compaction.c
> > @@ -240,11 +240,20 @@ static bool too_many_isolated(struct zone *zone)
> > return isolated > (inactive + active) / 2;
> > }
> >
> > +/* possible outcome of isolate_migratepages */
> > +typedef enum {
> > + ISOLATE_ABORT, /* Abort compaction now */
> > + ISOLATE_NONE, /* No pages isolated, continue scanning */
> > + ISOLATE_SUCCESS, /* Pages isolated, migrate */
> > +} isolate_migrate_t;
> > +
> > /*
> > * Isolate all pages that can be migrated from the block pointed to by
> > * the migrate scanner within compact_control.
> > + *
> > + * Returns false if compaction should abort at this point due to congestion.
>
> false? I think it would be better to use explicit word, ISOLATE_ABORT.
>

Oops, thanks for pointing that out. I'll post a V2 once it has been
figured out why NR_ISOLATE_* is getting screwed up on !CONFIG_SMP.

--
Mel Gorman
SUSE Labs


\
 
 \ /
  Last update: 2011-05-31 10:35    [W:0.126 / U:0.596 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site