def test_execute( self ):
job = Job()
job.setName( "helloWorld-test" )
job.setExecutable( find_all( "helloWorld.py", '.', 'Integration' )[0],
arguments = "This is an argument",
logFile = "aLogFileForTest.txt" ,
parameters=[('executable', 'string', '', "Executable Script"),
('arguments', 'string', '', 'Arguments for executable Script'),
( 'applicationLog', 'string', '', "Log file name" ),
( 'someCustomOne', 'string', '', "boh" )],
paramValues = [( 'someCustomOne', 'aCustomValue' )] )
job.setBannedSites( ['LCG.SiteA.com', 'DIRAC.SiteB.org'] )
job.setOwner( 'ownerName' )
job.setOwnerGroup( 'ownerGroup' )
job.setName( 'jobName' )
job.setJobGroup( 'jobGroup' )
job.setType( 'jobType' )
job.setDestination( 'DIRAC.someSite.ch' )
job.setCPUTime( 12345 )
job.setLogLevel( 'DEBUG' )
res = job.runLocal( self.d )
self.assertTrue( res['OK'] )
def SoftClean(args=None):
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args) != 3):
Script.showHelp()
package = args[0]
version = args[1]
site = args[2]
j = Job()
j.setInputSandbox(['cta-swclean.py'])
arguments = package + ' ' + version
j.setExecutable('./cta-swclean.py', arguments)
j.setDestination([site])
name = 'SoftClean_' + package + '_' + version
j.setName('SoftClean')
j.setJobGroup('SoftClean')
j.setCPUTime(100000)
Script.gLogger.info(j._toJDL())
res = Dirac().submit(j)
print res['Value']
def test_execute(self):
job = Job()
job.setName("helloWorld-test")
job.setExecutable(find_all("helloWorld.py", '.', 'Integration')[0],
arguments="This is an argument",
logFile="aLogFileForTest.txt",
parameters=[('executable', 'string', '',
"Executable Script"),
('arguments', 'string', '',
'Arguments for executable Script'),
('applicationLog', 'string', '',
"Log file name"),
('someCustomOne', 'string', '', "boh")],
paramValues=[('someCustomOne', 'aCustomValue')])
job.setBannedSites(['LCG.SiteA.com', 'DIRAC.SiteB.org'])
job.setOwner('ownerName')
job.setOwnerGroup('ownerGroup')
job.setName('jobName')
job.setJobGroup('jobGroup')
job.setType('jobType')
job.setDestination('DIRAC.someSite.ch')
job.setCPUTime(12345)
job.setLogLevel('DEBUG')
res = job.runLocal(self.d)
self.assertTrue(res['OK'])
def submitProbeJobs(self, ce):
""" Submit some jobs to the CEs
"""
#need credentials, should be there since the initialize
from DIRAC.Interfaces.API.Dirac import Dirac
d = Dirac()
from DIRAC.Interfaces.API.Job import Job
from DIRAC.ConfigurationSystem.Client.Helpers.Operations import Operations
import DIRAC
ops = Operations()
scriptname = ops.getValue("ResourceStatus/SofwareManagementScript", self.script)
j = Job()
j.setDestinationCE(ce)
j.setCPUTime(1000)
j.setName("Probe %s" % ce)
j.setJobGroup("SoftwareProbe")
j.setExecutable("%s/GlastDIRAC/ResourceStatusSystem/Client/%s" % (DIRAC.rootPath, scriptname),
logFile='SoftwareProbe.log')
j.setOutputSandbox('*.log')
res = d.submit(j)
if not res['OK']:
return res
return S_OK()
def submitProbeJobs(self, ce):
""" Submit some jobs to the CEs
"""
#need credentials, should be there since the initialize
from DIRAC.Interfaces.API.Dirac import Dirac
d = Dirac()
from DIRAC.Interfaces.API.Job import Job
from DIRAC.ConfigurationSystem.Client.Helpers.Operations import Operations
import os
ops = Operations("glast.org")
scriptname = ops.getValue("ResourceStatus/SofwareManagementScript",
self.script)
j = Job()
j.setDestinationCE(ce)
j.setCPUTime(1000)
j.setName("Probe %s" % ce)
j.setJobGroup("SoftwareProbe")
j.setExecutable("%s/GlastDIRAC/ResourceStatusSystem/Client/%s" %
(os.environ['DIRAC'], scriptname),
logFile='SoftwareProbe.log')
j.setOutputSandbox('*.log')
res = d.submit(j)
if not res['OK']:
return res
return S_OK()
def softinstall( args = None ) :
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args)!=2):
Script.showHelp()
version = args[0]
site = args[1]
if version not in ['prod-2_21122012','prod-2_08032013']:
Script.gLogger.error('Version not valid')
Script.showHelp()
j = Job()
j.setInputSandbox( ['cta-swinstall.py','SoftwareInstallation.py','CODE'] )
j.setExecutable('./cta-swinstall.py', version)
j.setDestination([site])
j.setName('SoftInstall')
j.setCPUTime(100000)
Script.gLogger.info( j._toJDL() )
Dirac().submit( j )
def base():
job = Job()
job.setName("helloWorld-TEST-TO-Jenkins")
job.setInputSandbox([find_all('exe-script.py', '..', '/DIRAC/tests/Workflow/')[0]])
job.setExecutable("exe-script.py", "", "helloWorld.log")
job.setCPUTime(1780)
job.setDestination('DIRAC.Jenkins.ch')
job.setLogLevel('DEBUG')
return job
def base():
job = Job()
job.setName("helloWorld-TEST-TO-Jenkins")
executablePath = find_all("exe-script.py", "..",
"/DIRAC/tests/Workflow/")[0]
job.setInputSandbox([executablePath])
job.setExecutable(executablePath, "", "helloWorld.log")
job.setCPUTime(1780)
job.setDestination("DIRAC.Jenkins.ch")
job.setLogLevel("DEBUG")
return job
def softinstall(args=None):
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args) < 2):
Script.showHelp()
version = args[0]
site = args[1]
if version not in ['18122013', 'v0r7p0']:
Script.gLogger.error('Version not valid')
Script.showHelp()
j = Job()
j.setInputSandbox(['cta-ctools-install.py', 'SoftwareInstallation.py'])
j.setExecutable('./cta-ctools-install.py', version)
j.setDestination([site])
j.setName('ctoolsInstall')
j.setCPUTime(100000)
Script.gLogger.info(j._toJDL())
if site in ['LCG.GRIF.fr', 'LCG.M3PEC.fr']:
if site == 'LCG.GRIF.fr':
ceList = [
'apcce02.in2p3.fr', 'grid36.lal.in2p3.fr',
'lpnhe-cream.in2p3.fr', 'llrcream.in2p3.fr',
'node74.datagrid.cea.fr'
]
elif site == 'LCG.M3PEC.fr':
# ceList = ['ce0.bordeaux.inra.fr','ce0.m3pec.u-bordeaux1.fr']
ceList = ['ce0.bordeaux.inra.fr']
for ce in ceList:
j.setDestinationCE(ce)
name = 'ctoolsInstall' + '_' + ce
j.setName(name)
res = Dirac().submit(j)
print res
DIRAC.exit()
else:
name = 'ctoolsInstall'
j.setName(name)
res = Dirac().submit(j)
print res
def read_hessjob(args=None):
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args) != 1):
Script.showHelp()
version = args[0]
user_script = './read_hess2dst.sh'
sim_file = 'simtel_file.list'
infileLFNList = [
'/vo.cta.in2p3.fr/MC/PROD2/Config_310113/prod-2_21122012_corsika/gamma/prod-2_06052013_simtel_STD/Data/002xxx/gamma_20.0_180.0_alt2662.0_run002997.simtel.gz',
'/vo.cta.in2p3.fr/MC/PROD2/Config_310113/prod-2_21122012_corsika/gamma/prod-2_06052013_simtel_STD/Data/002xxx/gamma_20.0_180.0_alt2662.0_run002998.simtel.gz'
]
f = open(sim_file, 'w')
for infileLFN in infileLFNList:
filein = os.path.basename(infileLFN)
f.write(filein)
f.write('\n')
f.close()
j = Job()
j.setInputData(infileLFNList)
options = []
options = [sim_file]
executablestr = "%s %s %s" % (version, user_script, ' '.join(options))
j.setExecutable('./cta-read_hess.py', executablestr)
j.setInputSandbox(['cta-read_hess.py', user_script, sim_file])
j.setOutputSandbox(['read_hess.log'])
j.setOutputData(['*dst.gz'])
j.setName(user_script)
j.setCPUTime(100000)
Script.gLogger.info(j._toJDL())
Dirac().submit(j)
def do_installonsite(self, argss):
""" Install a release on a grid site :
installonsite tag site
"""
args = argss.split()
if len(args) < 2:
print self.do_installonsite.__doc__
return
tag = args[0]
site = args[1]
#print "Check if the software with the tag '"+tag+"' exists on the rsync server..."
