def doStartupChecks():
global doStartFromPAT
log.output("********** Checking environment **********")
log.output("--> Checking if you have a "+options.cmssw_ver+" release.")
if (os.path.isdir(options.cmssw_ver)):
log.output(" ---> Ok, the release is present!")
cmd ='cd '+options.cmssw_ver+'; cmsenv'
pExe = Popen(cmd, shell=True, stdin=PIPE, stdout=PIPE, stderr=STDOUT, close_fds=True)
else:
log.output(" ---> ERROR: Please scram the proper release first! (Exiting)")
dieOnError("Environment: resquested CMSSW version is not found in the working directory")
log.output("--> Checking if "+options.cmssw_ver+" contains the TopTreeProducer package.")
if (os.path.isdir(options.cmssw_ver+TopTreeProducerDir)):
log.output(" ---> Ok, the "+TopTreeProducerDir+" directory exists!")
else:
log.output(" ---> ERROR: Please ensure that you have the TopTreeProducer package installed! (Exiting)")
dieOnError("Environment: resquested CMSSW version does not contain the TopTreeProducer package")
log.output("--> Checking if "+options.cmssw_ver+" contains the PatAlgos package.")
if (os.path.isdir(options.cmssw_ver+PatDir)):
log.output(" ---> Ok, the "+PatDir+" directory exists!")
else:
log.output(" ---> ERROR: Please ensure that you have the PatAlgos package installed! (Exiting)")
dieOnError("Environment: resquested CMSSW version does not contain the PatAlgos package")
log.output("--> Checking DBS to see wether the requested Dataset exists")
if dbsInst == "":
dbsMgr = DBSHandler("cms_dbs_prod_global");
else:
dbsMgr = DBSHandler(dbsInst);
if doStartFromPAT:
dbsMgr.setDBSInst("cms_dbs_ph_analysis_02")
if not dbsMgr.datasetExists(options.dataset):
log.output(" ---> ERROR: "+options.dataset+" was not found in DBS! (Exiting)")
dieOnError("Dataset: DBS query for your dataset returned an empty set.")
else:
log.output(" ---> Ok, Dataset was found!")
log.output("--> Checking status of CRABServer (not yet implemented)")
crab = CRABHandler("","","",log)
crab.checkGridProxy(False)
crab.checkCredentials(False)
# log.sendErrorMails=bool(True) # FIXME
##################
## MAIN ROUTINE ##
##################
log.output("--------------------------------------------")
log.output("--> Automated FAST SIMULATION production <--")
log.output("--------------------------------------------")
# display input options and do consistency checks
inputSummary()
# check GRID proxy
crab = CRABHandler("", "", log)
crab.checkGridProxy(False)
crab.checkCredentials(False)
# create working directories
if not cmssw_sim == "":
workingDir_sim = setupDirs(cmssw_sim + "/src", "GEN-FASTSIM_" + publish_sim)
processGENFASTSIM()
if not options.dryRun:
updateTopDB("GENFASTSIM")
if not doDry:
def processPATandTOPTREE():
global workingDir
global dbsInst
global dataType
global doDry
global nEventsDBS
global workingDir
global dataType
global nEventsTT
global nEventsDBS
global topTreeLocation
global topCffName
global patCffName
global ttreeEventContent
global options
global jobEffPat
global jobEffTT
global CrabJSON
log.output("********** Preparing to produce the PAT-tuple and TopTree in one go **********")
startTime = gmtime()
# create pat cfg
pat = PatProducer(timestamp,workingDir,log);
pat.createPatConfig(options.dataset,options.GlobalTag,dataType,options.doGenEvent,options.cmssw_ver,options.cmssw_ver_sample,options.flavourHistoryFilterPath,options.runOnMC,options.pat_config)
patCffName = pat.getConfigFileName()
# create toptree cfg
top = TopTreeProducer(timestamp,workingDir,log)
# top.createTopTreeConfig(options.dataset,dataType,options.doGenEvent,options.GlobalTag,options.cmssw_ver,options.cmssw_ver_sample)
top.createTopTreeConfig(options.dataset,dataType,options.doGenEvent,options.GlobalTag,options.cmssw_ver,options.cmssw_ver_sample,options.top_config)
topCffName = top.getConfigFileName()
log.output(" ---> will expand the TopTree config before sending it with crab " )
cmd2 = 'cd '+options.cmssw_ver+'; eval `scramv1 runtime -sh`; cd -; python '+workingDir+'/'+top.getConfigFileName()+'; mv -v expanded.py '+workingDir+'/'
if not workingDir.rfind("CMSSW_5_") == -1:
log.output("Expanding TopTree config:: CMSSW_5_X_Y release detected, setting scram arch to slc5_amd64_gcc462")
cmd2 = "export SCRAM_ARCH=\"slc5_amd64_gcc462\";"+cmd2
pExe = Popen(cmd2, shell=True, stdin=PIPE, stdout=PIPE, stderr=STDOUT, close_fds=True)
log.output(pExe.stdout.read())
# create crab cfg
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver,timestamp,workingDir,log);
if not dbsInst == "":
crab.setDBSInst(dbsInst)
log.output(" ---> CRAB will use DBS instance "+dbsInst+" to look for your data.")
