[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: First Beowulf cluster. Some pointers?

>>>>> "e" == exa  <Eray> writes:

    e> "A.J. Rossini" wrote:
    >> In fact, since it'll enhance balancing for PVM/MPI, you might
    >> say that it has all the world to do with it.

    e> where on earth did you make that up? :) 

On the cluster and code I use for simulations, of course :-).

    e> It won't enhance anything for a parallel virtual machine that
    e> has to know the topology.

It WILL balance jobs which are run via PVM/MPI, esp if you've got
multiple processes on the same nodes.   PVM/MPI are not
load-balancing, not without a good bit of direct coding.

    e> otoh, it has got something to do with beowulf of course, since
    e> a distributed os extension may run on a beowulf cluster. since
    e> that thing probably wastes a lot of bandwidth, an optimized
    e> beowulf interconnect would speed things up for it. :)

    e> mosix doesn't have much to do with HPC, so we can say that it
    e> isn't very related to a beowulf class supercomputer.

It is a nice tool for HPC, depending on the jobs you do.  It enhances
the underlying system, at a lower level than PVM/MPI/shmem.  It's
definitely NOT a panacea.  You still have to write the parallel code.
If you've got a really tight process and are targetting differential
code at specific nodes in a topology, of course it's pretty useless.
But that's a specific example (though I admit there are numerous other
examples when MOSIX won't enhance the performance -- but you can
always lock processes onto particular nodes in the topology).  

But in general, it's a nice tool. 

Maybe it's not the tool for the HPC problems _YOU_ have; perhaps
you've got a nice scenario where your cluster is only running a single
HPC job at a time, and your nodes are equivalent.  But for those of us
with a smallish clusters running several large, indeterminately
long-term jobs from numerous sources/people...


A.J. Rossini				Rsrch. Asst. Prof. of Biostatistics
UW Biostat/Center for AIDS Research	rossini@u.washington.edu	
FHCRC/SCHARP/HIV Vaccine Trials Net	rossini@scharp.org
-------- (friday is unknown) --------
FHCRC: M--W : 206-667-7025 (fax=4812)|Voicemail is pretty sketchy
CFAR:  ??   : 206-731-3647 (fax=3694)|Email is far better than phone
UW:    Th   : 206-543-1044 (fax=3286)|Change last 4 digits of phone to FAX

Reply to: