[ https://issues.apache.org/jira/browse/SPARK-8427?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Patrick Wendell updated SPARK-8427: ----------------------------------- Priority: Critical (was: Blocker) > Incorrect ACL checking for partitioned table in Spark SQL-1.4 > ------------------------------------------------------------- > > Key: SPARK-8427 > URL: https://issues.apache.org/jira/browse/SPARK-8427 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 1.4.0 > Environment: CentOS 6 & OS X 10.9.5, Hive-0.13.1, Spark-1.4, Hadoop > 2.6.0 > Reporter: Karthik Subramanian > Priority: Critical > Labels: security > > Problem Statement: > While doing query on a partitioned table using Spark SQL (Version 1.4.0), > access denied exception is observed on the partition the user doesn’t belong > to (The user permission is controlled using HDF ACLs). The same works > correctly in hive. > Usercase: To address Multitenancy > Consider a table containing multiple customers and each customer with > multiple facility. The table is partitioned by customer and facility. The > user belonging to on facility will not have access to other facility. This is > enforced using HDFS ACLs on corresponding directories. When querying on the > table as ‘user1’ belonging to ‘facility1’ and ‘customer1’ on the particular > partition (using ‘where’ clause) only the corresponding directory access > should be verified and not the entire table. > The above use case works as expected when using HIVE client, version 0.13.1 & > 1.1.0. > The query used: select count(*) from customertable where customer=‘customer1’ > and facility=‘facility1’ > Below is the exception received in Spark-shell: > org.apache.hadoop.security.AccessControlException: Permission denied: > user=user1, access=READ_EXECUTE, > inode="/data/customertable/customer=customer2/facility=facility2”:root:supergroup:drwxrwx---:group::r-x,group:facility2:rwx > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkAccessAcl(FSPermissionChecker.java:351) > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:253) > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:185) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPermission(FSNamesystem.java:6512) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPermission(FSNamesystem.java:6494) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPathAccess(FSNamesystem.java:6419) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getListingInt(FSNamesystem.java:4954) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getListing(FSNamesystem.java:4915) > at > org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getListing(NameNodeRpcServer.java:826) > at > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getListing(ClientNamenodeProtocolServerSideTranslatorPB.java:612) > at > org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:962) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2039) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2035) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2033) > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57) > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > at java.lang.reflect.Constructor.newInstance(Constructor.java:526) > at > org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:106) > at > org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73) > at org.apache.hadoop.hdfs.DFSClient.listPaths(DFSClient.java:1971) > at org.apache.hadoop.hdfs.DFSClient.listPaths(DFSClient.java:1952) > at > org.apache.hadoop.hdfs.DistributedFileSystem.listStatusInternal(DistributedFileSystem.java:693) > at > org.apache.hadoop.hdfs.DistributedFileSystem.access$600(DistributedFileSystem.java:105) > at > org.apache.hadoop.hdfs.DistributedFileSystem$15.doCall(DistributedFileSystem.java:755) > at > org.apache.hadoop.hdfs.DistributedFileSystem$15.doCall(DistributedFileSystem.java:751) > at > org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) > at > org.apache.hadoop.hdfs.DistributedFileSystem.listStatus(DistributedFileSystem.java:751) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache.org$apache$spark$sql$sources$HadoopFsRelation$FileStatusCache$$listLeafFilesAndDirs$1(interfaces.scala:390) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$2$$anonfun$apply$2.apply(interfaces.scala:402) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$2$$anonfun$apply$2.apply(interfaces.scala:402) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at > scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251) > at scala.collection.mutable.ArrayOps$ofRef.flatMap(ArrayOps.scala:108) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$2.apply(interfaces.scala:402) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache$$anonfun$2.apply(interfaces.scala:398) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:251) > at > scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33) > at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108) > at > scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:251) > at scala.collection.mutable.ArrayOps$ofRef.flatMap(ArrayOps.scala:108) > at > org.apache.spark.sql.sources.HadoopFsRelation$FileStatusCache.refresh(interfaces.scala:398) > at > org.apache.spark.sql.sources.HadoopFsRelation.org$apache$spark$sql$sources$HadoopFsRelation$$fileStatusCache$lzycompute(interfaces.scala:416) > at > org.apache.spark.sql.sources.HadoopFsRelation.org$apache$spark$sql$sources$HadoopFsRelation$$fileStatusCache(interfaces.scala:414) > at > org.apache.spark.sql.sources.HadoopFsRelation.cachedLeafStatuses(interfaces.scala:421) > at > org.apache.spark.sql.parquet.ParquetRelation2$MetadataCache.refresh(newParquet.scala:355) > at > org.apache.spark.sql.parquet.ParquetRelation2.org$apache$spark$sql$parquet$ParquetRelation2$$metadataCache$lzycompute(newParquet.scala:154) > at > org.apache.spark.sql.parquet.ParquetRelation2.org$apache$spark$sql$parquet$ParquetRelation2$$metadataCache(newParquet.scala:152) > at > org.apache.spark.sql.parquet.ParquetRelation2$$anonfun$dataSchema$1.apply(newParquet.scala:193) > at > org.apache.spark.sql.parquet.ParquetRelation2$$anonfun$dataSchema$1.apply(newParquet.scala:193) > at scala.Option.getOrElse(Option.scala:120) > at > org.apache.spark.sql.parquet.ParquetRelation2.dataSchema(newParquet.scala:193) > at > org.apache.spark.sql.sources.HadoopFsRelation.schema$lzycompute(interfaces.scala:505) > at > org.apache.spark.sql.sources.HadoopFsRelation.schema(interfaces.scala:504) > at > org.apache.spark.sql.sources.LogicalRelation.