Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/1616#discussion_r18259263
--- Diff: core/src/main/scala/org/apache/spark/util/Utils.scala ---
@@ -313,15 +313,84 @@ private[spark] object Utils extends Logging {
}
/**
- * Download a file requested by the executor. Supports fetching the file
in a variety of ways,
+ * Download a file to target directory. 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 to a local
cache that's shared
+ * across executors running the same application. `useCache` is used
mainly for
+ * the the executors, not in local mode.
+ *
* 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) {
- val filename = url.split("/").last
+ 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 = s"${url.hashCode}${timestamp}_cache"
+ val lockFileName = s"${url.hashCode}${timestamp}_lock"
+ val localDir = new File(getLocalDir(conf))
+ val lockFile = new File(localDir, lockFileName)
+ val raf = new RandomAccessFile(lockFile, "rw")
+ // Only one executor entry.
+ // The FileLock is only used to control synchronization for
executors download file,
+ // it's always safe regardless of lock type(mandatory or advisory).
--- End diff --
space after type
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
