From: Dawid Kuroczko <qnex42@gmail.com>
To: pgsql-performance@postgresql.org
Subject: Re: What's the best hardver for PostgreSQL 8.1?
Date: Tue, 27 Dec 2005 08:24:45 +0100
Message-ID: <758d5e7f0512262324i4dccd6bbs87d80e59eb776a8@mail.gmail.com> (raw)
In-Reply-To: <Pine.LNX.4.62.0512261004230.2807@qnivq.ynat.uz>
References: <43A84D03.7090002@ritek.hu>
<200512212209.50234.caseroj@comcast.net>
<200512212231.55100.caseroj@comcast.net>
<20051224135042.484c6e32.frank@wiles.org>
<6.2.5.6.0.20051224161551.01dc5d98@earthlink.net>
<Pine.LNX.4.62.0512241350010.2807@qnivq.ynat.uz>
<6.2.5.6.0.20051224172653.01dd4c08@earthlink.net>
<20051225173755.GA6986@mathom.us>
<33c6269f0512260932g38c9b7a4uc2aba00f72ff77@mail.gmail.com>
<Pine.LNX.4.62.0512261004230.2807@qnivq.ynat.uz>
On 12/26/05, David Lang <dlang@invendra.net> wrote:
> raid5 writes n+1 blocks not n+n/2 (unless n=2 for a 3-disk raid). you can
> have a 15+1 disk raid5 array for example
>
> however raid1 (and raid10) have to write 2*n blocks to disk. so if you are
> talking about pure I/O needed raid5 wins hands down. (the same 16 drives
> would be a 8+8 array)
>
> what slows down raid 5 is that to modify a block you have to read blocks
> from all your drives to re-calculate the parity. this interleaving of
> reads and writes when all you are logicly doing is writes can really hurt.
> (this is why I asked the question that got us off on this tangent, when
> doing new writes to an array you don't have to read the blocks as they are
> blank, assuming your cacheing is enough so that you can write blocksize*n
> before the system starts actually writing the data)
Not exactly true.
Let's assume you have a 4+1 RAID5 (drives A, B, C, D and E),
and you want to update drive A. Let's assume the parity
is stored in this particular write on drive E.
One way to write it is:
write A,
read A, B, C, D,
combine A+B+C+D and write it E.
(4 reads + 2 writes)
The other way to write it is:
read oldA,
read old parity oldE
write newA,
write E = oldE + (newA-oldA) -- calculate difference between new and
old A, and apply it to old parity, then write
(2 reads + 2 writes)
The more drives you have, the smarter it is to use the second approach,
unless of course A, B, C and D are available in the cache, which is the
niciest situation.
Regards,
Dawid
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: qnex42@gmail.com
Subject: Re: What's the best hardver for PostgreSQL 8.1?
In-Reply-To: <758d5e7f0512262324i4dccd6bbs87d80e59eb776a8@mail.gmail.com>
* 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