Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 23 May 2008 21:08:54 +0000
From:      Kris Kennaway <kris@FreeBSD.org>
To:        paul beard <paulbeard@gmail.com>
Cc:        questions@freebsd.org
Subject:   Re: kernel debugging: seeing swap issues in 7.0
Message-ID:  <20080523210854.GB20868@hub.freebsd.org>
In-Reply-To: <aeca57d90805231302h5281f0b0ocb26fb8b0a9250fa@mail.gmail.com>
References:  <aeca57d90805231302h5281f0b0ocb26fb8b0a9250fa@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, May 23, 2008 at 01:02:35PM -0700, paul beard wrote:
> I see a lot of these as my system grinds to a halt. It never crashes
> (I reboot it when it gets really boggy . . .
> 
> 
> May 23 11:41:13 stinky kernel: swap_pager: indefinite wait buffer:
> bufobj: 0, blkno: 49155, size: 4096
> May 23 11:41:21 stinky kernel: swap_pager: indefinite wait buffer:
> bufobj: 0, blkno: 48905, size: 4096
> 
> This is the top of the kernel debug
> 
> Unread portion of the kernel message buffer:
> <118>May 23 12:48:46 stinky syslogd: exiting on signal 15
> Waiting (max 60 seconds) for system process `vnlru' to stop...done
> Waiting (max 60 seconds) for system process `bufdaemon' to stop...done
> Waiting (max 60 seconds) for system process `syncer' to stop...
> Syncing disks, vnodes remaining...1 0 0 done
> All buffers synced.
> swap_pager: I/O error - pagein failed; blkno 35668,size 4096, error 5
> panic: swap_pager_force_pagein: read from swap failed
> Uptime: 14h20m56s
> Physical memory: 115 MB
> Dumping 37 MB: 22 6
> #0  doadump () at pcpu.h:195
> 195             __asm __volatile("movl %%fs:0,%0" : "=r" (td));
> 
> I have partition-based swap and swap files I set up after gcc was
> running out of memory.
> 
> Device:       1048576-blocks      Used:
> /dev/ad0s2b          139              0
> /dev/md0              128              0
> 
> Any ideas what I can do (besides buy more hardware)?

You can try increasing the timeout by editing the relevant kernel
source, but if it's failing to reply to the I/O after 30 seconds then
something is drastically overloaded on your system.

Kris



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080523210854.GB20868>