Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/7927#discussion_r38481057
--- Diff: core/src/main/scala/org/apache/spark/storage/BlockManager.scala
---
@@ -590,10 +590,25 @@ private[spark] class BlockManager(
private def doGetRemote(blockId: BlockId, asBlockResult: Boolean):
Option[Any] = {
require(blockId != null, "BlockId is null")
val locations = Random.shuffle(master.getLocations(blockId))
+ var attemptTimes = 0
for (loc <- locations) {
logDebug(s"Getting remote block $blockId from $loc")
- val data = blockTransferService.fetchBlockSync(
- loc.host, loc.port, loc.executorId,
blockId.toString).nioByteBuffer()
+ val data = try {
+ blockTransferService.fetchBlockSync(
+ loc.host, loc.port, loc.executorId,
blockId.toString).nioByteBuffer()
+ } catch {
+ case t: Throwable if attemptTimes < locations.size - 1 =>
--- End diff --
please use `scala.util.controlNonFatal(e)` instead. We don't want to catch
OOM's here.
---
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]
