# HG changeset patch # User Henry S. Thompson # Date 1582546570 0 # Node ID 3b56c2c9d0eed03ac94f39fae334fb10197d908a # Parent 25ca3505b4d7be7788ae12b0c3ffdf1b9a02a9c5 longer run, terser logging diff -r 25ca3505b4d7 -r 3b56c2c9d0ee bin/doPlinks.sh --- a/bin/doPlinks.sh Mon Feb 24 00:44:53 2020 +0000 +++ b/bin/doPlinks.sh Mon Feb 24 12:16:10 2020 +0000 @@ -11,9 +11,10 @@ plinks.py $tfn || { echo $(date) $hn aborted job $jn for $tfn \[remember to clean up\] ; rm -f /dev/shm/stopJob ; exit 1 ; } echo $(date) $hn tarring $(ls badpdfs_*|wc -l)/$(ls links_*_*|wc -l) results from job $jn for $tfn in $(pwd) 1>&2 tar -cf /beegfs/common_crawl/CC-MAIN-2019-35/pdfs/links/${tfn}.tar badpdfs_${tfn} links_${tfn}_* -echo $(pwd) rm * 1>&2 +echo $(date) $(pwd) rm $(ls -lt badpdfs_*) +echo . . . $(ls -lt links_*_* | tee >(tail -1 1>&2) | head -1) 1>&2 rm * cd .. -echo $(pwd) rmdir ${tfn} 1>&2 +echo $(date) $(pwd) rmdir ${tfn} 1>&2 rmdir ${tfn} echo $(date) $hn finished job ${jn} for ${tfn} diff -r 25ca3505b4d7 -r 3b56c2c9d0ee bin/plinks.sh --- a/bin/plinks.sh Mon Feb 24 00:44:53 2020 +0000 +++ b/bin/plinks.sh Mon Feb 24 12:16:10 2020 +0000 @@ -3,6 +3,6 @@ echo $(date) $(hostname) h=$(hostname) hn=${h##*n} -if [ $hn -eq 0 ]; then echo {001..002}; else echo {003..004}; fi |\ -tr ' ' '\012' |parallel --will-cite -j 71 -N 1 doPlinks.sh ${hn} '{#}' '{}' +if [ $hn -eq 0 ]; then echo {005..008}; else echo {009..012}; fi |\ +tr ' ' '\012' |parallel --will-cite -j 4 -N 1 doPlinks.sh ${hn} '{#}' '{}' echo $(date) $(hostname) $? diff -r 25ca3505b4d7 -r 3b56c2c9d0ee plinksJob.sh --- a/plinksJob.sh Mon Feb 24 00:44:53 2020 +0000 +++ b/plinksJob.sh Mon Feb 24 12:16:10 2020 +0000 @@ -11,7 +11,7 @@ cd ${PBS_O_WORKDIR} export MPI_SHEPHERD=true -export MPI_UNBUFFERED_STDIO=true +#export MPI_UNBUFFERED_STDIO=true not needed anymore since debug logging pruned mpiexec_mpt -ppn 1 -n 2 bin/plinks.sh 2019-35