[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20090716132639.9D31.A69D9226@jp.fujitsu.com>
Date: Thu, 16 Jul 2009 13:35:07 +0900 (JST)
From: KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: kosaki.motohiro@...fujitsu.com,
LKML <linux-kernel@...r.kernel.org>,
linux-mm <linux-mm@...ck.org>,
Wu Fengguang <fengguang.wu@...el.com>,
Rik van Riel <riel@...hat.com>,
Minchan Kim <minchan.kim@...il.com>,
Christoph Lameter <cl@...ux-foundation.org>
Subject: Re: [PATCH 3/3] add isolate pages vmstat
> > reproduce way
> > -----------------------
> > % ./hackbench 140 process 1000
> > => OOM occur
> >
> > active_anon:146 inactive_anon:0 isolated_anon:49245
> > active_file:79 inactive_file:18 isolated_file:113
> > unevictable:0 dirty:0 writeback:0 unstable:0 buffer:39
> > free:370 slab_reclaimable:309 slab_unreclaimable:5492
> > mapped:53 shmem:15 pagetables:28140 bounce:0
> >
> > @@ -1164,6 +1170,9 @@ static unsigned long shrink_inactive_lis
> > spin_lock_irq(&zone->lru_lock);
> > }
> > }
> > + __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
> > + __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
> > +
> > } while (nr_scanned < max_scan);
>
> This is a non-trivial amount of extra stuff. Do we really need it?
In general, Administrator really hate large amount unaccounted memory.
Recent msgctl11 discussion, We faced it isolate pages about 1/3 system
memory.
Ahtough Rik's patch is applied, vmscan can isolate >1GB memory.
That's my point.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists