linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
To: Christoph Lameter <clameter@sgi.com>
Cc: Aubrey Li <aubreylee@gmail.com>,
	Nick Piggin <nickpiggin@yahoo.com.au>,
	Robin Getz <rgetz@blackfin.uclinux.org>,
	"Henn, erich, Michael" <Michael.Hennerich@analog.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC] Limit the size of the pagecache
Date: Wed, 24 Jan 2007 18:03:12 +0530	[thread overview]
Message-ID: <45B75208.90208@linux.vnet.ibm.com> (raw)
In-Reply-To: <Pine.LNX.4.64.0701231645260.5239@schroedinger.engr.sgi.com>


Christoph Lameter wrote:
> This is a patch using some of Aubrey's work plugging it in what is IMHO
> the right way. Feel free to improve on it. I have gotten repeatedly
> requests to be able to limit the pagecache. With the revised VM statistics
> this is now actually possile. I'd like to know more about possible uses of
> such a feature.
> 
> 

[snip]

Hi Christoph,

With your patch, MMAP of a file that will cross the pagecache limit hangs the
system.  As I mentioned in my previous mail, without subtracting the
NR_FILE_MAPPED, the reclaim will infinitely try and fail.

I have tested your patch with the attached fix on my PPC64 box.

Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>

---
 mm/page_alloc.c |    3 ++-
 mm/vmscan.c     |    3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

--- linux-2.6.20-rc5.orig/mm/page_alloc.c
+++ linux-2.6.20-rc5/mm/page_alloc.c
@@ -1171,7 +1171,8 @@ zonelist_scan:
                                goto try_next_zone;

                if ((gfp_mask & __GFP_PAGECACHE) &&
-                               zone_page_state(zone, NR_FILE_PAGES) >
+                               (zone_page_state(zone, NR_FILE_PAGES) -
+                                zone_page_state(zone, NR_FILE_MAPPED)) >
                                        zone->max_pagecache_pages)
                                goto try_next_zone;

--- linux-2.6.20-rc5.orig/mm/vmscan.c
+++ linux-2.6.20-rc5/mm/vmscan.c
@@ -936,7 +936,8 @@ static unsigned long shrink_zone(int pri
         * If the page cache is too big then focus on page cache
         * and ignore anonymous pages
         */
-       if (sc->may_swap && zone_page_state(zone, NR_FILE_PAGES)
+       if (sc->may_swap && (zone_page_state(zone, NR_FILE_PAGES) -
+                       zone_page_state(zone, NR_FILE_MAPPED))
                        > zone->max_pagecache_pages)
                sc->may_swap = 0;

--
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>

  parent reply	other threads:[~2007-01-25  0:35 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-01-24  0:49 Christoph Lameter
2007-01-24  2:53 ` KAMEZAWA Hiroyuki
2007-01-24  3:01   ` Christoph Lameter
2007-01-24  5:47   ` Aubrey Li
2007-01-24  3:00 ` Nick Piggin
2007-01-24  3:14   ` Christoph Lameter
2007-01-24  3:51     ` Aubrey Li
2007-01-24  4:03       ` Nick Piggin
2007-01-26 10:27         ` Andrew Morton
2007-01-24  3:13 ` KAMEZAWA Hiroyuki
2007-01-24  4:30   ` Christoph Lameter
2007-01-24  5:15     ` KAMEZAWA Hiroyuki
2007-01-25  0:32       ` KAMEZAWA Hiroyuki
2007-01-25  2:41         ` Christoph Lameter
2007-01-25  3:12           ` KAMEZAWA Hiroyuki
2007-01-25  4:28             ` Rik van Riel
2007-01-25  5:19               ` KAMEZAWA Hiroyuki
2007-01-25  5:40                 ` Rik van Riel
2007-01-25  6:00                   ` KAMEZAWA Hiroyuki
2007-01-26 10:29       ` Andrew Morton
2007-01-26 18:01         ` KAMEZAWA Hiroyuki
2007-01-24  7:04 ` Vaidyanathan Srinivasan
2007-01-24  7:55 ` Peter Zijlstra
2007-01-24 12:50   ` Nick Piggin
2007-01-24 12:58     ` Peter Zijlstra
2007-01-24 14:58     ` Christoph Lameter
2007-01-24 20:06       ` Erik Andersen
2007-01-25  2:40         ` Christoph Lameter
2007-01-25  8:07           ` Vaidyanathan Srinivasan
2007-01-24 14:22   ` Aubrey Li
2007-01-24 14:56     ` Peter Zijlstra
2007-01-25  2:27       ` Aubrey Li
2007-01-24 12:33 ` Vaidyanathan Srinivasan [this message]
2007-01-24 14:56   ` Christoph Lameter
2007-01-25  4:17     ` Vaidyanathan Srinivasan
2007-01-25  4:45       ` Rik van Riel
2007-01-25  5:49         ` Vaidyanathan Srinivasan
2007-01-25 16:07           ` Rik van Riel
2007-01-25 17:57             ` Balbir Singh
2007-01-25  6:35       ` Aubrey Li
2007-01-25  6:47         ` Christoph Lameter
2007-01-25  7:49         ` Vaidyanathan Srinivasan
2007-01-25  4:18 ` Rik van Riel
     [not found] <7GEEK-4lH-39@gated-at.bofh.it>
     [not found] ` <7GLdb-5Uz-13@gated-at.bofh.it>
     [not found]   ` <7GRix-7fU-1@gated-at.bofh.it>
     [not found]     ` <7GRLZ-7Uy-29@gated-at.bofh.it>
2007-01-25 14:51       ` Bodo Eggert

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=45B75208.90208@linux.vnet.ibm.com \
    --to=svaidy@linux.vnet.ibm.com \
    --cc=Michael.Hennerich@analog.com \
    --cc=aubreylee@gmail.com \
    --cc=clameter@sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=rgetz@blackfin.uclinux.org \
    /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