diff options
| author | Reynold Xin <rxin@apache.org> | 2014-06-08 18:39:57 -0700 |
|---|---|---|
| committer | Reynold Xin <rxin@apache.org> | 2014-06-08 18:39:57 -0700 |
| commit | 219dc00b30c8d9c4c0a6ce5d566497a93f21cb57 (patch) | |
| tree | 7f82e34deee7dfc25cb2839df008b9f22f9971ac | |
| parent | e9261d0866a610eab29fa332726186b534d1018f (diff) | |
| download | spark-219dc00b30c8d9c4c0a6ce5d566497a93f21cb57.tar.gz spark-219dc00b30c8d9c4c0a6ce5d566497a93f21cb57.tar.bz2 spark-219dc00b30c8d9c4c0a6ce5d566497a93f21cb57.zip | |
SPARK-1628 follow up: Improve RangePartitioner's documentation.
Adding a paragraph clarifying a weird behavior in RangePartitioner.
See also #549.
Author: Reynold Xin <rxin@apache.org>
Closes #1012 from rxin/partitioner-doc and squashes the following commits:
6f0109e [Reynold Xin] SPARK-1628 follow up: Improve RangePartitioner's documentation.
| -rw-r--r-- | core/src/main/scala/org/apache/spark/Partitioner.scala | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/core/src/main/scala/org/apache/spark/Partitioner.scala b/core/src/main/scala/org/apache/spark/Partitioner.scala index 01e918fabe..e7f7548193 100644 --- a/core/src/main/scala/org/apache/spark/Partitioner.scala +++ b/core/src/main/scala/org/apache/spark/Partitioner.scala @@ -90,6 +90,10 @@ class HashPartitioner(partitions: Int) extends Partitioner { /** * A [[org.apache.spark.Partitioner]] that partitions sortable records by range into roughly * equal ranges. The ranges are determined by sampling the content of the RDD passed in. + * + * Note that the actual number of partitions created by the RangePartitioner might not be the same + * as the `partitions` parameter, in the case where the number of sampled records is less than + * the value of `partitions`. */ class RangePartitioner[K : Ordering : ClassTag, V]( partitions: Int, @@ -158,7 +162,6 @@ class RangePartitioner[K : Ordering : ClassTag, V]( false } - override def hashCode(): Int = { val prime = 31 var result = 1 |