text-sort.small 1.1 KB

12345678910111213141516171819202122232425
  1. #!/usr/bin/env bash
  2. # Licensed under the Apache License, Version 2.0 (the "License");
  3. # you may not use this file except in compliance with the License.
  4. # You may obtain a copy of the License at
  5. #
  6. # http://www.apache.org/licenses/LICENSE-2.0
  7. #
  8. # Unless required by applicable law or agreed to in writing, software
  9. # distributed under the License is distributed on an "AS IS" BASIS,
  10. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  11. # See the License for the specific language governing permissions and
  12. # limitations under the License.
  13. GRID_DIR=`dirname "$0"`
  14. GRID_DIR=`cd "$GRID_DIR"; pwd`
  15. source $GRID_DIR/../gridmix-env
  16. INDIR="${VARINFLTEXT}/{part-00000,part-00001,part-00002}"
  17. Date=`date +%F-%H-%M-%S-%N`
  18. OUTDIR=perf-out/sort-out-dir-small_$Date
  19. ${HADOOP_PREFIX}/bin/hadoop dfs -rmr $OUTDIR
  20. ${HADOOP_PREFIX}/bin/hadoop jar ${EXAMPLE_JAR} sort -m 1 -r $NUM_OF_REDUCERS_FOR_SMALL_JOB -inFormat org.apache.hadoop.mapred.KeyValueTextInputFormat -outFormat org.apache.hadoop.mapred.TextOutputFormat -outKey org.apache.hadoop.io.Text -outValue org.apache.hadoop.io.Text $INDIR $OUTDIR