Repository: spark
Updated Branches:
  refs/heads/master d7dbce8f7 -> 7f4b58373


[SPARK-7181] [CORE] fix inifite loop in Externalsorter's mergeWithAggregation

see [SPARK-7181](https://issues.apache.org/jira/browse/SPARK-7181).

Author: Qiping Li <[email protected]>

Closes #5737 from chouqin/externalsorter and squashes the following commits:

2924b93 [Qiping Li] fix inifite loop in Externalsorter's mergeWithAggregation


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/7f4b5837
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/7f4b5837
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/7f4b5837

Branch: refs/heads/master
Commit: 7f4b583733714bbecb43fb0823134bf2ec720a17
Parents: d7dbce8
Author: Qiping Li <[email protected]>
Authored: Wed Apr 29 23:52:16 2015 +0100
Committer: Sean Owen <[email protected]>
Committed: Wed Apr 29 23:52:16 2015 +0100

----------------------------------------------------------------------
 .../scala/org/apache/spark/util/collection/ExternalSorter.scala | 3 ++-
 .../org/apache/spark/util/collection/ExternalSorterSuite.scala  | 5 ++++-
 2 files changed, 6 insertions(+), 2 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/7f4b5837/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala
----------------------------------------------------------------------
diff --git 
a/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala 
b/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala
index ef3cac6..4ed8a74 100644
--- a/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala
+++ b/core/src/main/scala/org/apache/spark/util/collection/ExternalSorter.scala
@@ -527,7 +527,8 @@ private[spark] class ExternalSorter[K, V, C](
           val k = elem._1
           var c = elem._2
           while (sorted.hasNext && sorted.head._1 == k) {
-            c = mergeCombiners(c, sorted.head._2)
+            val pair = sorted.next()
+            c = mergeCombiners(c, pair._2)
           }
           (k, c)
         }

http://git-wip-us.apache.org/repos/asf/spark/blob/7f4b5837/core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala
----------------------------------------------------------------------
diff --git 
a/core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala
 
b/core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala
index 9ff067f..de26aa3 100644
--- 
a/core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala
+++ 
b/core/src/test/scala/org/apache/spark/util/collection/ExternalSorterSuite.scala
@@ -506,7 +506,10 @@ class ExternalSorterSuite extends FunSuite with 
LocalSparkContext with PrivateMe
     val agg = new Aggregator[Int, Int, Int](i => i, (i, j) => i + j, (i, j) => 
i + j)
     val ord = implicitly[Ordering[Int]]
     val sorter = new ExternalSorter(Some(agg), Some(new HashPartitioner(3)), 
Some(ord), None)
-    sorter.insertAll((0 until 100000).iterator.map(i => (i / 2, i)))
+
+    // avoid combine before spill
+    sorter.insertAll((0 until 50000).iterator.map(i => (i , 2 * i)))
+    sorter.insertAll((0 until 50000).iterator.map(i => (i, 2 * i + 1)))
     val results = sorter.partitionedIterator.map{case (p, vs) => (p, 
vs.toSet)}.toSet
     val expected = (0 until 3).map(p => {
       (p, (0 until 50000).map(i => (i, i * 4 + 1)).filter(_._1 % 3 == p).toSet)


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to