From dcb6e22a9e8be55cc5246b2e129ea307088cfeea Mon Sep 17 00:00:00 2001 From: tqchen Date: Mon, 22 Dec 2014 00:20:13 -0800 Subject: [PATCH] add mapred tasks --- tracker/rabit_hadoop.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tracker/rabit_hadoop.py b/tracker/rabit_hadoop.py index 4a2cdb718..79e0cb133 100755 --- a/tracker/rabit_hadoop.py +++ b/tracker/rabit_hadoop.py @@ -35,7 +35,7 @@ if hadoop_streaming_jar != None: args.hadoop_streaming_jar = hadoop_streaming_jar def hadoop_streaming(nslaves, slave_args): - cmd = '%s jar %s -input %s -output %s -mapper \"%s stdin %d %d stdout %s\" -reducer \"/bin/cat\" -file %s' % (args.hadoop_binary, args.hadoop_streaming_jar, args.input, args.output, args.mapper, args.nclusters, args.iterations, ' '.join(slave_args), args.mapper) + cmd = '%s jar %s -input %s -output %s -mapper \"%s stdin %d %d stdout %s\" -reducer \"/bin/cat\" -file %s -D mapred.map.tasks=%d' % (args.hadoop_binary, args.hadoop_streaming_jar, args.input, args.output, args.mapper, args.nclusters, args.iterations, ' '.join(slave_args), args.mapper, nslaves) print cmd subprocess.check_call(cmd, shell = True)