Github user kayousterhout commented on a diff in the pull request:
https://github.com/apache/spark/pull/147#discussion_r10637306
--- Diff: core/src/main/scala/org/apache/spark/MapOutputTracker.scala ---
@@ -35,13 +35,21 @@ private[spark] case class
GetMapOutputStatuses(shuffleId: Int)
extends MapOutputTrackerMessage
private[spark] case object StopMapOutputTracker extends
MapOutputTrackerMessage
-private[spark] class MapOutputTrackerMasterActor(tracker:
MapOutputTrackerMaster)
+private[spark] class MapOutputTrackerMasterActor(tracker:
MapOutputTrackerMaster, conf: SparkConf)
extends Actor with Logging {
+ val maxAkkaFrameSize = AkkaUtils.maxFrameSize(conf) * 1024 * 1024 // MB
+
def receive = {
case GetMapOutputStatuses(shuffleId: Int) =>
val hostPort = sender.path.address.hostPort
logInfo("Asked to send map output locations for shuffle " +
shuffleId + " to " + hostPort)
- sender ! tracker.getSerializedMapOutputStatuses(shuffleId)
+ val mapOutputStatuses =
tracker.getSerializedMapOutputStatuses(shuffleId)
+ val serializedSize = mapOutputStatuses.size
+ if (serializedSize > maxAkkaFrameSize) {
+ throw new SparkException(
+ "spark.akka.frameSize exceeded! Map output statuses were %d
bytes".format(serializedSize))
--- End diff --
would be helpful to also include the configured frame size in this output
message, since otherwise these problems can be extremely annoying to debug
---
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.
---
