qstat and long job names

Question

How can I get qstat to give me full job names?

I know qstat -r gives detailed information about the task, but it\'s too much and the resource r

Answer 1

A poor KISS solution :

qstat -xml -f -u \* | fgrep JB_name | wc -l

Answer 2

This on is a bit messy, but it works as a simple solution to have in the command history. All standard tools. Output is pretty much the same as what you get from a normal qstat call, but you won't get the headers:

One-liner:

qstat -xml | tr '\n' ' ' | sed 's#<job_list[^>]*>#\n#g' \
  | sed 's#<[^>]*>##g' | grep " " | column -t

Description of commands:

List jobs as XML:

qstat -xml

Remove all newlines:

tr '\n' ' '

Add newline before each job entry in the list:

sed 's#<job_list[^>]*>#\n#g'

Remove all XML stuff:

sed 's#<[^>]*>##g'

Hack to add newline at the end:

grep " "

Columnize:

column -t

Example output

351996  0.50502  ProjectA_XXXXXXXXX_XXXX_XXXXXX                user123  r   2015-06-25T15:38:41  xxxxx-sim01@xxxxxx02.xxxxx.xxx  1
351997  0.50502  ProjectA_XXX_XXXX_XXX                         user123  r   2015-06-25T15:39:26  xxxxx-sim01@xxxxxx23.xxxxx.xxx  1
351998  0.50502  ProjectA_XXXXXXXXXXXXX_XXXX_XXXX              user123  r   2015-06-25T15:40:26  xxxxx-sim01@xxxxxx14.xxxxx.xxx  1
351999  0.50502  ProjectA_XXXXXXXXXXXXXXXXX_XXXX_XXXX          user123  r   2015-06-25T15:42:11  xxxxx-sim01@xxxxxx19.xxxxx.xxx  1
352001  0.50502  ProjectA_XXXXXXXXXXXXXXXXXXXXXXX_XXXX_XXXX    user123  r   2015-06-25T15:42:11  xxxxx-sim01@xxxxxx11.xxxxx.xxx  1
352008  0.50501  runXXXX69                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx17.xxxxx.xxx  1
352009  0.50501  runXXXX70                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx01.xxxxx.xxx  1
352010  0.50501  runXXXX71                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx06.xxxxx.xxx  1
352011  0.50501  runXXXX72                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx21.xxxxx.xxx  1
352012  0.50501  runXXXX73                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx13.xxxxx.xxx  1
352013  0.50501  runXXXX74                                     usr1     r   2015-06-25T15:49:04  xxxxx-sim01@xxxxxx11.xxxxx.xxx  1

Answer 3

For me the script of Physical Chemist didn't work so I wrote a very simple script using the xml.tree.ElementTree module which i regard as somewhat easier than xml.dom.minidom

import os
import xml.etree.ElementTree as ET
f = os.popen('qstat -x')
tree = ET.parse(f)
root = tree.getroot()
print "Job_Id   walltime state     nodes       Job_Name"
print "------   -------- ----- --------------- --------------------------"
for job in root:
    print job.find('Job_Id').text, " ",
    print job.find('resources_used').find('walltime').text, " ",
    print job.find('job_state').text, " ",
    print job.find('Resource_List').find('nodes').text, " ",
    print job.find('Job_Name').text

Answer 4

python code

import xmltodict
import subprocess as sp
import pandas as pd

qstat_xml = sp.check_output(['qstat','--xml'], stderr=sp.STDOUT)  # read xml
stat_dict = xmltodict.parse(qstat_xml) # convert to dict
job_list = stat_dict['Data']['Job'] # select job_list
job_df = pd.DataFrame(job_list) # convert to dataframe
print('columns', job_df.columns) # print available columns
column_list = ['Job_Id', 'Job_Name']
selection_df = job_df[column_list]  # select columns
print(selection_df)

Answer 5

Thanks to JLT for nice simple code. I've expanded it a bit to fit my needs and make it look nice.

Sample Output:

Job ID             Job Name                   Owner   Status  
------  ------------------------------------  ------  ------  
201716  AtacSilN100400K                       mtsige  R       
201771  IsoOnGrap400K                         mtsige  R       
202067  AtacOnSilica400K                      mtsige  R       
202100  AtacGrapN100400K                      mtsige  R       
202135  AtacOnSilc400K                        mtsige  R       
202145  AtacOnGrap400K                        mtsige  R       
202152  AtacOnGraphN3360K                     mtsige  R       
202161  AtacticSilicaN10                      mtsige  R       
202163  AtacGrapN10                           mtsige  R       
202169  AtacSilcN10                           mtsige  R       
202192  wallpmma07                            am110   R       
202193  wallpmma03                            am110   R       
202194  att03wpm_95solps                      am110   R       
202202  AtacticSilicaN3                       mtsige  R       
203260  8test18_trop_2p                       ico     R       
203359  parseAll_Bob/Sub951By50/Cyl20A_atom1  oge1    R       
203360  parseAll_Bob/Sub951By50/Cyl30A_atom1  oge1    R       
203361  parseAll_Bob/Sub951By50/Cyl30A_atom2  oge1    R      

