Вопрос:

Проблемы пробного примера в Spark-shell

scala apache-spark apache-spark-sql

8500 просмотра

1 ответ

3 Репутация автора

Хотел попробовать Spark 2.0, но когда я попытался запустить следующий код с http://spark.apache.org/docs/latest/sql-programming-guide.html#getting-started

import org.apache.spark.sql.SparkSession
import spark.implicits._

val peopleDF = spark.read.format("json").load("myDir/examples/src/main/resources/people.json")

Я получаю:

16/08/22 22:59:53 WARN Hive: Failed to access metastore. This class should not accessed in runtime.
org.apache.hadoop.hive.ql.metadata.HiveException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.Sess
ionHiveMetaStoreClient
        at org.apache.hadoop.hive.ql.metadata.Hive.getAllDatabases(Hive.java:1236)
        at org.apache.hadoop.hive.ql.metadata.Hive.reloadFunctions(Hive.java:174)
        at org.apache.hadoop.hive.ql.metadata.Hive.<clinit>(Hive.java:166)
        at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:503)
        at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:171)
        at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
        at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
        at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
        at java.lang.reflect.Constructor.newInstance(Unknown Source)
        at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:258)
        at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:359)
        at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:263)
        at org.apache.spark.sql.hive.HiveSharedState.metadataHive$lzycompute(HiveSharedState.scala:39)
        at org.apache.spark.sql.hive.HiveSharedState.metadataHive(HiveSharedState.scala:38)
        at org.apache.spark.sql.hive.HiveSharedState.externalCatalog$lzycompute(HiveSharedState.scala:46)
        at org.apache.spark.sql.hive.HiveSharedState.externalCatalog(HiveSharedState.scala:45)
        at org.apache.spark.sql.hive.HiveSessionState.catalog$lzycompute(HiveSessionState.scala:50)
        at org.apache.spark.sql.hive.HiveSessionState.catalog(HiveSessionState.scala:48)
        at org.apache.spark.sql.hive.HiveSessionState$$anon$1.<init>(HiveSessionState.scala:63)
        at org.apache.spark.sql.hive.HiveSessionState.analyzer$lzycompute(HiveSessionState.scala:63)
        at org.apache.spark.sql.hive.HiveSessionState.analyzer(HiveSessionState.scala:62)
        at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
        at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
        at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(SparkSession.scala:382)
        at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:143)
        at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:132)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:27)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:32)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:34)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:36)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw$$iw.<init>(<console>:38)
        at $line19.$read$$iw$$iw$$iw$$iw$$iw.<init>(<console>:40)
        at $line19.$read$$iw$$iw$$iw$$iw.<init>(<console>:42)
        at $line19.$read$$iw$$iw$$iw.<init>(<console>:44)
        at $line19.$read$$iw$$iw.<init>(<console>:46)
        at $line19.$read$$iw.<init>(<console>:48)
        at $line19.$read.<init>(<console>:50)
        at $line19.$read$.<init>(<console>:54)
        at $line19.$read$.<clinit>(<console>)
        at $line19.$eval$.$print$lzycompute(<console>:7)
        at $line19.$eval$.$print(<console>:6)
        at $line19.$eval.$print(<console>)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
        at java.lang.reflect.Method.invoke(Unknown Source)
        at scala.tools.nsc.interpreter.IMain$ReadEvalPrint.call(IMain.scala:786)
        at scala.tools.nsc.interpreter.IMain$Request.loadAndRun(IMain.scala:1047)
        at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:638)
        at scala.tools.nsc.interpreter.IMain$WrappedRequest$$anonfun$loadAndRunReq$1.apply(IMain.scala:637)
        at scala.reflect.internal.util.ScalaClassLoader$class.asContext(ScalaClassLoader.scala:31)
        at scala.reflect.internal.util.AbstractFileClassLoader.asContext(AbstractFileClassLoader.scala:19)
        at scala.tools.nsc.interpreter.IMain$WrappedRequest.loadAndRunReq(IMain.scala:637)
        at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:569)
        at scala.tools.nsc.interpreter.IMain.interpret(IMain.scala:565)
        at scala.tools.nsc.interpreter.ILoop.interpretStartingWith(ILoop.scala:807)
        at scala.tools.nsc.interpreter.ILoop.command(ILoop.scala:681)
        at scala.tools.nsc.interpreter.ILoop.processLine(ILoop.scala:395)
        at scala.tools.nsc.interpreter.ILoop.loop(ILoop.scala:415)
        at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply$mcZ$sp(ILoop.scala:923)
        at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
        at scala.tools.nsc.interpreter.ILoop$$anonfun$process$1.apply(ILoop.scala:909)
        at scala.reflect.internal.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:97)
        at scala.tools.nsc.interpreter.ILoop.process(ILoop.scala:909)
        at org.apache.spark.repl.Main$.doMain(Main.scala:68)
        at org.apache.spark.repl.Main$.main(Main.scala:51)
        at org.apache.spark.repl.Main.main(Main.scala)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
        at java.lang.reflect.Method.invoke(Unknown Source)
        at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
        at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
        at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
        at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
        at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
        at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1523)
        at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:86)
        at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:132)
        at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:104)
        at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:3005)
        at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3024)
        at org.apache.hadoop.hive.ql.metadata.Hive.getAllDatabases(Hive.java:1234)
        ... 75 more

