justIN           Dashboard       Workflows       Jobs       AWT       Sites       Storages       Docs       Login

Workflow 2312, Stage 1

Priority50
Processors1
Wall seconds80000
RSS bytes4193255424 (3999 MiB)
Max distance for inputs30.0
Enabled input RSEs CERN_PDUNE_EOS, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_LANCASTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, MANCHESTER, MONTECARLO, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled output RSEs CERN_PDUNE_EOS, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_LANCASTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, MANCHESTER, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled sites 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_Imperial, UK_Lancaster, UK_Liverpool, UK_Manchester, UK_Oxford, UK_QMUL, UK_RAL-Tier1, UK_Sheffield, US_BNL, 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 stage
1https://fndcadoor.fnal.gov:2880/dune/scratch/users/calcuttj/justin/keepup_calib_test_DC061224_5888ticks_full/02312/1*keepup.root
2https://fndcadoor.fnal.gov:2880/dune/scratch/users/calcuttj/justin/keepup_calib_test_DC061224_5888ticks_hists_full/02312/1*hists.root

Environment variables

NameValue
DUNESW_DIR/cvmfs/fifeuser1.opensciencegrid.org/sw/dune/a825075d2d667761c53ad75e9ed3854813f79300
METADATA_DIR/cvmfs/fifeuser1.opensciencegrid.org/sw/dune/71312b084e88d11383c26dec68480085013309ce

File states

Total filesFindingUnallocatedAllocatedOutputtingProcessedNot foundFailed
550901440053261722

Job states

TotalSubmittedStartedProcessingOutputtingFinishedNotusedAbortedStalledJobscript errorOutputting failedNone processed
9291000073210055611332810
Files processed0020020040040060060080080010001000120012001400140016001600Jun-13 13:00Jun-13 20:00Jun-14 03:00Jun-14 10:00Jun-14 17:00Jun-15 00:00Jun-15 07:00Jun-15 14:00Jun-15 21:00Jun-16 04:00Jun-16 11:00Jun-16 18:00Jun-17 01:00Jun-17 08:00Jun-17 15:00Jun-17 22:00Jun-18 05:00Jun-18 12:00Jun-18 19:00Jun-19 02:00Jun-19 09:00Files processedBin start timesNumber per binCERNIT_CNAFFR_CCIN2P3NL_NIKHEFUK_QMULUK_BrunelUK_ImperialUK_LancasterUK_ManchesterUK_SheffieldUK_LiverpoolUK_DurhamES_PICNL_SURFsara
Replicas per RSE5492490.025244.55492269.975244.50000000000003Replicas per RSEDUNE_CERN_EOS (50%)FNAL_DCACHE (50%)

RSEs used

NameInputsOutputs
DUNE_CERN_EOS72530

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
CERN11826
UK_Manchester1140
NL_NIKHEF7411
UK_Sheffield461
IT_CNAF401
ES_PIC200
UK_Brunel200
FR_CCIN2P3170
UK_Imperial161
UK_Liverpool1360
UK_QMUL110
UK_Lancaster70
UK_Edinburgh70
NL_SURFsara20
UK_RAL-Tier11182

Jobscript

#!/bin/bash
#

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 [ -n "${DUNESW_DIR}" ]; then
  stat ${DUNESW_DIR}
  if [ $? -ne 0 ]; then
    echo "failed to stat dunesw dir"
  fi

  export PRODUCTS=$DUNESW_DIR:$PRODUCTS
fi

echo "PRODUCTS $PRODUCTS"

#Setup recent lar software suite
DUNE_VERSION=${DUNE_VERSION:-v09_90_01d00}
setup dunesw \
   "${DUNE_VERSION}" \
   -q "${DUNE_QUALIFIER:-e26:prof}"

if [ $? -ne 0 ]; then
  echo "Failed to setup dunesw $DUNE_VERSION $DUNE_QUALIFIER"
  exit 1
fi

if [ -n "${USE_INPUT_FCL}" ]; then
  
  if [ -z ${INPUT_DIR} ]; then
    echo "Error, INPUT_DIR is undefined but user requested USE_INPUT_FCL"
    exit 1
  fi

  stat ${INPUT_DIR}
  if [ $? -ne 0 ]; then
    echo "Failed to stat input dir. Exiting safely"
    exit 0
  fi

