From 7d1b769f943bdc35a410e0225584b047602f68f4 Mon Sep 17 00:00:00 2001 From: Aaron Davidson Date: Mon, 14 Jul 2014 14:58:58 -0700 Subject: [PATCH] SPARK-1097: Do not introduce deadlock while fixing concurrency bug We recently added this lock on 'conf' in order to prevent concurrent creation. However, it turns out that this can introduce a deadlock because Hadoop also synchronizes on the Configuration objects when creating new Configurations (and they do so via a static REGISTRY which contains all created Configurations). This fix forces all Spark initialization of Configuration objects to occur serially by using a static lock that we control, and thus also prevents introducing the deadlock. --- core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala b/core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala index 041028514399..e521612ffc27 100644 --- a/core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/HadoopRDD.scala @@ -140,8 +140,8 @@ class HadoopRDD[K, V]( // Create a JobConf that will be cached and used across this RDD's getJobConf() calls in the // local process. The local cache is accessed through HadoopRDD.putCachedMetadata(). // The caching helps minimize GC, since a JobConf can contain ~10KB of temporary objects. - // synchronize to prevent ConcurrentModificationException (Spark-1097, Hadoop-10456) - conf.synchronized { + // Synchronize to prevent ConcurrentModificationException (Spark-1097, Hadoop-10456). + HadoopRDD.CONFIGURATION_INSTANTIATION_LOCK.synchronized { val newJobConf = new JobConf(conf) initLocalJobConfFuncOpt.map(f => f(newJobConf)) HadoopRDD.putCachedMetadata(jobConfCacheKey, newJobConf) @@ -246,6 +246,9 @@ class HadoopRDD[K, V]( } private[spark] object HadoopRDD { + /** Constructing Configuration objects is not threadsafe, use this lock to serialize. */ + val CONFIGURATION_INSTANTIATION_LOCK = new Object() + /** * The three methods below are helpers for accessing the local map, a property of the SparkEnv of * the local process.