#crab.nEventsPerJob = "20000"
#crab.nEventsPerJob = "500"
if not doDry:
crab.scaleJobsSize(options.dataset,options.RunSelection,1) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.runTwoConfigs(patCffName,topCffName)
crab.AdditionalCrabInput=getAdditionalInputFiles(crab.AdditionalCrabInput)
crab.createCRABcfg("crab_"+timestamp+".cfg",
options.dataset,
pat.getConfigFileName(),
top.getOutputFileName(),
"TOPTREE",
bool(False),
options.CEBlacklist,
options.RunSelection,
options.forceStandAlone)
topTreeLocation = crab.getOutputLocation().split("\n")[0]
if not doDry:
crab.submitJobs()
crab.checkJobs()
crab.publishDataSet()
nEventsDBS = crab.getnEventsDBS()
nEventsTT = crab.checkFJR()
CrabJSON = crab.getCrabJSON()
if doStartFromPAT:
nEventsDBS = crab.getnEventsDBS()
ttreeEventContent = top.dumpEventContent(topTreeLocation)
jobEffPat = crab.getJobEff() # same job-eff for pat & TT in case of duo-jobs
jobEffTT = crab.getJobEff()
log.output("--> Job Efficiency: "+str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The TopTree production took "+ str((time.mktime(endTime)-time.mktime(startTime))/3600.0)+" hours.")
log.appendToMSG("\n* TopTree production information: \n")
if not crab.getOutputLocation() == "":
log.appendToMSG("\t-> Data location: "+topTreeLocation+"\n")
log.appendToMSG("\t-> Number of events processed: "+str(nEventsTT))
log.appendToMSG("\n Note: This TopTree was created from PAT inside one single job, the PATtuple was not stored")
def processTOPTREE():
log.output("********** Preparing to produce the TopTree **********")
startTime = gmtime()
global workingDir
global dataType
global doDry
global nEventsDBS
global nEventsTT
global doPBS
global topTreeLocation
global topCffName
global options
global ttreeEventContent
global jobEffTT
global CrabJSON
top = TopTreeProducer(timestamp,workingDir,log)
top.createTopTreeConfig(options.dataset,dataType,options.doGenEvent,options.GlobalTag,options.cmssw_ver,options.cmssw_ver_sample,options.top_config)
topCffName = top.getConfigFileName()
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver,timestamp,workingDir,log);
useDataSet=""
if doStartFromPAT:
useDataSet=options.dataset
else:
useDataSet=patPublishName
options.RunSelection = ""
crab.setDBSInst("cms_dbs_ph_analysis_02")
type = "TOPTREE"
if not doDry:
crab.scaleJobsSize(useDataSet,options.RunSelection,10) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.AdditionalCrabInput=getAdditionalInputFiles(crab.AdditionalCrabInput)
crab.createCRABcfg("crab_toptree_"+timestamp+".cfg",
useDataSet,
top.getConfigFileName(),
top.getOutputFileName(),
type,
bool(False),
options.CEBlacklist,
options.RunSelection,
options.forceStandAlone) # empty runselection for top
topTreeLocation = crab.getOutputLocation().split("\n")[0]
if not doDry:
crab.submitJobs()
crab.checkJobs()
#time.sleep(60) # to be shure the jobs are in done status
crab.publishDataSet()
CrabJSON = crab.getCrabJSON()
nEventsTT = crab.checkFJR()
if doStartFromPAT:
nEventsDBS = crab.getnEventsDBS()
ttreeEventContent = top.dumpEventContent(topTreeLocation)
jobEffTT = crab.getJobEff()
log.output("--> Job Efficiency: "+str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The TopTree production took "+ str((time.mktime(endTime)-time.mktime(startTime))/3600.0)+" hours.")
