From: | Alex Turner <armtuk(at)gmail(dot)com> |
---|---|
To: | Merlin Moncure <merlin(dot)moncure(at)rcsonline(dot)com> |
Cc: | pgsql-performance(at)postgresql(dot)org, Arshavir Grigorian <ag(at)m-cam(dot)com> |
Subject: | Re: Postgres on RAID5 |
Date: | 2005-03-14 21:42:07 |
Message-ID: | 33c6269f05031413424d749d5f@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-performance |
He doesn't have a RAID controller, it's software RAID...
Alex Turner
netEconomis
On Mon, 14 Mar 2005 16:18:00 -0500, Merlin Moncure
<merlin(dot)moncure(at)rcsonline(dot)com> wrote:
> Alex Turner wrote:
> > 35 Trans/sec is pretty slow, particularly if they are only one row at
> > a time. I typicaly get 200-400/sec on our DB server on a bad day. Up
> > to 1100 on a fresh database.
>
> Well, don't rule out that his raid controller is not caching his writes.
> His WAL sync method may be overriding his raid cache policy and flushing
> his writes to disk, always. Win32 has the same problem, and before
> Magnus's O_DIRECT patch, there was no way to easily work around it
> without turning fsync off. I'd suggest playing with different WAL sync
> methods before trying anything else.
>
> Merli
>
From | Date | Subject | |
---|---|---|---|
Next Message | Michael Tokarev | 2005-03-14 22:47:16 | Re: Postgres on RAID5 |
Previous Message | Alex Turner | 2005-03-14 21:31:03 | Re: Postgres on RAID5 |