Date: Sat, 25 Feb 2006 14:18:31 +1300
From: Mark Kirkwood <markir@paradise.net.nz>
Subject: Re: Reliability recommendations
In-reply-to: <125CA0A8-6142-4DF5-822E-CF0B0C46B4C1@hi5.com>
To: Dan Gorman <dgorman@hi5.com>
Cc: Luke Lonergan <llonergan@greenplum.com>,
	"Joshua D. Drake" <jd@commandprompt.com>,
	"Craig A. James" <cjames@modgraph-usa.com>,
	pgsql-performance@postgresql.org
Message-id: <43FFB067.2070406@paradise.net.nz>
MIME-version: 1.0
Content-type: text/plain; format=flowed; charset=ISO-8859-1
Content-transfer-encoding: 7bit
User-Agent: Mozilla Thunderbird 1.0.6 (X11/20051106)
References: <C024DFA1.1DC2D%llonergan@greenplum.com>
	<43FFA503.5070700@paradise.net.nz>
	<125CA0A8-6142-4DF5-822E-CF0B0C46B4C1@hi5.com>

Dan Gorman wrote:
> All,
> 
> Was that sequential reads? If so, yeah you'll get 110MB/s? How big  was 
> the datafile size? 8MB? Yeah, you'll get 110MB/s. 2GB? No, they  can't 
> sustain that. There are so many details missing from this test  that 
> it's hard to have any context around it :)
>

Actually they can. Datafile size was 8G, machine had 2G RAM (i.e. 
datafile 4 times memory). The test was for a sequential read with 8K 
blocks. I believe this is precisely the type of test that the previous 
posters were referring to - while clearly, its not a real-world measure, 
we are comparing like to like, and as such terrible results on such a 
simple test are indicative of something 'not right'.

regards

Mark

P.s. FWIW - I'm quoting a test from a few years ago - the (same) machine 
now has 4 RAID0 ata disks and does 175MB/s on the same test....