Github user markhamstra commented on a diff in the pull request: https://github.com/apache/spark/pull/1106#discussion_r17253575 --- Diff: core/src/main/scala/org/apache/spark/deploy/master/Master.scala --- @@ -481,13 +481,23 @@ private[spark] class Master( if (state != RecoveryState.ALIVE) { return } // First schedule drivers, they take strict precedence over applications - val shuffledWorkers = Random.shuffle(workers) // Randomization helps balance drivers - for (worker <- shuffledWorkers if worker.state == WorkerState.ALIVE) { - for (driver <- List(waitingDrivers: _*)) { // iterate over a copy of waitingDrivers - if (worker.memoryFree >= driver.desc.mem && worker.coresFree >= driver.desc.cores) { + // Randomization helps balance drivers + val shuffledAliveWorkers = Random.shuffle(workers).toArray + val aliveWorkerNum = shuffledAliveWorkers.size --- End diff -- Is there any value to keeping workers whose state is not `WorkerState.ALIVE` in the array of shuffled workers, or should this be: ```scala val shuffledAliveWorkers = Random.shuffle(workers.toSeq.filter(_.state == WorkerState.ALIVE)) ```
--- 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