flume構築

jdk構成/etc/profile環境変数の変更

export JAVA_HOME=/usr/java/jdk1.8.0_77
export HADOOP_HOME=/lj/hadoop-2.2.0
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin

source/etc/profile
tar-zxvf apache-flume-1.5.0-bin.tar.gz-Cパスの解凍
/lj/apache-flume-1.5.0-bin/conf名前変更mv flume-env.sh.template flume-env.sh flume-env.sh下構成JAVA_HOME=/usr/java/jdk1.8.0_77
hadoopパッケージが必要で、scpを使用して/lj/haadoop-2.2.0/share/hare/hade oop/common/haadoop/common/haadoop-common-hare/hare/hare/haadoop/commons-configuration-1.6.jar、hadoop-auth-2.20.jar、htrace-core-3.0.4.jar/letv/data/hare/haadoop/hdfs/hadoop-hdfs-2.6.0.jar、hadoop-hdfs-2.6.0.jar、/lj/apache- flumumjar/jj/apachehhhhhhhhhhhhhhhe-1.5.0-bin/lib下
/lj/hadoop-2.2.0/etc/hadoop/{core-site.xml,hdfs-site.xml}を/lj/apache-flume-1.5.0-bin/confにコピー
vim/etc/hosts

10.185.28.92 THadoop1
10.185.28.94 THadoop2
10.185.28.95 THadoop3
10.185.28.23 THadoop4
10.185.28.58 THadoop5
10.185.28.16 THadoop6
10.185.28.26 THadoop7
10.185.28.50 THadoop8

次に、リスニングするディレクトリmkdir/root/logsを作成します.
bin/flume-ng agent-n a 4-c conf-f conf/a 4.conf-Dflume.root.logger=INFO,consoleを起動
bin/flume-ng agent -n a2 -f/home/hadoop/a2.conf -c conf -Dflume.root.logger=INFO,console
-D実行時にコンソールに印刷するログレベルINFO,Debug,warningを指定
次に指定したディレクトリにファイルを入れます
プロファイルa 4

#  agent ， source、channel、sink   
a4.sources = r1
a4.channels = c1
a4.sinks = k1

#    source
a4.sources.r1.type = spooldir
a4.sources.r1.spoolDir = /home/hadoop/logs

#    channel
a4.channels.c1.type = memory
#    
a4.channels.c1.capacity = 10000
#    
a4.channels.c1.transactionCapacity = 100

#     ，        
#        
a4.sources.r1.interceptors = i1
a4.sources.r1.interceptors.i1.type = org.apache.flume.interceptor.TimestampInterceptor$Builder


#    sink
a4.sinks.k1.type = hdfs
#    ，nameService，  
#%Y%m%d         
a4.sinks.k1.hdfs.path = hdfs://ns1/flume/%Y%m%d
#  ，     ,   event-.   
a4.sinks.k1.hdfs.filePrefix = events-
#   
a4.sinks.k1.hdfs.fileType = DataStream
#         
a4.sinks.k1.hdfs.rollCount = 0
#             
#HDFS      128M       
a4.sinks.k1.hdfs.rollSize = 134217728
#HDFS      60       
a4.sinks.k1.hdfs.rollInterval = 60

#  source、channel、sink
a4.sources.r1.channels = c1
a4.sinks.k1.channel = c1

プロファイルa 2

#  agent ， source、channel、sink   
a2.sources = r1
a2.channels = c1
a2.sinks = k1

#    source
a2.sources.r1.type = exec
#tail -F        
a2.sources.r1.command = tail -F /home/hadoop/a.log

#    channel
a2.channels.c1.type = memory
a2.channels.c1.capacity = 1000
a2.channels.c1.transactionCapacity = 100

#    sink
#logger        
a2.sinks.k1.type = logger

#  source、channel、sink
a2.sources.r1.channels = c1
a2.sinks.k1.channel = c1