Summary: 6 instances, 6 unique

Text	Count
# TODO: use a map with spark version as the key to maintain the optional jars	1
# TODO: wait for daemons to stabilize on primary + worker nodes	1
# TODO (amoeller@): Every file has the same log config, need common place for	1
# TODO: use glob.glob	1
# TODO: sync with EMR puppet scripts - ensure we are following best practices for starting hdfs/yarn daemons	1
# TODO: check Yarn configs for yarn.log.dir/YARN_LOG_DIR, in case of overrides	1