flume监听文件

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

# Describe/configure the sources
# exec即execute执行命令
a1.sources.r1.type = exec
# 要执行的命令。对应自己的路径修改
a1.sources.r1.command = tail -F /opt/hadoop-2.7.7/logs/hadoop-root-namenode-host-192-168-3-73.log
# 执行shell脚本的绝对路径
a1.sources.r1.shell = /bin/bash -c

# Describe the sink
a1.sinks.k1.type = hdfs
# 上传到hdfs的路径
a1.sinks.k1.hdfs.path = hdfs://master:9000/tmp/flume/%Y%m%d%H
# 文件前缀
a1.sinks.k1.hdfs.filePrefix = logs-
# 是否按时间新建文件夹
a1.sinks.k1.hdfs.round = true
# 定义多久新建文件夹
a1.sinks.k1.hdfs.roundValue = 1
# 重新定义时间单位
a1.sinks.k1.hdfs.roundUnit = minute
# 是否使用本地时间戳
a1.sinks.k1.hdfs.useLocalTimeStamp = true
# flush到hdfs需要积攒event的数量
a1.sinks.k1.hdfs.batchSize = 1000
# 设置文件类型
a1.sinks.k1.hdfs.fileType = DataStream
# 多久生成一个新的文件（单位：秒）
a1.sinks.k1.hdfs.rollInterval = 900
# 接收多少数据生成一个新文件（单位：字节）
a1.sinks.k1.hdfs.rollSize = 10485760
# 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

# 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```