Revert "[SPARK-8437] [DOCS] Using directory path without wildcard for filename slow for large number of files with wholeTextFiles and binaryFiles"
This reverts commit b2684557fa
.
This commit is contained in:
parent
c0fbd6781e
commit
80d53565ae
|
@ -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 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.
|
* @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)
|
* (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.
|
* @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
|
@Experimental
|
||||||
def binaryFiles(
|
def binaryFiles(
|
||||||
|
|
Loading…
Reference in a new issue