Skip site navigation (1) Skip section navigation (2)

Re: Which hardware ?

From: "Scott Marlowe" <scott(dot)marlowe(at)gmail(dot)com>
To: "Greg Smith" <gsmith(at)gregsmith(dot)com>
Cc: lionel(at)art-informatique(dot)com, pgsql-performance(at)postgresql(dot)org
Subject: Re: Which hardware ?
Date: 2008-06-17 15:42:34
Message-ID: dcc563d10806170842g6d039d7bsec81fb562ba9facd@mail.gmail.com (view raw or flat)
Thread:
Lists: pgsql-performance
On Tue, Jun 17, 2008 at 9:32 AM, Greg Smith <gsmith(at)gregsmith(dot)com> wrote:

>  Considering that Lionel's system seems pretty overpowered for what he's
> doing--runs plenty fast on a much slower system, enough RAM to hold a large
> portion of the primary tables and database, all batch updates that don't
> really need a good RAID setup--I'd say "looks good" here and recommend he
> just follow the plan he outlined.  Just watch the system with top for a bit
> under load to make sure the Java processes are staying under control.

In the original post he mentioned that he had 5 years of data at about
25G / year.

With 125G of data, it's likely that if most queries are on recent data
it'll be in RAM, but anything that hits older data will NOT have that
luxury.  Which is why I recommended RAID-10.  It doesn't have to be on
a $1200 card with 44 disks or something, but even 4 disks in a sw
RAID-10 will be noticeably faster (about 2x) than a simple RAID-1 at
hitting that old data.

We had a reporting server with about 80G of data on a machine with 4G
ram last place I worked, and it could take it a few extra seconds to
hit the old data, but the SW RAID-10 on it made it much faster at
reporting than it would have been with a single disk.

In response to

Responses

pgsql-performance by date

Next:From: Alan HodgsonDate: 2008-06-17 15:55:21
Subject: Re: Tsearch2 Initial Search Speed
Previous:From: Andrew SullivanDate: 2008-06-17 15:42:15
Subject: Re: Which hardware ?

Privacy Policy | About PostgreSQL
Copyright © 1996-2014 The PostgreSQL Global Development Group