justIN           Dashboard       Workflows       Jobs       AWT       Sites       Storages       Docs       Login

20th March: justIN upgraded to 01.03 - please report any problems in #computing-operations or #user_grid_usage on Slack

Workflow 5780, Stage 1

Priority50
Processors1
Wall seconds80000
Image/cvmfs/singularity.opensciencegrid.org/fermilab/fnal-wn-sl7:latest
RSS bytes6815744000 (6500 MiB)
Max distance for inputs100.0
Enabled input RSEs CERN_PDUNE_EOS, DUNE_CA_SFU, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_GLASGOW, DUNE_UK_LANCASTER_CEPH, DUNE_UK_MANCHESTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, MONTECARLO, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled output RSEs CERN_PDUNE_EOS, DUNE_CA_SFU, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_GLASGOW, DUNE_UK_LANCASTER_CEPH, DUNE_UK_MANCHESTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled sites BR_CBPF, CA_SFU, CA_Victoria, CERN, CH_UNIBE-LHEP, CZ_FZU, ES_CIEMAT, ES_PIC, FR_CCIN2P3, IN_TIFR, IT_CNAF, NL_NIKHEF, NL_SURFsara, UK_Bristol, UK_Brunel, UK_Durham, UK_Edinburgh, UK_Glasgow, UK_Imperial, UK_Lancaster, UK_Liverpool, UK_Manchester, UK_Oxford, UK_QMUL, UK_RAL-PPD, UK_RAL-Tier1, UK_Sheffield, US_Caltech, US_Colorado, US_FNAL-FermiGrid, US_FNAL-T1, US_Michigan, US_MIT, US_Nebraska, US_NotreDame, US_PuertoRico, US_SU-ITS, US_Swan, US_UChicago, US_UConn-HPC, US_UCSD, US_Wisconsin
Scopeusertests
Events for this stage

Output patterns

 DestinationPatternLifetimeFor next stageRSE expression
1https://fndcadoor.fnal.gov:2880/dune/scratch/users/ykermaid/pdvd_muon/05780/1prod_muon_*.*

Environment variables

NameValue
DUNESW_TAR/cvmfs/fifeuser2.opensciencegrid.org/sw/dune/497fe0b9af7ebfe5ac11fff59041e9416f4d09cb
MCJob1
NEVENTS10
pipyaml1
UTIL_TAR/cvmfs/fifeuser3.opensciencegrid.org/sw/dune/199131cee684dd1320bd420afcd34d86f3b3b48c
YAMLFILEpdvd_muon_m_450MeV_gen.yaml

File states

Total filesFindingUnallocatedAllocatedOutputtingProcessedNot foundFailed
10000000100000

Job states

TotalSubmittedStartedProcessingOutputtingFinishedNotusedAbortedStalledJobscript errorOutputting failedNone processed
151300001198002350278
Files processed00100100200200300300400400500500600600700700800800900900Mar-28 13:00Mar-28 16:00Mar-28 19:00Mar-28 22:00Mar-29 01:00Mar-29 04:00Mar-29 07:00Mar-29 10:00Mar-29 13:00Mar-29 16:00Mar-29 19:00Mar-29 22:00Mar-30 01:00Mar-30 04:00Mar-30 07:00Mar-30 10:00Mar-30 13:00Mar-30 16:00Mar-30 19:00Mar-30 22:00Mar-31 01:00Mar-31 04:00Files processedBin start timesNumber per binUS_ColoradoUK_RAL-PPDFR_CCIN2P3US_UChicagoES_PICUS_WisconsinCZ_FZUUK_LiverpoolUK_OxfordUK_LancasterNL_NIKHEFUK_RAL-Tier1US_FNAL-FermiG…US_FNAL-FermiGridUK_QMULCA_SFUUK_GlasgowUK_Brunel

RSEs used

NameInputsOutputs
MONTECARLO10370
None015000

Stats of processed input files as CSV or JSON, and of uploaded output files as CSV or JSON (up to 10000 files included)

File reset events, by site

SiteAllocatedOutputting
US_FNAL-FermiGrid20

Jobscript

#!/bin/bash
#

#These must be defined
#if [ -z $FCL_FILE ]; then
#  echo "Fatal Must provide FCL_FILE env var"
#  exit 1
#fi

if [ -z $UTIL_TAR ]; then
  echo "Fatal must provide UTIL_TAR env var"
  exit 1
fi
export PYTHONPATH=$UTIL_TAR:$PYTHONPATH

source /cvmfs/dune.opensciencegrid.org/products/dune/setup_dune.sh
setup metacat
export METACAT_SERVER_URL=https://metacat.fnal.gov:9443/dune_meta_prod/app
export METACAT_AUTH_SERVER_URL=https://metacat.fnal.gov:8143/auth/dune

if [ -z ${JUSTIN_PROCESSORS} ]; then
  JUSTIN_PROCESSORS=1
fi

echo "Justin processors: ${JUSTIN_PROCESSORS}"

