Repository: spark Updated Branches: refs/heads/branch-1.4 5b468cf0c -> e33c0f0a4
[SPARK-8769] [TRIVIAL] [DOCS] toLocalIterator should mention it results in many jobs Author: Holden Karau <hol...@pigscanfly.ca> Closes #7171 from holdenk/SPARK-8769-toLocalIterator-documentation-improvement and squashes the following commits: 97ddd99 [Holden Karau] Add note (cherry picked from commit 15d41cc501f5fa7ac82c4a6741e416bb557f610a) Signed-off-by: Andrew Or <and...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e33c0f0a Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e33c0f0a Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e33c0f0a Branch: refs/heads/branch-1.4 Commit: e33c0f0a497194d93b3c034502a9a49dc22c0cdf Parents: 5b468cf Author: Holden Karau <hol...@pigscanfly.ca> Authored: Wed Jul 1 23:05:45 2015 -0700 Committer: Andrew Or <and...@databricks.com> Committed: Wed Jul 1 23:05:57 2015 -0700 ---------------------------------------------------------------------- core/src/main/scala/org/apache/spark/rdd/RDD.scala | 4 ++++ 1 file changed, 4 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/e33c0f0a/core/src/main/scala/org/apache/spark/rdd/RDD.scala ---------------------------------------------------------------------- diff --git a/core/src/main/scala/org/apache/spark/rdd/RDD.scala b/core/src/main/scala/org/apache/spark/rdd/RDD.scala index 10610f4..cac6e3b 100644 --- a/core/src/main/scala/org/apache/spark/rdd/RDD.scala +++ b/core/src/main/scala/org/apache/spark/rdd/RDD.scala @@ -890,6 +890,10 @@ abstract class RDD[T: ClassTag]( * Return an iterator that contains all of the elements in this RDD. * * The iterator will consume as much memory as the largest partition in this RDD. + * + * Note: this results in multiple Spark jobs, and if the input RDD is the result + * of a wide transformation (e.g. join with different partitioners), to avoid + * recomputing the input RDD should be cached first. */ def toLocalIterator: Iterator[T] = withScope { def collectPartition(p: Int): Array[T] = { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