#res = self.client.getSitesForTag(tag)
#if not res['OK']:
#print res['Message']
#return
#print "tag found !"
from DIRAC.Interfaces.API.Dirac import Dirac
d = Dirac()
from DIRAC.Interfaces.API.Job import Job
from DIRAC.ConfigurationSystem.Client.Helpers.Operations import Operations
import os
ops = Operations()
scriptname = "InstallSoftware.py"
j = Job()
j.setDestination(site)
j.setCPUTime(1000)
j.setName("Installation " + tag)
j.setExecutable(os.environ['DIRAC'] +
"/GlastDIRAC/ResourceStatusSystem/Client/externals/" +
scriptname,
logFile='SoftwareInstallation.log')
j.setOutputSandbox('*.log')
res = d.submit(j)
if not res['OK']:
print "Could not submit the installation at site %s, message %s" % (
site, res['Message'])
return
print "Job submitted, id = " + str(res['Value'])
print "Add tag :"
res = self.client.addTagAtSite(tag, site)
if not res['OK']:
print "Could not register tag %s at site %s, message %s" % (
tag, site, res['Message'])
return
print "Added %s to %i CEs" % (tag, len(res['Value'][tag]))
def run_test_job(args):
simtel_files = load_files_from_list(args[0])
#simtel_files = ["/vo.cta.in2p3.fr/MC/PROD3/LaPalma/proton/simtel/1260/Data/071xxx/proton_40deg_180deg_run71001___cta-prod3-lapalma3-2147m-LaPalma.simtel.gz",
#"/vo.cta.in2p3.fr/MC/PROD3/LaPalma/proton/simtel/1260/Data/070xxx/proton_40deg_180deg_run70502___cta-prod3-lapalma3-2147m-LaPalma.simtel.gz"]
dirac = Dirac()
j = Job()
j.setCPUTime(500)
j.setInputData(simtel_files[0])
j.setExecutable('echo', 'Hello World!')
j.setName('Hello World')
res = dirac.submit(j)
print('Submission Result: {}'.format(res))
return res
def submitJob(jobPara):
dirac = Dirac()
j = Job()
j.setName(jobPara['jobName'])
j.setJobGroup(jobPara['jobGroup'])
j.setExecutable(jobPara['jobScript'], logFile = jobPara['jobScriptLog'])
j.setInputSandbox(jobPara['inputSandbox'])
j.setOutputSandbox(jobPara['outputSandbox'])
j.setOutputData(jobPara['outputData'], jobPara['SE'])
j.setDestination(jobPara['sites'])
j.setCPUTime(jobPara['CPUTime'])
result = dirac.submit(j)
if result['OK']:
print 'Job %s submitted successfully. ID = %d' %(jobPara['jobName'],result['Value'])
else:
print 'Job %s submitted failed' %jobPara['jobName']
return result
def CorsikaSimtelInstall(args=None):
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args) != 2):
Script.showHelp()
version = args[0]
site = args[1]
if version not in ['prod-2_13112014']:
Script.gLogger.error('Version not valid')
Script.showHelp()
j = Job()
CorsikaSimtelPack = os.path.join('corsika_simhessarray', version,
'corsika_simhessarray')
CorsikaSimtelLFN = 'LFN:' + os.path.join('/vo.cta.in2p3.fr/software',
CorsikaSimtelPack) + '.tar.gz'
j.setInputSandbox(['cta-corsikasimtel-install.py', CorsikaSimtelLFN])
j.setExecutable('./cta-corsikasimtel-install.py', version)
j.setDestination([site])
j.setJobGroup('SoftInstall')
j.setCPUTime(100000)
if site in ['LCG.GRIF.fr', 'LCG.M3PEC.fr']:
if site == 'LCG.GRIF.fr':
ceList = [
'apcce02.in2p3.fr', 'grid36.lal.in2p3.fr',
'lpnhe-cream.in2p3.fr', 'llrcream.in2p3.fr',
'node74.datagrid.cea.fr'
]
if site == 'LCG.M3PEC.fr':
ceList = ['ce0.bordeaux.inra.fr', 'ce0.m3pec.u-bordeaux1.fr']
for ce in ceList:
j.setDestinationCE(ce)
name = 'corsikasimtelInstall' + '_' + ce
j.setName(name)
Dirac().submit(j)
DIRAC.exit()
j.setName('corsikasimtelInstall')
Script.gLogger.info(j._toJDL())
Dirac().submit(j)
def do_installonsite(self,argss):
""" Install a release on a grid site :
installonsite tag site
"""
args = argss.split()
if len(args)<2:
print self.do_installonsite.__doc__
return
tag = args[0]
site = args[1]
#print "Check if the software with the tag '"+tag+"' exists on the rsync server..."
#res = self.client.getSitesForTag(tag)
#if not res['OK']:
#print res['Message']
#return
#print "tag found !"
