Github user mgummelt commented on a diff in the pull request:
https://github.com/apache/spark/pull/18098#discussion_r118392464
--- Diff:
resource-managers/mesos/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosCoarseGrainedSchedulerBackend.scala
---
@@ -393,7 +409,30 @@ private[spark] class
MesosCoarseGrainedSchedulerBackend(
val offerId = offer.getId.getValue
val resources = remainingResources(offerId)
- if (canLaunchTask(slaveId, resources)) {
+ var createTask = canLaunchTask(slaveId, resources)
+ if (hostToLocalTaskCount.nonEmpty) {
--- End diff --
The semantics you're going for is "Launch an executor on a host only when
we have a task that wants to be on that host, or the configurable delay has
elapsed", right? By launching an executor on any host when we don't yet have
any tasks to schedule, you're violating those semantics, right?
---
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]
