mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
Cc: kas@fi.muni.cz, nickpiggin@yahoo.com.au,
	linux-kernel@vger.kernel.org, bharata@in.ibm.com
Subject: Re: 2.6.14 kswapd eating too much CPU
Date: Sun, 27 Nov 2005 15:21:08 -0800	[thread overview]
Message-ID: <20051127152108.11f58f9c.akpm@osdl.org> (raw)
In-Reply-To: <20051127160207.GE21383@logos.cnet>

Marcelo Tosatti <marcelo.tosatti@cyclades.com> wrote:
>
> It does seem to scan SLABs intensively:
>

It might be worth trying the below.  Mainly for the debugging check.


From: Andrea Arcangeli <andrea@suse.de>

Greg Edwards found some deadlock in the icache shrinker.

I believe the major bug is that the VM is currently potentially setting nr
= LONG_MAX before shrinking the icache (and the icache shrinker never
returns -1, which means the api doesn't currently require shrinkers to
return -1 when they're finished).

The below is the most obviously safe way I could address this problem
(still untested).

This is not necessairly the way we want to fix it in mainline, but it at
least shows what I believe to be the major cuplrit in the code (i.e.  nr
growing insane ;).

Signed-off-by: Andrea Arcangeli <andrea@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 mm/vmscan.c |   18 +++++++++++++++---
 1 files changed, 15 insertions(+), 3 deletions(-)

diff -puN mm/vmscan.c~shrinker-nr-=-long_max-means-deadlock-for-icache mm/vmscan.c
--- devel/mm/vmscan.c~shrinker-nr-=-long_max-means-deadlock-for-icache	2005-11-19 02:53:18.000000000 -0800
+++ devel-akpm/mm/vmscan.c	2005-11-19 03:00:25.000000000 -0800
@@ -201,13 +201,25 @@ static int shrink_slab(unsigned long sca
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		unsigned long long delta;
 		unsigned long total_scan;
+		unsigned long max_pass = (*shrinker->shrinker)(0, gfp_mask);
 
 		delta = (4 * scanned) / shrinker->seeks;
-		delta *= (*shrinker->shrinker)(0, gfp_mask);
+		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
 		shrinker->nr += delta;
-		if (shrinker->nr < 0)
-			shrinker->nr = LONG_MAX;	/* It wrapped! */
+		if (shrinker->nr < 0) {
+			printk(KERN_ERR "%s: nr=%ld\n",
+					__FUNCTION__, shrinker->nr);
+			shrinker->nr = max_pass;
+		}
+
+		/*
+		 * Avoid risking looping forever due to too large nr value:
+		 * never try to free more than twice the estimate number of
+		 * freeable entries.
+		 */
+		if (shrinker->nr > max_pass * 2)
+			shrinker->nr = max_pass * 2;
 
 		total_scan = shrinker->nr;
 		shrinker->nr = 0;
_


  reply	other threads:[~2005-11-27 23:21 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-11-22 12:59 Jan Kasprzak
2005-11-23  0:35 ` Andrew Morton
2005-11-23  1:01   ` Jan Kasprzak
2005-11-23  2:19     ` Nick Piggin
2005-11-23  5:13       ` Jan Kasprzak
2005-11-23 13:14         ` Jan Kasprzak
2005-11-23 19:02           ` Andrew Morton
2005-11-23 20:24             ` Jan Kasprzak
2005-11-23 20:32               ` Jesper Juhl
2005-11-23 20:34                 ` Jan Kasprzak
2005-11-23 20:35               ` Andrew Morton
2005-11-24  8:31                 ` Jan Kasprzak
2005-11-27  8:42                   ` Marcelo Tosatti
2005-11-27 20:39                     ` Jan Kasprzak
2005-11-27 15:45                       ` Marcelo Tosatti
2005-11-27 16:02                       ` Marcelo Tosatti
2005-11-27 23:21                         ` Andrew Morton [this message]
2005-11-28 13:16                           ` Jan Kasprzak
2005-11-28  8:04                             ` Marcelo Tosatti
2005-12-06  0:10                               ` Jan Kasprzak
2005-12-06 18:14                                 ` Marcelo Tosatti

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=20051127152108.11f58f9c.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=bharata@in.ibm.com \
    --cc=kas@fi.muni.cz \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marcelo.tosatti@cyclades.com \
    --cc=nickpiggin@yahoo.com.au \
    /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

all inboxes | Powered by JetHome®