hadoop streaming 语法
$HADOOP_HOME/bin/hadoop jar hadoop-streaming.jar \ -D mapred.job.name="streaming_wordcount" \-D mapred.map.tasks=3 \
-D mapred.reduce.tasks=3 \
-D mapred.job.priority=3 \
-input /input/ \
-output /output/ \
-mapper python mapper.py \
-reducer python reducer.py \
-file ./mapper.py \
-file ./reducer.py
页:
[1]