linux-kernel - Re: [PATCH v2 06/10] vmscan: make isolate_lru

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 31 May 2011 22:51:29 +0900
From:	Minchan Kim <minchan.kim@...il.com>
To:	Johannes Weiner <hannes@...xchg.org>
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	linux-mm <linux-mm@...ck.org>,
	LKML <linux-kernel@...r.kernel.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
	Mel Gorman <mgorman@...e.de>, Rik van Riel <riel@...hat.com>,
	Andrea Arcangeli <aarcange@...hat.com>
Subject: Re: [PATCH v2 06/10] vmscan: make isolate_lru_page with filter
 aware

On Tue, May 31, 2011 at 03:46:09PM +0200, Johannes Weiner wrote:
> On Mon, May 30, 2011 at 03:13:45AM +0900, Minchan Kim wrote:
> > In __zone_reclaim case, we don't want to shrink mapped page.
> > Nonetheless, we have isolated mapped page and re-add it into
> > LRU's head. It's unnecessary CPU overhead and makes LRU churning.
> > 
> > Of course, when we isolate the page, the page might be mapped but
> > when we try to migrate the page, the page would be not mapped.
> > So it could be migrated. But race is rare and although it happens,
> > it's no big deal.
> > 
> > Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> > Acked-by: Johannes Weiner <hannes@...xchg.org>
> > Cc: Mel Gorman <mgorman@...e.de>
> > Cc: Rik van Riel <riel@...hat.com>
> > Cc: Andrea Arcangeli <aarcange@...hat.com>
> > Signed-off-by: Minchan Kim <minchan.kim@...il.com>
> > ---
> >  mm/vmscan.c |   29 +++++++++++++++++++++--------
> >  1 files changed, 21 insertions(+), 8 deletions(-)
> > 
> > diff --git a/mm/vmscan.c b/mm/vmscan.c
> > index 9972356..39941c7 100644
> > --- a/mm/vmscan.c
> > +++ b/mm/vmscan.c
> > @@ -1395,6 +1395,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
> >  	unsigned long nr_taken;
> >  	unsigned long nr_anon;
> >  	unsigned long nr_file;
> > +	enum ISOLATE_PAGE_MODE mode = ISOLATE_NONE;
> >  
> >  	while (unlikely(too_many_isolated(zone, file, sc))) {
> >  		congestion_wait(BLK_RW_ASYNC, HZ/10);
> > @@ -1406,13 +1407,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
> >  
> >  	set_reclaim_mode(priority, sc, false);
> >  	lru_add_drain();
> > +
> > +	if (!sc->may_unmap)
> > +		mode |= ISOLATE_UNMAPPED;
> > +	if (!sc->may_writepage)
> > +		mode |= ISOLATE_CLEAN;
> > +	mode |= sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
> > +				ISOLATE_BOTH : ISOLATE_INACTIVE;
> 
> Hmm, it would probably be cleaner to fully convert the isolation mode
> into independent flags.  INACTIVE, ACTIVE, BOTH is currently a
> tri-state among flags, which is a bit ugly.
> 
> 	mode = ISOLATE_INACTIVE;
> 	if (!sc->may_unmap)
> 		mode |= ISOLATE_UNMAPPED;
> 	if (!sc->may_writepage)
> 		mode |= ISOLATE_CLEAN;
> 	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
> 		mode |= ISOLATE_ACTIVE;
> 
> What do you think?

It's good point.
Actually, I am trying it for unevictable page migration.
I removed BOTH and insert ISOLATE_UNEVICTABLE.
But it's in my queue and doesn't published yet.
The summary is that I am going on that way.
I will clean up it in v3, too. 

==
Subject: [PATCH 1/2] Cleanup ISOLATE_BOTH

Before 2.6.38, we just had two lru list(active/inactive).
Now we have added one more lru type list. ie, unevictable.
So ISOLATE_BOTH is not clear naming.
This patch removes ISOLATE_BOTH and instead of it,
it require to use more explicit word.

This patch should not change old behavir and it's used by
next patch series.
==

-- 
Kind regards
Minchan Kim
--
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/