mridulm commented on a change in pull request #34743:
URL: https://github.com/apache/spark/pull/34743#discussion_r760674810



##########
File path: core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala
##########
@@ -259,21 +259,29 @@ private[spark] class TaskSetManager(
       loc match {
         case e: ExecutorCacheTaskLocation =>
           pendingTaskSetToAddTo.forExecutor.getOrElseUpdate(e.executorId, new 
ArrayBuffer) += index
+          pendingTaskSetToAddTo.forHost.getOrElseUpdate(loc.host, new 
ArrayBuffer) += index
         case e: HDFSCacheTaskLocation =>
           val exe = sched.getExecutorsAliveOnHost(loc.host)
           exe match {
             case Some(set) =>
               for (e <- set) {
                 pendingTaskSetToAddTo.forExecutor.getOrElseUpdate(e, new 
ArrayBuffer) += index
               }
+              pendingTaskSetToAddTo.forHost.getOrElseUpdate(loc.host, new 
ArrayBuffer) += index
               logInfo(s"Pending task $index has a cached location at ${e.host} 
" +
                 ", where there are executors " + set.mkString(","))
             case None => logDebug(s"Pending task $index has a cached location 
at ${e.host} " +
               ", but there are no executors alive there.")
           }
-        case _ =>
+        case _: HostTaskLocation =>
+          val exe = sched.getExecutorsAliveOnHost(loc.host)
+          exe match {
+            case Some(_) =>
+              pendingTaskSetToAddTo.forHost.getOrElseUpdate(loc.host, new 
ArrayBuffer) += index
+            case _ => logDebug(s"Pending task $index has a location at 
${loc.host} " +
+              ", but there are no executors alive there.")
+          }
       }
-      pendingTaskSetToAddTo.forHost.getOrElseUpdate(loc.host, new ArrayBuffer) 
+= index

Review comment:
       Irrespective of whether we have an executor on a host or not, we should 
update.
   An executor could be added later on to that host.




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to