Caused by: java.lang.reflect.InvocationTargetException
        at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
        at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
        at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
        at java.lang.reflect.Constructor.newInstance(Unknown Source)
        at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1521)
        ... 81 more

Caused by: java.lang.IllegalArgumentException: java.net.URISyntaxException: Relative path in absolute URI: file:C:/Users/Woahstan/spark-war
ehouse
        at org.apache.hadoop.fs.Path.initialize(Path.java:206)
        at org.apache.hadoop.fs.Path.<init>(Path.java:172)
        at org.apache.hadoop.hive.metastore.Warehouse.getWhRoot(Warehouse.java:159)
        at org.apache.hadoop.hive.metastore.Warehouse.getDefaultDatabasePath(Warehouse.java:177)
        at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB_core(HiveMetaStore.java:600)
        at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB(HiveMetaStore.java:620)
        at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.init(HiveMetaStore.java:461)
        at org.apache.hadoop.hive.metastore.RetryingHMSHandler.<init>(RetryingHMSHandler.java:66)
        at org.apache.hadoop.hive.metastore.RetryingHMSHandler.getProxy(RetryingHMSHandler.java:72)
        at org.apache.hadoop.hive.metastore.HiveMetaStore.newRetryingHMSHandler(HiveMetaStore.java:5762)
        at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:199)
        at org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.<init>(SessionHiveMetaStoreClient.java:74)
        ... 86 more

Caused by: java.net.URISyntaxException: Relative path in absolute URI: file:C:/Users/Woahstan/spark-warehouse
        at java.net.URI.checkPath(Unknown Source)
        at java.net.URI.<init>(Unknown Source)
        at org.apache.hadoop.fs.Path.initialize(Path.java:203)
        ... 97 more

16/08/22 22:59:53 WARN ObjectStore: Failed to get database default, returning NoSuchObjectException
java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient

