From 8a75a3049539eeef04c0db51736e97070c162b46 Mon Sep 17 00:00:00 2001 From: Tathagata Das Date: Tue, 1 Dec 2015 21:04:52 -0800 Subject: [SPARK-12087][STREAMING] Create new JobConf for every batch in saveAsHadoopFiles The JobConf object created in `DStream.saveAsHadoopFiles` is used concurrently in multiple places: * The JobConf is updated by `RDD.saveAsHadoopFile()` before the job is launched * The JobConf is serialized as part of the DStream checkpoints. These concurrent accesses (updating in one thread, while the another thread is serializing it) can lead to concurrentModidicationException in the underlying Java hashmap using in the internal Hadoop Configuration object. The solution is to create a new JobConf in every batch, that is updated by `RDD.saveAsHadoopFile()`, while the checkpointing serializes the original JobConf. Tests to be added in #9988 will fail reliably without this patch. Keeping this patch really small to make sure that it can be added to previous branches. Author: Tathagata Das Closes #10088 from tdas/SPARK-12087. --- .../org/apache/spark/streaming/dstream/PairDStreamFunctions.scala | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala index fb691eed27..2762309134 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/PairDStreamFunctions.scala @@ -730,7 +730,8 @@ class PairDStreamFunctions[K, V](self: DStream[(K, V)]) val serializableConf = new SerializableJobConf(conf) val saveFunc = (rdd: RDD[(K, V)], time: Time) => { val file = rddToFileName(prefix, suffix, time) - rdd.saveAsHadoopFile(file, keyClass, valueClass, outputFormatClass, serializableConf.value) + rdd.saveAsHadoopFile(file, keyClass, valueClass, outputFormatClass, + new JobConf(serializableConf.value)) } self.foreachRDD(saveFunc) } -- cgit v1.2.3