log.appendToMSG("\n* TopTree production information: \n")
if not crab.getOutputLocation() == "":
log.appendToMSG("\t-> Data location: "+topTreeLocation+"\n")
log.appendToMSG("\t-> Number of events processed: "+str(nEventsTT))
def processPAT():
global workingDir
global dbsInst
global dataType
global doDry
global patPublishName
global nEventsPAT
global nEventsDBS
global patCffName
global patLocation
global patEventContent
global jobEffPat
global options
global CrabJSON
log.output("********** Preparing to produce the PAT-tuple **********")
startTime = gmtime()
pat = PatProducer(timestamp,workingDir,log);
pat.createPatConfig(options.dataset,options.GlobalTag,dataType,options.doGenEvent,options.cmssw_ver,options.cmssw_ver_sample,options.flavourHistoryFilterPath,options.runOnMC,options.pat_config)
patCffName = pat.getConfigFileName()
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver,timestamp,workingDir,log);
#print "**"+crab.baseDir
if not dbsInst == "":
crab.setDBSInst(dbsInst)
log.output(" ---> CRAB will use DBS instance "+dbsInst+" to look for your data.")
if not doDry:
crab.scaleJobsSize(options.dataset,options.RunSelection,1) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.AdditionalCrabInput=getAdditionalInputFiles(crab.AdditionalCrabInput)
crab.createCRABcfg("crab_pat_"+timestamp+".cfg",
options.dataset,
pat.getConfigFileName(),
pat.getOutputFileName(),
"PAT",
bool(True),
options.CEBlacklist,
options.RunSelection,
options.forceStandAlone)
if not doDry:
crab.submitJobs()
nEventsDBS = crab.getnEventsDBS()
crab.checkJobs()
time.sleep(60) # to be shure the jobs are in done status
patPublishName = crab.publishDataSet()
nEventsPAT = crab.checkFJR()
patLocation = crab.getOutputLocation()
patEventContent = pat.dumpEventContent(patLocation)
jobEffPat = crab.getJobEff()
log.output("--> Job Efficiency: "+str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The PAT production took "+ str((time.mktime(endTime)-time.mktime(startTime))/3600.0)+" hours.")
log.appendToMSG("\n* PAT production information: ")
if not crab.getOutputLocation() == "":
log.appendToMSG("\n\t-> Data location: "+patLocation+"\n")
log.appendToMSG("\t-> DataSet was published in DBS as: "+patPublishName)
log.appendToMSG("\t-> Number of events processed: "+str(nEventsPAT))
def doStartupChecks():
global doStartFromPAT
log.output("********** Checking environment **********")
log.output("--> Checking if you have a " + options.cmssw_ver + " release.")
if (os.path.isdir(options.cmssw_ver)):
log.output(" ---> Ok, the release is present!")
cmd = 'cd ' + options.cmssw_ver + '; cmsenv'
pExe = Popen(cmd,
shell=True,
stdin=PIPE,
stdout=PIPE,
stderr=STDOUT,
close_fds=True)
else:
log.output(
" ---> ERROR: Please scram the proper release first! (Exiting)")
dieOnError(
"Environment: resquested CMSSW version is not found in the working directory"
)
log.output("--> Checking if " + options.cmssw_ver +
" contains the TopTreeProducer package.")
if (os.path.isdir(options.cmssw_ver + TopTreeProducerDir)):
log.output(" ---> Ok, the " + TopTreeProducerDir +
" directory exists!")
else:
log.output(
" ---> ERROR: Please ensure that you have the TopTreeProducer package installed! (Exiting)"
)
dieOnError(
"Environment: resquested CMSSW version does not contain the TopTreeProducer package"
)
log.output("--> Checking if " + options.cmssw_ver +
" contains the PatAlgos package.")
if (os.path.isdir(options.cmssw_ver + PatDir)):
log.output(" ---> Ok, the " + PatDir + " directory exists!")
else:
log.output(
" ---> ERROR: Please ensure that you have the PatAlgos package installed! (Exiting)"
)
dieOnError(
"Environment: resquested CMSSW version does not contain the PatAlgos package"
)
log.output("--> Checking DBS to see wether the requested Dataset exists")
if dbsInst == "":
dbsMgr = DBSHandler("cms_dbs_prod_global")
else:
dbsMgr = DBSHandler(dbsInst)
if doStartFromPAT:
dbsMgr.setDBSInst("cms_dbs_ph_analysis_02")
if not dbsMgr.datasetExists(options.dataset):
log.output(" ---> ERROR: " + options.dataset +
" was not found in DBS! (Exiting)")
dieOnError(
"Dataset: DBS query for your dataset returned an empty set.")
else:
log.output(" ---> Ok, Dataset was found!")
