The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Jeff Garzik <jgarzik@mandrakesoft.com>
To: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Cc: Alexander Viro <viro@math.psu.edu>,
	Linus Torvalds <torvalds@transmeta.com>,
	Marcelo Tosatti <marcelo@conectiva.com.br>
Subject: Re: pre6 oom killer oops
Date: Wed, 31 Oct 2001 09:27:45 -0500	[thread overview]
Message-ID: <3BE00A61.EAA52CE1@mandrakesoft.com> (raw)
In-Reply-To: <Pine.GSO.4.21.0110310916210.5536-100000@weyl.math.psu.edu>

Alexander Viro wrote:
> 
> On Wed, 31 Oct 2001, Jeff Garzik wrote:
> 
> > further comments #2:
> >
> > when rebooting, there was some disk corruption in the ext2 filesystem.
> >
> > It is my guess that this is to the large number of buffers in the vmstat
> > output, which I believe are dirty buffers that never got written out
> 
> Judging by your log it's not an OOM - page table corruption got caught by
> do_wp_page(), which means that handle_mm_fault() fails (surprise, surprise),
> which kills the process.
> 
> Looks like a massive memory corruption - later it fscked you in pte_alloc()
> and then it screwed buffer cache lists.

I'm reinstalling now, with a bad blocks check, to make sure random disk
crap isn't affecting things.  Disk is good AFAIK.  Vaguely recent ATA-33
drive.  I'll switch to the other alpha to see if I can see similar
symptoms.  

Unfortunately I don't know of a good alpha memory tester like
memtest86.  SRM firmware tests memory ok, but that probably doesn't mean
much.

Final comment before leaving this machine.  Restarting the rpm-rebuilder
(post reboot and fsck), I still see a very large number of buffs.  Since
there is zero swapped, this may or may not be normal.  The cache value
appears sane, FWIW.


   procs                      memory    swap          io    
system         cpu
 r  b  w   swpd   free   buff  cache  si  so    bi    bo   in    cs  us 
sy  id
 2  0  0      0  35024  13016 267256   0   0     3   491 1046   136  84 
12   4
 1  0  0      0 106776  14864 191984   0   0   380     0 1903   696  13 
20  67
 3  0  0      0  85448  16424 210216   0   0   239    11 1066  1305  58 
25  17
 1  0  0      0  83624  16560 210712   0   0   107    21 1068   550  54 
25  21
 1  0  0      0  81952  16600 211224   0   0     3     0 1030    96 
93   6   0
 1  0  0      0  78720  16704 212080   0   0   144    11 1045   118  79 
12   9
 2  0  0      0  79608  16728 212400   0   0    30     0 1037   108 
86   8   5
 1  0  0      0  73288  16792 212736   0   0    35    11 1039    84 
91   5   4
 1  0  0      0  71784  16792 212736   0   0     0    11 1038    25 
99   1   0
 1  0  0      0  81560  16944 214840   0   0   446     0 1049   259  70 
19  11
 1  0  0      0  76920  16984 215480   0   0     4     0 1031   487  75 
24   1
 1  0  0      0  79384  17016 215600   0   0     0     0 1029    23 
94   6   0
 0  1  1      0  79432  17056 215976   0   0    12  1396 1132   188  48 
12  40
 0  1  1      0  79384  17056 216008   0   0    11  4542 1107    14  
0   2  98
 1  0  0      0  74400  17128 216984   0   0   331   217 1090   269  25 
10  65
 2  0  0      0  70456  17136 217064   0   0     0   288 1030   119 
96   4   0
 1  0  0      0  72200  17152 217176   0   0     0     0 1050    96 
97   3   0
 1  0  0      0  67232  17152 217264   0   0     0   107 1041    93 
98   2   0
 1  0  0      0  70072  17160 217416   0   0     0     0 1029    91 
97   3   0
 1  0  0      0  68272  17168 217496   0   0     0    75 1035   122 
96   4   0

-- 
Jeff Garzik      | Only so many songs can be sung
Building 1024    | with two lips, two lungs, and one tongue.
MandrakeSoft     |         - nomeansno


  reply	other threads:[~2001-10-31 14:27 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-10-31 13:45 pre6 oom killer oops Jeff Garzik
2001-10-31 13:52 ` Jeff Garzik
2001-10-31 14:12   ` Jeff Garzik
2001-10-31 14:18     ` Alexander Viro
2001-10-31 14:27       ` Jeff Garzik [this message]
2001-10-31 15:43         ` Linus Torvalds
2001-10-31 15:28 ` Linus Torvalds

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=3BE00A61.EAA52CE1@mandrakesoft.com \
    --to=jgarzik@mandrakesoft.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marcelo@conectiva.com.br \
    --cc=torvalds@transmeta.com \
    --cc=viro@math.psu.edu \
    /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