from DIRAC.Interfaces.API.Dirac import Dirac
d = Dirac()
from DIRAC.Interfaces.API.Job import Job
from DIRAC.ConfigurationSystem.Client.Helpers.Operations import Operations
import os
ops = Operations()
scriptname = "InstallSoftware.py"
j = Job()
j.setDestination(site)
j.setCPUTime(1000)
j.setName("Installation "+tag)
j.setExecutable(os.environ['DIRAC']+"/GlastDIRAC/ResourceStatusSystem/Client/"+scriptname , logFile='SoftwareInstallation.log')
j.setOutputSandbox('*.log')
res = d.submit(j)
if not res['OK']:
print "Could not submit the installation at site %s, message %s"%(site,res['Message'])
return
print "Job submitted, id = "+str(res['Value'])
print "Add tag :"
res = self.client.addTagAtSite(tag,site)
if not res['OK']:
print "Could not register tag %s at site %s, message %s"%(tag,site,res['Message'])
return
print "Added %s to %i CEs"%(tag,len(res['Value'][tag]))
def submitJob(jobPara):
dirac = Dirac()
j = Job()
j.setName(jobPara['jobName'])
j.setJobGroup(jobPara['jobGroup'])
j.setExecutable(jobPara['jobScript'], logFile=jobPara['jobScriptLog'])
j.setInputSandbox(jobPara['inputSandbox'])
j.setOutputSandbox(jobPara['outputSandbox'])
j.setOutputData(jobPara['outputData'], jobPara['SE'])
j.setDestination(jobPara['sites'])
j.setCPUTime(jobPara['CPUTime'])
result = dirac.submit(j)
if result['OK']:
print 'Job %s submitted successfully. ID = %d' % (jobPara['jobName'],
result['Value'])
else:
print 'Job %s submitted failed' % jobPara['jobName']
return result
def test_submit(self):
print "**********************************************************************************************************"
gLogger.info("\n Submitting hello world job")
helloJ = Job()
helloJ.setName("helloWorld-test-T2s")
helloJ.setInputSandbox(
[find_all('exe-script.py', '.', 'GridTestSubmission')[0]])
helloJ.setExecutable("exe-script.py", "", "helloWorld.log")
helloJ.setCPUTime(17800)
result = self.dirac.submit(helloJ)
gLogger.info("Hello world job: ", result)
jobID = int(result['Value'])
jobsSubmittedList.append(jobID)
self.assert_(result['OK'])
print "**********************************************************************************************************"
gLogger.info("\n Submitting a job that uploads an output")
helloJ = Job()
helloJ.setName("upload-Output-test")
helloJ.setInputSandbox(
[find_all('testFileUpload.txt', '.', 'GridTestSubmission')[0]])
helloJ.setExecutable("exe-script.py", "", "helloWorld.log")
helloJ.setCPUTime(17800)
helloJ.setOutputData(['testFileUpload.txt'])
result = self.dirac.submit(helloJ)
gLogger.info("Hello world with output: ", result)
jobID = int(result['Value'])
jobsSubmittedList.append(jobID)
self.assert_(result['OK'])
def basicTest(self):
j = Job()
j.setCPUTime(50000)
j.setExecutable(
'/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/myPythonScript.py'
)
# j.setExecutable('/bin/echo hello')
j.setOwner('paterson')
j.setType('test')
j.setName('MyJobName')
#j.setAncestorDepth(1)
j.setInputSandbox([
'/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/DV.opts',
'/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/DV2.opts'
])
j.setOutputSandbox(['firstfile.txt', 'anotherfile.root'])
j.setInputData([
'/lhcb/production/DC04/v2/DST/00000742_00003493_11.dst',
'/lhcb/production/DC04/v2/DST/00000742_00003493_10.dst'
])
j.setOutputData(['my.dst', 'myfile.log'])
j.setDestination('LCG.CERN.ch')
j.setPlatform('LCG')
j.setSystemConfig('x86_64-slc5-gcc43-opt')
j.setSoftwareTags(['VO-lhcb-Brunel-v30r17', 'VO-lhcb-Boole-v12r10'])
#print j._toJDL()
#print j.printObj()
xml = j._toXML()
testFile = 'jobDescription.xml'
if os.path.exists(testFile):
os.remove(testFile)
xmlfile = open(testFile, 'w')
xmlfile.write(xml)
xmlfile.close()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Creating code for the workflow'
print j.createCode()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Executing the workflow'
j.execute()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Trying to run the same workflow from generated XML file'
workflow = fromXMLFile(testFile)
code = workflow.createCode()
print code
workflow.execute()
def simteljob(args = None ):
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
if (len(args)!=1):
Script.showHelp()
version = args[0]
user_script = './run_simtel.sh'
infileLFNList = ['/vo.cta.in2p3.fr/MC/PROD2/Config_120213/prod-2_21122012_corsika/proton/Data/044xxx/proton_20.0_180.0_alt2662.0_run044019.corsika.gz',
'/vo.cta.in2p3.fr/MC/PROD2/Config_120213/prod-2_21122012_corsika/proton/Data/044xxx/proton_20.0_180.0_alt2662.0_run044085.corsika.gz']
for infileLFN in infileLFNList:
filein = os.path.basename(infileLFN)
j = Job()
j.setInputSandbox( ['cta-simtel.py', user_script] )
j.setInputData(infileLFN)
user_args = []
user_args = [filein]
executablestr = "%s %s %s" % ( version, user_script, ' '.join( user_args ) )
j.setExecutable('./cta-simtel.py', executablestr)
sim_out = 'Data/sim_telarray/cta-ultra5/0.0deg/Data/*.simtel.gz'
log_out = 'Data/sim_telarray/cta-ultra5/0.0deg/Log/*.log.gz'
hist_out = 'Data/sim_telarray/cta-ultra5/0.0deg/Histograms/*.hdata.gz'
j.setOutputData([sim_out,log_out,hist_out])
j.setOutputSandbox('simtel.log')
j.setName(user_script)
j.setCPUTime(100000)
Script.gLogger.info( j._toJDL() )
Dirac().submit( j )
def launch_batch_pict( pitch_start, step, n_pict ):
j = Job()
j.setCPUTime(500)
j.setName('%s_%f' % (EXEC, pitch_start))
j.setJobGroup(JOBGROUP)
j.setInputSandbox([EXEC])
out_bmp_list=[]
pitch=pitch_start
for i in range(n_pict):
out_bmp='out_%f.bmp' % pitch
out_bmp_list.append(out_bmp)
j.setExecutable(EXEC,arguments="-W 600 -H 600 -X -0.77568377 -Y -0.13646737 -P %f -M 500 %s" % (pitch, out_bmp))
pitch+=step
j.setOutputSandbox(out_bmp_list + ["StdOut"] + ["StdErr"])
result = dirac.submit(j)
print 'Submission Result: ',result
return result
def test_execute(self):
job = Job()
job._siteSet = {"DIRAC.someSite.ch"}
job.setName("helloWorld-test")
job.setExecutable(
self.helloWorld,
arguments="This is an argument",
logFile="aLogFileForTest.txt",
parameters=[
("executable", "string", "", "Executable Script"),
("arguments", "string", "", "Arguments for executable Script"),
("applicationLog", "string", "", "Log file name"),
("someCustomOne", "string", "", "boh"),
],
paramValues=[("someCustomOne", "aCustomValue")],
)
job.setBannedSites(["LCG.SiteA.com", "DIRAC.SiteB.org"])
job.setOwner("ownerName")
job.setOwnerGroup("ownerGroup")
job.setName("jobName")
job.setJobGroup("jobGroup")
job.setType("jobType")
job.setDestination("DIRAC.someSite.ch")
job.setCPUTime(12345)
job.setLogLevel("DEBUG")
try:
# This is the standard location in Jenkins
job.setInputSandbox(
find_all("pilot.cfg",
os.environ["WORKSPACE"] + "/PilotInstallDIR")[0])
except (IndexError, KeyError):
job.setInputSandbox(find_all("pilot.cfg", rootPath)[0])
job.setConfigArgs("pilot.cfg")
res = job.runLocal(self.d)
self.assertTrue(res["OK"])
def test_execute(self):
job = Job()
job._siteSet = {'DIRAC.someSite.ch'}
job.setName("helloWorld-test")
job.setExecutable(self.helloWorld,
arguments="This is an argument",
logFile="aLogFileForTest.txt",
parameters=[('executable', 'string', '',
"Executable Script"),
('arguments', 'string', '',
'Arguments for executable Script'),
('applicationLog', 'string', '',
"Log file name"),
('someCustomOne', 'string', '', "boh")],
paramValues=[('someCustomOne', 'aCustomValue')])
job.setBannedSites(['LCG.SiteA.com', 'DIRAC.SiteB.org'])
job.setOwner('ownerName')
job.setOwnerGroup('ownerGroup')
job.setName('jobName')
job.setJobGroup('jobGroup')
job.setType('jobType')
