Mercurial > hg > cc > cirrus_home

view bin/ezip.sh @ 190:f2bf736c2d40

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
working, with issues: 1) warc.export.cdx.path is not set 2) mime property isn't getting through 3) lastMod isn't showing up
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Tue, 24 Sep 2024 17:08:05 +0100
parents 464d2dfb99c9
children
line wrap: on
line source

#!/bin/bash
# Invoke this as e.g. sbatch -n 4 -c 32 --exclusive masterJob.sh ezip
# run pigz -p 8 on extract_...tar files
n=$SLURM_NTASKS
c=$SLURM_CPUS_PER_TASK
node=$SLURMD_NODENAME
local=$SLURM_LOCALID
proc=$SLURM_PROCID
echo $(date) $node:$proc start

module load gnu-parallel

parallel --will-cite -j $c -n 1 'pigz -p 8 {}/orig/extracts/*.tar' < ezip/$proc.txt

echo $(date) $proc end