From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <1200220e0243f49e3aea5c3756f981b6@plan9.ucalgary.ca>
To: 9fans@cse.psu.edu
Subject: Re: [9fans] xcpu note 
Date: Mon, 17 Oct 2005 22:57:33 -0600
From: andrey mirtchovski <mirtchov@cpsc.ucalgary.ca>
In-Reply-To: <20051018044405.10724.qmail@g.galapagos.bx.psu.edu>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Topicbox-Message-UUID: 9c04ef5a-ead0-11e9-9d60-3106f5b1d025

> | No other scheduler we have used 
> | comes close to this kind of performance. Scheduler overhead was 
> | basically insignificant.
>  
> Probably apples and oranges, but Jim Kent wrote a job scheduler for his
> kilocluster that nicely handled about 1M jobs in six hours.  It's the
> standard thing for whole genome sequence alignments at ucsc.

the vitanuova guys probably have better numbers, but when we ran their
grid code at ucalgary it executed over a million jobs in a 24-hour
period.  the jobs were non-null (md5sum using inferno's dis code).  it
ran on a 12 (or so) -node cluster :)