[SPARK-32256][SQL][TEST-HADOOP2.7] Force to initialize Hadoop VersionInfo in HiveExternalCatalog
### What changes were proposed in this pull request? Force to initialize Hadoop VersionInfo in HiveExternalCatalog to make sure Hive can get the Hadoop version when using the isolated classloader. ### Why are the changes needed? This is a regression in Spark 3.0.0 because we switched the default Hive execution version from 1.2.1 to 2.3.7. Spark allows the user to set `spark.sql.hive.metastore.jars` to specify jars to access Hive Metastore. These jars are loaded by the isolated classloader. Because we also share Hadoop classes with the isolated classloader, the user doesn't need to add Hadoop jars to `spark.sql.hive.metastore.jars`, which means when we are using the isolated classloader, hadoop-common jar is not available in this case. If Hadoop VersionInfo is not initialized before we switch to the isolated classloader, and we try to initialize it using the isolated classloader (the current thread context classloader), it will fail and report `Unknown` which causes Hive to throw the following exception: ``` java.lang.RuntimeException: Illegal Hadoop Version: Unknown (expected A.B.* format) at org.apache.hadoop.hive.shims.ShimLoader.getMajorVersion(ShimLoader.java:147) at org.apache.hadoop.hive.shims.ShimLoader.loadShims(ShimLoader.java:122) at org.apache.hadoop.hive.shims.ShimLoader.getHadoopShims(ShimLoader.java:88) at org.apache.hadoop.hive.metastore.ObjectStore.getDataSourceProps(ObjectStore.java:377) at org.apache.hadoop.hive.metastore.ObjectStore.setConf(ObjectStore.java:268) at org.apache.hadoop.util.ReflectionUtils.setConf(ReflectionUtils.java:76) at org.apache.hadoop.util.ReflectionUtils.newInstance(ReflectionUtils.java:136) at org.apache.hadoop.hive.metastore.RawStoreProxy.<init>(RawStoreProxy.java:58) at org.apache.hadoop.hive.metastore.RawStoreProxy.getProxy(RawStoreProxy.java:67) at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.newRawStore(HiveMetaStore.java:517) at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.getMS(HiveMetaStore.java:482) at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.createDefaultDB(HiveMetaStore.java:544) at org.apache.hadoop.hive.metastore.HiveMetaStore$HMSHandler.init(HiveMetaStore.java:370) at org.apache.hadoop.hive.metastore.RetryingHMSHandler.<init>(RetryingHMSHandler.java:78) at org.apache.hadoop.hive.metastore.RetryingHMSHandler.getProxy(RetryingHMSHandler.java:84) at org.apache.hadoop.hive.metastore.HiveMetaStore.newRetryingHMSHandler(HiveMetaStore.java:5762) at org.apache.hadoop.hive.metastore.HiveMetaStoreClient.<init>(HiveMetaStoreClient.java:219) at org.apache.hadoop.hive.ql.metadata.SessionHiveMetaStoreClient.<init>(SessionHiveMetaStoreClient.java:67) 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:1548) 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:3080) at org.apache.hadoop.hive.ql.metadata.Hive.getMSC(Hive.java:3108) at org.apache.hadoop.hive.ql.metadata.Hive.getAllFunctions(Hive.java:3349) at org.apache.hadoop.hive.ql.metadata.Hive.reloadFunctions(Hive.java:217) at org.apache.hadoop.hive.ql.metadata.Hive.registerAllFunctionsOnce(Hive.java:204) at org.apache.hadoop.hive.ql.metadata.Hive.<init>(Hive.java:331) at org.apache.hadoop.hive.ql.metadata.Hive.get(Hive.java:292) at org.apache.hadoop.hive.ql.metadata.Hive.getInternal(Hive.java:262) at org.apache.hadoop.hive.ql.metadata.Hive.get(Hive.java:247) at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:543) at org.apache.hadoop.hive.ql.session.SessionState.start(SessionState.java:511) at org.apache.spark.sql.hive.client.HiveClientImpl.newState(HiveClientImpl.scala:175) at org.apache.spark.sql.hive.client.HiveClientImpl.