venkata91 commented on a change in pull request #30164:
URL: https://github.com/apache/spark/pull/30164#discussion_r524805840



##########
File path: 
core/src/main/scala/org/apache/spark/storage/BlockManagerMasterEndpoint.scala
##########
@@ -657,6 +688,43 @@ class BlockManagerMasterEndpoint(
     }
   }
 
+  private def getShufflePushMergerLocations(
+      numMergersNeeded: Int,
+      hostsToFilter: Set[String]): Seq[BlockManagerId] = {
+    val blockManagersWithExecutors = 
blockManagerIdByExecutor.groupBy(_._2.host)
+      .mapValues(_.head).values.map(_._2).toSet
+    val filteredBlockManagersWithExecutors = blockManagersWithExecutors
+      .filterNot(x => hostsToFilter.contains(x.host))
+    val filteredMergersWithExecutors = filteredBlockManagersWithExecutors.map(
+      x => BlockManagerId(x.executorId, x.host, 
StorageUtils.externalShuffleServicePort(conf)))
+
+    // Enough mergers are available as part of active executors list
+    if (filteredMergersWithExecutors.size >= numMergersNeeded) {
+      filteredMergersWithExecutors.toSeq
+    } else {
+      // Delta mergers added from inactive mergers list to the active mergers 
list
+      val filteredMergersWithExecutorsHosts = 
filteredMergersWithExecutors.map(_.host)
+      val filteredMergersWithoutExecutors = shuffleMergerLocations.values
+        .filterNot(x => hostsToFilter.contains(x.host))
+        .filterNot(x => filteredMergersWithExecutorsHosts.contains(x.host))
+      val randomFilteredMergersLocations =
+        if (filteredMergersWithoutExecutors.size >
+          numMergersNeeded - filteredMergersWithExecutors.size) {
+          Utils.randomize(filteredMergersWithoutExecutors)
+        } else {
+          filteredMergersWithoutExecutors
+        }
+      filteredMergersWithExecutors.toSeq ++ randomFilteredMergersLocations
+        .take(numMergersNeeded - filteredMergersWithExecutors.size)

Review comment:
       I checked the `Iterable` size and its not scanning through the 
collection. It seems to work fine. Also we have a test case which is covering 
this case. Let me know if I'm missing something here. Thanks




----------------------------------------------------------------
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.

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