Spark - 伪分布式，配置文件

1. hadoop

1.1 hadoop-env.sh 

配置JAVA_HOME

1.2 core-site.xml

<configuration>
<property>
<name>hadoop.tmp.dir</name>
<value>file:{}</value>
<description>Abase for other temporary directories.</description>
</property>
<property>
<name>fs.defaultFS</name>
<value>hdfs://localhost:9000</value>
</property>
</configuration>

1.3  hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>1</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:{}tmp/dfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:{}tmp/dfs/data</value>
</property>
</configuration>

2. spark

2.1 spark-env.sh

JAVA_HOME

2.2 spark-defaults.conf

spark.local.dir

3. .profile

JAVA_HOME=/home/peerslee/opt/jdk
SCALA_HOME=/home/peerslee/opt/scala
HADOOP_HOME=/home/peerslee/opt/hadoop
SPARK_HOME=/home/peerslee/opt/spark-hadoop
PATH=$SPARK_HOME/sbin:$SPARK_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/bin:$SCALA_HOME/bin:$JAVA_HOME/bin:$PATH
export HADOOP_HOME SCALA_HOME JAVA_HOME PATH