log.output("--> Checking status of CRABServer (not yet implemented)")
crab = CRABHandler("", "", "", log)
crab.checkGridProxy(False)
crab.checkCredentials(False)
from logHandler import logHandler
from CrabHandler import CRABHandler
crab = CRABHandler("",".",logHandler(""))
crab.createGridProxy()
crab.createMyProxyCredentials()
#print crab.pickProxy()
dbsPublish = []
CffFilePath = []
# toptree to remove
idTop = []
storagePathTop = []
mergedTopLocation = []
# logging
log = logHandler("")
# update grid-proxy for srm commands
crab = CRABHandler("", "", log)
crab.checkGridProxy(False)
#rmSRMdir("/pnfs/iihe/cms/store/user/dhondt/QCD_Pt-20to30_EMEnriched_TuneZ2_7TeV-pythia6/Spring11-PU_S1_START311_V1G1-v1/29032011_213110/TOPTREE")
#sys.exit(1)
#### Remove DataSet -> ALL associated PatTuples -> All associated TopTrees
if not options.cleanup and not options.rmDataSet == "None":
log.output("--> Removing dataset " + options.rmDataSet +
" and all associated PATtuples and TopTrees")
sql.createQuery("SELECT", "datasets", "id",
## provide the desired logfile name to logHandler
## if you provide an empty string the output will be written on the stdOut
if not options.stdout:
log = logHandler(logFileName)
else:
log = logHandler("")
#################
## MAIN METHOD ##
#################
# create a CrabHandler
crab = CRABHandler(timestamp,options.dir,log)
# change idle time
crab.idleTime=float(options.idleTime)
crab.idleTimeResubmit=float(options.idleTimeResubmit)
# set the crab env
crab.crabSource = "source /etc/profile.d/set_globus_tcp_port_range.sh; export EDG_WL_LOCATION=/opt/edg "
# check GRID proxy
crab.checkGridProxy(0)
crab.checkCredentials(0)
## provide the desired logfile name to logHandler
## if you provide an empty string the output will be written on the stdOut
if not options.stdout:
log = logHandler(logFileName)
else:
log = logHandler("")
#################
## MAIN METHOD ##
#################
# create a CrabHandler
crab = CRABHandler(timestamp, options.dir, log)
# change idle time
crab.idleTime = float(options.idleTime)
crab.idleTimeResubmit = float(options.idleTimeResubmit)
# set the crab env
crab.crabSource = "source /etc/profile.d/set_globus_tcp_port_range.sh; export EDG_WL_LOCATION=/opt/edg "
# check GRID proxy
crab.checkGridProxy(0)
crab.checkCredentials(0)
def processPATandTOPTREE():
global workingDir
global dbsInst
global dataType
global doDry
global nEventsDBS
global workingDir
global dataType
global nEventsTT
global nEventsDBS
global topTreeLocation
global topCffName
global patCffName
global ttreeEventContent
global options
global jobEffPat
global jobEffTT
global CrabJSON
log.output(
"********** Preparing to produce the PAT-tuple and TopTree in one go **********"
)
startTime = gmtime()
# create pat cfg
pat = PatProducer(timestamp, workingDir, log)
pat.createPatConfig(options.dataset, options.GlobalTag, dataType,
options.doGenEvent, options.cmssw_ver,
options.cmssw_ver_sample,
options.flavourHistoryFilterPath, options.runOnMC,
options.pat_config)
patCffName = pat.getConfigFileName()
# create toptree cfg
top = TopTreeProducer(timestamp, workingDir, log)
# top.createTopTreeConfig(options.dataset,dataType,options.doGenEvent,options.GlobalTag,options.cmssw_ver,options.cmssw_ver_sample)
top.createTopTreeConfig(options.dataset, dataType, options.doGenEvent,
options.GlobalTag, options.cmssw_ver,
options.cmssw_ver_sample, options.top_config)
topCffName = top.getConfigFileName()
log.output(
" ---> will expand the TopTree config before sending it with crab ")
cmd2 = 'cd ' + options.cmssw_ver + '; eval `scramv1 runtime -sh`; cd -; python ' + workingDir + '/' + top.getConfigFileName(
) + '; mv -v expanded.py ' + workingDir + '/'
if not workingDir.rfind("CMSSW_5_") == -1:
log.output(
"Expanding TopTree config:: CMSSW_5_X_Y release detected, setting scram arch to slc5_amd64_gcc462"
)
cmd2 = "export SCRAM_ARCH=\"slc5_amd64_gcc462\";" + cmd2
pExe = Popen(cmd2,
shell=True,
stdin=PIPE,
stdout=PIPE,
stderr=STDOUT,
close_fds=True)
log.output(pExe.stdout.read())
# create crab cfg
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver, timestamp, workingDir, log)
if not dbsInst == "":
crab.setDBSInst(dbsInst)
log.output(" ---> CRAB will use DBS instance " + dbsInst +
" to look for your data.")
