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
Site
Allocated
Outputting
US_NERSC-CPU
15
0
Jobscript
#!/bin/bash
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#
# This script for running the pandora workflow is based on the data production
# development by Matt Kramer (https://github.com/DUNE/2x2_sim/blob/feature_spine_on_data/run-cafmaker)
#
# Starting on July 1, 2025, please use the software deployed on dune cvmfs repository
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#++++++++++++++++++++++++++++++++++++++++
# the script with common functions
#++++++++++++++++++++++++++++++++++++++++
source /cvmfs/dune.opensciencegrid.org/dunend/2x2/releases/${TWOBYTWO_RELEASE}/ndlar_prod_scripts/ND_Production/toolbox/scripts/NDUtilsForJustin.sh
#++++++++++++++++++++++++++++++++++++++++++
# sanity check
#++++++++++++++++++++++++++++++++++++++++++
if [[ "${DATA_TIER}" != "caf" ]]; then
echo -e "This script [$(basename $BASH_SOURCE)] submits the CAF analysis jobs. Please see the help menu. The data tier is not defined correctly."
exit 0
fi
#+++++++++++++++++++++++++++++++++++++++++
# environment variables
#+++++++++++++++++++++++++++++++++++++++++
echo -e "\tThe SPINE JustIN workflow id is [ ${SPINE_WORKFLOW_ID} ]\n" 2>&1 | tee -a $envlog
echo -e "\tThe Mx2 JustIN workflow id is [ ${MX2_WORKFLOW_ID} ]\n" 2>&1 | tee -a $envlog
#++++++++++++++++++++++++++++++++++++++++
# Begin JustIN
#++++++++++++++++++++++++++++++++++++++++
justin_begin_of_job_commands
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# containers to store the parent and child files
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
PARENT_FILES=("${did}")
MATCHED_FILES=()
CREATED_FILES=()
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# get the file namespace
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++
get_namespace()
{
filename=$1
if [[ "${filename}" == *"dst"* ]]; then
echo "neardet-2x2-minerva"
elif [[ "${filename}" == *SPINE* ]]; then
echo "neardet-2x2-lar"
fi
}
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# Get the matching files
#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++
get_matching_files()
{
echo -e "Downloading the matching files for the cafmaker workflow." 2>&1 | tee -a $envlog
(
source /cvmfs/dune.opensciencegrid.org/products/dune/setup_dune.sh
setup python ${PYTHON_VERSION}
echo -e "\tRunning the command [ python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/GetInputList.py --file=${did} ${MATCHING_OPTION} ].\n" 2>&1 | tee -a $envlog
python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/GetInputList.py --file=${did} ${MATCHING_OPTION} 2>&1 | tee -a $envlog
)
namespace="downloads"
if [ ! -d ${namespace} ]; then
echo -e "\tFailed to get the matching ${MATCHED_TYPE} files.\n" 2>&1 | tee -a $envlog
exit 0
else
cd ${namespace}
for filename in * ;
do
read -r -a file_namespace <<< "$(get_namespace ${filename})"
PARENT_FILES+=("${file_namespace}:${filename}")
MATCHED_FILES+=("${filename}")
done
fi
echo -e "\tThe parent files are [${PARENT_FILES[@]}].\n" 2>&1 | tee -a $envlog
echo -e "\t\tThe matching files are [${MATCHED_FILES[@]}].\n" 2>&1 | tee -a $envlog
cd ${WORKSPACE}
mv ${namespace}/* ${WORKSPACE}/
rm -rf ${namespace}
}
#+++++++++++++++++++++++++++++++++++++++++++++
# parse the matching minvera file
#+++++++++++++++++++++++++++++++++++++++++++++
parse_matching_mx2_file()
{
echo -e "Parse the matching mx2 files using the input file metadata." 2>&1 | tee -a $envlog
cd ${WORKSPACE}
MX2_FILENAME=`ls *dst*root`
(
source /cvmfs/dune.opensciencegrid.org/products/dune/setup_dune.sh
setup python ${PYTHON_VERSION}
setup root ${ROOT_VERSION} -q ${ROOT_QUALIFIER}
echo -e "\tRunning the command [ python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/ParseMatchedMx2Data.py --input_file=${did} --minerva_file=${MX2_FILENAME} ].\n" 2>&1 | tee -a $envlog
python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/ParseMatchedMx2Data.py --input_file=${did} --minerva_file=${MX2_FILENAME}
)
namespace="matched_mx2"
if [ ! -d ${namespace} ]; then
echo -e "\tFailed to get the parsed mx2 matching file.\n" 2>&1 | tee -a $envlog
exit 0
else
TMP_ARRAY=("${MATCHED_FILES[@]}")
unset MATCHED_FILES
for filename in "${TMP_ARRAY[@]}" ;