job.setDestination('DIRAC.someSite.ch')
job.setCPUTime(12345)
job.setLogLevel('DEBUG')
try:
# This is the standard location in Jenkins
job.setInputSandbox(
find_all('pilot.cfg',
os.environ['WORKSPACE'] + '/PilotInstallDIR')[0])
except (IndexError, KeyError):
job.setInputSandbox(find_all('pilot.cfg', rootPath)[0])
job.setConfigArgs('pilot.cfg')
res = job.runLocal(self.d)
self.assertTrue(res['OK'])
def basicTest(self):
j = Job()
j.setCPUTime(50000)
j.setExecutable('/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/myPythonScript.py')
# j.setExecutable('/bin/echo hello')
j.setOwner('paterson')
j.setType('test')
j.setName('MyJobName')
#j.setAncestorDepth(1)
j.setInputSandbox(['/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/DV.opts','/Users/stuart/dirac/workspace/DIRAC3/DIRAC/Interfaces/API/test/DV2.opts'])
j.setOutputSandbox(['firstfile.txt','anotherfile.root'])
j.setInputData(['/lhcb/production/DC04/v2/DST/00000742_00003493_11.dst',
'/lhcb/production/DC04/v2/DST/00000742_00003493_10.dst'])
j.setOutputData(['my.dst','myfile.log'])
j.setDestination('LCG.CERN.ch')
j.setPlatform('LCG')
j.setSystemConfig('x86_64-slc5-gcc43-opt')
j.setSoftwareTags(['VO-lhcb-Brunel-v30r17','VO-lhcb-Boole-v12r10'])
#print j._toJDL()
#print j.printObj()
xml = j._toXML()
testFile = 'jobDescription.xml'
if os.path.exists(testFile):
os.remove(testFile)
xmlfile = open(testFile,'w')
xmlfile.write(xml)
xmlfile.close()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Creating code for the workflow'
print j.createCode()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Executing the workflow'
j.execute()
print '>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>Trying to run the same workflow from generated XML file'
workflow = fromXMLFile(testFile)
code = workflow.createCode()
print code
workflow.execute()
prodJobType = 'Merge'
transName = 'testProduction_' + str(int(time.time()))
desc = 'just test'
prodJob = Job()
prodJob._addParameter(prodJob.workflow, 'PRODUCTION_ID', 'string', '00012345', 'ProductionID')
prodJob._addParameter(prodJob.workflow, 'JOB_ID', 'string', '00006789', 'ProductionJobID')
prodJob._addParameter(prodJob.workflow, 'eventType', 'string', 'TestEventType', 'Event Type of the prodJobuction')
prodJob._addParameter(prodJob.workflow, 'numberOfEvents', 'string', '-1', 'Number of events requested')
prodJob._addParameter(prodJob.workflow, 'ProcessingType', 'JDL', str('Test'), 'ProductionGroupOrType')
prodJob._addParameter(prodJob.workflow, 'Priority', 'JDL', str(9), 'UserPriority')
prodJob.setType(prodJobType)
prodJob.workflow.setName(transName)
prodJob.workflow.setDescrShort(desc)
prodJob.workflow.setDescription(desc)
prodJob.setCPUTime(86400)
prodJob.setInputDataPolicy('Download')
prodJob.setExecutable('/bin/ls', '-l')
# Let's submit the prodJobuction now
#result = prodJob.create()
name = prodJob.workflow.getName()
name = name.replace('/', '').replace('\\', '')
prodJob.workflow.toXMLFile(name)
print 'Workflow XML file name is: %s' % name
workflowBody = ''
if os.path.exists(name):
with open(name, 'r') as fopen:
print "Usage %s <scriptName> <jobName> <nbJobs>"%sys.argv[0]
sys.exit(1)
scriptName = sys.argv[1]
jobName = sys.argv[2]
nbJobs = int(sys.argv[3])
if not os.path.exists(jobName):
os.makedirs(jobName)
os.makedirs("%s/Done"%jobName)
os.makedirs("%s/Failed"%jobName)
else:
print "Folder %s exists"%jobName
sys.exit(1)
f = open("%s/jobIdList.txt"%jobName, 'w')
for i in xrange(nbJobs):
j = Job()
j.setCPUTime(10000)
j.setExecutable(scriptName)
j.addToOutputSandbox.append('myLog.txt')
j.addToOutputSandbox.append('clock.txt')
j.addToOutputSandbox.append('time.txt')
dirac = Dirac()
jobID = dirac.submit(j)
realId = jobID.get('JobID')
f.write("%s\n"%realId)
f.close()
## PREPARE JOB ##
#####################
if (DO_NOT_SUBMIT):
sys.exit(os.EX_USAGE)
### ALWAYS, INFO, VERBOSE, WARN, DEBUG
j.setLogLevel('debug')
j.setDestination(site_dirac)
JOB_IDX = first_job + 1 + idx
JOB_NAME = PROD_NAME + " IDX_" + str(JOB_IDX)
print '\nJOB NAME is : ', JOB_NAME
j.setName(JOB_NAME)
j.setCPUTime(JOB_CPUTIME) ## 4 days
run_corsika_sim_args = input_file_base + " " + corsika_version + " " + corsika_bin
j.setExecutable( './run_corsika_sim', arguments = run_corsika_sim_args, logFile='run_sim.log')
if (TEST_JOB) :
jobID = dirac.submit(j,mode='local')
else :
jobID = dirac.submit(j)
id = str(jobID) + "\n"
print 'Submission Result: ',jobID
with open('jobids.list', 'a') as f_id_log:
f_id_log.write(id + '\n')
dat = input_file_base.replace('aug', 'DAT')
datlong = dat + ".long"
output_files= [run_log, 'fluka11.out', 'fluka15.err', dat, datlong ]
## prepare the output location in GRID storage; the input path will be the used also for GRID storage
outdir = grid_basedir_output + path + "/" + str(runnr)
## ALWAYS, INFO, VERBOSE, WARN, DEBUG
j.setLogLevel('debug')
j.setName('AUGER test simulation')
j.setDestinationCE(ce1)
## j.setDestination(site_dirac)
j.setCPUTime(345600) ## 4 days
## download the script for preparing corsika input file for usage with cvmfs
j.setExecutable( 'curl', arguments = ' -fsSLkO http://issaf.spacescience.ro/adrian/AUGER/make_run4cvmfs',logFile='cmd_logs.log')
j.setExecutable( 'chmod', arguments = ' +x make_run4cvmfs',logFile='cmd_logs.log')
## create the simulation script configured for use with cvmfs
## set the make_run4cvmfs arguments to include the corsika_version and corsika_bin
make_run4cvmfs_arg = input_file_base + " " + corsika_version + " " + corsika_bin
j.setExecutable( './make_run4cvmfs', arguments = make_run4cvmfs_arg, logFile='cmd_logs.log')
## run simulation
j.setExecutable( './execsim',logFile='cmd_logs.log')
j.setOutputSandbox(output_files)
j.setOutputData(output_files, outputSE=se, outputPath=outdir)
""" simple hello world job """ from DIRAC.Interfaces.API.Job import Job from DIRAC.Interfaces.API.Dirac import Dirac from DIRAC.DataManagementSystem.Utilities.DMSHelpers import DMSHelpers j = Job() j.setName( "helloWorld-test" ) j.setExecutable( "exe-script.py", "", "Executable.log" ) # <-- user settings j.setCPUTime( 172800 ) tier1s = DMSHelpers().getTiers( tier = ( 0, 1 ) ) j.setBannedSites( tier1s ) # user settings --> # print j.workflow # submit the job to dirac result = Dirac().submitJob(j) print result
def main(dataset, chunksize, test):
'''
The DATASET argument is a list of paths to MC files on the grid. Like the output of
cta-prod3-dump-dataset for example. See also
https://forge.in2p3.fr/projects/cta_dirac/wiki/CTA-DIRAC_MC_PROD3_Status
Keep in mind that for some effing reason this needs to be executed within this weird 'dirac'
environment which comes with its own glibc, python and pip. I guess the real Mr. Dirac would turn in his grave.
'''
dirac = Dirac()
with open(dataset) as f:
simtel_files = f.readlines()
print('Analysing {}'.format(len(simtel_files)))
server_list = [
"TORINO-USER", "CYF-STORM-USER", "CYF-STORM-Disk", "M3PEC-Disk",
"OBSPM-Disk", "POLGRID-Disk", "FRASCATI-USER", "LAL-Disk",
"CIEMAT-Disk", "CIEMAT-USER", "CPPM-Disk", "LAL-USER", "CYFRONET-Disk",
"DESY-ZN-USER", "M3PEC-USER", "LPNHE-Disk", "LPNHE-USER", "LAPP-USER",
"LAPP-Disk"
]
desy_server = 'DESY-ZN-USER'
servers_with_miniconda = [
'LCG.IN2P3-CC.fr', 'LCG.DESY-ZEUTHEN.de', 'LCG.CNAF.it', 'LCG.GRIF.fr',
'LCG.CYFRONET.pl', 'LCG.Prague.cz', 'LCG.CIEMAT.es'
]
chunks = np.array_split(sorted(simtel_files),
int(len(simtel_files) / chunksize))
print('Got a total of {} chunks'.format(len(chunks)))
for c, simtel_filenames in tqdm(enumerate(
chunks[0:2])): # send just 2 jobs for now.
