From: Jan Dittmer <j.dittmer@portrix.net>
To: Greg Stark <gsstark@mit.edu>
Cc: Joshua D. Drake <jd@commandprompt.com>
Cc: Christopher Browne <cbbrowne@acm.org>
Cc: pgsql-performance@postgresql.org
Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL?
Date: Sat, 15 Jan 2005 00:32:55 +0100
Message-ID: <41E856A7.6080804@portrix.net> (raw)
In-Reply-To: <87is60ug7z.fsf@stark.xeocode.com>
References: <59b2d39b05011018421680264b@mail.gmail.com>
<m3mzvgd323.fsf@knuth.knuth.cbbrowne.com>
<41E3569A.4030102@commandprompt.com>
<41E3A780.3020505@portrix.net>
<87is60ug7z.fsf@stark.xeocode.com>
Greg Stark wrote:
> Jan Dittmer <j.dittmer@portrix.net> writes:
>
>
>>You could always do raid 1 over raid 0, with newer kernels (2.6ish)
>>there is even a dedicated raid10 driver.
>
>
> Aren't you much better off doing raid 0 over raid 1?
>
> With raid 1 over raid 0 you're mirroring two stripe sets. That means if any
> drive from the first stripe set goes you lose the whole side of the mirror. If
> any drive of the second stripe set goes you lost your array. Even if they're
> not the same position in the array.
>
> If you do raid 0 over raid 1 then you're striping a series of mirrored drives.
> So if any drive fails you only lose that drive from the stripe set. If another
> drive fails then you're ok as long as it isn't the specific drive that was
> paired with the first failed drive.
Ever heart of Murphy? :-) But of course you're right - I tend to mix up
the raid levels...
Jan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: j.dittmer@portrix.net, gsstark@mit.edu, jd@commandprompt.com, cbbrowne@acm.org
Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL?
In-Reply-To: <41E856A7.6080804@portrix.net>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox