diff --git a/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala b/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala
index f9f39f2314e94..ce84fa119ca47 100644
--- a/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala
+++ b/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/YarnAllocator.scala
@@ -305,21 +305,21 @@ private[yarn] class YarnAllocator(
       s"pending: $numPendingAllocate, running: ${runningExecutors.size}, " +
       s"executorsStarting: ${numExecutorsStarting.get}")
 
+    // Split the pending container request into three groups: locality matched list, locality
+    // unmatched list and non-locality list. Take the locality matched container request into
+    // consideration of container placement, treat as allocated containers.
+    // For locality unmatched and locality free container requests, cancel these container
+    // requests, since required locality preference has been changed, recalculating using
+    // container placement strategy.
+    val (localRequests, staleRequests, anyHostRequests) = splitPendingAllocationsByLocality(
+      hostToLocalTaskCounts, pendingAllocate)
+
     if (missing > 0) {
       logInfo(s"Will request $missing executor container(s), each with " +
         s"${resource.getVirtualCores} core(s) and " +
         s"${resource.getMemory} MB memory (including $memoryOverhead MB of overhead) and " +
         s"${resource.getGPUs} GPU(s)")
 
-      // Split the pending container request into three groups: locality matched list, locality
-      // unmatched list and non-locality list. Take the locality matched container request into
-      // consideration of container placement, treat as allocated containers.
-      // For locality unmatched and locality free container requests, cancel these container
-      // requests, since required locality preference has been changed, recalculating using
-      // container placement strategy.
-      val (localRequests, staleRequests, anyHostRequests) = splitPendingAllocationsByLocality(
-        hostToLocalTaskCounts, pendingAllocate)
-
       // cancel "stale" requests for locations that are no longer needed
       staleRequests.foreach { stale =>
         amClient.removeContainerRequest(stale)
@@ -379,14 +379,9 @@ private[yarn] class YarnAllocator(
       val numToCancel = math.min(numPendingAllocate, -missing)
       logInfo(s"Canceling requests for $numToCancel executor container(s) to have a new desired " +
         s"total $targetNumExecutors executors.")
-
-      val matchingRequests = amClient.getMatchingRequests(RM_REQUEST_PRIORITY, ANY_HOST, resource)
-      if (!matchingRequests.isEmpty) {
-        matchingRequests.iterator().next().asScala
-          .take(numToCancel).foreach(amClient.removeContainerRequest)
-      } else {
-        logWarning("Expected to find pending requests, but found none.")
-      }
+      // cancel pending allocate requests by taking locality preference into account
+      val cancelRequests = (staleRequests ++ anyHostRequests ++ localRequests).take(numToCancel)
+      cancelRequests.foreach(amClient.removeContainerRequest)
     }
   }