#crab.nEventsPerJob = "20000"
#crab.nEventsPerJob = "500"
if not doDry:
crab.scaleJobsSize(
options.dataset, options.RunSelection,
1) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.runTwoConfigs(patCffName, topCffName)
crab.AdditionalCrabInput = getAdditionalInputFiles(
crab.AdditionalCrabInput)
crab.createCRABcfg("crab_" + timestamp + ".cfg", options.dataset,
pat.getConfigFileName(), top.getOutputFileName(),
"TOPTREE", bool(False), options.CEBlacklist,
options.RunSelection, options.forceStandAlone)
topTreeLocation = crab.getOutputLocation().split("\n")[0]
if not doDry:
crab.submitJobs()
crab.checkJobs()
crab.publishDataSet()
nEventsDBS = crab.getnEventsDBS()
nEventsTT = crab.checkFJR()
CrabJSON = crab.getCrabJSON()
if doStartFromPAT:
nEventsDBS = crab.getnEventsDBS()
ttreeEventContent = top.dumpEventContent(topTreeLocation)
jobEffPat = crab.getJobEff(
) # same job-eff for pat & TT in case of duo-jobs
jobEffTT = crab.getJobEff()
log.output("--> Job Efficiency: " + str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The TopTree production took " +
str((time.mktime(endTime) - time.mktime(startTime)) / 3600.0) +
" hours.")
log.appendToMSG("\n* TopTree production information: \n")
if not crab.getOutputLocation() == "":
log.appendToMSG("\t-> Data location: " + topTreeLocation + "\n")
log.appendToMSG("\t-> Number of events processed: " + str(nEventsTT))
log.appendToMSG(
"\n Note: This TopTree was created from PAT inside one single job, the PATtuple was not stored"
)
def processTOPTREE():
log.output("********** Preparing to produce the TopTree **********")
startTime = gmtime()
global workingDir
global dataType
global doDry
global nEventsDBS
global nEventsTT
global doPBS
global topTreeLocation
global topCffName
global options
global ttreeEventContent
global jobEffTT
global CrabJSON
top = TopTreeProducer(timestamp, workingDir, log)
top.createTopTreeConfig(options.dataset, dataType, options.doGenEvent,
options.GlobalTag, options.cmssw_ver,
options.cmssw_ver_sample, options.top_config)
topCffName = top.getConfigFileName()
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver, timestamp, workingDir, log)
useDataSet = ""
if doStartFromPAT:
useDataSet = options.dataset
else:
useDataSet = patPublishName
options.RunSelection = ""
crab.setDBSInst("cms_dbs_ph_analysis_02")
type = "TOPTREE"
if not doDry:
crab.scaleJobsSize(
useDataSet, options.RunSelection,
10) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.AdditionalCrabInput = getAdditionalInputFiles(
crab.AdditionalCrabInput)
crab.createCRABcfg("crab_toptree_" + timestamp + ".cfg", useDataSet,
top.getConfigFileName(), top.getOutputFileName(), type,
bool(False), options.CEBlacklist, options.RunSelection,
options.forceStandAlone) # empty runselection for top
topTreeLocation = crab.getOutputLocation().split("\n")[0]
if not doDry:
crab.submitJobs()
crab.checkJobs()
#time.sleep(60) # to be shure the jobs are in done status
crab.publishDataSet()
CrabJSON = crab.getCrabJSON()
nEventsTT = crab.checkFJR()
if doStartFromPAT:
nEventsDBS = crab.getnEventsDBS()
ttreeEventContent = top.dumpEventContent(topTreeLocation)
jobEffTT = crab.getJobEff()
log.output("--> Job Efficiency: " + str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The TopTree production took " +
str((time.mktime(endTime) - time.mktime(startTime)) / 3600.0) +
" hours.")
