On Wed, 10 Jan 2007, Jim C. Nasby wrote:
>>>> RAID1 for those of you who have been wondering if the BBU write back cache
>>>> mitigates the need for separate WAL (at least on this workload). Those
>>>> are
>>>> the fastest times for each config, but ext2 WAL was always faster than the
>>>> other two options. I didn't test any other filesystems in this go around.
>>>
>>> Uh, if I'm reading this correctly, you're saying that WAL on a separate
>>> ext2 vs. one big ext3 with data=writeback saved ~39 seconds out of
>>> ~158.5 minutes, or 0.4%? Is that even above the noise for your
>>> measurements? I suspect the phase of the moon might play a bigger role
>>> ;P
>>
>> That's what I thought too...cept I ran it 20 times and ext2 won by that
>> margin every time, so it was quite repeatable. :-/
>
> Even so, you've got to really be hunting for performance to go through
> the hassle of different filesystems just to gain 0.4%... :)
Indeed, but actually, I did the math again and it appears that it saves close
to 2 minutes versus one big ext3. I guess the moral of the story is that
having a separate pg_xlog even on the same physical volume tends to be
slightly faster for write oriented workloads. Ext2 is slightly faster than
ext3, but of course you could likely go with another filesystem yet and be
even slightly faster as well. :-)
I guess the real moral of the story is that you can probably use one big ext3
with the default config and it won't matter much more than 1-2% if you have a
BBU.
--
Jeff Frost, Owner <jeff@frostconsultingllc.com>
Frost Consulting, LLC http://www.frostconsultingllc.com/
Phone: 650-780-7908 FAX: 650-649-1954