From: Andrew Morton <akpm@linux-foundation.org>
To: Christoph Lameter <cl@linux.com>
Cc: npiggin@kernel.dk, Pekka Enberg <penberg@cs.helsinki.fi>,
David Rientjes <rientjes@google.com>,
linux-mm@kvack.org, Andi Kleen <andi@firstfloor.org>
Subject: Re: vmscan: Do not run shrinkers for zones other than ZONE_NORMAL
Date: Thu, 21 Oct 2010 13:14:28 -0700 [thread overview]
Message-ID: <20101021131428.f2f7214a.akpm@linux-foundation.org> (raw)
In-Reply-To: <alpine.DEB.2.00.1010211455100.30295@router.home>
On Thu, 21 Oct 2010 15:03:32 -0500 (CDT)
Christoph Lameter <cl@linux.com> wrote:
> On Thu, 21 Oct 2010, Andrew Morton wrote:
>
> > The patch doesn't patch direct reclaim, in do_try_to_free_pages(). How
> > come?
>
> Direct reclaim does not run node specific shrink_slab. Direct reclaim does
> a general pass after the individual zones have been shrunk.
>
> > OK, maybe this. Suppose we have a machine with 800M lowmem and 200M
> > highmem. And suppose the lowmem region is stuffed full of clean
> > icache/dcache. A __GFP_HIGHMEM allocation should put pressure on
> > lowmem to get some of those pages back. What we don't want to do is to
> > keep on reclaiming the highmem zone and allocating pages from there,
> > because the machine would effectively end up with only 200M available
> > for pagecache.
>
> Shrinker reclaim is not zone specific. It either occurs on a node or on
> the system as a whole. A failure of HIGHMEM allocation in the direct
> reclaim path will result in shrinkers being called with NO_NUMA_NODE and
> therefore global reclaim will take place everywhere.
>
> Per node reclaim occurs from kswapd and covers all zones of that node.
>
> > Please convince us that your patch doesn't screw up zone balancing?
>
> There are no slab allocations in HIGHMEM or MOVABLE. Nothing to balance
> there.
>
The patch changes balance_pgdat() to not shrink slab when inspecting
the highmem zone. It will therefore change zone balancing behaviour on
a humble 1G laptop, will it not?
--
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>
next prev parent reply other threads:[~2010-10-21 20:15 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
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 [this message]
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=20101021131428.f2f7214a.akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=cl@linux.com \
--cc=linux-mm@kvack.org \
--cc=npiggin@kernel.dk \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.