bhat-vinay commented on code in PR #10876:
URL: https://github.com/apache/hudi/pull/10876#discussion_r1536560898
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/BaseSparkCommitActionExecutor.java:
##########
@@ -411,4 +427,90 @@ public Partitioner getLayoutPartitioner(WorkloadProfile
profile, String layoutPa
protected void
runPrecommitValidators(HoodieWriteMetadata<HoodieData<WriteStatus>>
writeMetadata) {
SparkValidatorUtils.runValidators(config, writeMetadata, context, table,
instantTime);
}
+
+ private HoodieData<WriteStatus>
sortAndMapPartitionsAsRDD(HoodieData<HoodieRecord<T>> dedupedRecords,
Partitioner partitioner) {
+ JavaPairRDD<Tuple2<HoodieKey, Long>, HoodieRecord<T>> mappedRDD =
getSortedIndexedRecords(dedupedRecords);
+ JavaPairRDD<Tuple2<HoodieKey, Long>, HoodieRecord<T>> partitionedRDD;
+ if (table.requireSortedRecords()) {
+ // Partition and sort within each partition as a single step. This is
faster than partitioning first and then
+ // applying a sort.
+ Comparator<Tuple2<HoodieKey, Long>> comparator =
(Comparator<Tuple2<HoodieKey, Long>> & Serializable) (t1, t2) -> {
+ HoodieKey key1 = t1._1();
+ HoodieKey key2 = t2._1();
+ return key1.getRecordKey().compareTo(key2.getRecordKey());
+ };
+ partitionedRDD =
mappedRDD.repartitionAndSortWithinPartitions(partitioner, comparator);
+ } else {
+ // Partition only
+ partitionedRDD = mappedRDD.partitionBy(partitioner);
+ }
+
+ return
HoodieJavaRDD.of(partitionedRDD.map(Tuple2::_2).mapPartitionsWithIndex((partition,
recordItr) -> {
+ if (WriteOperationType.isChangingRecords(operationType)) {
+ return handleUpsertPartition(instantTime, partition, recordItr,
partitioner);
+ } else {
+ return handleInsertPartition(instantTime, partition, recordItr,
partitioner);
+ }
+ }, true).flatMap(List::iterator));
+ }
+
+ private boolean operationRequiresSorting() {
+ return operationType == WriteOperationType.INSERT &&
config.getBoolean(INSERT_SORT);
Review Comment:
The current implementation (in this PR) does not support sorting for UPSERT
operation
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
