You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by an...@apache.org on 2015/06/30 03:32:43 UTC
spark git commit: Revert "[SPARK-8437] [DOCS] Using directory path
without wildcard for filename slow for large number of files with
wholeTextFiles and binaryFiles"
Repository: spark
Updated Branches:
refs/heads/master 4a9e03fa8 -> 4c1808be4
Revert "[SPARK-8437] [DOCS] Using directory path without wildcard for filename slow for large number of files with wholeTextFiles and binaryFiles"
This reverts commit 5d30eae56051c563a8427f330b09ef66db0a0d21.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/4c1808be
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/4c1808be
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/4c1808be
Branch: refs/heads/master
Commit: 4c1808be4d3aaa37a5a878892e91ca73ea405ffa
Parents: 4a9e03f
Author: Andrew Or <an...@databricks.com>
Authored: Mon Jun 29 18:32:31 2015 -0700
Committer: Andrew Or <an...@databricks.com>
Committed: Mon Jun 29 18:32:31 2015 -0700
----------------------------------------------------------------------
core/src/main/scala/org/apache/spark/SparkContext.scala | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/4c1808be/core/src/main/scala/org/apache/spark/SparkContext.scala
----------------------------------------------------------------------
diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala
index cb7e24c..b3c3bf3 100644
--- a/core/src/main/scala/org/apache/spark/SparkContext.scala
+++ b/core/src/main/scala/org/apache/spark/SparkContext.scala
@@ -831,8 +831,6 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
* }}}
*
* @note Small files are preferred, large file is also allowable, but may cause bad performance.
- * @note On some filesystems, `.../path/*` can be a more efficient way to read all files in a directory
- * rather than `.../path/` or `.../path`
*
* @param minPartitions A suggestion value of the minimal splitting number for input data.
*/
@@ -880,11 +878,9 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli
* (a-hdfs-path/part-nnnnn, its content)
* }}}
*
- * @note Small files are preferred; very large files may cause bad performance.
- * @note On some filesystems, `.../path/*` can be a more efficient way to read all files in a directory
- * rather than `.../path/` or `.../path`
- *
* @param minPartitions A suggestion value of the minimal splitting number for input data.
+ *
+ * @note Small files are preferred; very large files may cause bad performance.
*/
@Experimental
def binaryFiles(
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org