Hadoop-20 Flume 采集数据双写至本地+HDFS中 监控目录变化 3个Agent MemoryChannel Source对比

# Name the components on this agent
a3.sources = r3
a3.channels = c3
a3.sinks = k3
# Describe/configure the source
a3.sources.r3.type = spooldir
# 注意这里的文件夹 换成自己的！！！
a3.sources.r3.spoolDir = /opt/wzk/upload
a3.sources.r3.fileSuffix = .COMPLETED
a3.sources.r3.fileHeader = true

# 忽略以.tmp结尾的文件，不上传
a3.sources.r3.ignorePattern = ([^ ]*\.tmp)
# Use a channel which buffers events in memory
a3.channels.c3.type = memory
a3.channels.c3.capacity = 10000
a3.channels.c3.transactionCapacity = 500
# Describe the sink
a3.sinks.k3.type = hdfs
# 注意修改成你自己的IP!!!
a3.sinks.k3.hdfs.path = hdfs://h121.wzk.icu:9000/flume/upload/%Y%m%d/%H%M

# 上传文件的前缀
a3.sinks.k3.hdfs.filePrefix = upload-
# 是否使用本地时间戳
a3.sinks.k3.hdfs.useLocalTimeStamp = true
# 积攒500个Event，flush到HDFS一次
a3.sinks.k3.hdfs.batchSize = 500
# 设置文件类型
a3.sinks.k3.hdfs.fileType = DataStream
# 60秒滚动一次
a3.sinks.k3.hdfs.rollInterval = 60
# 128M滚动一次
a3.sinks.k3.hdfs.rollSize = 134217700
# 文件滚动与event数量无关
a3.sinks.k3.hdfs.rollCount = 0
# 最小冗余数
a3.sinks.k3.hdfs.minBlockReplicas = 1

# Bind the source and sink to the channel
a3.sources.r3.channels = c3
a3.sinks.k3.channel = c3

# Name the components on this agent
a1.sources = r1
a1.sinks = k1 k2
a1.channels = c1 c2
# 将数据流复制给所有channel
a1.sources.r1.selector.type = replicating
# source
a1.sources.r1.type = taildir
# 记录每个文件最新消费位置
a1.sources.r1.positionFile = /root/flume/taildir_position.json
a1.sources.r1.filegroups = f1
# 备注：.*log 是正则表达式；这里写成 *.log 是错误的
a1.sources.r1.filegroups.f1 = /tmp/root/.*log
# sink
a1.sinks.k1.type = avro
a1.sinks.k1.hostname = linux123
a1.sinks.k1.port = 9091
a1.sinks.k2.type = avro
a1.sinks.k2.hostname = linux123
a1.sinks.k2.port = 9092
# channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 10000
a1.channels.c1.transactionCapacity = 500
a1.channels.c2.type = memory
a1.channels.c2.capacity = 10000
a1.channels.c2.transactionCapacity = 500
# Bind the source and sink to the channel
a1.sources.r1.channels = c1 c2
a1.sinks.k1.channel = c1
a1.sinks.k2.channel = c2

# Name the components on this agent
a2.sources = r1
a2.sinks = k1
a2.channels = c1
# Describe/configure the source
a2.sources.r1.type = avro
a2.sources.r1.bind = linux123
a2.sources.r1.port = 9091
# Describe the channel
a2.channels.c1.type = memory
a2.channels.c1.capacity = 10000
a2.channels.c1.transactionCapacity = 500
# Describe the sink
a2.sinks.k1.type = hdfs
a2.sinks.k1.hdfs.path = hdfs://linux121:8020/flume2/%Y%m%d/%H
# 上传文件的前缀
a2.sinks.k1.hdfs.filePrefix = flume2-
# 是否使用本地时间戳
a2.sinks.k1.hdfs.useLocalTimeStamp = true
# 500个Event才flush到HDFS一次
a2.sinks.k1.hdfs.batchSize = 500
# 设置文件类型，可支持压缩
a2.sinks.k1.hdfs.fileType = DataStream
# 60秒生成一个新的文件
a2.sinks.k1.hdfs.rollInterval = 60
a2.sinks.k1.hdfs.rollSize = 0
a2.sinks.k1.hdfs.rollCount = 0
a2.sinks.k1.hdfs.minBlockReplicas = 1
# Bind the source and sink to the channel
a2.sources.r1.channels = c1
a2.sinks.k1.channel = c1

# Name the components on this agent
a3.sources = r1
a3.sinks = k1
a3.channels = c2
# Describe/configure the source
a3.sources.r1.type = avro
a3.sources.r1.bind = linux123
a3.sources.r1.port = 9092
# Describe the sink
a3.sinks.k1.type = file_roll
# 目录需要提前创建好
a3.sinks.k1.sink.directory = /root/flume/output
# Describe the channel
a3.channels.c2.type = memory
a3.channels.c2.capacity = 10000
a3.channels.c2.transactionCapacity = 500
# Bind the source and sink to the channel
a3.sources.r1.channels = c2
a3.sinks.k1.channel = c2

$FLUME_HOME/bin/flume-ng agent --name a1 \
--conf-file ~/conf/flume-taildir-avro.conf \
-Dflume.root.logger=INFO,console &

hive -e "show databases;"