Workflow 9596, Stage 1

Priority	50
Processors	1
Wall seconds	80000
Image	/cvmfs/singularity.opensciencegrid.org/fermilab/fnal-wn-sl7:latest
RSS bytes	4194304000 (4000 MiB)
Max distance for inputs	30.0
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, CERN, CH_UNIBE-LHEP, CZ_FZU, ES_CIEMAT, ES_PIC, FR_CCIN2P3, IT_CNAF, NL_NIKHEF, NL_SURFsara, UK_Bristol, UK_Brunel, UK_Durham, UK_Edinburgh, UK_Lancaster, UK_Liverpool, UK_Manchester, UK_Oxford, UK_QMUL, UK_RAL-PPD, UK_RAL-Tier1, UK_Sheffield, US_Colorado, US_FNAL-FermiGrid, US_FNAL-T1, US_Michigan, US_PuertoRico, US_SU-ITS, US_Swan, US_UChicago, US_UConn-HPC, US_UCSD, US_Wisconsin
Scope	usertests
Events for this stage

Output patterns

	Destination	Pattern	Lifetime	For next stage	RSE expression
1	Rucio usertests:fardet-hd-reco-ritm2612698_9596-fnal-w9596s1p1	*reco.root	864000	False

Environment variables

Name	Value
INPUT_DIR	/cvmfs/fifeuser4.opensciencegrid.org/sw/dune/11e96361e108812362e467eac67e1214a366b630

File states

Total files	Finding	Unallocated	Allocated	Outputting	Processed	Not found	Failed
30	0	0	0	0	30	0	0

Job states

Total	Submitted	Started	Processing	Outputting	Finished	Notused	Aborted	Stalled	Jobscript error	Outputting failed	None processed
87	0	0	0	0	87	0	0	0	0	0	0

RSEs used

Name	Inputs	Outputs
DUNE_US_FNAL_DISK_STAGE	28	28
PRAGUE	2	0
DUNE_ES_PIC	0	2

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

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


#Setup recent lar software suite

#setup dunesw v10_11_00d01 -q e26:prof
setup dunesw v10_12_01d01 -q e26:prof
#echo "printing env"
#env


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 "Will use justin-get-file" 
 

for nf in {1..6}
  do
  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
   continue
 fi

FILE=`echo ${DID_PFN_RSE} | cut -f2 -d' '`
DID=`echo ${DID_PFN_RSE} | cut -f1 -d' '`
 echo ${DID} >> did.list
 echo ${FILE} >> file.list 
done
 
while read inFile; do

temp=`echo "$inFile" | awk -F'/' '{print $NF}'`
DID="fardet-hd:"$temp
FILE=$inFile 
 
 
metacat file show -mj ${DID} > old_md.json
mcExit=$?
if [ $mcExit -eq 0 ] ; then
  echo "old metadata:"
  cat old_md.json
else
  echo "Could not retrieve old metadata"
  exit 1 
fi

now=$(date -u +"%Y%m%dT%H%M%SZ")  
namespace=${JUSTIN_SCOPE:-"usertests"}

echo "===============JUSTIN_JOBSUB_ID"
runid=$JUSTIN_WORKFLOW_ID
CLUSTER=`echo $JUSTIN_JOBSUB_ID | awk '{split($0,a,"."); print a[1]}'`
echo $CLUSTER
 
# reco2
echo "============TPG========================" 


infile=`echo $DID | awk -F ':' '{print $2}'`
reco="${infile%.root}" 
reco_name=${reco}_${now}_reco

echo "check  output filename "  ${reco_name}.root

lar -c  tpg_dune10kt_1x2x6.fcl $FILE -o ${reco_name}.root -n -1
larExit=$? 


#echo "Reco step lar exit code $larExit"


if [ $larExit -eq 0 ] ; then 
  echo "Moving on to metadata extractor "
else
  exit $larExit 
fi
 
#OUTFILE=`ls *reco.root`
OUTFILE=${reco_name}.root

#mv triggerAnaTree_hist.root triggerAnaTree_${reco_name}_hist.root


echo "============OUTPUT FILE: " $OUTFILE  
 
extractor_prod.py --infile ${OUTFILE}  --no_crc    --appfamily art --appname reco --appversion  v10_12_01d01  --requestid ritm2612698  --input_json ${INPUT_DIR}/trg_input.json> ${OUTFILE}.ext.json  && sed -i -e 's/physics/fardet-hd/g' ${OUTFILE}.ext.json

extractorExit=$?
if [ $extractorExit -eq 0 ] ; then
  # Success !
  echo "Extracted metadata"
else
  # Error -- exit immediately 
  jobscriptExit=1
  echo "Failed to extract md"
  exit $extractorExit
fi

sed -i 's/Reco2/reco2/g'  ${OUTFILE}.ext.json

echo "checking file======" $DID
echo $DID > all-input-dids.txt
python ${INPUT_DIR}/pdjson2metadata ${OUTFILE}.ext.json  all-input-dids.txt usertests > ${OUTFILE}.temp.json 


sed '/DUNE/ s/.*/\L&/'  ${OUTFILE}.temp.json >  ${OUTFILE}.json

idrun=`jq -r '.. | objects | select(has("core.runs")) | .["core.runs"][0]' old_md.json`
idsubrun=`jq -r '.. | objects | select(has("core.runs_subruns")) | .["core.runs_subruns"][0]' old_md.json`

sed -i "s/-99999/$idrun/g" ${OUTFILE}.json
sed -i "s/-88888/$idsubrun/g" ${OUTFILE}.json

# cp ${OUTFILE}.json triggerAnaTree_${reco_name}_hist.root.json
		  
converterExit=$?
if [ $converterExit -eq 0 ] ; then
  # Success !
  echo "MD conversion to MetaCat OK"
#  echo "$FILE" > justin-processed-pfns.txt
   echo "$FILE" >> temp_pfns.txt
else 
  jobscriptExit=1
  echo "Failed to convert md to MetacaCat"
  exit $converterExit
fi

 
ls

done < file.list
cp temp_pfns.txt justin-processed-pfns.txt
exit 0