From: Anthony Ransley <anthonyr@aurema.com>
To: pgsql-performance@postgresql.org
Subject: Re: Sun Fire T2000 and PostgreSQL 8.1.3
Date: Thu, 06 Apr 2006 13:35:47 +1000
Message-ID: <44348C93.2080106@aurema.com> (raw)
In-Reply-To: <7583B3F1891CC0429FA4A44952AA539C66FA2C@wfm-exchprd2.wfm.pvt>
References: <7583B3F1891CC0429FA4A44952AA539C66FA2C@wfm-exchprd2.wfm.pvt>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Hi Juan Casero,<br>
<br>
I've found that serial query clients are best served by PostgreSQL
running on fast single or dual core processors, ( such as the Athlon
FX60 ) rather than expensive n-way systems. I was orginally using an
8-way Xeon computer for a similar serial throughput problem. and i
wasn't supprised to find that at least 6 of the 8 processors were idle.
The point is, for this type client, you are better off spending the
money on the fastest single or dual core processors than a multiway box.<br>
<br>
Anthony.<br>
<br>
Juan Casero (FL FLC) wrote:
<blockquote
cite="mid7583B3F1891CC0429FA4A44952AA539C66FA2C@wfm-exchprd2.wfm.pvt"
type="cite">
<meta http-equiv="Content-Type" content="text/html; ">
<meta content="MSHTML 6.00.2900.2838" name="GENERATOR">
<div align="left" dir="ltr"><span class="812374617-05042006"><font
face="Arial" size="2">Greetings -</font></span></div>
<div><span class="812374617-05042006"></span> </div>
<div><span class="812374617-05042006"><font face="Arial" size="2">I
am testing a Sun Microsystems Sun Fire T2000 demo server at our
company. I want to know if anyone here has any experience with this
hardware and postgresql 8.1.3. I installed the copy of postgresql
8.1.3 from blastwave.org onto this demo box and loaded our production
database into it. This box has a single Ultrasparc T1 cpu with six
execution piplelines that can each handle 4 threads. With the Unix top
utility the postgresql server appears to bounce around between the
available threads on the system. For example I run a single large
query and I can see the postgresql server sometimes running on cpu/0,
other times on cpu/1, cpu/3,....etc up to cpu/23. However, never is
the load for the postgres server reported to be higher than 4.16%. I
did the math and 4.16% x 24 threads = 98.84% cpu load. So I wonder if
the Solaris 10 kernel is somehow throttling the processes so that any
single virtual processor can do no more than 4.16% load. We got this
server last week and I was able to install it in our rack just
yesterday. Now I need to see how I can optimize the postgresql server
to work on this box. Does anyone have any suggestions? I know the
postgresql server is not smp aware but I believe parts of it are. In
particular the buffer manager is supposed to scale the performance
almost linearly with the number of cpu's (including virtual ones). I
don't know however, if I need to recompile the postgresql server myself
to get those benefits. I am using the version of postgresql 8.1.3
that is available on blastwave.org. I am also working with the 64 bit
version of the database server. This machine has over 8GB of ram so I
was thinking of using the 64 bit version of the postgresql server so I
can access ram beyong the 4gb limit imposed by 32 bit addressing. Any
help or recommendations for performance tweaking of postgresql is very
much appreciated.</font></span></div>
<div><span class="812374617-05042006"></span> </div>
<div><span class="812374617-05042006"></span> </div>
<div><span class="812374617-05042006"><font face="Arial" size="2">Thanks,</font></span></div>
<div><span class="812374617-05042006"><font face="Arial" size="2">Juan</font></span></div>
</blockquote>
<br>
</body>
</html>
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: anthonyr@aurema.com
Subject: Re: Sun Fire T2000 and PostgreSQL 8.1.3
In-Reply-To: <44348C93.2080106@aurema.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