diff options
| -rwxr-xr-x | please | 11 |
1 files changed, 10 insertions, 1 deletions
@@ -124,9 +124,13 @@ def run_matchcrossref(args): HDFS_DIR, args.env, datetime.strftime(datetime.now(), "%Y-%m-%d-%H%M.%S")) + # Notes: -D options must come after Tool but before class name + # https://github.com/twitter/scalding/wiki/Frequently-asked-questions#how-do-i-pass-parameters-to-my-hadoop-job-number-of-reducers--memory-options--etc- cmd = """hadoop jar \ scalding/target/scala-2.11/sandcrawler-assembly-0.2.0-SNAPSHOT.jar \ - com.twitter.scalding.Tool sandcrawler.HBaseCrossrefScoreJob \ + com.twitter.scalding.Tool \ + -Dmapred.reduce.tasks={reducers} \ + sandcrawler.ScoreJob \ --hdfs \ --app.conf.path scalding/ia_cluster.conf \ --hbase-table wbgrp-journal-extract-0-{env} \ @@ -136,6 +140,7 @@ def run_matchcrossref(args): output=output, zookeeper_hosts=ZOOKEEPER_HOSTS, env=args.env, + reducers=args.reducers, crossref_input=args.crossref_input) subprocess.call(cmd, shell=True) @@ -173,6 +178,10 @@ def main(): sub_matchcrossref.set_defaults(func=run_matchcrossref) sub_matchcrossref.add_argument('crossref_input', help="full HDFS path of Crossref JSON dump") + sub_matchcrossref.add_argument('--reducers', + help="number of reducers to run", + type=int, default=30) + args = parser.parse_args() if not args.__dict__.get("func"): |