log.appendToMSG("\n* TopTree production information: \n")
if not crab.getOutputLocation() == "":
log.appendToMSG("\t-> Data location: " + topTreeLocation + "\n")
log.appendToMSG("\t-> Number of events processed: " + str(nEventsTT))
def processPAT():
global workingDir
global dbsInst
global dataType
global doDry
global patPublishName
global nEventsPAT
global nEventsDBS
global patCffName
global patLocation
global patEventContent
global jobEffPat
global options
global CrabJSON
log.output("********** Preparing to produce the PAT-tuple **********")
startTime = gmtime()
pat = PatProducer(timestamp, workingDir, log)
pat.createPatConfig(options.dataset, options.GlobalTag, dataType,
options.doGenEvent, options.cmssw_ver,
options.cmssw_ver_sample,
options.flavourHistoryFilterPath, options.runOnMC,
options.pat_config)
patCffName = pat.getConfigFileName()
#crab = CRABHandler(timestamp,workingDir,log);
crab = CRABHandler(options.toptree_ver, timestamp, workingDir, log)
#print "**"+crab.baseDir
if not dbsInst == "":
crab.setDBSInst(dbsInst)
log.output(" ---> CRAB will use DBS instance " + dbsInst +
" to look for your data.")
if not doDry:
crab.scaleJobsSize(
options.dataset, options.RunSelection,
1) # if to much jobs (>2500) we create new cfg with 2500 jobs
crab.AdditionalCrabInput = getAdditionalInputFiles(
crab.AdditionalCrabInput)
crab.createCRABcfg("crab_pat_" + timestamp + ".cfg", options.dataset,
pat.getConfigFileName(), pat.getOutputFileName(), "PAT",
bool(True), options.CEBlacklist, options.RunSelection,
options.forceStandAlone)
if not doDry:
crab.submitJobs()
nEventsDBS = crab.getnEventsDBS()
crab.checkJobs()
time.sleep(60) # to be shure the jobs are in done status
patPublishName = crab.publishDataSet()
nEventsPAT = crab.checkFJR()
patLocation = crab.getOutputLocation()
patEventContent = pat.dumpEventContent(patLocation)
jobEffPat = crab.getJobEff()
log.output("--> Job Efficiency: " + str(crab.getJobEff()))
endTime = gmtime()
log.output("--> The PAT production took " +
str((time.mktime(endTime) - time.mktime(startTime)) / 3600.0) +
" hours.")
log.appendToMSG("\n* PAT production information: ")
if not crab.getOutputLocation() == "":
log.appendToMSG("\n\t-> Data location: " + patLocation + "\n")
log.appendToMSG("\t-> DataSet was published in DBS as: " + patPublishName)
log.appendToMSG("\t-> Number of events processed: " + str(nEventsPAT))
def processGENFASTSIM():
log.output(" ----> Preparing to produce the GEN-FASTSIM sample <----")
startTime = gmtime()
global workingDir_sim
global doDry
global options
global cmssw_sim
global gt_sim
global publish_sim
global GENFASTSIM_CFFPath
global GENFASTSIM_PublishName
global GENFASTSIM_nEvents
global GENFASTSIM_PNFSLocation
global GENFASTSIM_jobEff
global GENFASTSIM_LHEFiles
sim = GENFASTSIMProducer(timestamp, workingDir_sim, log, setarchitecture)
sim.createConfig(publish_sim, options.configfile, gt_sim, options.lhedir, options.nEvents, options.campaign)
crab = CRABHandler(timestamp, workingDir_sim, log)
if options.nEvents == "-1" or int(options.nEvents) > int(sim.getNLHEevents()):
options.nEvents = sim.getNLHEevents()
crab.nEvents = str(options.nEvents)
if not str(options.nEvents) == "-1" and int(options.nEvents) < 500:
crab.nEventsPerJob = crab.nEvents
else:
crab.nEventsPerJob = "500"
crab.AdditionalCrabInput = sim.getlhefiles()
crab.createCRABcfg(
"crab_genfastsim_" + timestamp + ".cfg",
publish_sim + "_" + options.campaign,
sim.getConfigFileName(),
sim.getOutputFileName(),
"GENFASTSIM",
bool(True),
"",
"",
bool(False),
)
# the 'publish' argument set to bool(False) does not work yet, crabhandler encounters a problem because it wants to split "None" (the dataset when doing GEN-FASTSIM) into several pieces divided by "/" (as in a normal DAS dataset)...