<init>(HiveClientImpl.scala:128) 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:301) at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:431) at org.apache.spark.sql.hive.HiveUtils$.newClientForMetadata(HiveUtils.scala:324) at org.apache.spark.sql.hive.HiveExternalCatalog.client$lzycompute(HiveExternalCatalog.scala:72) at org.apache.spark.sql.hive.HiveExternalCatalog.client(HiveExternalCatalog.scala:71) at org.apache.spark.sql.hive.client.HadoopVersionInfoSuite.$anonfun$new$1(HadoopVersionInfoSuite.scala:63) at org.scalatest.OutcomeOf.outcomeOf(OutcomeOf.scala:85) at org.scalatest.OutcomeOf.outcomeOf$(OutcomeOf.scala:83) ``` Technically, This is indeed an issue of Hadoop VersionInfo which has been fixed: https://issues.apache.org/jira/browse/HADOOP-14067. But since we are still supporting old Hadoop versions, we should fix it. Why this issue starts to happen in Spark 3.0.0? In Spark 2.4.x, we use Hive 1.2.1 by default. It will trigger `VersionInfo` initialization in the static codes of `Hive` class. This will happen when we load `HiveClientImpl` class because `HiveClientImpl.clent` method refers to `Hive` class. At this moment, the thread context classloader is not using the isolcated classloader, so it can access hadoop-common jar on the classpath and initialize it correctly. In Spark 3.0.0, we use Hive 2.3.7. The static codes of `Hive` class are not accessing `VersionInfo` because of the change in https://issues.apache.org/jira/browse/HIVE-11657. Instead, accessing `VersionInfo` happens when creating a `Hive` object (See the above stack trace). This happens here https://github.com/apache/spark/blob/v3.0.0/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala#L260. But we switch to the isolated classloader before calling `HiveClientImpl.client` (See https://github.com/apache/spark/blob/v3.0.0/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala#L283). This is exactly what I mentioned above: `If Hadoop VersionInfo is not initialized before we switch to the isolated classloader, and we try to initialize it using the isolated classloader (the current thread context classloader), it will fail` ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? The new regression test added in this PR. Note that the new UT doesn't fail with the default profiles (-Phadoop-3.2) because it's already fixed at Hadoop 3.1. Please use the following to verify this. ``` build/sbt -Phadoop-2.7 -Phive "hive/testOnly *.HadoopVersionInfoSuite" ``` Closes #29059 from zsxwing/SPARK-32256. Authored-by: Shixiong Zhu <zsxwing@gmail.com> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
This commit is contained in:
Shixiong Zhu
HyukjinKwon
parent
e6e43cb2f9
commit
c8779d9dfc
|
|
@ -476,6 +476,7 @@ object SparkParallelTestGrouping {
|
|||
"org.apache.spark.ml.classification.LogisticRegressionSuite",
|
||||
"org.apache.spark.ml.classification.LinearSVCSuite",
|
||||
"org.apache.spark.sql.SQLQueryTestSuite",
|
||||
"org.apache.spark.sql.hive.client.HadoopVersionInfoSuite",
|
||||
"org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperationSuite",
|
||||
"org.apache.spark.sql.hive.thriftserver.ThriftServerQueryTestSuite",
|
||||
"org.apache.spark.sql.hive.thriftserver.SparkSQLEnvSuite",
|
||||
|
|
|
|||
|
|
@ -61,6 +61,10 @@ private[spark] class HiveExternalCatalog(conf: SparkConf, hadoopConf: Configurat
|
|||
import HiveExternalCatalog._
|
||||
import CatalogTableType._
|
||||
|
||||
// SPARK-32256: Make sure `VersionInfo` is initialized before touching the isolated classloader.
|
||||
// This is to ensure Hive can get the Hadoop version when using the isolated classloader.
|
||||
org.apache.hadoop.util.VersionInfo.getVersion()
|
||||
|
||||
/**
|
||||
* A Hive client used to interact with the metastore.