Code:

#!/opt/bin/python3
import os
import xml.etree.ElementTree as ET

#Fields
fields=['Job_Id','Job_Name','Job_Owner','job_state']
names=['Job ID','Job Name','Owner','Status']

#Get job info
f = os.popen('qstat -x')
tree = ET.parse(f)
root = tree.getroot()
n_fields=len(fields)
jobs=[[job.find(field).text for field in fields] for job in root]
max_lengths=[len(name) for name in names]
sep='  '

#Identify max characer length per field
for j in jobs:
    for i in range(n_fields):
            #Chop off anything after and including '@' or '.' from all fields
            if j[i].find('@')>0:
                    j[i]=j[i][:j[i].find('@')]
            if j[i].find('.')>0:
                    j[i]=j[i][:j[i].find('.')]
            if(len(j[i])>max_lengths[i]):
                    max_lengths[i]=len(j[i])

#Field names
for i in range(n_fields):
    print('{s:^{length}}'.format(s=names[i],length=max_lengths[i]),end=sep)
print()

#Dashes
for i in range(n_fields):
    print('-'*max_lengths[i],end=sep)
print()

#Jobs
for j in jobs:
    for i in range(n_fields):
            if j[i].find('@')>0:
                    j[i]=j[i][:j[i].find('@')]
            print('{s:<{length}}'.format(s=j[i],length=max_lengths[i]),end=sep)
    print()

Answer 6

This script works pretty well. It looks like it is from cambridge. http://www.hep.ph.ic.ac.uk/~dbauer/grid/myqstat.py

For Python 3:

#!/usr/bin/python
import xml.dom.minidom
import os
import sys
import string    

f=os.popen('qstat -u \* -xml -r')

dom=xml.dom.minidom.parse(f)


jobs=dom.getElementsByTagName('job_info')
run=jobs[0]

runjobs=run.getElementsByTagName('job_list')


def fakeqstat(joblist):
    for r in joblist:
        try:
            jobname=r.getElementsByTagName('JB_name')[0].childNodes[0].data
            jobown=r.getElementsByTagName('JB_owner')[0].childNodes[0].data
            jobstate=r.getElementsByTagName('state')[0].childNodes[0].data
            jobnum=r.getElementsByTagName('JB_job_number')[0].childNodes[0].data
            jobtime='not set'
            if(jobstate=='r'):
                jobtime=r.getElementsByTagName('JAT_start_time')[0].childNodes[0].data
            elif(jobstate=='dt'):
                jobtime=r.getElementsByTagName('JAT_start_time')[0].childNodes[0].data
            else:
                jobtime=r.getElementsByTagName('JB_submission_time')[0].childNodes[0].data

            print(jobnum, '\t', jobown.ljust(16), '\t', jobname.ljust(16),'\t', jobstate,'\t',jobtime)
        except Exception as e:
            print(e)

fakeqstat(runjobs)

For Python 2:

#!/usr/bin/python
import xml.dom.minidom
import os
import sys
import string
#import re


f=os.popen('qstat -u \* -xml -r')

dom=xml.dom.minidom.parse(f)


jobs=dom.getElementsByTagName('job_info')
run=jobs[0]

runjobs=run.getElementsByTagName('job_list')


def fakeqstat(joblist):
        for r in joblist:
                jobname=r.getElementsByTagName('JB_name')[0].childNodes[0].data
                jobown=r.getElementsByTagName('JB_owner')[0].childNodes[0].data
                jobstate=r.getElementsByTagName('state')[0].childNodes[0].data
                jobnum=r.getElementsByTagName('JB_job_number')[0].childNodes[0].data
                jobtime='not set'
                if(jobstate=='r'):
                        jobtime=r.getElementsByTagName('JAT_start_time')[0].childNodes[0].data
                elif(jobstate=='dt'):
                        jobtime=r.getElementsByTagName('JAT_start_time')[0].childNodes[0].data
                else:
                        jobtime=r.getElementsByTagName('JB_submission_time')[0].childNodes[0].data



                print  jobnum, '\t', jobown.ljust(16), '\t', jobname.ljust(16),'\t', jobstate,'\t',jobtime


fakeqstat(runjobs)