# convert chunk to a list of strings. becasue this dirac thing cant take numpy arrays
simtel_filenames = [
str(s).strip() for s in simtel_filenames if 'SCT' not in s
]
print('Starting processing for chunk {}'.format(c))
print(simtel_filenames)
j = Job()
# set runtime to 0.5h
j.setCPUTime(30 * 60)
j.setName('cta_preprocessing_{}'.format(c))
j.setInputData(simtel_filenames)
j.setOutputData(['./processing_output/*.hdf5'],
outputSE=None,
outputPath='cta_preprocessing/')
j.setInputSandbox(
['../process_simtel.py', './install_dependencies.py'])
j.setOutputSandbox(['cta_preprocessing.log'])
j.setExecutable('./job_script.sh')
# These servers seem to have mini conda installed
# destination = np.random.choice(servers_with_miniconda)
j.setDestination(servers_with_miniconda)
value = dirac.submit(j)
print('Number {} Submission Result: {}'.format(c, value))
def main():
"""
Launch job on the GRID
"""
# this thing pilots everything related to the GRID
dirac = Dirac()
if switches["output_type"] in "TRAINING":
print("Preparing submission for TRAINING data")
elif switches["output_type"] in "DL2":
print("Preparing submission for DL2 data")
else:
print("You have to choose either TRAINING or DL2 as output type!")
sys.exit()
# Read configuration file
cfg = load_config(switches["config_file"])
# Analysis
config_path = cfg["General"]["config_path"]
config_file = cfg["General"]["config_file"]
mode = cfg["General"]["mode"] # One mode naw
particle = cfg["General"]["particle"]
estimate_energy = cfg["General"]["estimate_energy"]
force_tailcut_for_extended_cleaning = cfg["General"][
"force_tailcut_for_extended_cleaning"]
# Take parameters from the analysis configuration file
ana_cfg = load_config(os.path.join(config_path, config_file))
config_name = ana_cfg["General"]["config_name"]
cam_id_list = ana_cfg["General"]["cam_id_list"]
# Regressor and classifier methods
regressor_method = ana_cfg["EnergyRegressor"]["method_name"]
classifier_method = ana_cfg["GammaHadronClassifier"]["method_name"]
# Someone might want to create DL2 without score or energy estimation
if regressor_method in ["None", "none", None]:
use_regressor = False
else:
use_regressor = True
if classifier_method in ["None", "none", None]:
use_classifier = False
else:
use_classifier = True
# GRID
outdir = os.path.join(cfg["GRID"]["outdir"], config_name)
n_file_per_job = cfg["GRID"]["n_file_per_job"]
n_jobs_max = cfg["GRID"]["n_jobs_max"]
model_dir = cfg["GRID"]["model_dir"]
training_dir_energy = cfg["GRID"]["training_dir_energy"]
training_dir_classification = cfg["GRID"]["training_dir_classification"]
dl2_dir = cfg["GRID"]["dl2_dir"]
home_grid = cfg["GRID"]["home_grid"]
user_name = cfg["GRID"]["user_name"]
banned_sites = cfg["GRID"]["banned_sites"]
# HACK
if force_tailcut_for_extended_cleaning is True:
print("Force tail cuts for extended cleaning!!!")
# Prepare command to launch script
source_ctapipe = "source /cvmfs/cta.in2p3.fr/software/conda/dev/setupConda.sh"
source_ctapipe += " && conda activate ctapipe_v0.11.0"
if switches["output_type"] in "TRAINING":
execute = "data_training.py"
script_args = [
"--config_file={}".format(config_file),
"--estimate_energy={}".format(str(estimate_energy)),
"--regressor_config={}.yaml".format(regressor_method),
"--regressor_dir=./",
"--outfile {outfile}",
"--indir ./ --infile_list={infile_name}",
"--max_events={}".format(switches["max_events"]),
"--{mode}",
"--cam_ids {}".format(cam_id_list),
]
output_filename_template = "TRAINING"
elif switches["output_type"] in "DL2":
execute = "write_dl2.py"
script_args = [
"--config_file={}".format(config_file),
"--regressor_config={}.yaml".format(regressor_method),
"--regressor_dir=./",
"--classifier_config={}.yaml".format(classifier_method),
"--classifier_dir=./",
"--outfile {outfile}",
"--indir ./ --infile_list={infile_name}",
"--max_events={}".format(switches["max_events"]),
"--{mode}",
"--force_tailcut_for_extended_cleaning={}".format(
force_tailcut_for_extended_cleaning),
"--cam_ids {}".format(cam_id_list),
]
output_filename_template = "DL2"
# Make the script save also the full calibrated images if required
if switches["save_images"] is True:
script_args.append("--save_images")
# Make the script print debug information if required
if switches["debug_script"] is True:
script_args.append("--debug")
cmd = [source_ctapipe, "&&", "./" + execute]
cmd += script_args
pilot_args_write = " ".join(cmd)
# For table merging if multiple runs
pilot_args_merge = " ".join([
source_ctapipe,
"&&",
"./merge_tables.py",
"--template_file_name",
"{in_name}",
"--outfile",
"{out_name}",
])
prod3b_filelist = dict()
if estimate_energy is False and switches["output_type"] in "TRAINING":
prod3b_filelist["gamma"] = cfg["EnergyRegressor"]["gamma_list"]
elif estimate_energy is True and switches["output_type"] in "TRAINING":
prod3b_filelist["gamma"] = cfg["GammaHadronClassifier"]["gamma_list"]
prod3b_filelist["proton"] = cfg["GammaHadronClassifier"]["proton_list"]
elif switches["output_type"] in "DL2":
prod3b_filelist["gamma"] = cfg["Performance"]["gamma_list"]
prod3b_filelist["proton"] = cfg["Performance"]["proton_list"]
prod3b_filelist["electron"] = cfg["Performance"]["electron_list"]
# from IPython import embed
# embed()
# Split list of files according to stoprage elements
with open(prod3b_filelist[particle]) as f:
filelist = f.readlines()
filelist = ["{}".format(_.replace("\n", "")) for _ in filelist]
res = dirac.splitInputData(filelist, n_file_per_job)
list_run_to_loop_on = res["Value"]
# define a template name for the file that's going to be written out.
# the placeholder braces are going to get set during the file-loop
output_filename = output_filename_template
output_path = outdir
if estimate_energy is False and switches["output_type"] in "TRAINING":
output_path += "/{}/".format(training_dir_energy)
step = "energy"
if estimate_energy is True and switches["output_type"] in "TRAINING":
output_path += "/{}/".format(training_dir_classification)
step = "classification"
if switches["output_type"] in "DL2":
if force_tailcut_for_extended_cleaning is False:
output_path += "/{}/".format(dl2_dir)
else:
output_path += "/{}_force_tc_extended_cleaning/".format(dl2_dir)
step = ""
output_filename += "_{}.h5"
