我遇到了一个奇怪的Spark结构化流问题。您可以按照以下步骤重现这种情况：
（1）准备在端口9999上监听netcat
nc -lk 9999
（2）在spark-shell上运行以下代码：
def mapper(line: String): String = line.toUpperCase
val writer = spark.readStream.format("socket").option("host", "localhost").option("port", 9999).load.as[String].map(mapper).writeStream.format("console")
writer.start.awaitTermination
（3）Spark结构化流开始后，在netcat端输入任何内容，然后在spark-shell端抛出异常
org.apache.spark.SparkException: Task not serializable
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:345)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:335)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:159)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2292)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:844)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:843)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:843)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:608)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:59)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:294)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3272)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3253)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3252)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2722)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3$$anonfun$apply$16.apply(MicroBatchExecution.scala:480)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3.apply(MicroBatchExecution.scala:475)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:474)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:133)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:117)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: java.io.NotSerializableException: org.apache.spark.sql.streaming.DataStreamWriter
Serialization stack:
- object not serializable (class: org.apache.spark.sql.streaming.DataStreamWriter, value: org.apache.spark.sql.streaming.DataStreamWriter@b0d4873)
- field (class: $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw, name: writer, type: class org.apache.spark.sql.streaming.DataStreamWriter)
- object (class $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw, $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw@2b0e9ae0)
- field (class: $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1, name: $outer, type: class $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw)
- object (class $line15.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1, <function1>)
- element of array (index: 0)
- array (class [Ljava.lang.Object;, size 1)
- field (class: org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10, name: references$1, type: class [Ljava.lang.Object;)
- object (class org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10, <function2>)
at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:46)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:342)
... 48 more
org.apache.spark.sql.streaming.StreamingQueryException: Query [id = dfafdedb-8c7e-4aa6-867b-5685a6216775, runId = e9e4a674-c61e-43fb-b0a3-f80c8d0e8182] terminated with exception: Task not serializable
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:295)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: org.apache.spark.SparkException: Task not serializable
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:345)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:335)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:159)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2292)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:844)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsWithIndex$1.apply(RDD.scala:843)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:843)
at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:608)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2.scala:59)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:294)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3272)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2722)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3253)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3252)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2722)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3$$anonfun$apply$16.apply(MicroBatchExecution.scala:480)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$3.apply(MicroBatchExecution.scala:475)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:474)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:133)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:271)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:121)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:117)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
... 1 more
Caused by: java.io.NotSerializableException: org.apache.spark.sql.streaming.DataStreamWriter
Serialization stack:
- object not serializable (class: org.apache.spark.sql.streaming.DataStreamWriter, value: org.apache.spark.sql.streaming.DataStreamWriter@b0d4873)
- field (class: $iw, name: writer, type: class org.apache.spark.sql.streaming.DataStreamWriter)
- object (class $iw, $iw@2b0e9ae0)
- field (class: $anonfun$1, name: $outer, type: class $iw)
- object (class $anonfun$1, <function1>)
- element of array (index: 0)
- array (class [Ljava.lang.Object;, size 1)
- field (class: org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10, name: references$1, type: class [Ljava.lang.Object;)
- object (class org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10, <function2>)
at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:46)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:342)
... 48 more
根本原因是
java.io.NotSerializableException：org.apache.spark.sql.streaming.DataStreamWriter
对我来说很奇怪，因为以下等效代码不会引起任何异常。
val writer = spark.readStream.format("socket").option("host", "localhost").option("port", 9999).load.as[String].map(_.toUpperCase).writeStream.format("console")
writer.start.awaitTermination
以下代码也是等效的，也不会引起任何异常。
def mapper(line: String): String = line.toUpperCase
spark.readStream.format("socket").option("host", "localhost").option("port", 9999).load.as[String].map(mapper).writeStream.format("console").start.awaitTermination
这是怎么了？
它已在Cloudera和Hortonworks提供的Spark 2.3.0上进行了测试。
P.S。
我做了进一步的实验，发现DataStreamReader发生了同样的情况
def mapper(line: String): String = line.toUpperCase
val reader = spark.readStream
reader.format("socket").option("host", "localhost").option("port", 9999).load.as[String].map(mapper).writeStream.format("console").start.awaitTermination
java.io.NotSerializableException：org.apache.spark.sql.streaming.DataStreamReader
但不包含DataFrame
def mapper(line: String): String = line.toUpperCase
val dataframe = spark.readStream.format("socket").option("host", "localhost").option("port", 9999).load
dataframe.as[String].map(mapper).writeStream.format("console").start.awaitTermination
StreamingQuery也可以。
def mapper(line: String): String = line.toUpperCase
val query = spark.readStream.format("socket").option("host", "localhost").option("port", 9999).load.as[String].map(mapper).writeStream.format("console").start
query.awaitTermination
对我来说，所有6个代码块都应该等效，并且用户只需要注意mapper（）可序列化即可。我说的对吗？