Github user ravipesala commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2953#discussion_r236640610
--- Diff:
integration/spark-common/src/main/scala/org/apache/carbondata/spark/rdd/CarbonMergerRDD.scala
---
@@ -401,7 +401,11 @@ class CarbonMergerRDD[K, V](
.add(new CarbonInputSplitTaskInfo(entry._1,
entry._2).asInstanceOf[Distributable])
)
- val nodeBlockMap = CarbonLoaderUtil.nodeBlockMapping(taskInfoList, -1)
+ // get all the active nodes of cluster and prepare the nodeBlockMap
based on these nodes
+ val activeNodes = DistributionUtil
+ .ensureExecutorsAndGetNodeList(taskInfoList.asScala, sparkContext)
+
+ val nodeBlockMap = CarbonLoaderUtil.nodeBlockMapping(taskInfoList, -1,
activeNodes.asJava)
--- End diff --
Below code is redundant, please remove it
---