# sets all the local files that are going to be uploaded with the job
# plus the pickled classifier
# if file name starts with `LFN:`, it will be copied from the GRID
input_sandbox = [
# Utility to assign one job to one command...
os.path.expandvars("$GRID/pilot.sh"),
os.path.expandvars("$PROTOPIPE/protopipe/"),
os.path.expandvars("$GRID/merge_tables.py"),
# python wrapper for the mr_filter wavelet cleaning
# os.path.expandvars("$PYWI/pywi/"),
# os.path.expandvars("$PYWICTA/pywicta/"),
# script that is being run
os.path.expandvars("$PROTOPIPE/protopipe/scripts/" + execute),
# Configuration file
os.path.expandvars(os.path.join(config_path, config_file)),
]
models_to_upload = []
configs_to_upload = []
if estimate_energy is True and switches["output_type"] in "TRAINING":
config_path_template = "LFN:" + os.path.join(home_grid, outdir,
model_dir, "{}.yaml")
config_to_upload = config_path_template.format(regressor_method)
model_path_template = "LFN:" + os.path.join(
home_grid, outdir, model_dir, "regressor_{}_{}.pkl.gz")
for cam_id in cam_id_list:
model_to_upload = model_path_template.format(
cam_id, regressor_method) # TBC
print("The following model(s) will be uploaded to the GRID:")
print(model_to_upload)
models_to_upload.append(model_to_upload)
print(
"The following configs(s) for such models will be uploaded to the GRID:"
)
print(config_to_upload)
configs_to_upload.append(config_to_upload)
# input_sandbox.append(model_to_upload)
elif estimate_energy is False and switches["output_type"] in "TRAINING":
pass
else: # Charge also classifer for DL2
model_type_list = ["regressor", "classifier"]
model_method_list = [regressor_method, classifier_method]
config_path_template = "LFN:" + os.path.join(home_grid, outdir,
model_dir, "{}.yaml")
model_path_template = "LFN:" + os.path.join(
home_grid, outdir, model_dir, "{}_{}_{}.pkl.gz")
if force_tailcut_for_extended_cleaning is True:
force_mode = mode.replace("wave", "tail")
print("################")
print(force_mode)
else:
force_mode = mode
for idx, model_type in enumerate(model_type_list):
print(
"The following configuration file will be uploaded to the GRID:"
)
config_to_upload = config_path_template.format(
model_method_list[idx])
print(config_to_upload)
configs_to_upload.append(config_to_upload) # upload only 1 copy
print(
"The following model(s) related to such configuration file will be uploaded to the GRID:"
)
for cam_id in cam_id_list:
if model_type in "regressor" and use_regressor is False:
print("Do not upload regressor model on GRID!!!")
continue
if model_type in "classifier" and use_classifier is False:
print("Do not upload classifier model on GRID!!!")
continue
model_to_upload = model_path_template.format(
model_type_list[idx], cam_id, model_method_list[idx])
print(model_to_upload)
models_to_upload.append(model_to_upload)
# input_sandbox.append(model_to_upload)
# summary before submitting
print("\nDEBUG> running as:")
print(pilot_args_write)
print("\nDEBUG> with input_sandbox:")
print(input_sandbox)
print("\nDEBUG> with output file:")
print(output_filename.format("{job_name}"))
print("\nDEBUG> Particles:")
print(particle)
print("\nDEBUG> Energy estimation:")
print(estimate_energy)
# ######## ## ## ## ## ## ## #### ## ## ######
# ## ## ## ## ### ## ### ## ## ### ## ## ##
# ## ## ## ## #### ## #### ## ## #### ## ##
# ######## ## ## ## ## ## ## ## ## ## ## ## ## ## ####
# ## ## ## ## ## #### ## #### ## ## #### ## ##
# ## ## ## ## ## ### ## ### ## ## ### ## ##
# ## ## ####### ## ## ## ## #### ## ## ######
# list of files on the GRID SE space
# not submitting jobs where we already have the output
batcmd = "dirac-dms-user-lfns --BaseDir {}".format(
os.path.join(home_grid, output_path))
result = subprocess.check_output(batcmd, shell=True)
try:
grid_filelist = open(result.split()[-1]).read()
except IOError:
raise IOError("ERROR> cannot read GRID filelist...")
# get jobs from today and yesterday...
days = []
for i in range(2): # how many days do you want to look back?
days.append(
(datetime.date.today() - datetime.timedelta(days=i)).isoformat())
# get list of run_tokens that are currently running / waiting
running_ids = set()
running_names = []
for status in ["Waiting", "Running", "Checking"]:
for day in days:
try:
[
running_ids.add(id) for id in dirac.selectJobs(
status=status, date=day, owner=user_name)["Value"]
]
except KeyError:
pass
n_jobs = len(running_ids)
if n_jobs > 0:
print("Scanning {} running/waiting jobs... please wait...".format(
n_jobs))
for i, id in enumerate(running_ids):
if ((100 * i) / n_jobs) % 5 == 0:
print("\r{} %".format(((20 * i) / n_jobs) * 5)),
jobname = dirac.getJobAttributes(id)["Value"]["JobName"]
running_names.append(jobname)
else:
print("\n... done")
for bunch in list_run_to_loop_on:
# for bunch in bunches_of_run:
# from IPython import embed
# embed()
# this selects the `runxxx` part of the first and last file in the run
# list and joins them with a dash so that we get a nice identifier in
# the output file name.
# if there is only one file in the list, use only that one
# run_token = re.split('_', bunch[+0])[3] # JLK JLK
run_token = re.split("_", bunch[0])[3]
if len(bunch) > 1:
run_token = "-".join([run_token, re.split("_", bunch[-1])[3]])
print("-" * 50)
print("-" * 50)
# setting output name
output_filenames = dict()
if switches["output_type"] in "DL2":
job_name = "protopipe_{}_{}_{}_{}_{}".format(
config_name, switches["output_type"], particle, run_token,
mode)
output_filenames[mode] = output_filename.format("_".join(
[particle, mode, run_token]))
else:
job_name = "protopipe_{}_{}_{}_{}_{}_{}".format(
config_name, switches["output_type"], step, particle,
run_token, mode)
output_filenames[mode] = output_filename.format("_".join(
[step, particle, mode, run_token]))
# if job already running / waiting, skip
if job_name in running_names:
print("\n WARNING> {} still running\n".format(job_name))
continue
print("Output file name: {}".format(output_filenames[mode]))
# if file already in GRID storage, skip
# (you cannot overwrite it there, delete it and resubmit)
# (assumes tail and wave will always be written out together)
already_exist = False
file_on_grid = os.path.join(output_path, output_filenames[mode])
print("DEBUG> check for existing file on GRID...")
if file_on_grid in grid_filelist:
print("\n WARNING> {} already on GRID SE\n".format(job_name))
continue
if n_jobs_max == 0:
print("WARNING> maximum number of jobs to submit reached")
print("WARNING> breaking loop now")
break
else:
n_jobs_max -= 1
j = Job()
# runtime in seconds times 8 (CPU normalisation factor)
j.setCPUTime(6 * 3600 * 8)
j.setName(job_name)
j.setInputSandbox(input_sandbox)
if banned_sites:
j.setBannedSites(banned_sites)
# Add simtel files as input data
j.setInputData(bunch)
for run_file in bunch:
file_token = re.split("_", run_file)[3]
# wait for a random number of seconds (up to five minutes) before
# starting to add a bit more entropy in the starting times of the
# dirac queries.
# if too many jobs try in parallel to access the SEs,
# the interface crashes
# #sleep = random.randint(0, 20) # seconds
# #j.setExecutable('sleep', str(sleep))
# JLK: Try to stop doing that
# consecutively downloads the data files, processes them,
# deletes the input
# and goes on to the next input file;
# afterwards, the output files are merged
# j.setExecutable('dirac-dms-get-file', "LFN:" + run_file)
# source the miniconda ctapipe environment and
# run the python script with all its arguments
if switches["output_type"] in "DL2":
output_filename_temp = output_filename.format("_".join(
[particle, mode, file_token]))
if switches["output_type"] in "TRAINING":
output_filename_temp = output_filename.format("_".join(
[step, particle, mode, file_token]))
j.setExecutable(
"./pilot.sh",
pilot_args_write.format(
outfile=output_filename_temp,
infile_name=os.path.basename(run_file),
mode=mode,
),
)
# remove the current file to clear space
j.setExecutable("rm", os.path.basename(run_file))
# simple `ls` for good measure
j.setExecutable("ls", "-lh")
# if there is more than one file per job, merge the output tables
if len(bunch) > 1:
names = []
names.append(("*_{}_".format(particle), output_filenames[mode]))
for in_name, out_name in names:
print("in_name: {}, out_name: {}".format(in_name, out_name))
j.setExecutable(
"./pilot.sh",
pilot_args_merge.format(in_name=in_name,
out_name=out_name),
)
print("DEBUG> args append: {}".format(
pilot_args_merge.format(in_name=in_name,
out_name=out_name)))
bunch.extend(models_to_upload)
bunch.extend(configs_to_upload)
j.setInputData(bunch)
print("Input data set to job = {}".format(bunch))
outputs = []
outputs.append(output_filenames[mode])
print("Output file path: {}{}".format(output_path,
output_filenames[mode]))
j.setOutputData(outputs, outputSE=None, outputPath=output_path)
# check if we should somehow stop doing what we are doing
if switches["dry"] is True:
print("\nThis is a DRY RUN! -- NO job has been submitted!")
