blob: e1329f43d543d0456e6f7f13fd85829e99a459be (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
|
#!/bin/sh
hadoop jar /usr/lib/hadoop-0.20-mapreduce/contrib/streaming/hadoop-streaming-2.0.0-mr1-cdh4.1.2.jar \
-D mapred.reduce.tasks=23 \
-D mapred.task.timeout=120000000 \
-input overlap/g120+index-16mb \
-cacheFile 'hdfs://10.0.0.1:8020/user/simianer/overlap/g120+index#g120+index' \
-output overlap/test-g120 \
-mapper merge_rules.rb \
-reducer /usr/bin/uniq \
-file merge_rules.rb \
|