2017-07-29 11:22:16,303 (SinkRunner-PollingRunner-DefaultSinkProcessor) [WARN - org.apache.flume.sink.hdfs.BucketWriter.append(BucketWriter.java:521)] Block Under-replication detected. Rotating file.
2017-07-29 11:22:16,303 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.hdfs.BucketWriter.close(BucketWriter.java:357)] Closing hdfs://master:9000/data/types/20170729//run.1501298449107.data.tmp
2017-07-29 11:22:16,538 (hdfs-hdfsSink-call-runner-0) [INFO - org.apache.flume.sink.hdfs.BucketWriter$8.call(BucketWriter.java:618)] Renaming hdfs://master:9000/data/types/20170729/run.1501298449107.data.tmp to hdfs://master:9000/data/types/20170729/run.1501298449107.data
2017-07-29 11:22:16,907 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.hdfs.BucketWriter.open(BucketWriter.java:231)] Creating hdfs://master:9000/data/types/20170729//run.1501298449108.data.tmp
2017-07-29 11:22:17,866 (SinkRunner-PollingRunner-DefaultSinkProcessor) [WARN - org.apache.flume.sink.hdfs.BucketWriter.append(BucketWriter.java:521)] Block Under-replication detected. Rotating file.
2017-07-29 11:22:17,867 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.hdfs.BucketWriter.close(BucketWriter.java:357)] Closing hdfs://master:9000/data/types/20170729//run.1501298449108.data.tmp
2017-07-29 11:22:18,055 (hdfs-hdfsSink-call-runner-1) [INFO - org.apache.flume.sink.hdfs.BucketWriter$8.call(BucketWriter.java:618)] Renaming hdfs://master:9000/data/types/20170729/run.1501298449108.data.tmp to hdfs://master:9000/data/types/20170729/run.1501298449108.data
2017-07-29 11:22:19,567 (SinkRunner-PollingRunner-DefaultSinkProcessor) [INFO - org.apache.flume.sink.hdfs.BucketWriter.open(BucketWriter.java:231)] Creating hdfs://master:9000/data/types/20170729//run.1501298449109.data.tmp
2017-07-29 11:22:21,869 (SinkRunner-PollingRunner-DefaultSinkProcessor) [ERROR - org.apache.flume.sink.hdfs.BucketWriter.append(BucketWriter.java:516)] Hit max consecutive under-replication rotations (30); will not continue rolling files under this path due to under-replication

[hadoop@master flume-1.7.0]$ su root
Password: 
[root@master flume-1.7.0]# ntpdate pool.ntp.org
29 Jul 13:31:36 ntpdate[7954]: step time server 85.199.214.101 offset 19.074422 sec
[root@master flume-1.7.0]# 

[hadoop@slave1 ~]$ su root
Password: 
[root@slave1 hadoop]# ntpdate pool.ntp.org
29 Jul 13:31:33 ntpdate[3851]: step time server 85.199.214.101 offset 326.201928 sec
[root@slave1 hadoop]# 

[hadoop@slave2 ~]$ su root
Password: 
[root@slave2 hadoop]# ntpdate pool.ntp.org
29 Jul 13:31:32 ntpdate[3850]: step time server 85.199.214.101 offset 36.857045 sec
[root@slave2 hadoop]# 

[hadoop@master flume-1.7.0]$ date
Sat Jul 29 13:33:01 CST 2017
[hadoop@master flume-1.7.0]$ 

[hadoop@slave1 ~]$ date
Sat Jul 29 13:33:01 CST 2017
[hadoop@slave1 ~]$ 

[hadoop@slave2 ~]$ date
Sat Jul 29 13:33:02 CST 2017
[hadoop@slave2 ~]$ 

#source的名字
agent1.sources = fileSource
# channels的名字，建议按照type来命名
agent1.channels = memoryChannel
# sink的名字，建议按照目标来命名
agent1.sinks = hdfsSink

# 指定source使用的channel名字
agent1.sources.fileSource.channels = memoryChannel
# 指定sink需要使用的channel的名字,注意这里是channel
agent1.sinks.hdfsSink.channel = memoryChannel


agent1.sources.fileSource.type = exec
agent1.sources.fileSource.command = tail -F /usr/local/log/server.log



#------- fileChannel-1相关配置-------------------------
# channel类型

agent1.channels.memoryChannel.type = memory
agent1.channels.memoryChannel.capacity = 1000
agent1.channels.memoryChannel.transactionCapacity = 1000
agent1.channels.memoryChannel.byteCapacityBufferPercentage = 20
agent1.channels.memoryChannel.byteCapacity = 800000
agent1.channels.memoryChannel.keep-alive = 60
agent1.channels.memoryChannel.capacity = 1000000

#---------拦截器相关配置------------------
#定义拦截器
agent1.sources.r1.interceptors = i1 i2
# 设置拦截器类型
agent1.sources.r1.interceptors.i1.type = zhouls.bigdata.MySearchAndReplaceInterceptor$Builder
agent1.sources.r1.interceptors.i1.searchReplace = gift_record:giftRecord,video_info:videoInfo,user_info:userInfo

# 设置拦截器类型
agent1.sources.r1.interceptors.i2.type = regex_extractor
# 设置正则表达式，匹配指定的数据，这样设置会在数据的header中增加log_type="某个值"
agent1.sources.r1.interceptors.i2.regex = "type":"(\\w+)"
agent1.sources.r1.interceptors.i2.serializers = s1
agent1.sources.r1.interceptors.i2.serializers.s1.name = log_type


#---------hdfsSink 相关配置------------------
agent1.sinks.hdfsSink.type = hdfs
# 注意, 我们输出到下面一个子文件夹datax中
agent1.sinks.hdfsSink.hdfs.path = hdfs://master:9000/data/types/%Y%m%d/%{log_type}
agent1.sinks.hdfsSink.hdfs.writeFormat = Text
agent1.sinks.hdfsSink.hdfs.fileType = DataStream
agent1.sinks.hdfsSink.hdfs.callTimeout = 3600000
agent1.sinks.hdfsSink.hdfs.useLocalTimeStamp = true

#当文件大小为52428800字节时，将临时文件滚动成一个目标文件
agent1.sinks.hdfsSink.hdfs.rollSize = 52428800
#events数据达到该数量的时候，将临时文件滚动成目标文件
agent1.sinks.hdfsSink.hdfs.rollCount = 0
#每隔N s将临时文件滚动成一个目标文件
agent1.sinks.hdfsSink.hdfs.rollInterval = 1200

#配置前缀和后缀
agent1.sinks.hdfsSink.hdfs.filePrefix=run
agent1.sinks.hdfsSink.hdfs.fileSuffix=.data