flume 配置和使用

官网 http://flume.apache.org

核心组件

1) Source 收集日志
2) Channel 聚集，传输日志
3) Sink 输出日志方式

安装 (Flume 1.8.0)

1. 安装 JDK 1.7以上版本
2. http://flume.apache.org/download.html 下载flume包 解压并配置FLUME_HOME
3. 修改配置文件 $FLUME_HOME/conf/flume-env.sh

export JAVA_HOME=/Library/Java/JavaVirtualMachines/jdk1.8.0_152.jdk/Contents/Home

配置使用flume

1. example.conf

# a1 是启动flume时指定的名字
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /Users/xy/bigdata/infos.txt
a1.sources.r1.shell = /bin/sh -c

# Describe the sink
a1.sinks.k1.type = logger

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# 启动命令
flume-ng agent \
--name a1  \
--conf $FLUME_HOME/conf  \
--conf-file $FLUME_HOME/conf/example.conf \
-Dflume.root.logger=INFO,console

1. hdfs.conf

a1.sources = r1
a1.sinks = k1
a1.channels = c1

# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /Users/xy/bigdata/infos.txt
a1.sources.r1.shell = /bin/sh -c

# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = hdfs://172.18.0.2:9000/flume/events/my.logs
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = minute

# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# 启动命令
flume-ng agent \
--name a1  \
--conf $FLUME_HOME/conf  \
--conf-file $FLUME_HOME/conf/hdfs.conf \
-Dflume.root.logger=INFO,console

1. exec-memory-avro.conf

exec-memory-avro.sources = exec-source
exec-memory-avro.sinks = avro-sink
exec-memory-avro.channels = memory-channel

exec-memory-avro.sources.exec-source.type = exec
exec-memory-avro.sources.exec-source.command = tail -F /Users/xy/bigdata/infos.txt
exec-memory-avro.sources.exec-source.shell = /bin/sh -c

exec-memory-avro.sinks.avro-sink.type = avro
exec-memory-avro.sinks.avro-sink.hostname = localhost
exec-memory-avro.sinks.avro-sink.port = 44444

exec-memory-avro.channels.memory-channel.type = memory

exec-memory-avro.sources.exec-source.channels = memory-channel
exec-memory-avro.sinks.avro-sink.channel = memory-channel
# 启动命令
flume-ng agent \
--name exec-memory-avro  \
--conf $FLUME_HOME/conf  \
--conf-file $FLUME_HOME/conf/exec-memory-avro.conf \
-Dflume.root.logger=INFO,console

1. avro-memory-logger.conf

avro-memory-logger.sources = avro-source
avro-memory-logger.sinks = logger-sink
avro-memory-logger.channels = memory-channel

avro-memory-logger.sources.avro-source.type = avro
avro-memory-logger.sources.avro-source.bind = localhost
avro-memory-logger.sources.avro-source.port = 44444

avro-memory-logger.sinks.logger-sink.type = logger

avro-memory-logger.channels.memory-channel.type = memory

avro-memory-logger.sources.avro-source.channels = memory-channel
avro-memory-logger.sinks.logger-sink.channel = memory-channel
# 启动命令
flume-ng agent \
--name avro-memory-logger  \
--conf $FLUME_HOME/conf  \
--conf-file $FLUME_HOME/conf/avro-memory-logger.conf \
-Dflume.root.logger=INFO,console

1. avro-memory-kafka.conf

avro-memory-kafka.sources = avro-source
avro-memory-kafka.sinks = kafka-sink
avro-memory-kafka.channels = memory-channel

# Describe/configure the source
avro-memory-kafka.sources.avro-source.type = avro
avro-memory-kafka.sources.avro-source.bind = localhost
avro-memory-kafka.sources.avro-source.port = 44444

avro-memory-kafka.sinks.kafka-sink.type = org.apache.flume.sink.kafka.KafkaSink
avro-memory-kafka.sinks.kafka-sink.kafka.bootstrap.servers = localhost:9092
avro-memory-kafka.sinks.kafka-sink.kafka.topic = hello_topic
avro-memory-kafka.sinks.kafka-sink.flumeBatchSize = 5

avro-memory-kafka.channels.memory-channel.type = memory

avro-memory-kafka.sources.avro-source.channels = memory-channel
avro-memory-kafka.sinks.kafka-sink.channel = memory-channel
# 启动命令
flume-ng agent \
--name avro-memory-kafka  \
--conf $FLUME_HOME/conf  \
--conf-file $FLUME_HOME/conf/avro-memory-kafka.conf \
-Dflume.root.logger=INFO,console