crab.setForceWhiteList(bool(True))
if not doDry:
crab.submitJobs()
nEventsDBS = crab.getnEventsDBS()
##for testing
# crab.idleTime = int(60)
# crab.idleTimeResubmit = int(120)
crab.checkJobs()
time.sleep(60) # to be sure the jobs are in done status
GENFASTSIM_CFFPath = workingDir_sim + "/" + sim.getConfigFileName()
GENFASTSIM_LHEFiles = sim.getlhefiles()
GENFASTSIM_PublishName = crab.publishDataSet()
GENFASTSIM_nEvents = crab.checkFJR()
GENFASTSIM_PNFSLocation = crab.getOutputLocation()
GENFASTSIM_jobEff = crab.getJobEff()
# remove sandbox (lhe files are compressed, but can be sizable when you have a lot of lhe files and tasks: better clean up when a task is done)
log.output("--> Removing task sandbox ")
Popen(
"rm " + workingDir_sim + "/" + crab.UIWorkingDir + "/share/*.tgz",
shell=True,
stdin=PIPE,
stdout=PIPE,
stderr=STDOUT,
close_fds=True,
).stdout.read()
# remove lhe files in crab directory if they were copied when the lhe files in the original lhe directory were gzipped
log.output("--> Removing local copied LHE files in directory for crab")
Popen(
"rm " + workingDir_sim + "/*.lhe", shell=True, stdin=PIPE, stdout=PIPE, stderr=STDOUT, close_fds=True
).stdout.read()
log.output("--> Job Efficiency: " + str(GENFASTSIM_jobEff))
endTime = gmtime()
log.output(
"--> The GEN-FASTSIM production took "
+ str((time.mktime(endTime) - time.mktime(startTime)) / 3600.0)
+ " hours."
)
log.appendToMSG("\n* GEN-FASTSIM production information: ")
if not crab.getOutputLocation() == "":
log.appendToMSG("\n\t-> Data location: " + GENFASTSIM_PNFSLocation + "\n")
log.appendToMSG("\t-> DataSet was published in DBS as: " + GENFASTSIM_PublishName)
log.appendToMSG("\t-> Number of events processed: " + str(GENFASTSIM_nEvents))
def processGENFASTSIM():
log.output(" ----> Preparing to produce the GEN-FASTSIM sample <----")
startTime = gmtime()
global workingDir_sim
global doDry
global options
global cmssw_sim
global gt_sim
global publish_sim
global GENFASTSIM_CFFPath
global GENFASTSIM_PublishName
global GENFASTSIM_nEvents
global GENFASTSIM_PNFSLocation
global GENFASTSIM_jobEff
global GENFASTSIM_LHEFiles
sim = GENFASTSIMProducer(timestamp, workingDir_sim, log, setarchitecture)
sim.createConfig(publish_sim, options.configfile, gt_sim, options.lhedir,
options.nEvents, options.campaign)
crab = CRABHandler(timestamp, workingDir_sim, log)
if options.nEvents == "-1" or int(options.nEvents) > int(
sim.getNLHEevents()):
options.nEvents = sim.getNLHEevents()
crab.nEvents = str(options.nEvents)
if not str(options.nEvents) == "-1" and int(options.nEvents) < 500:
crab.nEventsPerJob = crab.nEvents
else:
crab.nEventsPerJob = "500"
crab.AdditionalCrabInput = sim.getlhefiles()
crab.createCRABcfg("crab_genfastsim_" + timestamp + ".cfg",
publish_sim + "_" + options.campaign,
sim.getConfigFileName(), sim.getOutputFileName(),
"GENFASTSIM", bool(True), "", "", bool(False))
#the 'publish' argument set to bool(False) does not work yet, crabhandler encounters a problem because it wants to split "None" (the dataset when doing GEN-FASTSIM) into several pieces divided by "/" (as in a normal DAS dataset)...
crab.setForceWhiteList(bool(True))
if not doDry:
crab.submitJobs()
nEventsDBS = crab.getnEventsDBS()
##for testing
#crab.idleTime = int(60)
#crab.idleTimeResubmit = int(120)
crab.checkJobs()
time.sleep(60) # to be sure the jobs are in done status
GENFASTSIM_CFFPath = workingDir_sim + "/" + sim.getConfigFileName()
GENFASTSIM_LHEFiles = sim.getlhefiles()
GENFASTSIM_PublishName = crab.publishDataSet()
GENFASTSIM_nEvents = crab.checkFJR()
GENFASTSIM_PNFSLocation = crab.getOutputLocation()
GENFASTSIM_jobEff = crab.getJobEff()
#remove sandbox (lhe files are compressed, but can be sizable when you have a lot of lhe files and tasks: better clean up when a task is done)
log.output("--> Removing task sandbox ")
Popen('rm ' + workingDir_sim + '/' + crab.UIWorkingDir +
'/share/*.tgz',
shell=True,
stdin=PIPE,
stdout=PIPE,
stderr=STDOUT,
close_fds=True).stdout.read()
#remove lhe files in crab directory if they were copied when the lhe files in the original lhe directory were gzipped
log.output("--> Removing local copied LHE files in directory for crab")
Popen('rm ' + workingDir_sim + '/*.lhe',
shell=True,
stdin=PIPE,
stdout=PIPE,
stderr=STDOUT,
close_fds=True).stdout.read()
log.output("--> Job Efficiency: " + str(GENFASTSIM_jobEff))
endTime = gmtime()
log.output("--> The GEN-FASTSIM production took " +
str((time.mktime(endTime) - time.mktime(startTime)) / 3600.0) +
" hours.")
