From: | "Scott Marlowe" <scott(dot)marlowe(at)gmail(dot)com> |
---|---|
To: | "John Huttley" <John(at)mib-infotech(dot)co(dot)nz> |
Cc: | pgsql-performance(at)postgresql(dot)org |
Subject: | Re: Slow updates, poor IO |
Date: | 2008-09-27 22:54:20 |
Message-ID: | dcc563d10809271554wd20049ch5fee8f02b8a06d34@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
On Sat, Sep 27, 2008 at 4:33 PM, John Huttley <John(at)mib-infotech(dot)co(dot)nz> wrote:
>
> > > this is part of the trade-offs of MVCC.
>
> > was... was a part of the trade-offs.
>
> You are thinking of HOT?
> I don't think it applies in the case of full table updates??
Sure, you just need a table with plenty of empty space in it, either
from vacuumed previous deletes / inserts or with a low fill factor
like 50%.
> It's really an effect of parallel updates / writes / accesses, and is
> always an issue for a database running on a poor storage subsystem. A
> db with a two drive mirror set is always going to be at a disadvantage
> to one running on a dozen or so drives in a RAID-10
>
> Oh well, I'm forever going to be disadvantaged.
Why? A decent caching raid controller and a set of 4 to 8 SATA drives
can make a world of difference and the cost is not that high for the
gain in performance. Even going to 4 drives in a software RAID-10 can
make a lot of difference in these situations, and that can be done
with spare machines and hard drives.
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2008-09-28 14:33:08 | Re: Slow updates, poor IO |
Previous Message | John Huttley | 2008-09-27 22:33:56 | Re: Slow updates, poor IO |