2、Yarn集群wordcount测试_Hadoop性能测试_托管Hadoop

帮助文档（华北一、二）

使用BigDataBench的数据源，从10GB开始，每次增加10GB，直至200GB。生成数据源代码如下：

● yarn-wordcount数据源生成代码

wget

http://prof.ict.ac.cn/bdb_uploads/bdb_3_1/packages/BigDataBench_V3.2.1_Hadoop.tar.gz

tar zxf BigDataBench_V3.2.1_Hadoop.tar.gz

cd BigDataBench_V3.2.1_Hadoop_Hive/MicroBenchmarks sh genData_MicroBenchmarks.sh 200

依次从数据源取数据，进行wordcount测试，并打印结果，代码如下：

● yarn-wordcount-run.sh

#!/bin/bash

source /home/hadoop/.bashrc

WORK_DIR=`pwd`

echo "WORK_DIR=$WORK_DIR data should be put in $WORK_DIR/data-MicroBenchmarks/in"

${HADOOP_HOME}/bin/hadoop fs -mkdir -p /MicroBenchmarks/in/

${HADOOP_HOME}/bin/hadoop fs -mv /MicroBenchmarks/in/* ${WORK_DIR}/data-MicroBenchmarks/in/

for i in {1..20}

#move 10GB file from ${WORK_DIR}/data-MicroBenchmarks/in/ to /MicroBenchmarks/in/

for f in `${HADOOP_HOME}/bin/hadoop fs -ls ${WORK_DIR}/data-

MicroBenchmarks/in/ | grep lda_wiki1w | awk '{print $NF}' | head -n 20`

${HADOOP_HOME}/bin/hadoop fs -mv $f /MicroBenchmarks/in/

Done

${HADOOP_HOME}/bin/hadoop fs -rmr ${WORK_DIR}/data-MicroBenchmarks/out/wordcount

echo -n "file count = "

${HADOOP_HOME}/bin/hadoop fs -ls /MicroBenchmarks/in/ | grep lda_wiki1w | wc -l

time ${HADOOP_HOME}/bin/hadoop jar

${HADOOP_HOME}/share/hadoop/mapreduce/hadoop-mapreduce-examples-*.jar

wordcount /MicroBenchmarks/in/ ${WORK_DIR}/data-MicroBenchmarks/out/wordcount

done

对四个集群的测试结果如下：

● 表2.1 yarn集群wordcount测试结果：

产品