PBS

Carlos O'Donell Jr. carlos at baldric.uwo.ca
Wed Jun 13 10:07:48 PDT 2001


Joey,

So you have two switches in a stack.
The stack backplane is 1GBit (not good enough for you).
With both switches connected as a stack, the ideal of switch1 and
switch2 disappears (it's supposed to be that way).

We have 2 Baystack E450's (24 Port 10/100, 2.8GBit backplane) in a
stack configuration.

And if I was in your position, I would:

a. Praise the lord for managed switches.
b. Hack out a wrapper lib that manages the switch, either via SNMP, telnet,
   or serial connection.

c. Use the hacked out lib to determine which nodes are on which switch,
   thus gluing together your business logic from the PBS side.

Good luck.

Cheers,
Carlos O'Donell Jr.
-------------------------
The Baldric Project
http://www.baldric.uwo.ca
-------------------------


> I've posted this message up a couple of times already with no response, I'll
> try one more time.  I would like to try something new with PBS.  We will soon
> be adding more computers to our cluster and therefore will require another
> switch.  Since the bottleneck in the communication exists in the switch-switch
> communication (1000 MB/s duplex) we would like to run all parallel jobs within
> the same switch since bandwidth is near theoretical max within the switch.  My
> idea was to create two execution queues named switch1 and switch2 (each would
> only send jobs to nodes on each respective switch) and one route queue which
> would direct jobs to either switch1 or switch2 depending on the number of
> nodes requested and the free number of nodes available.  I thought there would
> be an easy way to do this, but I am finding that there might not be.  Maybe
> PBS is not the correct queueing system, does anybody have any suggestions or
> ideas of how I can implement the above??
> 
> Joey
> 




More information about the Beowulf mailing list