Repository: hive Updated Branches: refs/heads/master 79580a64b -> 27683610f
HIVE-16004: OutOfMemory in SparkReduceRecordHandler with vectorization mode (Colin Ma, reviewed by Ferdinand Xu, Xuefu Zhang) Project: http://git-wip-us.apache.org/repos/asf/hive/repo Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/27683610 Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/27683610 Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/27683610 Branch: refs/heads/master Commit: 27683610f0665fe05e59d3cf5130fe33ecd81e77 Parents: 79580a6 Author: Ferdinand Xu <[email protected]> Authored: Fri Feb 24 02:41:19 2017 +0800 Committer: Ferdinand Xu <[email protected]> Committed: Fri Feb 24 02:41:19 2017 +0800 ---------------------------------------------------------------------- .../apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java | 1 + 1 file changed, 1 insertion(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/hive/blob/27683610/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java ---------------------------------------------------------------------- diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java index 8251900..27bed9c 100644 --- a/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java +++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/spark/SparkReduceRecordHandler.java @@ -364,6 +364,7 @@ public class SparkReduceRecordHandler extends SparkRecordHandler { private <E> boolean processVectors(Iterator<E> values, byte tag) throws HiveException { VectorizedRowBatch batch = batches[tag]; batch.reset(); + buffer.reset(); /* deserialize key into columns */ VectorizedBatchUtil.addRowToBatchFrom(keyObject, keyStructInspector, 0, 0, batch, buffer);
