Page History

...

Monitor its progress form URL: http://maghdp01.nersc.gov:50030/^{Image Removed}http://maghdp01.nersc.gov:50070/^{Image Removed}

xxxx

...

/

To re-run a job you must first CLEANUP old output files: hadoop dfs -rmr wordcount-opd

Next run Hadoop on 4 reducers : hadoop jar /usr/common/tig/hadoop/hadoop-0.20.2+228/hadoop-0.20.2+228-examples.jar wordcount -Dmapred.reduce.tasks=4   wordcount-in wordcount-op

Some suggestion: change user permision to allow me to read the Hadoop output because Hadopp owns all by default????
Or use provided script: fixperms.sh /global/scratch/sd/balewski/hadoop/wordcount- gpfs/
hadoop jar /usr/common/tig/hadoop/hadoop-0.20.2+228/hadoop-0.20.2+228-examples.jar wordcount -Dmapred.reduce.tasks=4   wordcount-in wordcount-op

• d
• d
•