export TF_NUM_THREADS=${JUSTIN_PROCESSORS}   
export OPENBLAS_NUM_THREADS=${JUSTIN_PROCESSORS} 
export JULIA_NUM_THREADS=${JUSTIN_PROCESSORS} 
export MKL_NUM_THREADS=${JUSTIN_PROCESSORS} 
export NUMEXPR_NUM_THREADS=${JUSTIN_PROCESSORS} 
export OMP_NUM_THREADS=${JUSTIN_PROCESSORS}  

echo "Justin specific env vars"
env | grep JUSTIN
now=$(date -u +"%Y%m%dT%H%M%SZ")
jobid=`echo "${JUSTIN_JOBSUB_ID:-1}" | cut -f1 -d'@' | sed -e "s/\./_/"`
stageid=${JUSTIN_STAGE_ID:-1}
a=1
 if [ -n "$DUNESW_TAR" ]; then
   stat ${DUNESW_TAR}
   if [ $? -ne 0 ]; then
     echo "Failed to stat $DUNESW_TAR. Exiting safely"
     exit 0
   fi
 
   export PRODUCTS=$DUNESW_TAR:$PRODUCTS 
   echo "Set dunesw to $DUNESW_TAR"
 fi

 if [ -n "$WIRECELL_TAR" ]; then
   stat ${WIRECELL_TAR}
   if [ $? -ne 0 ]; then
     echo "Failed to stat $WIRECELL_TAR. Exiting safely"
     exit 0
   fi
 
   export PRODUCTS=$WIRECELL_TAR:$PRODUCTS 
   echo "Set wirecell to $WIRECELL_TAR"
 fi

 #Setup recent lar software suite
 DUNESW_VERSION=${DUNESW_VERSION:-v10_04_01d00}
 setup dunesw \
    "${DUNESW_VERSION}" \
    -q "${DUNE_QUALIFIER:-e26:prof}"
 
 setup_exit=$?
 if [ $? -ne 0 ]; then
   echo "Failed to setup dunesw $DUNESW_VERSION $DUNE_QUALIFIER"
   exit $setup_exit
 fi
 
 echo "DUNESW loc:"
 ups active | grep dunesw

 echo "WIRECELL loc:"
 ups active | grep wirecell
 
 export FHICL_FILE_PATH=${DUNESW_TAR}:${FHICL_FILE_PATH}
 export FW_SEARCH_PATH=${DUNESW_TAR}:${FW_SEARCH_PATH}
 
 echo "printing env"
 env
 echo "DUNE specific env vars"
 env | grep DUNE

# User can specify to pip install pyyaml
if [ -n "$pipyaml" ]; then
  echo "Installing yaml"
  pip install --user pyyaml
  echo "Done"
# elif [ -n "${YAML_TAR}" ]; then
#   echo "Using venv at ${YAML_TAR}"
#   source ${YAML_TAR}/yaml_venv/bin/activate
fi


 echo "Will use justin-get-file"
 DID_PFN_RSE=`$JUSTIN_PATH/justin-get-file`
 if [ "${DID_PFN_RSE}" == "" ] ; then
   echo "Could not get file"
   exit 0
 fi
 pfn=`echo ${DID_PFN_RSE} | cut -f2 -d' '`
 did=`echo ${DID_PFN_RSE} | cut -f1 -d' '`
 
 input_filename=`echo $did | cut -f2 -d':'`
 echo "input file: $input_filename"

 echo "jobsub_id: ${JUSTIN_JOBSUB_ID:-1}"
 
 #Get run/subrun from parent if using input -- else from justin job ID/process"
 if [ -z "$MCJob" ]; then
   echo "Getting run subrun from $did"
   run_subrun=`python -m beam_job_utils get_run_subrun -i $did`
   get_run_ret=$?
   if [ $get_run_ret -ne 0 ]; then
     echo "error in get_run_subrun"
   fi
 
   echo $run_subrun
   run=`echo $run_subrun | cut -f1 -d' '`
   subrun=`echo $run_subrun | cut -f2 -d' '`
 else
   run=`echo $jobid | cut -f1 -d'_'`  ##TODO -- check order here
   subrun=`echo $jobid | cut -f2 -d'_'`
 fi
 nevents=${NEVENTS:--1} #Set from env override or -1 
 NSKIP=${NSKIP:-0} 
 echo "nevents: $nevents"
 
 overrides="core.data_tier=full-reconstructed \
  core.application.version=${DUNESW_VERSION} \
  core.application.name=reco \
  core.application.family=dunesw \
  core.application=dunesw.reco \
 "

#User specifies if they'd like to use an input file or not 
if [ -n "$MCJob" ]; then
  inputflag=""
else
  inputflag="-i $pfn --parent $did"
fi

echo "input flag: $inputflag"

# TODO -- metadata file configurable
python -m beam_job_utils run_job \
      --json ${UTIL_TAR}/pdvd_muon_base_meta.json \
      --overrides ${overrides} \
      --run $run \
      --subrun $subrun \
      --yaml ${UTIL_TAR}/${YAMLFILE:-pdvd_muon_gen.yaml} \
      --nevents $nevents \
      $inputflag

exitcode=$?
if [ $exitcode -ne 0 ]; then
  echo "Error running. Exiting with ${exitcode}"
  exit $exitcode
fi

echo "$pfn" > justin-processed-pfns.txt
justIN time: 2025-04-02 09:25:32 UTC       justIN version: 01.03.00