Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21859#discussion_r211167603 --- Diff: core/src/main/scala/org/apache/spark/Partitioner.scala --- @@ -166,9 +169,20 @@ class RangePartitioner[K : Ordering : ClassTag, V]( // Assume the input partitions are roughly balanced and over-sample a little bit. val sampleSizePerPartition = math.ceil(3.0 * sampleSize / rdd.partitions.length).toInt val (numItems, sketched) = RangePartitioner.sketch(rdd.map(_._1), sampleSizePerPartition) + val numSampled = sketched.map(_._3.length).sum if (numItems == 0L) { Array.empty } else { + // already got the whole data + if (sampleCacheEnabled && numItems == numSampled) { + // get the sampled data + sampledArray = new Array[K](numSampled) + var curPos = 0 + sketched.foreach(_._3.foreach(sampleRow => { --- End diff -- can't we just keep the `sketched` instead of copying it to a new array?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org