  FHICL_FILE_PATH=${INPUT_DIR}:${FHICL_FILE_PATH}
  echo "FCL PATH: $FHICL_FILE_PATH"
fi

if [ -n "${METADATA_DIR}" ]; then
  stat ${METADATA_DIR}
  if [ $? -ne 0 ]; then
    echo "failed to stat metadata dir"
  fi

  echo "metadata dir contents:"
  ls $METADATA_DIR
  PYTHONPATH=${METADATA_DIR}:$PYTHONPATH
fi


FCL=${FCL:-"standard_reco_calibration_protodunehd_keepup.fcl"}
echo "FCL dump:"
fhicl-dump ${FCL}

echo "DUNESW loc:"
ups active | grep dunesw

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 "printing env"
env

echo "Will use justin-get-file"
#
DID_PFN_RSE=`$JUSTIN_PATH/justin-get-file`
##Check that any file was returned
if [ "${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' '`
echo "pfn: ${pfn}"
echo "did: ${did}"
now=$(date -u +"%Y%m%dT%H%M%SZ")

nevents=${NEVENTS:--1}

echo "Running reco"
touch reco.log
starttime=`date +"%s"`.0
LD_PRELOAD=$XROOTD_LIB/libXrdPosixPreload.so lar \
    -c ${FCL} \
    -n ${nevents} \
    ${pfn} #>reco.log 2>&1
larExit=$?
endtime=`date +"%s"`.0

if [ $larExit -ne 0 ]; then
  echo "Error in reco"
  cat reco.log
  exit $larExit
fi

output_reco_file=`ls *keepup.root`
output_mr_file=`ls *keepup_hists.root`

echo "Output files:"
echo "\tReco: ${output_reco_file}"
echo "\tHists: ${output_mr_file}"

echo "Forming reco metadata"
python -m meta_maker --start_time $starttime --end_time $endtime --file_format "artroot" \
                     --app_family "dunesw" --app_name "reco" --app_version ${DUNE_VERSION} \
                     --data_tier "full-reconstructed" --get_events -p "$did" \
                     -f "${JUSTIN_SCOPE}:$output_reco_file" -j "${output_reco_file}.json"
echo "Ran successfully"
## TODO -- CHECK
cat ${output_reco_file}.json

echo "Forming hist metadata"
python -m meta_maker --start_time $starttime --end_time $endtime --file_format "root" \
                     --app_family "dunesw" --app_name "reco" --app_version ${DUNE_VERSION} \
                     --data_tier "root-tuple" -p $output_reco_file.json \
                     --parent_as_json \
                     -f "${JUSTIN_SCOPE}:$output_mr_file" -j "${output_mr_file}.json"
echo "formed"
cat ${output_mr_file}.json

####TEMPORARY FOR HIT CHECKER RUNNING
#output_reco_file=`ls *keepup.root`
#echo "Reco? ${output_reco_file}"
#output_mr_file=`echo ${output_reco_file}  | sed -e "s/keepup/keepup_hists/"`
#echo lar -c run_pdhd_hit_checker.fcl \
#     -T ${output_mr_file} \
#     ${output_reco_file}
#lar -c run_pdhd_hit_checker.fcl \
#     -T ${output_mr_file} \
#     ${output_reco_file}
#larExit=$?
#
#if [ $larExit -ne 0 ]; then
#  echo "Error in hit check"
#  exit $larExit
#fi
#



echo "$pfn" > justin-processed-pfns.txt
justIN time: 2024-11-17 05:17:50 UTC       justIN version: 01.01.09