[torqueusers] Non-cummulative pbsnodes -o command
brockp at umich.edu
Thu Feb 14 13:01:09 MST 2008
Sorry that thats the case, I would check make sure pbsnodes is the
Center for Advanced Computing
brockp at umich.edu
On Feb 14, 2008, at 1:04 PM, John Wang wrote:
> Hello Brock
> Well, that’s not the behaviour that I’m getting on torque 2.0.0p7
> and torque 2.2.1. With both of them, the sequence of commands
> that you’ve cited would result in only node nyx101 being offline
> and all other nodes being marked online regardless of what there
> previous states.
> On 2/13/08 5:04 PM, "Brock Palen" <brockp at umich.edu> wrote:
>> I never had to do this. I just always use a single node name. No
>> already offline nodes come back online.
>> pbsnodes -o nyx100
>> pbsnodes-o nyx101
>> both will be ofline
>> Brock Palen
>> Center for Advanced Computing
>> brockp at umich.edu
>> On Feb 13, 2008, at 5:41 PM, John Wang wrote:
>>> This is probably a fairly basic beef about Torque but it has been
>>> bugging the hell out of me.
>>> When using the command “pbsnode –o –N ‘message’ node1 node2 ...”
>>> to drain nodes, we have to list all the nodes that we want to
>>> stay drained in that single command ie.: even if a node was
>>> previously drained for another reason, issuing a “pbsnode –o”
>>> command without specifying the previously drained nodes results
>>> in those nodes being marked online instead of offline.
>>> This is truly ridiculous, it’s like playing a game of bonk the
>>> gopher. It is conceivable to have more nodes that you would
>>> want drained then can be specified on a single line and there
>>> should be no reason for us to have to independently track what
>>> nodes should be offline.
>>> As near as I can tell, most people avoid this with creative
>>> workarounds such as shutting down the pbs_mom daemon on the nodes
>>> to be offline or by creating very specific reservations. I’d
>>> imagine that there may be more such creative workarounds spurring
>>> more diversity in operational practices.
>>> So the question is, how do you work around this ridiculous
>>> behaviour at your site and is there any valid technical reason
>>> for pbsnodes to work in this fashion?
>>> torqueusers mailing list
>>> torqueusers at supercluster.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the torqueusers