  at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:522)
  at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:171)
  at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
  at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
  at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
  at java.lang.reflect.Constructor.newInstance(Unknown Source)
  at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:258)
  at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:359)
  at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:263)
  at org.apache.spark.sql.hive.HiveSharedState.metadataHive$lzycompute(HiveSharedState.scala:39)
  at org.apache.spark.sql.hive.HiveSharedState.metadataHive(HiveSharedState.scala:38)
  at org.apache.spark.sql.hive.HiveSharedState.externalCatalog$lzycompute(HiveSharedState.scala:46)
  at org.apache.spark.sql.hive.HiveSharedState.externalCatalog(HiveSharedState.scala:45)
  at org.apache.spark.sql.hive.HiveSessionState.catalog$lzycompute(HiveSessionState.scala:50)
  at org.apache.spark.sql.hive.HiveSessionState.catalog(HiveSessionState.scala:48)
  at org.apache.spark.sql.hive.HiveSessionState$$anon$1.<init>(HiveSessionState.scala:63)
  at org.apache.spark.sql.hive.HiveSessionState.analyzer$lzycompute(HiveSessionState.scala:63)
  at org.apache.spark.sql.hive.HiveSessionState.analyzer(HiveSessionState.scala:62)
  at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:49)
  at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
  at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(SparkSession.scala:382)
  at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:143)
  at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:132)
  ... 50 elided

Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
  at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1523)
  at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:86)
  at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:132)
  at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:104)
  at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:3005)
  at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3024)
  at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:503)
  ... 72 more

Caused by: java.lang.reflect.InvocationTargetException: java.lang.IllegalArgumentException: java.net.URISyntaxException: Relative path in a
bsolute URI: file:C:/Users/Woahstan/spark-warehouse
  at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
  at sun.reflect.NativeConstructorAccessorImpl.newInstance(Unknown Source)
  at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(Unknown Source)
  at java.lang.reflect.Constructor.newInstance(Unknown Source)
  at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1521)
  ... 78 more

Caused by: java.lang.IllegalArgumentException: java.net.URISyntaxException: Relative path in absolute URI: file:C:/Users/Woahstan/spark-war
ehouse
  at org.apache.hadoop.fs.Path.initialize(Path.java:206)
  at org.apache.hadoop.fs.Path.<init>(Path.java:172)
  at org.apache.hadoop.hive.metastore.Warehouse.getWhRoot(Warehouse.java:159)
  at org.apache.hadoop.hive.metastore.Warehouse.getDefaultDatabasePath(Warehouse.java:177)
  at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB_core(HiveMetaStore.java:600)
  at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB(HiveMetaStore.java:620)
  at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.init(HiveMetaStore.java:461)
  at org.apache.hadoop.hive.metastore.RetryingHMSHandler.<init>(RetryingHMSHandler.java:66)
  at org.apache.hadoop.hive.metastore.RetryingHMSHandler.getProxy(RetryingHMSHandler.java:72)
  at org.apache.hadoop.hive.metastore.HiveMetaStore.newRetryingHMSHandler(HiveMetaStore.java:5762)
  at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:199)
  at org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.<init>(SessionHiveMetaStoreClient.java:74)
  ... 83 more

Caused by: java.net.URISyntaxException: Relative path in absolute URI: file:C:/Users/Woahstan/spark-warehouse
  at java.net.URI.checkPath(Unknown Source)
  at java.net.URI.<init>(Unknown Source)
  at org.apache.hadoop.fs.Path.initialize(Path.java:203)
  ... 94 more

Любые идеи, что пошло не так и как мне решить эту проблему?

Автор: Ayu Источник Размещён: 22.08.2016 08:44

Ответы (1)


0 плюса

11165 Репутация автора

Решение

Это известная проблема ( https://issues.apache.org/jira/browse/SPARK-15899 ) в Spark 2.0.0. Запустите spark-shell с аргументом --conf, как показано ниже:

spark-shell --conf spark.sql.warehouse.dir=file:///C:/tmp/spark-warehouse

Если вы хотите запустить Java-пример в 2.0.0 с помощью Spark Session, используйте.

SparkSession spark = SparkSession
  .builder()
  .appName("JavaALSExample")
  .config("spark.sql.warehouse.dir", "file:///C:/tmp/spark-warehouse")
  .master("local[2]")
  .getOrCreate();
Автор: abaghel Размещён: 23.08.2016 06:46
Вопросы из категории :
32x32