Cookbook4Purdue_Cluster_job_submission

How to write a job file

How to display job and core usage

If you want to know how job and core usage by queues that you have access, you can use qlist.

qlist - Display job and core usage by queue in a human readable format

Here is an example:

$ qlist

                          Current Number of Cores
Queue                 Total    Queue      Run     Free      Max Walltime
===============    ====================================    ==============
mynode                  160        8       40      120         720:00:00
standby                 920      452      512      110           4:00:00

How to dispaly the jobs you submitted.

If you want to know how many jobs you submit, use qstat -u .

qstat -u <user name>

How to know how many jobs you have submitted or dispaly the jobs you submitted.

If you want to know how many jobs you have submitted. use qstat -u .

Here is an example:

$ qstat -u <username>

xxxx-adm.xxx.xxxx.edu:
                                                                                  Req'd    Req'd       Elap
Job ID                  Username    Queue    Jobname          SessID  NDS   TSK   Memory   Time    S   Time
----------------------- ----------- -------- ---------------- ------ ----- ------ ------ --------- - ---------
290650.<node>-adm.rcac  <username>      xxx   <jobname>  39468     1      1    --   10:00:00 R  03:14:03

How to know how long it spent to get your job started.

If you want to know how much time it spent to get your job started, use the following command:

qstat -f <job ID>

qstat

 -f Specifies that a full status display be written to standard out.
 

Here is an example:

$ qstat -f 290650

Job Id: 290650.xxx-adm.xxx.xxx.edu
    Job_Name = <jobname>
    Job_Owner = username@xxx.xxx.edu
    resources_used.cput = 02:54:48
    resources_used.energy_used = 0
    resources_used.mem = 55588kb
    resources_used.vmem = 111360kb
    resources_used.walltime = 02:59:37
    job_state = R
    queue = bioinf
    server = snyder-adm.rcac.purdue.edu
    Checkpoint = u
    ctime = Wed Aug  3 08:46:13 2016
    Error_Path = 
    exec_host = xxx-a019/0
    Hold_Types = n
    Join_Path = n
    Keep_Files = n
    Mail_Points = a
    mtime = Wed Aug  3 08:46:33 2016
    Output_Path = 
    Priority = 1023
    qtime = Wed Aug  3 08:46:13 2016
    Rerunable = True
    Resource_List.ncpus = 1
    Resource_List.nodect = 1
    Resource_List.nodes = 1:ppn=1
    Resource_List.walltime = 10:00:00
    session_id = 39468
    Variable_List = PBS_O_QUEUE=bioinf,PBS_O_HOME=/home/xie186,
        PBS_O_LOGNAME=xie186,
        PBS_O_PATH=
    euser = username
    egroup = student
    queue_type = E
    etime = Wed Aug  3 08:46:13 2016
    submit_args = test.sh
    start_time = Wed Aug  3 08:46:33 2016
    Walltime.Remaining = 25143
    start_count = 1
    fault_tolerant = False
    job_radix = 0
    submit_host = xx-fe01.xxx.xxxxx.edu

• ctime: Time job was created – unlike what I reported initially, this attribute exists. Not sure whether ctime or qtime are what saga needs to know
• etime: Time job became eligible to run – NOT the end time!
• qtime: Time job was queued
• stime: Time job started to run
• mtime: Time that the reservation was last modified

References: http://resources.altair.com/pbs/documentation/support/PBSProRefGuide12.2.pdf