| #!/usr/bin/env bash |
| |
| GRID_DIR=`dirname "$0"` |
| GRID_DIR=`cd "$GRID_DIR"; pwd` |
| source $GRID_DIR/../gridmix-env |
| |
| NUM_OF_REDUCERS=$NUM_OF_REDUCERS_FOR_LARGE_JOB |
| INDIR=${VARCOMPSEQ}/{part-000*0,part-000*1} |
| Date=`date +%F-%H-%M-%S-%N` |
| |
| OUTDIR=perf-out/webdata-sort-out-dir-large_$Date |
| ${HADOOP_HOME}/bin/hadoop dfs -rmr $OUTDIR |
| |
| ${HADOOP_HOME}/bin/hadoop jar $APP_JAR loadgen -keepmap 100 -keepred 100 -inFormat org.apache.hadoop.mapred.SequenceFileInputFormat -outFormat org.apache.hadoop.mapred.SequenceFileOutputFormat -outKey org.apache.hadoop.io.Text -outValue org.apache.hadoop.io.Text -indir $INDIR -outdir $OUTDIR -r $NUM_OF_REDUCERS |
| |
| |
