Clean context of most remaining functions in PairRDDFunctions, which ultimately call combineByKey

srowen · srowen · commit 8df68fed84cb · 2014-12-14T01:08:27.000Z
diff --git a/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala b/core/src/main/scala/org/apache/spark/rdd/PairRDDFunctions.scala
@@ -84,7 +84,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])
         throw new SparkException("Default partitioner cannot partition array keys.")
       }
     }
-    val aggregator = new Aggregator[K, V, C](createCombiner, mergeValue, mergeCombiners)
+    val aggregator = new Aggregator[K, V, C](
+      self.context.clean(createCombiner),
+      self.context.clean(mergeValue),
+      self.context.clean(mergeCombiners))
     if (self.partitioner == Some(partitioner)) {
       self.mapPartitions(iter => {
         val context = TaskContext.get()

Original file line number	Diff line number	Diff line change
`@@ -84,7 +84,10 @@ class PairRDDFunctions[K, V](self: RDD[(K, V)])`
`84`	`84`	`throw new SparkException("Default partitioner cannot partition array keys.")`
`85`	`85`	`}`
`86`	`86`	`}`
`87`		`- val aggregator = new Aggregator[K, V, C](createCombiner, mergeValue, mergeCombiners)`
	`87`	`+ val aggregator = new Aggregator[K, V, C](`
	`88`	`+ self.context.clean(createCombiner),`
	`89`	`+ self.context.clean(mergeValue),`
	`90`	`+ self.context.clean(mergeCombiners))`
`88`	`91`	`if (self.partitioner == Some(partitioner)) {`
`89`	`92`	`self.mapPartitions(iter => {`
`90`	`93`	`val context = TaskContext.get()`