linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Nick Piggin <npiggin@kernel.dk>
To: Christoph Lameter <cl@linux.com>
Cc: Christoph Hellwig <hch@infradead.org>,
	Nick Piggin <npiggin@kernel.dk>,
	akpm@linux-foundation.org, Pekka Enberg <penberg@cs.helsinki.fi>,
	David Rientjes <rientjes@google.com>,
	linux-mm@kvack.org, Andi Kleen <andi@firstfloor.org>
Subject: Re: shrinkers: Add node to indicate where to target shrinking
Date: Sun, 24 Oct 2010 12:42:56 +1100	[thread overview]
Message-ID: <20101024014256.GD3168@amd> (raw)
In-Reply-To: <alpine.DEB.2.00.1010221121550.22051@router.home>

On Fri, Oct 22, 2010 at 11:32:37AM -0500, Christoph Lameter wrote:
> On Fri, 22 Oct 2010, Christoph Hellwig wrote:
> >
> > I think making shrinking decision per-zone is fine.  But do we need to
> > duplicate all the lru lists and infrastructure per-zone for that instead
> > of simply per-zone?   Even with per-node lists we can easily skip over
> > items from the wrong zone.
> >
> > Given that we have up to 6 zones per node currently, and we would mostly
> > use one with a few fallbacks that seems like a lot of overkill.
> 
> Zones can also cause asymmetry in reclaim if per zone reclaim is done.
> 
> Look at the following zone setup of a Dell R910:
> 
> grep "^Node" /proc/zoneinfo
> Node 0, zone      DMA
> Node 0, zone    DMA32
> Node 0, zone   Normal
> Node 1, zone   Normal
> Node 2, zone   Normal
> Node 3, zone   Normal
> 
> A reclaim that does per zone reclaim (but in reality reclaims all objects
> in a node (or worse as most shrinkers do today in the whole system) will
> put 3x the pressure on node 0.

No it doesn't. This is how it works:

node0zoneD has 1% of pagecache for node 0
node0zoneD32 has 9% of pagecache
node0zoneN has 90% of pagecache

If there is a memory shortage in all node0 zones, the first zone will
get 1% of the pagecache scanning pressure, dma32 will get 9% and normal
will get 90%, for equal pressure on each zone.

In my patch, those numbers will pass through to shrinker for each zone,
and ask the shrinker to scan and equal proportion of objects in each of
its zones.

If you have a per node shrinker, you will get asymmetries in pressures
whenever there is not an equal amount of reclaimable objects in all
the zones of a node.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2010-10-24  1:42 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-10-21 17:59 vmscan: Do not run shrinkers for zones other than ZONE_NORMAL Christoph Lameter
2010-10-21 18:00 ` shrinkers: Add node to indicate where to target shrinking Christoph Lameter
2010-10-21 18:12   ` Andi Kleen
2010-10-21 20:57   ` David Rientjes
2010-10-21 21:07     ` Christoph Lameter
2010-10-22 13:27     ` Andi Kleen
2010-10-21 23:58   ` Nick Piggin
2010-10-22 12:12     ` Andi Kleen
2010-10-22 15:55     ` Christoph Hellwig
2010-10-22 16:32       ` Christoph Lameter
2010-10-24  1:42         ` Nick Piggin [this message]
2010-10-25  0:57           ` KOSAKI Motohiro
2010-10-25 14:59           ` Christoph Lameter
2010-11-09  4:03             ` Nick Piggin
2010-10-22 16:46       ` Andi Kleen
2010-10-24  1:31       ` Nick Piggin
2010-11-14  2:26   ` Michel Lespinasse
2010-11-14  7:10     ` KOSAKI Motohiro
2010-11-14 11:05       ` Michel Lespinasse
2010-11-15  0:29         ` KOSAKI Motohiro
2010-10-21 18:13 ` vmscan: Do not run shrinkers for zones other than ZONE_NORMAL Andi Kleen
2010-10-21 18:22   ` Christoph Lameter
2010-10-21 18:27   ` Christoph Lameter
2010-10-21 18:33     ` Andi Kleen
2010-10-21 20:48     ` David Rientjes
2010-10-21 20:54       ` Christoph Lameter
2010-10-21 19:40 ` Andrew Morton
2010-10-21 20:03   ` Christoph Lameter
2010-10-21 20:14     ` Andrew Morton
2010-10-21 20:28       ` Christoph Lameter
2010-10-21 20:36         ` Andrew Morton
2010-10-21 20:49           ` Christoph Lameter
2010-10-21 20:59             ` Andrew Morton
2010-10-21 21:13               ` Christoph Lameter
2010-10-21 21:21                 ` Andrew Morton
2010-10-21 23:04                   ` Christoph Lameter
2010-10-21 23:56 ` Nick Piggin
2010-10-22  1:37 ` KOSAKI Motohiro
2010-10-22 14:06   ` Christoph Lameter
2010-10-24  1:37     ` Nick Piggin
2010-10-25  1:22     ` KOSAKI Motohiro
2010-10-25 15:07       ` Christoph Lameter
2010-10-26  2:52         ` KOSAKI Motohiro
2010-10-26 12:42           ` KOSAKI Motohiro
2010-10-26 13:10           ` Christoph Lameter

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20101024014256.GD3168@amd \
    --to=npiggin@kernel.dk \
    --cc=akpm@linux-foundation.org \
    --cc=andi@firstfloor.org \
    --cc=cl@linux.com \
    --cc=hch@infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=rientjes@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).