You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (Jira)" <ji...@apache.org> on 2021/04/27 21:18:00 UTC
[jira] [Assigned] (SPARK-35248) Spark shall load system class first
in IsolatedClientLoader
[ https://issues.apache.org/jira/browse/SPARK-35248?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-35248:
------------------------------------
Assignee: (was: Apache Spark)
> Spark shall load system class first in IsolatedClientLoader
> -----------------------------------------------------------
>
> Key: SPARK-35248
> URL: https://issues.apache.org/jira/browse/SPARK-35248
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.4.7, 3.1.1
> Reporter: Daniel Dai
> Priority: Major
>
> This happens when Spark try to load HMS client jars using IsolatedClientLoader, in particular, when "spark.sql.hive.metastore.jars"="builtin" (default). Spark try to load a conflicting thrift lib in user jar, which results in exception:
> {code:java}
> 21/04/22 04:10:53 ERROR [main] yarn.Client: Application diagnostics message: User class threw exception: org.apache.spark.sql.AnalysisException: java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient;
> at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:106)
> at org.apache.spark.sql.hive.HiveExternalCatalog.databaseExists(HiveExternalCatalog.scala:220)
> at org.apache.spark.sql.internal.SharedState.externalCatalog$lzycompute(SharedState.scala:114)
> at org.apache.spark.sql.internal.SharedState.externalCatalog(SharedState.scala:102)
> at org.apache.spark.sql.internal.SharedState.globalTempViewManager$lzycompute(SharedState.scala:141)
> at org.apache.spark.sql.internal.SharedState.globalTempViewManager(SharedState.scala:136)
> at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
> at org.apache.spark.sql.hive.HiveSessionStateBuilder$$anonfun$2.apply(HiveSessionStateBuilder.scala:55)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager$lzycompute(SessionCatalog.scala:91)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.globalTempViewManager(SessionCatalog.scala:91)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.isTemporaryTable(SessionCatalog.scala:738)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.isRunningDirectlyOnFiles(Analyzer.scala:748)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.resolveRelation(Analyzer.scala:682)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:714)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$$anonfun$apply$8.applyOrElse(Analyzer.scala:707)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$apply$1.apply(AnalysisHelper.scala:90)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:89)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1$$anonfun$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:87)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsUp$1.apply(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsUp(AnalysisHelper.scala:86)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:707)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveRelations$.apply(Analyzer.scala:653)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
> at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
> at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:88)
> at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:84)
> at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:76)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:644)
> at com.pinterest.pintel.homefeed.pinnability.CreateFollowingScorpionDataInstances$.run(CreateFollowingScorpionDataInstances.scala:95)
> at com.pinterest.pintel.homefeed.pinnability.CreateFollowingScorpionDataInstances$.main(CreateFollowingScorpionDataInstances.scala:59)
> at com.pinterest.pintel.homefeed.pinnability.CreateFollowingScorpionDataInstances.main(CreateFollowingScorpionDataInstances.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:684)
> Caused by: java.lang.RuntimeException: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
> at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:528)
> at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:187)
> at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:121)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
> at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
> at org.apache.spark.sql.hive.client.IsolatedClientLoader.createClient(IsolatedClientLoader.scala:271)
> at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:384)
> at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:286)
> at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:66)
> at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:65)
> at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply$mcZ$sp(HiveExternalCatalog.scala:221)
> at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:221)
> at org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$databaseExists$1.apply(HiveExternalCatalog.scala:221)
> at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97)
> ... 71 more
> Caused by: java.lang.RuntimeException: Unable to instantiate org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient
> at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1532)
> at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.<init>(RetryingMetaStoreClient.java:86)
> at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:132)
> at org.apache.hadoop.hive.metastore.RetryingMetaStoreClient.getProxy(RetryingMetaStoreClient.java:104)
> at org.apache.hadoop.hive.ql.metadata.Hive.createMetaStoreClient(Hive.java:3066)
> at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3085)
> at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:509)
> ... 86 more
> Caused by: java.lang.reflect.InvocationTargetException
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
> at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
> at org.apache.hadoop.hive.metastore.MetaStoreUtils.newInstance(MetaStoreUtils.java:1530)
> ... 92 more
> Caused by: java.lang.NoSuchMethodError: com.facebook.fb303.FacebookService$Client.<init>(Lorg/apache/thrift/protocol/TProtocol;Lorg/apache/thrift/protocol/TProtocol;)V
> at org.apache.hadoop.hive.metastore.api.ThriftHiveMetastore$Client.<init>(ThriftHiveMetastore.java:552)
> at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.open(HiveMetaStoreClient.java:424)
> at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:238)
> at org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.<init>(SessionHiveMetaStoreClient.java:74)
> ... 97 more
> {code}
> By convention, Spark shall use system jars first unless spark.driver.userClassPathFirst is defined. The current behavior of IsolatedClientLoader breaks the contract and we'd like to fix.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org