Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/2844#discussion_r19119141 --- Diff: core/src/main/scala/org/apache/spark/broadcast/TorrentBroadcast.scala --- @@ -104,29 +112,23 @@ private[spark] class TorrentBroadcast[T: ClassTag]( for (pid <- Random.shuffle(Seq.range(0, numBlocks))) { val pieceId = BroadcastBlockId(id, "piece" + pid) - - // First try getLocalBytes because there is a chance that previous attempts to fetch the + logDebug(s"Reading piece $pieceId of $broadcastId") + // First try getLocalBytes because there is a chance that previous attempts to fetch the // broadcast blocks have already fetched some of the blocks. In that case, some blocks // would be available locally (on this executor). - var blockOpt = bm.getLocalBytes(pieceId) - if (!blockOpt.isDefined) { - blockOpt = bm.getRemoteBytes(pieceId) - blockOpt match { - case Some(block) => - // If we found the block from remote executors/driver's BlockManager, put the block - // in this executor's BlockManager. - SparkEnv.get.blockManager.putBytes( - pieceId, - block, - StorageLevel.MEMORY_AND_DISK_SER, - tellMaster = true) - - case None => - throw new SparkException("Failed to get " + pieceId + " of " + broadcastId) - } + val block: ByteBuffer = bm.getLocalBytes(pieceId).getOrElse { + bm.getRemoteBytes(pieceId).map { block => --- End diff -- given this block is long, can we avoid using map.getOrElse? Just make it more explicit
--- 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