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -0,0 +1,72 @@
|
|||
/*
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
* this work for additional information regarding copyright ownership.
|
||||
* The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
* (the "License"); you may not use this file except in compliance with
|
||||
* the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.spark.sql.hive.client
|
||||
|
||||
import java.io.File
|
||||
import java.net.URLClassLoader
|
||||
|
||||
import org.apache.hadoop.conf.Configuration
|
||||
|
||||
import org.apache.spark.{SparkConf, SparkFunSuite}
|
||||
import org.apache.spark.sql.hive.{HiveExternalCatalog, HiveUtils}
|
||||
import org.apache.spark.util.Utils
|
||||
|
||||
/**
|
||||
* This test suite requires a clean JVM because it's testing the initialization of static codes in
|
||||
* `org.apache.hadoop.util.VersionInfo`.
|
||||
*/
|
||||
class HadoopVersionInfoSuite extends SparkFunSuite {
|
||||
override protected val enableAutoThreadAudit = false
|
||||
|
||||
test("SPARK-32256: Hadoop VersionInfo should be preloaded") {
|
||||
val ivyPath =
|
||||
Utils.createTempDir(namePrefix = s"${classOf[HadoopVersionInfoSuite].getSimpleName}-ivy")
|
||||
try {
|
||||
val hadoopConf = new Configuration()
|
||||
hadoopConf.set("test", "success")
|
||||
hadoopConf.set("datanucleus.schema.autoCreateAll", "true")
|
||||
hadoopConf.set("hive.metastore.schema.verification", "false")
|
||||
|
||||
// Download jars for Hive 2.0
|
||||
val client = IsolatedClientLoader.forVersion(
|
||||
hiveMetastoreVersion = "2.0",
|
||||
hadoopVersion = "2.7.4",
|
||||
sparkConf = new SparkConf(),
|
||||
hadoopConf = hadoopConf,
|
||||
config = HiveClientBuilder.buildConf(Map.empty),
|
||||
ivyPath = Some(ivyPath.getCanonicalPath),
|
||||
sharesHadoopClasses = true)
|
||||
val jars = client.classLoader.getParent.asInstanceOf[URLClassLoader].getURLs
|
||||
.map(u => new File(u.toURI))
|
||||
// Drop all Hadoop jars to use the existing Hadoop jars on the classpath
|
||||
.filter(!_.getName.startsWith("org.apache.hadoop_hadoop-"))
|
||||
|
||||
val sparkConf = new SparkConf()
|
||||
sparkConf.set(HiveUtils.HIVE_METASTORE_VERSION, "2.0")
|
||||
sparkConf.set(
|
||||
HiveUtils.HIVE_METASTORE_JARS,
|
||||
jars.map(_.getCanonicalPath).mkString(File.pathSeparator))
|
||||
HiveClientBuilder.buildConf(Map.empty).foreach { case (k, v) =>
|
||||
hadoopConf.set(k, v)
|
||||
}
|
||||
new HiveExternalCatalog(sparkConf, hadoopConf).client.getState
|
||||
} finally {
|
||||
Utils.deleteRecursively(ivyPath)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -33,7 +33,7 @@ private[client] object HiveClientBuilder {
|
|||
Some(new File(sys.props("java.io.tmpdir"), "hive-ivy-cache").getAbsolutePath))
|
||||
}
|
||||
|
||||
private def buildConf(extraConf: Map[String, String]) = {
|
||||
private[client] def buildConf(extraConf: Map[String, String]): Map[String, String] = {
|
||||
lazy val warehousePath = Utils.createTempDir()
|
||||
lazy val metastorePath = Utils.createTempDir()
|
||||
metastorePath.delete()
|
||||
|
|
|
|||
Loading…
Reference in a new issue