基础配置
单个Source 单个Sink
# Name the components on this agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1
单个Source 多个Sink
# Name the components on this agent
a1.sources = r1
a1.sinks = k1 k2
a1.channels = c1 c2
# 将数据流复制给多个channel 副本，还有负载均衡
a1.sources.r1.selector.type = replicating
Source配置
Kafka
# 定义消息源类型
agent.sources.kafkaSource.type = org.apache.flume.source.kafka.KafkaSource
# 定义kafka所在zk的地址
agent.sources.kafkaSource.zookeeperConnect = 10.45.9.139:2181
# 配置消费的kafka topic
agent.sources.kafkaSource.topic = my-topic
# 配置消费者组的id
agent.sources.kafkaSource.groupId = flume
# 消费超时时间,参照如下写法可以配置其他所有kafka的consumer选项。注意格式从kafka.xxx开始是consumer的配置属性
agent.sources.kafkaSource.kafka.consumer.timeout.ms = 100
netcat的source
bind指定IP，port指定port
# Describe/configure the source
a1.sources.r1.type = netcat
a1.sources.r1.bind = localhost
a1.sources.r1.port = 44444
读文件exec
commd中写命令，如果用tail的话记得用大写的F
# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /opt/module/hive/logs/hive.log
a1.sources.r1.shell = /bin/bash -c
读取文件夹source
spooldir source ，tmp记得一定要忽略
# Describe/configure the source
a1.sources.r1.type = spooldir
# 指定文件夹
a1.sources.r1.spoolDir = /opt/module/flume/upload
#指定文件上传后的后缀
a1.sources.r1.fileSuffix = .COMPLETED
a1.sources.r1.fileHeader = true
#忽略所有以.tmp结尾的文件，不上传
a1.sources.r1.ignorePattern = ([^ ]*\.tmp)
arvo模式
bind指的是接收的主机，port不是随意的，是看sink给的端口
# Describe/configure the source
a1.sources.r1.type = avro
a1.sources.r1.bind = hadoop102
a1.sources.r1.port = 4141
Sink配置
Kafka
# Describe the sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.topic = mytopic
a1.sinks.k1.kafka.bootstrap.servers = hdp-qm-01:9092
a1.sinks.k1.kafka.flumeBatchSize = 20
a1.sinks.k1.kafka.producer.acks = 1
a1.sinks.k1.kafka.producer.linger.ms = 1
a1.sinks.ki.kafka.producer.compression.type = snappy
hdfs的sink
# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = hdfs://hadoop102:9000/flume/%Y%m%d/%H
#上传文件的前缀
a1.sinks.k1.hdfs.filePrefix = logs-
#是否按照时间滚动文件夹
a1.sinks.k1.hdfs.round = true
#多少时间单位创建一个新的文件夹
a1.sinks.k1.hdfs.roundValue = 1
#重新定义时间单位
a1.sinks.k1.hdfs.roundUnit = hour
#是否使用本地时间戳
a1.sinks.k1.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a1.sinks.k1.hdfs.batchSize = 1000
#设置文件类型，可支持压缩
a1.sinks.k1.hdfs.fileType = DataStream
#多久生成一个新的文件 单位是秒
a1.sinks.k1.hdfs.rollInterval = 600
#设置每个文件的滚动大小 128M
a1.sinks.k1.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a1.sinks.k1.hdfs.rollCount = 0
#最小冗余数
a1.sinks.k1.hdfs.minBlockReplicas = 1
arvo sink
hostname是IP指的是发送给谁，port指的是监听端口可以任意写
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = hadoop102
a1.sinks.k2.port = 4142
logger sink
如果是像在控制台看打印，要在命令加，-Dflume.root.logger=INFO,console
# Describe the sink
a1.sinks.k1.type = logger
Channel配置
channel主要分为memory channel和file channel,如果是要求速度和不追求数据的完整性用，memory channel, 一般也都用它
memory channel
1000指的是队列的容量，100指的是sink取数据的时候最大值
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
channel 和source，sink的绑定
单个source和单个sink
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
单个source和多个
# Bind the source and sink to the channel
a1.sources.r1.channels = c1 c2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c2
