Difference between revisions of "Torque monitoring"

From NEClusterWiki
Jump to navigation Jump to search
(Created page with "== Monitoring of cluster jobs == There are two web interfaces which will show you who runs what on which machines: * [http://necluster.engr.utk.edu/torque Torque Monitor] s...")
 
 
(One intermediate revision by the same user not shown)
Line 1: Line 1:
== Monitoring of cluster jobs ==
+
== Commands at the head node ==
 +
 
 +
* [http://docs.adaptivecomputing.com/torque/4-2-10/Content/topics/commands/qstat.htm qstat] command, from the head node.
 +
* nodes.py - shows free nodes and CPUs for all queues.
 +
 
 +
 
 +
== Web monitoring of cluster jobs ==
  
 
There are two web interfaces which will show you who runs what on which machines:
 
There are two web interfaces which will show you who runs what on which machines:
  
* [http://necluster.engr.utk.edu/torque  Torque Monitor] shows simple totals of users and jobs.
+
* [http://necluster.engr.utk.edu/ganglia/addons/job_monarch/?c=NECluster Job Monarch] is part of Ganglia.
* [http://necluster.engr.utk.edu/cgi-bin/pbswebmon.py PBS Web Monitor] provides more detailed information about the jobs.
 

Latest revision as of 05:19, 10 January 2019

Commands at the head node

  • qstat command, from the head node.
  • nodes.py - shows free nodes and CPUs for all queues.


Web monitoring of cluster jobs

There are two web interfaces which will show you who runs what on which machines: