Github user andrewor14 commented on a diff in the pull request: https://github.com/apache/spark/pull/1616#discussion_r17188055 --- Diff: core/src/main/scala/org/apache/spark/util/Utils.scala --- @@ -313,14 +313,74 @@ private[spark] object Utils extends Logging { } /** + * Download a file requested by the executor . Supports fetching the file in a variety of ways, + * including HTTP, HDFS and files on a standard filesystem, based on the URL parameter. + * + * If `useCache` is true, first attempts to fetch the file from a local cache that's shared across + * executors running the same application. + * + * Throws SparkException if the target file already exists and has different contents than + * the requested file. + */ + def fetchFile( + url: String, + targetDir: File, + conf: SparkConf, + securityMgr: SecurityManager, + hadoopConf: Configuration, + timestamp: Long, + useCache: Boolean) { + val fileName = url.split("/").last + val targetFile = new File(targetDir, fileName) + if (useCache) { + val cachedFileName = url.hashCode + timestamp + "_cach" --- End diff -- _cache
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org