[Bioclusters] High Availability Clustering

[Joseph Landman]

On Wed, 2003-07-23 at 09:50, Chris Dagdigian wrote:

[...]

> Your experience may vary but I've found SGE and LSF to be superior to all 
> versions of PBS that I've ever used. They all will work at the end of the 
> day but some packages require more care/feeding and operational overhead 
> over time than others.  
> 
> If you are running OpenPBS instead of at least PBSPro I'd argue 
> semi-seriously that you are silly to even be considering HA hardware 
> techniques for your cluster :)

In fairness to Mike Humphrey and his team at Altair (who now own PBS,
and are up the street from me), PBS is not designed for very high
throughput situations.  It seems to work reasonably well for low volume
long runs.  

LSF and to a degree SGE are designed for HTC (High Throughput
Computing).  This is Platform Computing's lifeblood, and IMO they do a
great job of it.  I am impressed with SGE as well, though I am still
working through some minor rough areas with it.



-- 
Joseph Landman, Ph.D
Scalable Informatics LLC
email: landman@scalableinformatics.com
  web: http://scalableinformatics.com
phone: +1 734 612 4615