Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/20002#discussion_r158108582
--- Diff: core/src/main/scala/org/apache/spark/Partitioner.scala ---
@@ -57,7 +60,8 @@ object Partitioner {
def defaultPartitioner(rdd: RDD[_], others: RDD[_]*): Partitioner = {
val rdds = (Seq(rdd) ++ others)
val hasPartitioner = rdds.filter(_.partitioner.exists(_.numPartitions
> 0))
- if (hasPartitioner.nonEmpty) {
+ if (hasPartitioner.nonEmpty
+ && isEligiblePartitioner(hasPartitioner.maxBy(_.partitions.length),
rdds)) {
--- End diff --
`hasPartitioner.maxBy(_.partitions.length)` is used repeatedly, pull that
into a variable ?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
