Differences

This shows you the differences between two versions of the page.

--- tutorial:torque_administrator_and_operator_commands [2024/03/08 11:07]
mjm519
+++ tutorial:torque_administrator_and_operator_commands [2024/04/10 14:07]
mjm519
@@ Line 1: / Line 1: @@
 ====== Torque Common Commands useful for Managers and Operators ======
+Information about command usage can be obtained using the links below or via the man or info commands.
+Example:
+<code>
+info qdel
+man qdel
+</code>
 ===== Commands: =====
@@ Line 31: / Line 39: @@
 == qstat ==
-[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qstat.htm|qstat]]
+[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qstat.htm|qstat]] - Qstat shows the status of jobs in the queuing system.
 <code>
 mjm519@polyp1:~$ qstat -q
@@ Line 73: / Line 82: @@
 == qalter ==
-[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qalter.htm|qalter]]
+[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qalter.htm|qalter]] - alter a non-running queued job.
+<code>
+qalter <job number> <change to the queued job>
+The line below changes the node specification for job id 1398668. Original job submission did not specify a node, this specifies a node with the same ppn (processors per node)
+                      qalter 1398668 -l nodes=polyp14:ppn=1
+</code>
 == qdel ==
-[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qdel.htm|qdel]]
+[[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qdel.htm|qdel]] - Delete a batch job
+<code>
+qdel <job id>
+                   qdel 1186460
+</code>
 == qhold ==
 [[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qhold.htm|qhold]]
+Place non-running job in a state so it will not run. If the job is running, and checkpointing is not enabled the job will terminate.
 == qmove ==
 [[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qmove.htm|qmove]]
+Move a submitted job to another queue.
 == qrun ==
 [[http://docs.adaptivecomputing.com/torque/4-1-4/Content/topics/commands/qrun.htm|qrun]]
+Command used to take a non-running job and make it run. When I use this, I look at running jobs and then use the qalter command to specify the node I want the job to run on (based on available resources).
 == qstart ==
-|qstat
+[[https://www.mankier.com/8/qstart|qstart]] The qstart command directs the torque server process batch jobs. This command can enable the entire server or a queue.
 == qstop ==
+[[https://www.mankier.com/8/qstop|qstop]] The qstop command directs the torque server to stop processing batch jobs. Can be use to disable the server or just a queue.
+== qenable ==
+[[https://www.mankier.com/8/qenable|qenable]] The qenable command directs the destination (server / queue) to accept jobs for processing.
+== qdisable ==
+[[https://www.mankier.com/8/qdisable|qdisable]] The qdisable command directs the destination (server / queue) to stop jobs for processing.
+== pbsnodes ==
+[[https://docs.adaptivecomputing.com/torque/4-1-3/Content/topics/commands/pbsnodes.htm|pbsnodes]]
+This command can be use to enable and disable nodes in the queuing system.
+<code>
+manager@polyp1:~$ pbsnodes -l
+polyp5               down
+polyp14              offline
+polyp15              offline
+polyp30              offline
+Take a node offline:
+manager@polyp1:~$ pbsnodes -o polyp15
+Put a node back online:
+manager@polyp1:~$ pbsnodes -c polyp15
+Current Normal Output from pbsnodes -l:
+manager@polyp1:~$ pbsnodes -l
+polyp5               down,offline
+polyp30              offline
+</code>

Lehigh ISE / COR@L Lab Wiki

User Tools

Site Tools

Differences

Page Tools