LantaoJin opened a new pull request #25944: [SPARK-29254][SQL] Failed to include jars passed in through --jars when isolatedLoader is enabled URL: https://github.com/apache/spark/pull/25944 ### What changes were proposed in this pull request? Failed to include jars passed in through --jars when isolatedLoader is enabled(spark.sql.hive.metastore.jars != builtin). How to reproduce: ```scala test("SPARK-29254: include jars passed in through --jars when isolatedLoader is enabled") { def getJarFromUrl(urlString: String): File = { val fileName = urlString.split("/").last Utils.doFetchFile(urlString, Utils.createTempDir(), fileName, new SparkConf, null, null) } val repository = "https://repository.apache.org/content/repositories/releases/"; val unusedJar = TestUtils.createJarWithClasses(Seq.empty) val jar1 = TestUtils.createJarWithClasses(Seq("SparkSubmitClassA")) val jar2 = TestUtils.createJarWithClasses(Seq("SparkSubmitClassB")) // download Hive 2.1.1, a non builtinHiveVersion(1.2.1) version for testing val jar3 = getJarFromUrl(s"${repository}org/apache/hive/hive-contrib/" + s"2.1.1/hive-contrib-2.1.1.jar").getCanonicalPath val jar4 = getJarFromUrl(s"${repository}org/apache/hive/hcatalog/hive-hcatalog-core/" + s"2.1.1/hive-hcatalog-core-2.1.1.jar").getCanonicalPath val jarsString = Seq(jar1, jar2, jar3, jar4).map(j => j.toString).mkString(",") val args = Seq( "--class", SparkSubmitClassLoaderTest.getClass.getName.stripSuffix("$"), "--name", "SparkSubmitClassLoaderTest", "--master", "local-cluster[2,1,1024]", "--conf", "spark.ui.enabled=false", "--conf", "spark.master.rest.enabled=false", "--conf", "spark.sql.hive.metastore.version=2.1.1", "--conf", "spark.sql.hive.metastore.jars=maven", "--driver-java-options", "-Dderby.system.durability=test", "--jars", jarsString, unusedJar.toString, "SparkSubmitClassA", "SparkSubmitClassB") runSparkSubmit(args) } ``` It will get ClassNotFoundException: ```shell 2019-09-25 22:11:42.854 - stderr> 19/09/25 22:11:42 ERROR log: error in initSerDe: java.lang.ClassNotFoundException Class org.apache.hive.hcatalog.data.JsonSerDe not found 2019-09-25 22:11:42.854 - stderr> java.lang.ClassNotFoundException: Class org.apache.hive.hcatalog.data.JsonSerDe not found 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:2101) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.metastore.HiveMetaStoreUtils.getDeserializer(HiveMetaStoreUtils.java:84) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.metastore.HiveMetaStoreUtils.getDeserializer(HiveMetaStoreUtils.java:77) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Table.getDeserializerFromMetaStore(Table.java:289) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Table.getDeserializer(Table.java:271) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Table.getColsInternal(Table.java:663) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Table.getCols(Table.java:646) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:898) 2019-09-25 22:11:42.854 - stderr> at org.apache.hadoop.hive.ql.metadata.Hive.createTable(Hive.java:937) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.$anonfun$createTable$1(HiveClientImpl.scala:539) 2019-09-25 22:11:42.854 - stderr> at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.$anonfun$withHiveState$1(HiveClientImpl.scala:311) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:245) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:244) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:294) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.client.HiveClientImpl.createTable(HiveClientImpl.scala:537) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.HiveExternalCatalog.$anonfun$createTable$1(HiveExternalCatalog.scala:284) 2019-09-25 22:11:42.854 - stderr> at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:99) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.hive.HiveExternalCatalog.createTable(HiveExternalCatalog.scala:242) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.createTable(ExternalCatalogWithListener.scala:94) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.createTable(SessionCatalog.scala:325) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.execution.command.CreateTableCommand.run(tables.scala:132) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68) 2019-09-25 22:11:42.854 - stderr> at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:79) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.Dataset.$anonfun$logicalPlan$1(Dataset.scala:225) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3372) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$4(SQLExecution.scala:100) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:87) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3368) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:225) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:87) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.hive.test.TestHiveSparkSession.sql(TestHive.scala:238) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:550) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.hive.SparkSubmitClassLoaderTest$.main(HiveSparkSubmitSuite.scala:638) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.sql.hive.SparkSubmitClassLoaderTest.main(HiveSparkSubmitSuite.scala) 2019-09-25 22:11:42.855 - stderr> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) 2019-09-25 22:11:42.855 - stderr> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) 2019-09-25 22:11:42.855 - stderr> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 2019-09-25 22:11:42.855 - stderr> at java.lang.reflect.Method.invoke(Method.java:498) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:901) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:179) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:202) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:89) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:980) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:989) 2019-09-25 22:11:42.855 - stderr> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) ``` ### Why are the changes needed? Fix but. ### Does this PR introduce any user-facing change? No ### How was this patch tested? Add an UT
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
