[HUDI-5289] Fix writeStatus RDD recalculated in cluster

Zouxxyy · Zouxxyy · commit a683b28c85e1 · 2022-12-03T19:05:33.000+08:00
diff --git a/hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/SparkRDDWriteClient.java b/hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/SparkRDDWriteClient.java
@@ -469,7 +469,7 @@ private void completeClustering(HoodieReplaceCommitMetadata metadata,
   }
 
   private void validateClusteringCommit(HoodieWriteMetadata<JavaRDD<WriteStatus>> clusteringMetadata, String clusteringCommitTime, HoodieTable table) {
-    if (clusteringMetadata.getWriteStatuses().isEmpty()) {
+    if (!clusteringMetadata.getWriteStats().isPresent() || clusteringMetadata.getWriteStats().get().isEmpty()) {
       HoodieClusteringPlan clusteringPlan = ClusteringUtils.getClusteringPlan(
               table.getMetaClient(), HoodieTimeline.getReplaceCommitRequestedInstant(clusteringCommitTime))
           .map(Pair::getRight).orElseThrow(() -> new HoodieClusteringException(

Original file line number	Diff line number	Diff line change
`@@ -469,7 +469,7 @@ private void completeClustering(HoodieReplaceCommitMetadata metadata,`
`469`	`469`	`}`
`470`	`470`
`471`	`471`	`private void validateClusteringCommit(HoodieWriteMetadata<JavaRDD<WriteStatus>> clusteringMetadata, String clusteringCommitTime, HoodieTable table) {`
`472`		`- if (clusteringMetadata.getWriteStatuses().isEmpty()) {`
	`472`	`+ if (!clusteringMetadata.getWriteStats().isPresent() \|\| clusteringMetadata.getWriteStats().get().isEmpty()) {`
`473`	`473`	`HoodieClusteringPlan clusteringPlan = ClusteringUtils.getClusteringPlan(`
`474`	`474`	`table.getMetaClient(), HoodieTimeline.getReplaceCommitRequestedInstant(clusteringCommitTime))`
`475`	`475`	`.map(Pair::getRight).orElseThrow(() -> new HoodieClusteringException(`