实时读取本地文件到HDFS案例
案例需求:实时监控Hive日志,并上传到HDFS中
实现步骤:
1.Flume想要将数据输出到HDFS,必须持有Hadoop相关jar包
将commons-configuration-1.6.jar、hadoop-auth-2.7.2.jar、hadoop-common-2.7.2.jar、
hadoop-hdfs-2.7.2.jar、commons-io-2.4.jar、htrace-core-3.1.0-incubating.jar
拷贝到/root/app/flume/lib文件夹下。
2.创建"flume-file-hdfs.conf"文件并修改
touch flume-file-hdfs.conf
vim flume-file-hdfs.conf
# Name the components on this agent
a2.sources = r2
a2.sinks = k2
a2.channels = c2
# Describe/configure the source
a2.sources.r2.type = exec
a2.sources.r2.command = tail -F /opt/module/hive/logs/hive.log
a2.sources.r2.shell = /bin/bash -c
# Describe the sink
a2.sinks.k2.type = hdfs
a2.sinks.k2.hdfs.path = hdfs://hadoop102:9000/flume/%Y%m%d/%H
#上传文件的前缀
a2.sinks.k2.hdfs.filePrefix = logs-
#是否按照时间滚动文件夹
a2.sinks.k2.hdfs.round = true
#多少时间单位创建一个新的文件夹
a2.sinks.k2.hdfs.roundValue = 1
#重新定义时间单位
a2.sinks.k2.hdfs.roundUnit = hour
#是否使用本地时间戳
a2.sinks.k2.hdfs.useLocalTimeStamp = true
#积攒多少个Event才flush到HDFS一次
a2.sinks.k2.hdfs.batchSize = 1000
#设置文件类型,可支持压缩
a2.sinks.k2.hdfs.fileType = DataStream
#多久生成一个新的文件
a2.sinks.k2.hdfs.rollInterval = 600
#设置每个文件的滚动大小
a2.sinks.k2.hdfs.rollSize = 134217700
#文件的滚动与Event数量无关
a2.sinks.k2.hdfs.rollCount = 0
#最小冗余数
a2.sinks.k2.hdfs.minBlockReplicas = 1
# Use a channel which buffers events in memory
a2.channels.c2.type = memory
a2.channels.c2.capacity = 1000
a2.channels.c2.transactionCapacity = 100
# Bind the source and sink to the channel
a2.sources.r2.channels = c2
a2.sinks.k2.channel = c2
3.执行监控配置
bin/flume-ng agent --conf conf/ --name a2
--conf-file job/flume-file-hdfs.conf
4.开启Hadoop和hive并操作hive产生日志
sbin/start-dfs.sh
sbin/start-yarn.sh
bin/hive
5.在HDFS上查看文件
"node01:50070"