log.appendToMSG("\n* GEN-FASTSIM production information: ")
if not crab.getOutputLocation() == "":
log.appendToMSG("\n\t-> Data location: " + GENFASTSIM_PNFSLocation +
"\n")
log.appendToMSG("\t-> DataSet was published in DBS as: " +
GENFASTSIM_PublishName)
log.appendToMSG("\t-> Number of events processed: " +
str(GENFASTSIM_nEvents))
# test suite
# for getting stuff from fjr files
# from fjrHandler import FJRHandler,GreenBoxHandler
# from xml.sax import make_parser
# from xml.sax.handler import ContentHandler
# file="CMSSW_4_1_4_patch4_TopTreeProd_41X_v4/src/ConfigurationFiles/WWtoAnything_TuneZ2_7TeV-pythia6-tauola/Spring11-PU_S1_START311_V1G1-v1/17062011_105711/TOPTREE_Spring11-PU_S1_START311_V1G1-v1_17062011_105711/res/crab_fjr_100.xml"
# parser = make_parser()
# handler = FJRHandler()
# parser.setContentHandler(handler)
# parser.parse(open(file))
# print handler.getEventsProcessed()
# print handler.getFrameworkExitCode().split("\n")[0]
from CrabHandler import CRABHandler
from logHandler import logHandler
crab = CRABHandler(
"1234567",
"CMSSW_4_1_4_patch4_TopTreeProd_41X_v4/src/ConfigurationFiles/WWtoAnything_TuneZ2_7TeV-pythia6-tauola/Spring11-PU_S1_START311_V1G1-v1/17062011_105711/",
logHandler(""),
)
crab.UIWorkingDir = "TOPTREE_Spring11-PU_S1_START311_V1G1-v1_17062011_105711"
crab.checkFJR()
from logHandler import logHandler
from CrabHandler import CRABHandler
crab = CRABHandler("", ".", logHandler(""))
crab.createGridProxy()
crab.createMyProxyCredentials()
#print crab.pickProxy()
dbsPublish = []
CffFilePath = []
# toptree to remove
idTop = []
storagePathTop = []
mergedTopLocation = []
# logging
log = logHandler("")
# update grid-proxy for srm commands
crab = CRABHandler("","",log)
crab.checkGridProxy(False)
#rmSRMdir("/pnfs/iihe/cms/store/user/dhondt/QCD_Pt-20to30_EMEnriched_TuneZ2_7TeV-pythia6/Spring11-PU_S1_START311_V1G1-v1/29032011_213110/TOPTREE")
#sys.exit(1)
#### Remove DataSet -> ALL associated PatTuples -> All associated TopTrees
if not options.cleanup and not options.rmDataSet == "None":
log.output("--> Removing dataset "+options.rmDataSet+" and all associated PATtuples and TopTrees")
# test suite
# for getting stuff from fjr files
#from fjrHandler import FJRHandler,GreenBoxHandler
#from xml.sax import make_parser
#from xml.sax.handler import ContentHandler
#file="CMSSW_4_1_4_patch4_TopTreeProd_41X_v4/src/ConfigurationFiles/WWtoAnything_TuneZ2_7TeV-pythia6-tauola/Spring11-PU_S1_START311_V1G1-v1/17062011_105711/TOPTREE_Spring11-PU_S1_START311_V1G1-v1_17062011_105711/res/crab_fjr_100.xml"
#parser = make_parser()
#handler = FJRHandler()
#parser.setContentHandler(handler)
#parser.parse(open(file))
#print handler.getEventsProcessed()
#print handler.getFrameworkExitCode().split("\n")[0]
from CrabHandler import CRABHandler
from logHandler import logHandler
crab = CRABHandler(
"1234567",
"CMSSW_4_1_4_patch4_TopTreeProd_41X_v4/src/ConfigurationFiles/WWtoAnything_TuneZ2_7TeV-pythia6-tauola/Spring11-PU_S1_START311_V1G1-v1/17062011_105711/",
logHandler(""))
crab.UIWorkingDir = "TOPTREE_Spring11-PU_S1_START311_V1G1-v1_17062011_105711"
crab.checkFJR()