print("Name of the job: {}".format(job_name))
print("Name of the output file: {}".format(outputs))
print("Output path from GRID home: {}".format(output_path))
break
# this sends the job to the GRID and uploads all the
# files into the input sandbox in the process
print("\nSUBMITTING job with the following INPUT SANDBOX:")
print(input_sandbox)
print("Submission RESULT: {}\n".format(dirac.submitJob(j)["Value"]))
# break if this is only a test submission
if switches["test"] is True:
print("This is a TEST RUN! -- Only ONE job will be submitted!")
print("Name of the job: {}".format(job_name))
print("Name of the output file: {}".format(outputs))
print("Output path from GRID home: {}".format(output_path))
break
# since there are two nested loops, need to break again
if switches["test"] is True:
break
try:
os.remove("datapipe.tar.gz")
os.remove("modules.tar.gz")
except:
pass
# Upload analysis configuration file for provenance
SE_LIST = ['CC-IN2P3-USER', 'DESY-ZN-USER', 'CNAF-USER', 'CEA-USER']
analysis_config_local = os.path.join(config_path, config_file)
# the configuration file is uploaded to the data directory because
# the training samples (as well as their cleaning settings) are independent
analysis_config_dirac = os.path.join(home_grid, output_path, config_file)
print("Uploading {} to {}...".format(analysis_config_local,
analysis_config_dirac))
if switches["dry"] is False:
# Upload this file to all Dirac Storage Elements in SE_LIST
for se in SE_LIST:
# the uploaded config file overwrites any old copy
ana_cfg_upload_cmd = "dirac-dms-add-file -f {} {} {}".format(
analysis_config_dirac, analysis_config_local, se)
ana_cfg_upload_result = subprocess.check_output(ana_cfg_upload_cmd,
shell=True)
print(ana_cfg_upload_result)
else:
print("This is a DRY RUN! -- analysis.yaml has NOT been uploaded.")
print("\nall done -- exiting now")
exit()
# (you cannot overwrite it there, delete it and resubmit)
# (assumes tail and wave will always be written out together)
if '/'.join([output_path.strip('/'), output_filename_wave]) in GRID_filelist:
print("\n{} already on GRID SE\n".format(job_name))
continue
if NJobs == 0:
print("maximum number of jobs to submit reached")
print("breaking loop now")
break
else:
NJobs -= 1
j = Job()
# runtime in seconds times 8 (CPU normalisation factor)
j.setCPUTime(6 * 3600 * 8)
j.setName(job_name)
j.setInputSandbox(input_sandbox)
if banned_sites:
j.setBannedSites(banned_sites)
# j.setDestination( 'LCG.IN2P3-CC.fr' )
# mr_filter loses its executable property by uploading it to the GRID SE; reset
j.setExecutable('chmod', '+x mr_filter')
j.setExecutable('ls -lah')
for run_file in run_filelist:
file_token = re.split('_', run_file)[3]
dexit(1)
os.chmod(executable,0755) # make file executable
input_sandbox_files.append(executable)
j.setExecutable(str(executable))
else:
gLogger.error("No executable defined.")
dexit(1)
j.setName("MC job")
if not opts.name is None:
j.setName(opts.name)
j.setInputSandbox(input_sandbox_files) # all input files in the sandbox
j.setOutputSandbox(output_sandbox_files)
j.setCPUTime(opts.cpu)
if not opts.site is None:
j.setDestination(opts.site.split(","))#can also be a list
if not opts.bannedSites is None:
j.setBannedSites(opts.bannedSites.split(","))
if not opts.release is None:
tag = opts.release
cl = SoftwareTagClient()
result = cl.getSitesForTag(tag,'Valid') # keyword doesn't work there.
if not result['OK']:
gLogger.error("*ERROR* Could not get sites for Tag %s"%tag,result['Message'])
dexit(1)
sites = result[ 'Value' ]
j.setDestination(sites)
print("\n{} already on GRID SE\n".format(job_name))
already_exist = True
break
if already_exist == True:
continue
if NJobs == 0:
print("maximum number of jobs to submit reached")
print("breaking loop now")
break
else:
NJobs -= 1
j = Job()
# runtime in seconds times 8 (CPU normalisation factor)
j.setCPUTime(6 * 3600 * 8)
j.setName(job_name)
j.setInputSandbox(input_sandbox)
if banned_sites:
j.setBannedSites(banned_sites)
# mr_filter loses its executable property by uploading it to the GRID SE; reset
j.setExecutable('chmod', '+x mr_filter')
j.setExecutable('ls -lah')
for run_file in run_filelist:
file_token = re.split('_', run_file)[3]
# wait for a random number of seconds (up to five minutes) before starting
print("Usage %s <scriptName> <jobName> <nbJobs>" % sys.argv[0])
sys.exit(1)
scriptName = sys.argv[1]
jobName = sys.argv[2]
nbJobs = int(sys.argv[3])
if not os.path.exists(jobName):
os.makedirs(jobName)
os.makedirs("%s/Done" % jobName)
os.makedirs("%s/Failed" % jobName)
else:
print("Folder %s exists" % jobName)
sys.exit(1)
f = open("%s/jobIdList.txt" % jobName, 'w')
for i in range(nbJobs):
j = Job()
j.setCPUTime(10000)
j.setExecutable(scriptName)
j.addToOutputSandbox.append('myLog.txt')
j.addToOutputSandbox.append('clock.txt')
j.addToOutputSandbox.append('time.txt')
dirac = Dirac()
jobID = dirac.submitJob(j)
realId = jobID.get('JobID')
f.write("%s\n" % realId)
f.close()
from DIRAC.Interfaces.API.Dirac import Dirac
#from tests.Workflow.Integration.Test_UserJobs import createJob
gLogger.setLevel('DEBUG')
cwd = os.path.realpath('.')
dirac = Dirac()
# Simple Hello Word job to DIRAC.Jenkins.ch
gLogger.info("\n Submitting hello world job targeting DIRAC.Jenkins.ch")
helloJ = Job()
helloJ.setName("helloWorld-TEST-TO-Jenkins")
helloJ.setInputSandbox([find_all('exe-script.py', '..', '/DIRAC/tests/Workflow/')[0]])
helloJ.setExecutable("exe-script.py", "", "helloWorld.log")
helloJ.setCPUTime(1780)
helloJ.setDestination('DIRAC.Jenkins.ch')
helloJ.setLogLevel('DEBUG')
result = dirac.submitJob(helloJ)
gLogger.info("Hello world job: ", result)
if not result['OK']:
gLogger.error("Problem submitting job", result['Message'])
exit(1)
# Simple Hello Word job to DIRAC.Jenkins.ch, that needs to be matched by a MP WN
gLogger.info("\n Submitting hello world job targeting DIRAC.Jenkins.ch and a MP WN")
helloJMP = Job()
helloJMP.setName("helloWorld-TEST-TO-Jenkins-MP")
helloJMP.setInputSandbox([find_all('exe-script.py', '..', '/DIRAC/tests/Workflow/')[0]])
helloJMP.setExecutable("exe-script.py", "", "helloWorld.log")
helloJMP.setCPUTime(1780)
logfile = 'HelloWorldjob.log'
# The executable here '' is later set, so don't confuse users later on
diracJob = Job('', stdout, stderr)
diracJob.setName(jobName)
