Message-ID: <437355C6.4030604@archonet.com>
Date: Thu, 10 Nov 2005 14:14:30 +0000
From: Richard Huxton <dev@archonet.com>
User-Agent: Mozilla Thunderbird 1.0.7 (X11/20051013)
MIME-Version: 1.0
To: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: WAL sync behaviour
References: <20051110133241.GA4031@uio.no>
In-Reply-To: <20051110133241.GA4031@uio.no>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit

Steinar H. Gunderson wrote:
> Hi,
> 
> We're having problems with our PostgreSQL server using forever for simple
> queries, even when there's little load -- or rather, the transactions seem
> to take forever to commit. We're using 8.1 (yay!) on a single Opteron, with
> WAL on the system two-disk (software) RAID-1, separate from the database
> four-disk RAID-10. All drives are 10000rpm SCSI disks, with write cache
> turned off; we value our data :-) We're running Linux 2.6.13.4, with 64-bit
> kernel but 32-bit userspace.

You're beyond my area of expertise, but I do know that someone's going 
to ask what filesystem this is (ext2/xfs/etc). And probably to see the 
strace too.

Hmm - the only things I can think to check:
Do vmstat/iostat show any unusual activity?
Are your system logs on these disks too?
Could it be the journalling on the fs clashing with the WAL?

--
   Richard Huxton
   Archonet Ltd