From 8cbcc33876c773722163b2259644037bbb259bd1 Mon Sep 17 00:00:00 2001 From: Dongjoon Hyun Date: Fri, 9 Feb 2018 12:54:57 +0800 Subject: [PATCH] [SPARK-23186][SQL] Initialize DriverManager first before loading JDBC Drivers ## What changes were proposed in this pull request? Since some JDBC Drivers have class initialization code to call `DriverManager`, we need to initialize `DriverManager` first in order to avoid potential executor-side **deadlock** situations like the following (or [STORM-2527](https://issues.apache.org/jira/browse/STORM-2527)). ``` Thread 9587: (state = BLOCKED) - sun.reflect.NativeConstructorAccessorImpl.newInstance0(java.lang.reflect.Constructor, java.lang.Object[]) bci=0 (Compiled frame; information may be imprecise) - sun.reflect.NativeConstructorAccessorImpl.newInstance(java.lang.Object[]) bci=85, line=62 (Compiled frame) - sun.reflect.DelegatingConstructorAccessorImpl.newInstance(java.lang.Object[]) bci=5, line=45 (Compiled frame) - java.lang.reflect.Constructor.newInstance(java.lang.Object[]) bci=79, line=423 (Compiled frame) - java.lang.Class.newInstance() bci=138, line=442 (Compiled frame) - java.util.ServiceLoader$LazyIterator.nextService() bci=119, line=380 (Interpreted frame) - java.util.ServiceLoader$LazyIterator.next() bci=11, line=404 (Interpreted frame) - java.util.ServiceLoader$1.next() bci=37, line=480 (Interpreted frame) - java.sql.DriverManager$2.run() bci=21, line=603 (Interpreted frame) - java.sql.DriverManager$2.run() bci=1, line=583 (Interpreted frame) - java.security.AccessController.doPrivileged(java.security.PrivilegedAction) bci=0 (Compiled frame) - java.sql.DriverManager.loadInitialDrivers() bci=27, line=583 (Interpreted frame) - java.sql.DriverManager.() bci=32, line=101 (Interpreted frame) - org.apache.phoenix.mapreduce.util.ConnectionUtil.getConnection(java.lang.String, java.lang.Integer, java.lang.String, java.util.Properties) bci=12, line=98 (Interpreted frame) - org.apache.phoenix.mapreduce.util.ConnectionUtil.getInputConnection(org.apache.hadoop.conf.Configuration, java.util.Properties) bci=22, line=57 (Interpreted frame) - org.apache.phoenix.mapreduce.PhoenixInputFormat.getQueryPlan(org.apache.hadoop.mapreduce.JobContext, org.apache.hadoop.conf.Configuration) bci=61, line=116 (Interpreted frame) - org.apache.phoenix.mapreduce.PhoenixInputFormat.createRecordReader(org.apache.hadoop.mapreduce.InputSplit, org.apache.hadoop.mapreduce.TaskAttemptContext) bci=10, line=71 (Interpreted frame) - org.apache.spark.rdd.NewHadoopRDD$$anon$1.(org.apache.spark.rdd.NewHadoopRDD, org.apache.spark.Partition, org.apache.spark.TaskContext) bci=233, line=156 (Interpreted frame) Thread 9170: (state = BLOCKED) - org.apache.phoenix.jdbc.PhoenixDriver.() bci=35, line=125 (Interpreted frame) - sun.reflect.NativeConstructorAccessorImpl.newInstance0(java.lang.reflect.Constructor, java.lang.Object[]) bci=0 (Compiled frame) - sun.reflect.NativeConstructorAccessorImpl.newInstance(java.lang.Object[]) bci=85, line=62 (Compiled frame) - sun.reflect.DelegatingConstructorAccessorImpl.newInstance(java.lang.Object[]) bci=5, line=45 (Compiled frame) - java.lang.reflect.Constructor.newInstance(java.lang.Object[]) bci=79, line=423 (Compiled frame) - java.lang.Class.newInstance() bci=138, line=442 (Compiled frame) - org.apache.spark.sql.execution.datasources.jdbc.DriverRegistry$.register(java.lang.String) bci=89, line=46 (Interpreted frame) - org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply() bci=7, line=53 (Interpreted frame) - org.apache.spark.sql.execution.datasources.jdbc.JdbcUtils$$anonfun$createConnectionFactory$2.apply() bci=1, line=52 (Interpreted frame) - org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$$anon$1.(org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD, org.apache.spark.Partition, org.apache.spark.TaskContext) bci=81, line=347 (Interpreted frame) - org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD.compute(org.apache.spark.Partition, org.apache.spark.TaskContext) bci=7, line=339 (Interpreted frame) ``` ## How was this patch tested? N/A Author: Dongjoon Hyun Closes #20359 from dongjoon-hyun/SPARK-23186. --- .../sql/execution/datasources/jdbc/DriverRegistry.scala | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/DriverRegistry.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/DriverRegistry.scala index 7a6c0f9fed..1723596de1 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/DriverRegistry.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/jdbc/DriverRegistry.scala @@ -32,6 +32,13 @@ import org.apache.spark.util.Utils */ object DriverRegistry extends Logging { + /** + * Load DriverManager first to avoid any race condition between + * DriverManager static initialization block and specific driver class's + * static initialization block. e.g. PhoenixDriver + */ + DriverManager.getDrivers + private val wrapperMap: mutable.Map[String, DriverWrapper] = mutable.Map.empty def register(className: String): Unit = {