依赖

<dependency><groupId>org.apache.flink</groupId><artifactId>flink-core</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-clients_2.11</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-scala_2.11</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-streaming-scala_2.11</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.slf4j</groupId><artifactId>slf4j-log4j12</artifactId><version>1.7.26</version></dependency><!--添加HDFS支持--><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-hdfs</artifactId><version>2.9.2</version></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-common</artifactId><version>2.9.2</version></dependency><!--添加Kafka支持--><dependency><groupId>org.apache.flink</groupId><artifactId>flink-connector-kafka_2.11</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-json</artifactId><version>1.8.1</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-connector-filesystem_2.11</artifactId><version>1.8.1</version></dependency><!--写到Redis中--><dependency><groupId>org.apache.bahir</groupId><artifactId>flink-connector-redis_2.11</artifactId><version>1.0</version></dependency></dependencies><build><plugins><!--在执行package时候，将scala源码编译进jar--><plugin><groupId>net.alchim31.maven</groupId><artifactId>scala-maven-plugin</artifactId><version>4.0.1</version><executions><execution><id>scala-compile-first</id><phase>process-resources</phase><goals><goal>add-source</goal><goal>compile</goal></goals></execution></executions></plugin></plugins></build>

代码

packagecom.baizhi.demo04importorg.apache.flink.streaming.api.CheckpointingModeimportorg.apache.flink.streaming.api.environment.CheckpointConfig.ExternalizedCheckpointCleanupimportorg.apache.flink.streaming.api.scala.{DataStream,StreamExecutionEnvironment,_}object Flink{defmain(args:Array[String]):Unit={val env=StreamExecutionEnvironment.getExecutionEnvironment//开启checkpointenv.enableCheckpointing(7000,CheckpointingMode.EXACTLY_ONCE)//checkpoint必须在2s内完成，如果完成不了终止env.getCheckpointConfig.setCheckpointTimeout(4000)//距离上一次的checkpoint完成之后需要等5s 之后再开启下一次的checkpointenv.getCheckpointConfig.setMinPauseBetweenCheckpoints(5000)env.getCheckpointConfig.setMaxConcurrentCheckpoints(1)//只开启一个checkpoint线程//在退出应用时候，不删除checkpoint数据env.getCheckpointConfig.enableExternalizedCheckpoints(ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION)//必须保证任务可以从checkpoint恢复，恢复不成功任务失败env.getCheckpointConfig.setFailOnCheckpointingErrors(true)val data:DataStream[String]=env.socketTextStream("Flink",9999)data.flatMap(line=>line.split("\\s+")).map((_,1)).keyBy(0).map(newCountMapFunction).print()env.execute()}}

packagecom.baizhi.demo04importorg.apache.flink.api.common.functions.RichMapFunctionimportorg.apache.flink.api.common.state.{StateTtlConfig,ValueState,ValueStateDescriptor}importorg.apache.flink.api.common.time.Timeimportorg.apache.flink.configuration.Configurationimportorg.apache.flink.streaming.api.scala._classCountMapFunctionextendsRichMapFunction[(String,Int),(String,Int)]{var state:ValueState[Int]=_ override defmap(value:(String,Int)):(String,Int)={var history=state.value()if(history==null){history=0}state.update(history+value._2)(value._1,history+value._2)}override defopen(parameters:Configuration):Unit={val dec=newValueStateDescriptor[Int]("count",createTypeInformation[Int])//1.创建TTLConfigval ttlConfig=StateTtlConfig.newBuilder(Time.seconds(80))//这是state存活时间10s.setUpdateType(StateTtlConfig.UpdateType.OnCreateAndWrite)//设置过期时间更新方式.setStateVisibility(StateTtlConfig.StateVisibility.NeverReturnExpired)//永远不要返回过期的状态//.cleanupInRocksdbCompactFilter(1000)//处理完1000个状态查询时候，会启用一次CompactFilter.build//2.开启TTLdec.enableTimeToLive(ttlConfig)val context=getRuntimeContext state=context.getState(dec)}}

配置Flink的环境

配置Flink-conf.yaml

#==============================================================================# Fault tolerance and checkpointing#==============================================================================# The backend that will be used to store operator state checkpoints if# checkpointing is enabled.## Supported backends are 'jobmanager', 'filesystem', 'rocksdb', or the# <class-name-of-factory>.#state.backend:rocksdb# Directory for checkpoints filesystem, when using any of the default bundled# state backends.#state.checkpoints.dir:hdfs:///flink-checkpoints# Default target directory for savepoints, optional.#state.savepoints.dir:hdfs:///flink-savepoints# Flag to enable/disable incremental checkpoints for backends that# support incremental checkpoints (like the RocksDB state backend).#state.backend.incremental:truestate.backend.rocksdb.ttl.compaction.filter.enabled:true#==============================================================================# HistoryServer#==============================================================================# The HistoryServer is started and stopped via bin/historyserver.sh (start|stop)# Directory to upload completed jobs to. Add this directory to the list of# monitored directories of the HistoryServer as well (see below).jobmanager.archive.fs.dir:hdfs:///completed-jobs/# The address under which the web-based HistoryServer listens.historyserver.web.address:CentOS# The port under which the web-based HistoryServer listens.historyserver.web.port:8082# Comma separated list of directories to monitor for completed jobs.historyserver.archive.fs.dir:hdfs:///completed-jobs/# Interval in milliseconds for refreshing the monitored directories.historyserver.archive.fs.refresh-interval:10000

将hadoop_classpath配置到环境变量中

export HADOOP_CLASSPATH=hadoop classpath