Run Giraph on Hadoop 2.7.5

1. Download Giraph 1.3 source code.

2. Download Hadoop 2.7.5

3. vim pom.xml, change hadoop veriosn

Replace

<id>hadoop_2</id>
      <activation>
        <activeByDefault>true</activeByDefault>
      </activation>
      <modules>
        <module>giraph-dist</module>
      </modules>
       <properties>
         <hadoop.version>2.5.1</hadoop.version>

with

<id>hadoop_2</id>
      <activation>
        <activeByDefault>true</activeByDefault>
      </activation>
      <modules>
        <module>giraph-dist</module>
      </modules>
       <properties>
         <hadoop.version>2.7.5</hadoop.version>

compile Giraph

mvn clean package -DskipTests

Replace guava in hadoop

cd ${HADOOP_HOME}
rm -rf ./share/hadoop/hdfs/lib/guava-11.0.2.jar
rm -rf ./share/hadoop/tools/lib/guava-11.0.2.jar
rm -rf ./share/hadoop/httpfs/tomcat/webapps/webhdfs/WEB-INF/lib/guava-11.0.2.jar
rm -rf ./share/hadoop/yarn/lib/guava-11.0.2.jar
rm -rf ./share/hadoop/common/lib/guava-11.0.2.jar

cd ${GIRAPH_HOME}
cp ./giraph-dist/target/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1-bin/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1/lib/guava-21.0.jar /usr/local/hadoop/share/hadoop/hdfs/lib/
cp ./giraph-dist/target/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1-bin/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1/lib/guava-21.0.jar /usr/local/hadoop/share/hadoop/tools/lib
cp ./giraph-dist/target/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1-bin/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1/lib/guava-21.0.jar /usr/local/hadoop/share/hadoop/httpfs/tomcat/webapps/webhdfs/WEB-INF/lib/
cp ./giraph-dist/target/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1-bin/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1/lib/guava-21.0.jar /usr/local/hadoop/share/hadoop/yarn/lib/
cp ./giraph-dist/target/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1-bin/giraph-1.3.0-SNAPSHOT-for-hadoop-2.5.1/lib/guava-21.0.jar /usr/local/hadoop/share/hadoop/common/lib

set up input file

 vim /home/houzhizhen/git/opensource/giraph/test/tiny_graph.txt
[0,0,[[1,1],[3,3]]]
[1,0,[[0,1],[2,2],[3,1]]]
[2,0,[[1,2],[4,4]]]
[3,0,[[0,3],[1,1],[4,4]]]
[4,0,[[3,4],[2,4]]]

execute shortest path algorithm

 hadoop jar giraph-examples/target/giraph-examples-1.3.0-SNAPSHOT-for-hadoop-2.7.5-jar-with-dependencies.jar org.apache.giraph.GiraphRunner org.apache.giraph.examples.SimpleShortestPathsComputation -vif org.apache.giraph.io.formats.JsonLongDoubleFloatDoubleVertexInputFormat -vip /home/houzhizhen/git/opensource/giraph/test/tiny_graph.txt -vof org.apache.giraph.io.formats.IdWithValueTextOutputFormat -op /home/houzhizhen/git/opensource/giraph/test/shortestpaths -w 1 -ca giraph.SplitMasterWorker=false
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章