user_friends.sources = userFriendsSource
user_friends.channels = userFriendsChannel
user_friends.sinks = userFriendsSink
user_friends.sources.userFriendsSource.type = spooldir
user_friends.sources.userFriendsSource.spoolDir = /opt/kb07file/flumeFile/user_friends
user_friends.sources.userFriendsSource.deserializer = LINE
user_friends.sources.userFriendsSource.deserializer.maxLineLength = 600000
user_friends.sources.userFriendsSource.includePattern = userFriends_[0-9]{4}-[0-9]{2}-[0-9]{2}.csv
user_friends.channels.userFriendsChannel.type = file
user_friends.channels.userFriendsChannel.checkpointDir = /opt/kb07file/flumeFile/checkpoint/ufriends
user_friends.channels.userFriendsChannel.dataDirs = /opt/kb07file/flumeFile/data/uFriends/
user_friends.sinks.userFriendsSink.type = hdfs
user_friends.sinks.userFriendsSink.hdfs.fileType = DataStream
user_friends.sinks.userFriendsSink.hdfs.filePrefix = userFriend
user_friends.sinks.userFriendsSink.hdfs.fileSuffix = .csv
user_friends.sinks.userFriendsSink.hdfs.path = hdfs://192.168.106.107:9000/flume/events/%Y-%m-%d
user_friends.sinks.userFriendsSink.hdfs.useLocalTimeStamp = true
user_friends.sinks.userFriendsSink.hdfs.batchSize = 640
user_friends.sinks.userFriendsSink.hdfs.rollCount = 0
user_friends.sinks.userFriendsSink.hdfs.rollSize = 64000000
user_friends.sinks.userFriendsSink.hdfs.rollInterval = 30
user_friends.sources.userFriendsSource.channels = userFriendsChannel
user_friends.sinks.userFriendsSink.channel = userFriendsChannel
配置conf如上
cp user_friends.csv /opt/kb07file/flumeFile/user_friends/userFriends_2020-08-17.csv
cp需要上传符合格式的文件
./bin/flume-ng agent --name user_friends --conf conf/ --conf-file conf/job/file-flume-hdfs.conf -Dflume.root.logger=INFO,console
输入命令开始