Re: see idle nodes? (or run distributed top?)
Thank you both for your help on this. I got this working. (I had "DISABLE_QUEUE = True" in the config file since I'm using ipcluster, and don't need SGE. As a result I didn't have qhost available. I turned DISABLE_QUEUE back off, and qhost works.)
-jascha
On Aug 15, 2013, at 2:20 PM, Sergio Mafra <sergiohmafra_at_gmail.com> wrote:
> Or you can do $ starcluster sm clustername "qstat -f" or "qhost" -u sgeadmin (or whatever username that submitted the jbos)
>
>
> On Thu, Aug 15, 2013 at 10:56 AM, Rayson Ho <raysonlogin_at_gmail.com> wrote:
> If you "sshmaster" inot the cluster, run qhost and then you will see the load of each instance.
>
> Note that it is not easy to run qhost (or other SGE commands) from your local machine to talk to the EC2 instances.
>
> Rayson
>
> ==================================================
> Open Grid Scheduler - The Official Open Source Grid Engine
> http://gridscheduler.sourceforge.net/
>
>
> On Wed, Aug 14, 2013 at 11:09 PM, Jascha Sohl-Dickstein <jascha_at_stanford.edu> wrote:
> Short of ssh-ing in to each node, is there a way to see a list of which nodes are idle? Or even better, to run a distributed version of top? (eg, something similar to wwtop in warewolf)
>
> I've looked through the documentation, and while there are instructions on configuring the load balancer, I wasn't able to figure out a way to see activity on the nodes. Maybe I need to install Sun Grid Engine, and use qhost or qstat?
>
> Thank you for any help!
>
> -jascha
> _______________________________________________
> StarCluster mailing list
> StarCluster_at_mit.edu
> http://mailman.mit.edu/mailman/listinfo/starcluster
>
>
> _______________________________________________
> StarCluster mailing list
> StarCluster_at_mit.edu
> http://mailman.mit.edu/mailman/listinfo/starcluster
>
>
Received on Mon Aug 19 2013 - 18:28:17 EDT
This archive was generated by
hypermail 2.3.0.