linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Alastair Stevens <alastair@altruxsolutions.co.uk>
Cc: Con Kolivas <kernel@kolivas.org>, linux-kernel@vger.kernel.org
Subject: Re: 2.6.9-ck1: swap mayhem under UT2004
Date: Sun, 24 Oct 2004 12:59:11 +1000	[thread overview]
Message-ID: <417B1A7F.2020607@yahoo.com.au> (raw)
In-Reply-To: <200410231722.59362.alastair@altruxsolutions.co.uk>

[-- Attachment #1: Type: text/plain, Size: 1857 bytes --]

Alastair Stevens wrote:
> On Saturday 23 October 2004 7:00, Nick Piggin wrote:
> 
>>Alastair, can you compile sysrq support into the kernel, and
>>press Alt+SysRq+M when kswapd is going crazy. Then send me
>>the output of `dmesg`. That would be very helpful.
> 
> 
> OK, here she is.....
> 
> It certainly doesn't do it _every_ time.  Going into X and straight into 
> UT2004 seems fine; but once other apps are loaded and memory is tighter, 
> off it goes into a frenzy.
> 
> Hope this is useful - thanks for your help!
> 

Yep it's great, thanks.

> SysRq : Show Memory
> Mem-info:
> DMA per-cpu:
> cpu 0 hot: low 2, high 6, batch 1
> cpu 0 cold: low 0, high 2, batch 1
> Normal per-cpu:
> cpu 0 hot: low 32, high 96, batch 16
> cpu 0 cold: low 0, high 32, batch 16
> HighMem per-cpu: empty
> 
> Free pages:        3596kB (0kB HighMem)
> Active:97415 inactive:15328 dirty:2 writeback:0 unstable:0 free:899 
> slab:2384 mapped:90021 pagetables:523
> DMA free:20kB min:20kB low:40kB high:60kB active:2080kB inactive:0kB 
> present:16384kB
> protections[]: 0 0 0
> Normal free:3576kB min:700kB low:1400kB high:2100kB active:387580kB 
> inactive:61312kB present:507888kB
> protections[]: 0 0 0
> HighMem free:0kB min:128kB low:256kB high:384kB active:0kB inactive:0kB 
> present:0kB
> protections[]: 0 0 0
> DMA: 1*4kB 0*8kB 1*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 
> 0*2048kB 0*4096kB = 20kB
> Normal: 2*4kB 56*8kB 51*16kB 40*32kB 6*64kB 1*128kB 0*256kB 1*512kB 
> 0*1024kB 0*2048kB 0*4096kB = 3576kB
> HighMem: empty
> Swap cache: add 697, delete 476, find 139/162, race 0+0
> Free swap:       1660584kB
> 131068 pages of RAM
> 0 pages of HIGHMEM
> 2408 reserved pages
> 86381 pages shared
> 221 pages swap cached
> 

Can you try the following patch to start with, please?
(against 2.6.10-rc1, but should apply to most recent kernels I think)

[-- Attachment #2: vm-pages_scanned-active_list.patch --]
[-- Type: text/x-patch, Size: 791 bytes --]




---

 linux-2.6-npiggin/mm/vmscan.c |    2 +-
 1 files changed, 1 insertion(+), 1 deletion(-)

diff -puN mm/memory.c~vm-pages_scanned-active_list mm/memory.c
diff -puN mm/vmscan.c~vm-pages_scanned-active_list mm/vmscan.c
--- linux-2.6/mm/vmscan.c~vm-pages_scanned-active_list	2004-10-24 12:56:25.000000000 +1000
+++ linux-2.6-npiggin/mm/vmscan.c	2004-10-24 12:57:14.000000000 +1000
@@ -574,7 +574,6 @@ static void shrink_cache(struct zone *zo
 			nr_taken++;
 		}
 		zone->nr_inactive -= nr_taken;
-		zone->pages_scanned += nr_taken;
 		spin_unlock_irq(&zone->lru_lock);
 
 		if (nr_taken == 0)
@@ -675,6 +674,7 @@ refill_inactive_zone(struct zone *zone, 
 		}
 		pgscanned++;
 	}
+	zone->pages_scanned += pgscanned;
 	zone->nr_active -= pgmoved;
 	spin_unlock_irq(&zone->lru_lock);
 

_

  reply	other threads:[~2004-10-24  2:59 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-10-22 22:46 2.6.9-ck1: swap mayhem under UT2004 Alastair Stevens
2004-10-23  0:03 ` Con Kolivas
2004-10-23  2:52   ` Lee Revell
2004-10-23  5:34   ` Nick Piggin
2004-10-23  5:38     ` Con Kolivas
2004-10-23  6:00       ` Nick Piggin
2004-10-23 16:22         ` Alastair Stevens
2004-10-24  2:59           ` Nick Piggin [this message]
2004-10-24 10:38             ` Alastair Stevens
2004-10-24 12:28               ` Nick Piggin
2004-10-25 16:31                 ` misty-

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=417B1A7F.2020607@yahoo.com.au \
    --to=nickpiggin@yahoo.com.au \
    --cc=alastair@altruxsolutions.co.uk \
    --cc=kernel@kolivas.org \
    --cc=linux-kernel@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).