From 4c1808be4d3aaa37a5a878892e91ca73ea405ffa Mon Sep 17 00:00:00 2001 From: Andrew Or Date: Mon, 29 Jun 2015 18:32:31 -0700 Subject: 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. --- core/src/main/scala/org/apache/spark/SparkContext.scala | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'core') diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index cb7e24c374..b3c3bf3746 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( -- cgit v1.2.3