linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Lameter <clameter@sgi.com>
To: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	linux-mm@kvack.org, dkegel@google.com, akpm@linux-foundation.org,
	Nick Piggin <npiggin@suse.de>,
	ak@suse.de, linux-kernel@vger.kernel.org
Subject: Re: [RFC 0/7] Postphone reclaim laundry to write at high water marks
Date: Tue, 21 Aug 2007 15:32:25 -0700 (PDT)	[thread overview]
Message-ID: <Pine.LNX.4.64.0708211521260.5728@schroedinger.engr.sgi.com> (raw)
In-Reply-To: <46CB5C89.2070807@redhat.com>

On Tue, 21 Aug 2007, Rik van Riel wrote:

> Christoph Lameter wrote:
> 
> > I want general improvements to reclaim to address the issues that you see
> > and other issues related to reclaim instead of the strange code that makes
> > PF_MEMALLOC allocs compete for allocations from a single slab and putting
> > logic into the kernel to decide which allocs to fail. We can reclaim after
> > all. Its just a matter of finding the right way to do this. 
> 
> The simplest way of achieving that would be to allow
> recursion of the page reclaim code, under the condition
> that the second level call can only reclaim clean pages,
> while the "outer" call does what the VM does today.

Yes that is what the precursor to this patchset does.

See http://marc.info/?l=linux-mm&m=118710207203449&w=2

This one did not even come up to the level of the earlier one. Sigh.

The way forward may be:

1. Like in the earlier patchset allow reentry to reclaim under 
   PF_MEMALLOC if we are out of all memory.

2. Do the laundry as here but do not write out laundry directly.
   Instead move laundry to a new lru style list in the zone structure.
   This will allow the recursive reclaim to also trigger writeout
   of pages (what this patchset was supposed to accomplish).

3. Perform writeback only from kswapd. Make other threads
   wait on kswapd if memory is low, we can wait and writeback still
   has to progress.

4. Then allow reclaim of GFP_ATOMIC allocs (see
   http://marc.info/?l=linux-kernel&m=118710595617696&w=2). Atomic
   reclaim can then also put pages onto the zone laundry lists from where
   it is going to be picked up and written out by kswapd ASAP. This one
   may be tricky so maybe keep this separate.

--
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:[~2007-08-21 22:32 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-08-20 21:50 Christoph Lameter
2007-08-20 21:50 ` [RFC 1/7] release_lru_pages(): Generic release of pages to the LRU Christoph Lameter
2007-08-21 14:52   ` Mel Gorman
2007-08-21 20:51     ` Christoph Lameter
2007-08-20 21:50 ` [RFC 2/7] Move checks from pageout() to shrink_page_list Christoph Lameter
2007-08-20 21:50 ` [RFC 3/7] shrink_page_list: Support isolating dirty pages on laundry list Christoph Lameter
2007-08-21 15:04   ` Mel Gorman
2007-08-21 20:53     ` Christoph Lameter
2007-08-20 21:50 ` [RFC 4/7] Pass laundry through shrink_inactive_list() and shrink_zone() Christoph Lameter
2007-08-20 21:50 ` [RFC 5/7] Laundry handling for direct reclaim Christoph Lameter
2007-08-21 15:06   ` Mel Gorman
2007-08-21 20:55     ` Christoph Lameter
2007-08-21 15:19   ` Mel Gorman
2007-08-21 21:00     ` Christoph Lameter
2007-08-20 21:50 ` [RFC 6/7] kswapd: Do laundry after reclaim Christoph Lameter
2007-08-20 21:50 ` [RFC 7/7] Switch of PF_MEMALLOC during writeout Christoph Lameter
2007-08-20 23:08   ` Andi Kleen
2007-08-20 23:19     ` Christoph Lameter
2007-08-21  1:13       ` Andi Kleen
2007-08-21 10:36 ` [RFC 0/7] Postphone reclaim laundry to write at high water marks Peter Zijlstra
2007-08-21 20:48   ` Christoph Lameter
2007-08-21 21:13     ` Peter Zijlstra
2007-08-21 21:29       ` Christoph Lameter
2007-08-21 21:43         ` Rik van Riel
2007-08-21 22:32           ` Christoph Lameter [this message]
2007-08-23 12:05             ` Andrea Arcangeli
2007-08-23 20:23               ` Christoph Lameter
2007-08-21 22:09         ` Peter Zijlstra
2007-08-21 22:43           ` Christoph Lameter
2007-08-22  7:02             ` Peter Zijlstra
2007-08-22 19:04               ` Christoph Lameter
2007-08-22 20:03                 ` Peter Zijlstra
2007-08-22 20:16                   ` Christoph Lameter
2007-08-23  7:39                     ` Peter Zijlstra
2007-08-26  4:52                     ` Rik van Riel
2007-08-23 12:16                   ` Andrea Arcangeli
2007-08-22  7:45             ` Ingo Molnar
2007-08-22 19:19               ` Christoph Lameter
2007-08-23 12:08           ` Andrea Arcangeli
2007-08-23 12:59             ` Peter Zijlstra
2007-08-21 15:16 ` Rik van Riel
2007-08-21 20:59   ` Christoph Lameter
2007-08-21 21:14     ` Rik van Riel
2007-08-21 21:30       ` Christoph Lameter
2007-08-21 15:51 ` Dave McCracken
2007-08-21 21:03   ` 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=Pine.LNX.4.64.0708211521260.5728@schroedinger.engr.sgi.com \
    --to=clameter@sgi.com \
    --cc=ak@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=dkegel@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=npiggin@suse.de \
    --cc=peterz@infradead.org \
    --cc=riel@redhat.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