hadoop生态搭建（3节点）-09.flume配置

# http://archive.apache.org/dist/flume/1.8.0/
# ==================================================================安装 flume

tar -zxvf ~/apache-flume-1.8.0-bin.tar.gz -C /usr/local
mv /usr/local/apache-flume-1.8.0-bin /usr/local/flume-1.8.0
rm -r ~/apache-flume-1.8.0-bin.tar.gz

# 环境变量
# ==================================================================node1 node2 node3

vi /etc/profile

# 在export PATH USER LOGNAME MAIL HOSTNAME HISTSIZE HISTCONTROL下添加
export JAVA_HOME=/usr/java/jdk1.8.0_111
export ZOOKEEPER_HOME=/usr/local/zookeeper-3.4.12
export HADOOP_HOME=/usr/local/hadoop/hadoop-2.7.6
export MYSQL_HOME=/usr/local/mysql
export HBASE_HOME=/usr/local/hbase-1.2.4
export HIVE_HOME=/usr/local/hive-2.1.1
export SCALA_HOME=/usr/local/scala-2.12.4
export KAFKA_HOME=/usr/local/kafka_2.12-0.10.2.1
export FLUME_HOME=/usr/local/flume-1.8.0

export PATH=$PATH:$JAVA_HOME/bin:$JAVA_HOME/jre/bin:$ZOOKEEPER_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$MYSQL_HOME/bin:$HBASE_HOME/bin:$HIVE_HOME/bin:$SCALA_HOME/bin:$KAFKA_HOME/bin:$FLUME_HOME/bin
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar

export HADOOP_INSTALL=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native

# ==================================================================node1

# 使环境变量生效
source /etc/profile

# 查看配置结果
echo $FLUME_HOME

# ==================================================================node1

cp $FLUME_HOME/conf/flume-env.sh.template $FLUME_HOME/conf/flume-env.sh
vi $FLUME_HOME/conf/flume-env.sh

export JAVA_HOME=/usr/java/jdk1.8.0_111

# rpm -qa | grep telnet-server
# rpm -qa | grep telnet
# rpm -qa | grep xinetd
# rpm -qa | grep net-tools

yum -y install xinetd telnet telnet-server net-tools

systemctl enable telnet.socket
systemctl start telnet.socket
systemctl enable xinetd
systemctl start xinetd

# 在使用hadoop会冲突，需去掉下面的文件
rm -r $FLUME_HOME/lib/slf4j-api-1.6.1.jar
rm -r $FLUME_HOME/lib/slf4j-log4j12-1.6.1.jar
rm -r $HBASE_HOME/lib/slf4j-log4j12-1.7.5.jar

# hdfs.path is required
cp $HADOOP_HOME/share/hadoop/common/lib/commons-configuration-1.6.jar $FLUME_HOME/lib/
cp $HADOOP_HOME/share/hadoop/common/lib/hadoop-auth-2.7.6.jar $FLUME_HOME/lib/
cp $HADOOP_HOME/share/hadoop/common/lib/htrace-core-3.1.0-incubating.jar $FLUME_HOME/lib/

cp $HADOOP_HOME/share/hadoop/common/hadoop-common-2.7.6.jar $FLUME_HOME/lib/
cp $HADOOP_HOME/share/hadoop/common/hadoop-nfs-2.7.6.jar $FLUME_HOME/lib/

cp $HADOOP_HOME/share/hadoop/hdfs/hadoop-hdfs-2.7.6.jar $FLUME_HOME/lib/
cp $HADOOP_HOME/share/hadoop/hdfs/hadoop-hdfs-nfs-2.7.6.jar $FLUME_HOME/lib/

cp $HADOOP_HOME/share/hadoop/hdfs/lib/commons-daemon-1.0.13.jar $FLUME_HOME/lib/

scp -r $FLUME_HOME node2:/usr/local/
scp -r $FLUME_HOME node3:/usr/local/

# ==================================================================node2 node3

# 使环境变量生效
source /etc/profile

# 查看配置结果
echo $FLUME_HOME

shutdown -h now
# 快照 flume

# ==================================================================参考

Source——日志来源，其中包括：Avro Source、Thrift Source、Exec Source、JMS Source、Spooling Directory Source、Kafka Source、
NetCat Source、Sequence Generator Source、Syslog Source、HTTP Source、Stress Source、Legacy Source、Custom Source、Scribe
Source以及Twitter 1% firehose Source。

Channel——日志管道，所有从Source过来的日志数据都会以队列的形式存放在里面，它包括：
Memory Channel、JDBC Channel、Kafka Channel、File Channel、Spillable Memory Channel、Pseudo Transaction Channel、Custom Channel。

Sink——日志出口，日志将通过Sink向外发射，它包括：HDFS Sink、Hive Sink、Logger Sink、Avro Sink、Thrift Sink、IRC Sink、File Roll Sink、
Null Sink、HBase Sink、Async HBase Sink、Morphline Solr Sink、Elastic Search Sink、Kite Dataset Sink、Kafka Sink、Custom Sink

# ==================================================================实例

后续更新