diff --git a/core/src/main/scala/org/apache/spark/SparkContext.scala b/core/src/main/scala/org/apache/spark/SparkContext.scala index b3c3bf3746e181d438c49b699da4977c5d6d3819..cb7e24c374152dd7974a62354ce55aaf351ca617 100644 --- a/core/src/main/scala/org/apache/spark/SparkContext.scala +++ b/core/src/main/scala/org/apache/spark/SparkContext.scala @@ -831,6 +831,8 @@ 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. */ @@ -878,9 +880,11 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli * (a-hdfs-path/part-nnnnn, its content) * }}} * - * @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. + * @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. */ @Experimental def binaryFiles(