Github user tgravescs commented on a diff in the pull request:
https://github.com/apache/spark/pull/15410#discussion_r86791239
--- Diff:
core/src/main/scala/org/apache/spark/deploy/history/FsHistoryProvider.scala ---
@@ -328,26 +334,43 @@ private[history] class FsHistoryProvider(conf:
SparkConf, clock: Clock)
if (logInfos.nonEmpty) {
logDebug(s"New/updated attempts found: ${logInfos.size}
${logInfos.map(_.getPath)}")
}
- logInfos.map { file =>
- replayExecutor.submit(new Runnable {
+
+ var tasks = mutable.ListBuffer[Future[_]]()
+
+ try {
+ for (file <- logInfos) {
+ tasks += replayExecutor.submit(new Runnable {
override def run(): Unit = mergeApplicationListing(file)
})
}
- .foreach { task =>
- try {
- // Wait for all tasks to finish. This makes sure that
checkForLogs
- // is not scheduled again while some tasks are already running
in
- // the replayExecutor.
- task.get()
- } catch {
- case e: InterruptedException =>
- throw e
- case e: Exception =>
- logError("Exception while merging application listings", e)
- }
+ } catch {
+ // let the iteration over logInfos break, since an exception on
+ // replayExecutor.submit (..) indicates the ExecutorService is
unable
+ // to take any more submissions at this time
+
+ case e: Exception =>
+ logError(s"Exception while submitting event log for replay", e)
+ }
+
+ pendingReplayTasksCount.addAndGet (tasks.size)
--- End diff --
nit: remove extra space after addAndGet before (
---
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