# Set the program/executable, arguments, logFile, ...
diracJob.setExecutable('echo', arguments='\"Hello world!\"')
# multiple executables can be set/appended
# diracJob.setExecutable('ls', arguments='-l')
# diracJob.setExecutable(executable, arguments='\"hello again\"')
# Set the job length, but not needed in this example
diracJob.setCPUTime(500)
print 'submitting job', jobName
dirac = Dirac()
result = dirac.submitJob(diracJob)
print 'Submission Result: ', result
# try to create job id file
try:
jid = 'JobID'
if jid in result.keys():
jid_file = open('%s.jid' % (jobName), 'w')
jid_file.write('%s\n' % (str(result[jid]).strip()))
jid_file.close()
else:
print 'Unable to creaate jid file for this job', jobName
from DIRAC.Interfaces.API.Dirac import Dirac #from tests.Workflow.Integration.Test_UserJobs import createJob gLogger.setLevel( 'DEBUG' ) cwd = os.path.realpath( '.' ) dirac = Dirac() # Simple Hello Word job to DIRAC.Jenkins.ch gLogger.info( "\n Submitting hello world job targeting DIRAC.Jenkins.ch" ) helloJ = Job() helloJ.setName( "helloWorld-TEST-TO-Jenkins" ) helloJ.setInputSandbox( [find_all( 'exe-script.py', '..', '/DIRAC/tests/Workflow/' )[0]] ) helloJ.setExecutable( "exe-script.py", "", "helloWorld.log" ) helloJ.setCPUTime( 17800 ) helloJ.setDestination( 'DIRAC.Jenkins.ch' ) result = dirac.submit( helloJ ) gLogger.info( "Hello world job: ", result ) if not result['OK']: gLogger.error( "Problem submitting job", result['Message'] ) exit( 1 ) # Simple Hello Word job to DIRAC.Jenkins.ch, that needs to be matched by a MP WN gLogger.info( "\n Submitting hello world job targeting DIRAC.Jenkins.ch and a MP WN" ) helloJMP = Job() helloJMP.setName( "helloWorld-TEST-TO-Jenkins-MP" ) helloJMP.setInputSandbox( [find_all( 'exe-script.py', '..', '/DIRAC/tests/Workflow/' )[0]] ) helloJMP.setExecutable( "exe-script.py", "", "helloWorld.log" ) helloJMP.setCPUTime( 17800 ) helloJMP.setDestination( 'DIRAC.Jenkins.ch' )
instcatname = visit + ".tar.gz"
insidename = 'phosim_cat_' + str(int(visit)) + '.txt'
#startsensor = idx * 4
#numsensors = 4
#if idx == 47:
# numsensors = 1
startsensor = idx
numsensors = 1
args = visit + ' ' + insidename + ' ' + str(startsensor) + ' ' + str(
numsensors) + ' ' + str(idx)
outputname = 'fits_' + visit + '_' + str(idx) + '.tar'
j.setCPUTime(1209600)
j.setExecutable('runimsim2.1.sh', arguments=args)
j.stderr = "std.err"
j.stdout = "std.out"
#!!! May need the 2.1i directory here depending on visit number !!!
j.setInputSandbox([
"runimsim2.1.sh", "run_imsim_nersc.py",
"LFN:/lsst/user/j/james.perry/instcats/2.1i/" + instcatname
])
j.setOutputSandbox(["std.out", "std.err"])
j.setTag(["8Processors"])
#j.setOutputData([visit + "/" + outputname], outputPath="", outputSE=["IN2P3-CC-disk"])
j.setOutputData([visit + "/" + outputname],
outputPath="",
outputSE=["UKI-NORTHGRID-LANCS-HEP-disk"])
j.setPlatform("AnyPlatform")
from DIRAC.Core.Base import Script
Script.parseCommandLine()
from DIRAC.Interfaces.API.Dirac import Dirac
from DIRAC.Interfaces.API.Job import Job
dirac = Dirac()
j = Job()
j.setName("compile_mrfilter")
j.setCPUTime(80)
j.setInputSandbox(["dirac_compile_mrfilter_pilot.sh"])
j.setExecutable("dirac_compile_mrfilter_pilot.sh", "")
j.setOutputData(["mr_filter"], outputSE=None,
outputPath="cta/bin/mr_filter/v3_1/")
Dirac().submit(j)
# and a valid proxy: dirac-proxy-init -g [your vo here]_user -M
# DIRAC does not work otherwise
from DIRAC.Core.Base import Script
Script.parseCommandLine(ignoreErrors=True)
# end of DIRAC setup
from DIRAC.Interfaces.API.Job import Job
from DIRAC.Interfaces.API.Dirac import Dirac
import pprint
dirac = Dirac()
j = Job()
j.setCPUTime(500)
j.setExecutable('/bin/echo hello')
j.setExecutable('/bin/hostname')
j.setExecutable('/bin/echo hello again')
j.setName('API')
result = dirac.submitJob(j)
print 'Submission Result: '
pprint.pprint(result)
jobid = result['JobID']
# print job id to file for future reference
joblog = open("jobid.log", "a")
joblog.write(str(jobid) + '\n')
joblog.close()
prodJobType = 'Merge'
transName = 'testProduction_' + str(int(time.time()))
desc = 'just test'
prodJob = Job()
prodJob._addParameter( prodJob.workflow, 'PRODUCTION_ID', 'string', '00012345', 'ProductionID' )
prodJob._addParameter( prodJob.workflow, 'JOB_ID', 'string', '00006789', 'ProductionJobID' )
prodJob._addParameter( prodJob.workflow, 'eventType', 'string', 'TestEventType', 'Event Type of the prodJobuction' )
prodJob._addParameter( prodJob.workflow, 'numberOfEvents', 'string', '-1', 'Number of events requested' )
prodJob._addParameter( prodJob.workflow, 'ProcessingType', 'JDL', str( 'Test' ), 'ProductionGroupOrType' )
prodJob._addParameter( prodJob.workflow, 'Priority', 'JDL', str( 9 ), 'UserPriority' )
prodJob.setType( prodJobType )
prodJob.workflow.setName(transName)
prodJob.workflow.setDescrShort( desc )
prodJob.workflow.setDescription( desc )
prodJob.setCPUTime( 86400 )
prodJob.setInputDataPolicy( 'Download' )
prodJob.setExecutable('/bin/ls', '-l')
#Let's submit the prodJobuction now
#result = prodJob.create()
name = prodJob.workflow.getName()
name = name.replace( '/', '' ).replace( '\\', '' )
prodJob.workflow.toXMLFile( name )
print 'Workflow XML file name is: %s' % name
workflowBody = ''
if os.path.exists( name ):
with open( name, 'r' ) as fopen:
# dirac job created by ganga
from DIRAC.Interfaces.API.Job import Job
from DIRAC.Interfaces.API.Dirac import Dirac
j = Job()
dirac = Dirac()
# default commands added by ganga
j.setName("helloWorld-test")
j.setInputSandbox( ['/afs/cern.ch/user/f/fstagni/userJobs/_inputHello.tar.bz2', '/afs/cern.ch/user/f/fstagni/userJobs/hello-script.py'] )
j.setExecutable("exe-script.py","","Ganga_Executable.log")
# <-- user settings
j.setCPUTime(172800)
j.setBannedSites(['LCG.CERN.ch', 'LCG.CNAF.it', 'LCG.GRIDKA.de',
'LCG.IN2P3.fr', 'LCG.NIKHEF.nl', 'LCG.PIC.es', 'LCG.RAL.uk',
'LCG.SARA.nl'])
# user settings -->
#print j.workflow
# submit the job to dirac
result = dirac.submit(j)
print result
"../tools/StorageElement.py"
]
# these files are created by the job
outputSandbox =\
[
stdout,
stderr,
logfile
]
# the executible here '' is later set, so don't confuse users later on
diracJob = Job('', stdout, stderr)
# give a descriptive name
diracJob.setName('ND280Custom')
# set the program/executable, arguments, logFile, ...
diracJob.setExecutable(exe, arguments=args, logFile=logfile)
# set the job length
diracJob.setCPUTime(3600)
diracJob.setExecutionEnv(environmentDict)
diracJob.setInputSandbox(inputSandbox)
diracJob.setOutputSandbox(outputSandbox)
print 'job being submitted...'
dirac = Dirac()
result = dirac.submit(diracJob)
print 'Submission Result: ', result
