You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@carbondata.apache.org by ku...@apache.org on 2019/06/21 08:35:56 UTC
[carbondata] 01/02: [DOC] Improve java doc for
DataSkewRangePartitioner
This is an automated email from the ASF dual-hosted git repository.
kunalkapoor pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/carbondata.git
commit 67f42a69fd042d184d32fd9c11304217bf21e75f
Author: QiangCai <qi...@qq.com>
AuthorDate: Wed Apr 10 11:39:52 2019 +0800
[DOC] Improve java doc for DataSkewRangePartitioner
Improve java doc for DataSkewRangePartitioner
This closes #3175
---
.../src/main/scala/org/apache/spark/DataSkewRangePartitioner.scala | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/integration/spark-common/src/main/scala/org/apache/spark/DataSkewRangePartitioner.scala b/integration/spark-common/src/main/scala/org/apache/spark/DataSkewRangePartitioner.scala
index d434108..733ee87 100644
--- a/integration/spark-common/src/main/scala/org/apache/spark/DataSkewRangePartitioner.scala
+++ b/integration/spark-common/src/main/scala/org/apache/spark/DataSkewRangePartitioner.scala
@@ -40,7 +40,7 @@ import org.apache.spark.util.{CollectionsUtils, Utils}
* the rangeBounds are also the distinct values, but it calculates the skew weight.
* So some rangeBounds maybe have more than one partitions.
*
- * for example, split following CSV file to 5 partitions:
+ * for example, split following CSV file to 5 partitions by col2:
* ---------------
* col1,col2
* 1,
@@ -77,6 +77,7 @@ import org.apache.spark.util.{CollectionsUtils, Utils}
* --------------------------------------------------------------
* The skew weight of range bound "null" is 2.
* So it will start two tasks for range bound "null" to create two partitions.
+ * For a range bound, the number of final partitions is the same as the skew weight.
*/
class DataSkewRangePartitioner[K: Ordering : ClassTag, V](
partitions: Int,