[GitHub] [spark] mridulm commented on a change in pull request #34461: [SPARK-37023][CORE] Avoid fetching merge status when shuffleMergeEnabled is false for a shuffleDependency during retry

[GitBox <gi...@apache.org>]

mridulm commented on a change in pull request #34461:
URL: https://github.com/apache/spark/pull/34461#discussion_r741582590



##########
File path: core/src/main/scala/org/apache/spark/MapOutputTracker.scala
##########
@@ -1174,14 +1182,43 @@ private[spark] class MapOutputTrackerWorker(conf: SparkConf) extends MapOutputTr
    */
   private val fetchingLock = new KeyLock[Int]
 
+  override def getMapSizesByExecutorId(
+      shuffleId: Int,
+      startMapIndex: Int,
+      endMapIndex: Int,
+      startPartition: Int,
+      endPartition: Int): Iterator[(BlockManagerId, Seq[(BlockId, Long, Int)])] = {
+    val mapSizesByExecutorId = getMapSizesByExecutorIdImpl(
+      shuffleId, startMapIndex, endMapIndex, startPartition, endPartition, useMergeResult = false)
+    assert(mapSizesByExecutorId.enableBatchFetch == true)
+    mapSizesByExecutorId.iter
+  }
+
   override def getPushBasedShuffleMapSizesByExecutorId(
       shuffleId: Int,
       startMapIndex: Int,
       endMapIndex: Int,
       startPartition: Int,
       endPartition: Int): MapSizesByExecutorId = {
+    getMapSizesByExecutorIdImpl(
+      shuffleId, startMapIndex, endMapIndex, startPartition, endPartition, useMergeResult = true)
+  }
+
+  private def getMapSizesByExecutorIdImpl(
+      shuffleId: Int,
+      startMapIndex: Int,
+      endMapIndex: Int,
+      startPartition: Int,
+      endPartition: Int,
+      useMergeResult: Boolean): MapSizesByExecutorId = {
     logDebug(s"Fetching outputs for shuffle $shuffleId")
-    val (mapOutputStatuses, mergedOutputStatuses) = getStatuses(shuffleId, conf)
+    val (mapOutputStatuses, mergedOutputStatuses) = getStatuses(shuffleId, conf,
+      // EnableBatchFetch can be unexpectedly set to false during stage retry when the

Review comment:
       remove `unexpectedly`




-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



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