do
if [[ "${filename}" != "${MX2_FILENAME}" ]]; then
MATCHED_FILES+=("${filename}")
fi
done
cd ${namespace}
UPDATED_MX2_FILE=`ls *.root`
MATCHED_FILES+=("${UPDATED_MX2_FILE}")
cd ${WORKSPACE}
mv ${namespace}/* ${WORKSPACE}/
rm -rf ${namespace}
fi
echo -e "Completed parsing the matching mx2 files using the input file metadata." 2>&1 | tee -a $envlog
}
#+++++++++++++++++++++++++++++++++++++++++
# Run the cafmaker workflow
#+++++++++++++++++++++++++++++++++++++++++
execute_cafmaker_workflow()
{
echo -e "Enter executing the caf maker workflow for data stream [${DATA_STREAM}] and input file [${INPUT_FILE}]" 2>&1 | tee -a $envlog
cd ${WORKSPACE}
DATA_FILES=""
for filename in "${MATCHED_FILES[@]}" ;
do
DATA_FILES+="${filename}"
DATA_FILES+=","
done
DATA_FILES+="${INPUT_FILE}"
echo -e "\tThe input files are [${DATA_FILES}]" 2>&1 | tee -a $envlog
if [[ "${RUN_CAF_MX2}" == "1" ]]; then
IFS='_' read -a flist <<< "${INPUT_FILE}"
CAF_OUTPUT_FILE="${flist[0]}_${flist[1]}_${flist[2]}_${flist[3]}_${flist[4]}_$(date +'%y%m%d%H%M%S')_CDT.CAF.root"
else
IFS='-' read -a flist <<< "${INPUT_FILE}"
CAF_OUTPUT_FILE="${flist[0]}-${flist[1]}-$(date +'%Y_%m_%d_%H_%M_%S')_CDT.CAF.root"
fi
echo -e "\tThe output caf file name is [${CAF_OUTPUT_FILE}]" 2>&1 | tee -a $envlog
(
source ${CVMFS_WORKING_DIR}/cafmaker/ND_CAFMaker/ndcaf_setup.sh
echo -e "\tRunning the command [ python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/MakeCafFhiclFile.py --infiles=${DATA_FILES} --outfile=${CAF_OUTPUT_FILE} ].\n" 2>&1 | tee -a $envlog
python ${CVMFS_WORKING_DIR}/ndlar_prod_scripts/ND_Production/toolbox/scripts/MakeCafFhiclFile.py --infiles="${DATA_FILES}" --outfile=${CAF_OUTPUT_FILE}
echo -e "\tRunning the command [ export CAFFCLFILE=`ls *.fcl` ].\n" 2>&1 | tee -a $envlog
export CAFFCLFILE=`ls *.fcl`
echo -e "\tRunning the command [ makeCAF --fcl=${CAFFCLFILE} ].\n" 2>&1 | tee -a $envlog
makeCAF --fcl=${CAFFCLFILE}
)
if [ ! -f ${CAF_OUTPUT_FILE} ]; then
echo -e "FATAL::The file [${CAF_OUTPUT_FILE}] does not exist! Will not continue." 2>&1 | tee -a $envlog
exit 1
fi
CAF_FLAT_OUTPUT_FILE="${CAF_OUTPUT_FILE/.CAF.root/.CAF.flat.root}"
if [ ! -f ${CAF_FLAT_OUTPUT_FILE} ]; then
echo -e "FATAL::The file [${CAF_FLAT_OUTPUT_FILE}] does not exist! Will not continue." 2>&1 | tee -a $envlog
exit 1
fi
CREATED_FILES+=("${CAF_OUTPUT_FILE}")
CREATED_FILES+=("${CAF_FLAT_OUTPUT_FILE}")
echo -e "Exit executing the caf maker workflow for data stream [${DATA_STREAM}]\n" 2>&1 | tee -a $envlog
}
#++++++++++++++++++++++++++++++++++++++
# execute the jobs
#+++++++++++++++++++++++++++++++++++++
echo -e "\n\n" 2>&1 | tee -a $envlog
if [[ "${RUN_CAF_PANDORA_SPINE_MX2}" == "1" ]]; then
export MATCHED_TYPE="spine and mx2"
export MATCHING_OPTION="--spine --mx2 --spine_justin=${SPINE_WORKFLOW_ID} --mx2_justin=${MX2_WORKFLOW_ID}"
get_matching_files
parse_matching_mx2_file
elif [[ "${RUN_CAF_PANDORA_SPINE}" == "1" ]]; then
export MATCHED_TYPE="spine"
export MATCHING_OPTION="--spine --spine_justin=${SPINE_WORKFLOW_ID}"
get_matching_files
elif [[ "${RUN_CAF_PANDORA_MX2}" == "1" || "${RUN_CAF_SPINE_MX2}" == "1" ]]; then
export MATCHED_TYPE="mx2"
export MATCHING_OPTION="--mx2 --mx2_justin=${MX2_WORKFLOW_ID}"
get_matching_files
parse_matching_mx2_file
fi
execute_cafmaker_workflow
WORKFLOW+=("cafmaker")
WORKFLOW+=("cafmaker_flat")
export NAMESPACE="neardet-2x2-lar"
export APPLICATION_DATA_TIER="caf-analysis"
#++++++++++++++++++++++++++++++++++++++++
# create metadata json file
#++++++++++++++++++++++++++++++++++++++++
create_metadata_file
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# remove all download matching files, do not want files to be transfer to rucio storage element
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
for filename in *.root ;
do
if [[ "${filename}" != *"CAF"* ]]; then
echo -e "\tRemoving the filename [${filename}]\n" 2>&1 | tee -a $envlog
rm ${filename}
fi
done
#+++++++++++++++++++++++++++++++++++++++
# End of justin job running
#+++++++++++++++++++++++++++++++++++++++
justin_end_of_job_commands
######################################
#
# END OF RUNNING NDLAr CAFMAKER JOBS
#
######################################
exit 0
justIN time: 2025-09-19 05:14:51 UTC justIN version: 01.05.00