<init>(LogicalRelation.scala:30) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$$anonfun$19.apply(HiveMetastoreCatalog.scala:314) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$$anonfun$19.apply(HiveMetastoreCatalog.scala:313) > at scala.Option.getOrElse(Option.scala:120) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog.org$apache$spark$sql$hive$HiveMetastoreCatalog$$convertToParquetRelation(HiveMetastoreCatalog.scala:313) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$ParquetConversions$$anonfun$1.applyOrElse(HiveMetastoreCatalog.scala:406) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$ParquetConversions$$anonfun$1.applyOrElse(HiveMetastoreCatalog.scala:378) > at scala.PartialFunction$Lifted.apply(PartialFunction.scala:218) > at scala.PartialFunction$Lifted.apply(PartialFunction.scala:214) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$collect$1.apply(TreeNode.scala:129) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$collect$1.apply(TreeNode.scala:129) > at > org.apache.spark.sql.catalyst.trees.TreeNode.foreach(TreeNode.scala:88) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreach$1.apply(TreeNode.scala:89) > at > org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$foreach$1.apply(TreeNode.scala:89) > at scala.collection.immutable.List.foreach(List.scala:318) > at > org.apache.spark.sql.catalyst.trees.TreeNode.foreach(TreeNode.scala:89) > at > org.apache.spark.sql.catalyst.trees.TreeNode.collect(TreeNode.scala:129) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$ParquetConversions$.apply(HiveMetastoreCatalog.scala:378) > at > org.apache.spark.sql.hive.HiveMetastoreCatalog$ParquetConversions$.apply(HiveMetastoreCatalog.scala:371) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:61) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:59) > at > scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111) > at scala.collection.immutable.List.foldLeft(List.scala:84) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:59) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:51) > at scala.collection.immutable.List.foreach(List.scala:318) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:51) > at > org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:922) > at > org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:922) > at > org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:920) > at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:131) > at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51) > at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:744) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:23) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:28) > at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:30) > at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:32) > at $iwC$$iwC$$iwC$$iwC.<init>(<console>:34) > at $iwC$$iwC$$iwC.<init>(<console>:36) > at $iwC$$iwC.<init>(<console>:38) > at $iwC.<init>(<console>:40) > at <init>(<console>:42) > at .<init>(<console>:46) > at .<clinit>(<console>) > at .<init>(<console>:7) > at .<clinit>(<console>) > at $print(<console>) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at > org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1065) > at > org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1338) > at > org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:840) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:871) > at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:819) > at > org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) > at > org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) > at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) > at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) > at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) > at > org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670) > at > org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997) > at > org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945) > at > org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945) > at > scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135) > at > org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945) > at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1059) > at org.apache.spark.repl.Main$.main(Main.scala:31) > at org.apache.spark.repl.Main.main(Main.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at > org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:664) > at > org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:169) > at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:192) > at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:111) > at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) > Caused by: > org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.security.AccessControlException): > Permission denied: user=user1, access=READ_EXECUTE, > inode="/data/customertable/customer=customer2/facility=facility2”:root:supergroup:drwxrwx---:group::r-x,group:facility2:rwx > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkAccessAcl(FSPermissionChecker.java:351) > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.check(FSPermissionChecker.java:253) > at > org.apache.hadoop.hdfs.server.namenode.FSPermissionChecker.checkPermission(FSPermissionChecker.java:185) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPermission(FSNamesystem.java:6512) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPermission(FSNamesystem.java:6494) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkPathAccess(FSNamesystem.java:6419) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getListingInt(FSNamesystem.java:4954) > at > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getListing(FSNamesystem.java:4915) > at > org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getListing(NameNodeRpcServer.java:826) > at > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getListing(ClientNamenodeProtocolServerSideTranslatorPB.java:612) > at > org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:962) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2039) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2035) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2033) > at org.apache.hadoop.ipc.Client.call(Client.java:1468) > at org.apache.hadoop.ipc.Client.call(Client.java:1399) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:232) > at com.sun.proxy.$Proxy17.getListing(Unknown Source) > at > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getListing(ClientNamenodeProtocolTranslatorPB.java:554) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) > at com.sun.proxy.$Proxy18.getListing(Unknown Source) > at org.apache.hadoop.hdfs.DFSClient.listPaths(DFSClient.java:1969) > ... 116 more -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org