[GitHub] [spark] Victsm commented on a change in pull request #30164: [SPARK-32919][SHUFFLE][test-maven][test-hadoop2.7] Driver side changes for coordinating push based shuffle by selecting external shuffle services for merging partitions

[GitBox]

Victsm commented on a change in pull request #30164:
URL: https://github.com/apache/spark/pull/30164#discussion_r524541577



##########
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:
       If # elements in `randomFilteredMergersLocations` is less than 
`numMergersNeeded - filteredMergersWithExecutors.size`, `take()` would just 
return all elements.
   What's the reason for `take()` cannot be called here if `randomize()` is not 
performed?




----------------------------------------------------------------
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:
us...@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org