From: Bernd Jagla <baj2107@columbia.edu>
To: 'Pgsql performance' <pgsql-performance@postgresql.org>
Subject: Best hardware
Date: Sat, 4 Jun 2005 09:30:57 -0400
Message-ID: <002701c56909$a5491720$0300a8c0@JAGLABLAPTOP> (raw)
Hi there,
And sorry for bringing this up again, but I couldn't find any recent
discussion on the best hardware, and I know it actually depends on what you
are doing...
So this is what I had in mind:
Our database is going to consist of about 100 tables or so of which only a
hand full will be really big, say in the 100 of million rows, fully indexed
and we are going to add a lot of entries (n* 100 000, n<100) on a daily
bases (24/5). So from my experience with MySql I know that it is somewhat
hard on the I/O, and that the speed of the head of the HD is actually
limitiing. Also, I only experimented with RAID5, and heard that RAID10 will
be good for reading but not writing.
So I wanted to go whith RAIDKing. They have a 16 bay Raid box that they fill
with Raptors (10krpm,73 GB, SATA), connected via FC. Now I am not sure what
server would be good or if I should go with redundant servers. Are Quad CPUs
any good? I heard that the IBM quad system is supposed to be 40% faster than
HP or Dell???. And how much RAM should go for: are 8GB enough? Oh, of course
I wanted to run it under RedHat...
I would appreciate any sugestions and comments or if you are too bored with
this topic, just send me a link where I can read up on this....
Thanks a lot for your kind replies.
Bernd
Bernd Jagla, PhD
Associate Research Scientist
Columbia University
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: baj2107@columbia.edu
Subject: Re: Best hardware
In-Reply-To: <002701c56909$a5491720$0300a8c0@JAGLABLAPTOP>
* 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