[Bioclusters] LSF 4.2 w/ Redhat 7.2 (2.4.X kernel with glibc2 .2) install problem

[Ron Chen]

Thanks for the feedback, I am going to send them to
the SGE dev mailing-list -- if you join the list and
send us more information, this is even better.

See me reply below --


> Preemption - the facility for jobs active within a
> queue with lower
> prioirty to be suspended by work running within
> higher priority queues.  GE
> handles this with prioiritisation within queue which
> isnt quite the same.
> The LSF model dynamically allows jobs at lower
> prioirty to be suspended on
> the system allowing higher prioirty work to go
> through.  Ideally we would
> like to see a product that accommodates both
> methodologies.
> 

There is a new cluster-wide queue design in SGE 6.0.
The new design will address the preemption stuff.

The feedback I got from Sun is that this is high
priority.


> Job accounting and history is poor in GE - superior
> in LSF.
> 	GE is free - LSF certainly isnt !

You mean the output of qacct in SGE vs. bacct in LSF?
SGE 5.2.x does not provide much accounting info, SGE
5.3 is much better, it provides CPU time, memory
usage, and many others.



> 	We've had problems with master to shadow daemon
> failover on GE which
> works fine on LSF.

The current shadow master fail-over works, can you
tell us more about the problem? The shadow
master/fail-over model will change in SGE 6.0 too. (I
did the design, do you like it?)

> We also remember working around the dual interface
> issue with our
> LSF install - but same issues with GE ?

In SGE, you might need the host_alias file to help
resolving host with more than 1 network interfaces.

 -Ron

__________________________________________________
Do You Yahoo!?
Yahoo! Health - your guide to health and wellness
http://health.yahoo.com