18/04/20 20:51:54 ERROR SparkContext: Error initializing SparkContext.
org.apache.spark.SparkException: Could not parse Master URL: '2'
at org.apache.spark.SparkContext$.org$apache$spark$SparkContext$$createTaskScheduler(SparkContext.scala:2760)
at org.apache.spark.SparkContext.(SparkContext.scala:501)
at cn.zhangyu.WordCountApp$.main(WordCountApp.scala:13)
at cn.zhangyu.WordCountApp.main(WordCountApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
18/04/20 20:51:54 INFO SparkUI: Stopped Spark web UI at http://192.168.137.130:4040
18/04/20 20:51:54 INFO MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped!
18/04/20 20:51:54 INFO MemoryStore: MemoryStore cleared
18/04/20 20:51:54 INFO BlockManager: BlockManager stopped
18/04/20 20:51:54 INFO BlockManagerMaster: BlockManagerMaster stopped
18/04/20 20:51:54 WARN MetricsSystem: Stopping a MetricsSystem that is not running
18/04/20 20:51:54 INFO OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped!
18/04/20 20:51:54 INFO SparkContext: Successfully stopped SparkContext
Exception in thread "main" org.apache.spark.SparkException: Could not parse Master URL: '2'
at org.apache.spark.SparkContext$.org$apache$spark$SparkContext$$createTaskScheduler(SparkContext.scala:2760)
at org.apache.spark.SparkContext.(SparkContext.scala:501)
at cn.zhangyu.WordCountApp$.main(WordCountApp.scala:13)
at cn.zhangyu.WordCountApp.main(WordCountApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
18/04/20 20:51:54 INFO ShutdownHookManager: Shutdown hook called
18/04/20 20:51:54 INFO ShutdownHookManager: Deleting directory /tmp/spark-2650cdae-496a-41db-9fc1-3e27ecda0e66
错误原因:这里我再设置–master的时候输入错误,或者再代码中进行设置:
--master local[2] \ 提交的时候进行设置
代码中设置
//创建一个SparkConf
val conf=new SparkConf().setMaster("local[2]");
//sparkContext中传递一个SparkConf
val sc=new SparkContext(conf);
Exception in thread "main" java.net.ConnectException: Call From hadoop/192.168.137.130 to hadoop:8020 failed on connection exception: java.net.ConnectException: Connection refused; For more details see: http://wiki.apache.org/hadoop/ConnectionRefused
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:791)
at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:731)
at org.apache.hadoop.ipc.Client.call(Client.java:1475)
at org.apache.hadoop.ipc.Client.call(Client.java:1408)
at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:230)
at com.sun.proxy.$Proxy20.getFileInfo(Unknown Source)
at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getFileInfo(ClientNamenodeProtocolTranslatorPB.java:757)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:256)
at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
at com.sun.proxy.$Proxy21.getFileInfo(Unknown Source)
at org.apache.hadoop.hdfs.DFSClient.getFileInfo(DFSClient.java:2102)
at org.apache.hadoop.hdfs.DistributedFileSystem$19.doCall(DistributedFileSystem.java:1215)
at org.apache.hadoop.hdfs.DistributedFileSystem$19.doCall(DistributedFileSystem.java:1211)
at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1211)
at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:64)
at org.apache.hadoop.fs.Globber.doGlob(Globber.java:272)
at org.apache.hadoop.fs.Globber.glob(Globber.java:151)
at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1656)
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:259)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:194)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:252)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:250)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:250)
at org.apache.spark.Partitioner$$anonfun$defaultPartitioner$2.apply(Partitioner.scala:66)
at org.apache.spark.Partitioner$$anonfun$defaultPartitioner$2.apply(Partitioner.scala:66)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
at scala.collection.immutable.List.foreach(List.scala:381)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
at scala.collection.immutable.List.map(List.scala:285)
at org.apache.spark.Partitioner$.defaultPartitioner(Partitioner.scala:66)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$reduceByKey$3.apply(PairRDDFunctions.scala:329)
at org.apache.spark.rdd.PairRDDFunctions$$anonfun$reduceByKey$3.apply(PairRDDFunctions.scala:329)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.PairRDDFunctions.reduceByKey(PairRDDFunctions.scala:328)
at cn.zhangyu.WordCountApp$.main(WordCountApp.scala:12)
at cn.zhangyu.WordCountApp.main(WordCountApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:755)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:205)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:119)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.net.ConnectException: Connection refused
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:530)
at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:494)
at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:614)
at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:713)
at org.apache.hadoop.ipc.Client$Connection.access$2900(Client.java:375)
at org.apache.hadoop.ipc.Client.getConnection(Client.java:1524)
at org.apache.hadoop.ipc.Client.call(Client.java:1447)
... 68 more
错误原因:设置输入地址的时候出错
./spark-submit \
--class cn.zhangyu.WordCountApp \
/home/hadoop/lib/spark_test-1.0.jar \
hdfs://主机名或者ip:8020/输入文件目录 hdfs://主机名或者ip:8020/输出文件目录
如果按照这种格式输入就会报错,改成下面的就可以了
spark-submit \
--class cn.zhangyu.WordCountApp \
--master local[2] \
/home/hadoop/lib/wordcount-1.0-SNAPSHOT.jar \
/input /output (hdfs上的地址)
Caused by: java.net.ConnectException: Connection refused
这里出现了拒绝连接的错误,原因是我的spark没有启动,错误忘记保存了,启动spark问题解决。