Re: moving pg_xlog -- yeah, it's worth it!

On Thu, Feb 11, 2010 at 4:29 AM, Bruce Momjian <bruce(at)momjian(dot)us> wrote:
> Kevin Grittner wrote:
>> Jesper Krogh <jesper(at)krogh(dot)cc> wrote:
>>
>> > Sorry if it is obvious.. but what filesystem/OS are you using and
>> > do you have BBU-writeback on the main data catalog also?
>>
>> Sorry for not providing more context.
>>
>> ATHENA:/var/pgsql/data # uname -a
>> Linux ATHENA 2.6.16.60-0.39.3-smp #1 SMP Mon May 11 11:46:34 UTC
>> 2009 x86_64 x86_64 x86_64 GNU/Linux
>> ATHENA:/var/pgsql/data # cat /etc/SuSE-release
>> SUSE Linux Enterprise Server 10 (x86_64)
>> VERSION = 10
>> PATCHLEVEL = 2
>>
>> File system is xfs noatime,nobarrier for all data; OS is on ext3.  I
>> *think* the pg_xlog mirrored pair is hanging off the same
>> BBU-writeback controller as the big RAID, but I'd have to track down
>> the hardware tech to confirm, and he's out today.  System has 16
>> Xeon CPUs and 64 GB RAM.
>
> I would be surprised if the RAID controller had a BBU-writeback cache.
> I don't think having xlog share a BBU-writeback makes things slower, and
> if it does, I would love for someone to explain why.

I believe in the past when this discussion showed up it was mainly due
to them being on the same file system (and then not with pg_xlog
separate) that made the biggest difference. I recall there being a
noticeable performance gain from having two file systems on the same
logical RAID device even.