Re: Tuning scenarios (was Changing the default

From: Andrew Sullivan <andrew(at)libertyrms(dot)info>
To: pgsql-performance(at)postgresql(dot)org
Subject: Re: Tuning scenarios (was Changing the default
Date: 2003-02-20 23:49:28
Message-ID: 20030220184928.D30080@mail.libertyrms.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-advocacy pgsql-hackers pgsql-performance

On Thu, Feb 20, 2003 at 06:35:44PM -0500, Robert Treat wrote:
> Do you know how well those numbers hold up under scsi and/ or raid based
> system? (I'd assume anyone doing serious work would run scsi)

On some Sun E450s we have used, the machines are unusable for any
load with xlog on the same disk (in the case I'm remembering, these
are older 5400 RPM drives). Moving the xlog changed us for
<hazymemory>something like 10tps to something like 30tps</hazymemory>
in one seat-of-the-pants case. Sorry I can't be more specific.

> ok (playing a bit of devil's advocate here), but you have two possible
> points of failure, the data disk and the xlog disk. If either one goes,
> your in trouble. OTOH if you put the OS disk on one drive and it goes,
> your database and xlog are still safe on the other drive.

If you're really worried about that, use RAID 1+0.

A

--
----
Andrew Sullivan 204-4141 Yonge Street
Liberty RMS Toronto, Ontario Canada
<andrew(at)libertyrms(dot)info> M2P 2A8
+1 416 646 3304 x110

In response to

Browse pgsql-advocacy by date

  From Date Subject
Next Message Bruno Wolff III 2003-02-21 04:13:19 Can someone respond to LWN comment?
Previous Message Robert Treat 2003-02-20 23:35:44 Re: Tuning scenarios (was Changing the default

Browse pgsql-hackers by date

  From Date Subject
Next Message Josh Berkus 2003-02-21 00:06:39 Re: request for sql3 compliance for the update command
Previous Message Robert Treat 2003-02-20 23:35:44 Re: Tuning scenarios (was Changing the default

Browse pgsql-performance by date

  From Date Subject
Next Message Christopher Kings-Lynne 2003-02-21 01:45:24 Re: cost and actual time
Previous Message Robert Treat 2003-02-20 23:35:44 Re: Tuning scenarios (was Changing the default