我正在运行 kafka 生产者和消费者代码以在 cdh 5.12 中进行测试。当我尝试这样做时，我在运行消费者代码时遇到以下错误。
dataSet: org.apache.spark.sql.Dataset[(String, String)] = [key: string, value: string]
query: org.apache.spark.sql.streaming.StreamingQuery = org.apache.spark.sql.execution.streaming.StreamingQueryWrapper@109a5573
2018-10-25 10:08:37 ERROR MicroBatchExecution:91 - Query [id = 70bc4f7a-cc41-470d-afd0-d46e5aebf3db, runId = 4d974468-6c6b-47e5-976b-8b9aa98114e2] terminated with error
java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.initializeLogIfNecessary(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.log(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.logDebug(Logging.scala:58)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.logDebug(KafkaSourceProvider.scala:369)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$ConfigUpdater.set(KafkaSourceProvider.scala:439)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.kafkaParamsForDriver(KafkaSourceProvider.scala:394)
at org.apache.spark.sql.kafka010.KafkaSourceProvider.createSource(KafkaSourceProvider.scala:90)
at org.apache.spark.sql.execution.datasources.DataSource.createSource(DataSource.scala:277)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:77)
at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:194)
at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:77)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:75)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:266)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:256)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan$lzycompute(MicroBatchExecution.scala:75)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan(MicroBatchExecution.scala:61)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:265)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Exception in thread "stream execution thread for [id = 70bc4f7a-cc41-470d-afd0-d46e5aebf3db, runId = 4d974468-6c6b-47e5-976b-8b9aa98114e2]" java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.initializeLogIfNecessary(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.log(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.logDebug(Logging.scala:58)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.logDebug(KafkaSourceProvider.scala:369)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$ConfigUpdater.set(KafkaSourceProvider.scala:439)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.kafkaParamsForDriver(KafkaSourceProvider.scala:394)
at org.apache.spark.sql.kafka010.KafkaSourceProvider.createSource(KafkaSourceProvider.scala:90)
at org.apache.spark.sql.execution.datasources.DataSource.createSource(DataSource.scala:277)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:77)
at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:194)
at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:77)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:75)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:266)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:256)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan$lzycompute(MicroBatchExecution.scala:75)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan(MicroBatchExecution.scala:61)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:265)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
org.apache.spark.sql.streaming.StreamingQueryException: Query [id = 70bc4f7a-cc41-470d-afd0-d46e5aebf3db, runId = 4d974468-6c6b-47e5-976b-8b9aa98114e2] terminated with exception: null
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:295)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.initializeLogIfNecessary(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.log(KafkaSourceProvider.scala:369)
at org.apache.spark.internal.Logging$class.logDebug(Logging.scala:58)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.logDebug(KafkaSourceProvider.scala:369)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$ConfigUpdater.set(KafkaSourceProvider.scala:439)
at org.apache.spark.sql.kafka010.KafkaSourceProvider$.kafkaParamsForDriver(KafkaSourceProvider.scala:394)
at org.apache.spark.sql.kafka010.KafkaSourceProvider.createSource(KafkaSourceProvider.scala:90)
at org.apache.spark.sql.execution.datasources.DataSource.createSource(DataSource.scala:277)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1$$anonfun$applyOrElse$1.apply(MicroBatchExecution.scala:77)
at scala.collection.mutable.MapLike$class.getOrElseUpdate(MapLike.scala:194)
at scala.collection.mutable.AbstractMap.getOrElseUpdate(Map.scala:80)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:77)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$1.applyOrElse(MicroBatchExecution.scala:75)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$2.apply(TreeNode.scala:267)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:266)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformDown$1.apply(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:306)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:304)
at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:272)
at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:256)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan$lzycompute(MicroBatchExecution.scala:75)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.logicalPlan(MicroBatchExecution.scala:61)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:265)
下面是我正在运行的 scala 代码：
import org.apache.kafka.clients.consumer.KafkaConsumer
import org.apache.kafka.clients.producer.{KafkaProducer, ProducerRecord}
val dataFrame = spark.readStream.format("kafka").option("kafka.bootstrap.servers","host:9093,host:9093,host:9093").option("kafka.security.protocol", "SASL_SSL").option("kafka.sasl.kerberos.service.name", "kafka").option("kafka.ssl.truststore.location","/opt/cloudera/security/jks/truststore.jks").option("kafka.ssl.truststore.password", "password").option("subscribe", "SampleTopic").load()
// dataFrame.writeStream.format("console").option("truncate","false").start().awaitTermination()
dataFrame.printSchema()
val dataSet =dataFrame.selectExpr("CAST(key AS STRING)", "CAST(value AS STRING)").as[(String, String)]
val query = dataSet.writeStream.outputMode("append").format("console").start()
query.awaitTermination()
下面是我正在运行以执行上述代码的命令：
spark2-shell --files /tmp/jaas.conf,/path/to/.keytab --conf spark.executor.extraJavaOptions=-Djava.security.auth.login.config=/tmp/jaas.conf --conf spark.driver.extraJavaOptions=-Djava.security.auth.login.config=/tmp/jaas.conf --packages org.apache.spark:spark-sql-kafka-0-10_2.11:2.2.0 -i /path/to/file.scala
谢谢
我遇到了类似的问题，事实证明问题是 Spark 版本与所用软件包的版本不兼容。
对于您的情况 - 根据 cloudera doccdh 5.12附带 Spark 1.6，而反过来需要 scala 2.10，而使用的包org.apache.spark:spark-sql-kafka-0-10_2.11:2.2.0是使用 scala 2.11 编译的。您可以尝试改用org.apache.spark：spark-streaming-kafka_2.10：1.6.1。
学分：https://community.hortonworks.com/articles/197922/spark-23-structured-streaming-integration-with-apa.html