Repository: spark Updated Branches: refs/heads/branch-1.4 c0fbd6781 -> 80d53565a
Revert "[SPARK-8437] [DOCS] Using directory path without wildcard for filename slow for large number of files with wholeTextFiles and binaryFiles" This reverts commit b2684557fa0d2ec14b7529324443c8154d81c348. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/80d53565 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/80d53565 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/80d53565 Branch: refs/heads/branch-1.4 Commit: 80d53565ae951f7ef0626ad2ad0e2ecb55993a21 Parents: c0fbd67 Author: Andrew Or <and...@databricks.com> Authored: Mon Jun 29 18:32:59 2015 -0700 Committer: Andrew Or <and...@databricks.com> Committed: Mon Jun 29 18:32:59 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/80d53565/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 f8af710..b4c0d4c 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -824,8 +824,6 @@ 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. */ @@ -873,11 +871,9 @@ 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-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
