CPU and Mem usage info for end user - postscripts?

[datakid]

While we are aware that adding an email address will send people resource usage statistics, we find that researchers running large array jobs turn those very valuable emails off or filter them to the bin. Not outrageous given the size of those arrays - and how useless that information is in that format.

Is there any command to deliver averages on each of the resources_used details once, at the end of an array job?

resources_used.cpupercent = 99                                                                
resources_used.cput = 05:12:49
resources_used.fs_usage = 311
resources_used.mem = 700348kb
resources_used.ncpus = 1
resources_used.vmem = 700348kb
resources_used.walltime = 05:12:50

I presume I’m going to have to script this myself. Does PBS have postscript functionality?

[datakid]

Also, what does resources_used.mem measure - avg over cput or max over cput?

[adarsh]

@datakid

I presume I’m going to have to script this myself. Does PBS have postscript functionality?

Design a Hook to monitor the Resources utilized by a Job

Please try the below as execjob_epilogue hook: f=open(’/tmp/abc.txt’, ‘w+’) f.write("======================================================================================\n\n\t\t\tResource Usage on %s:\n\nJobId: %s \n\tJob_Name = %s \n\tJob_Owner = %s \n\tresource_used.cpupercent = %s \n\tresource_used.cput = %s \n\tresources_used.mem = %s \n\tresources_used.ncpus = %s \n\tresources_used.vmem = %s \n\tresources_used.walltime = %s \n\tqueue = %s \n\tserver = %s \n\tAccount_Name = %s \n\tError…

@datakid

Also, what does resources_used.mem measure - avg over cput or max over cput?