alexeykudinkin commented on code in PR #5328:
URL: https://github.com/apache/hudi/pull/5328#discussion_r923686755
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/PartitionSortPartitionerWithRows.java:
##########
@@ -19,19 +19,39 @@
package org.apache.hudi.execution.bulkinsert;
import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.table.HoodieTableConfig;
import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.spark.sql.Column;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
/**
- * A built-in partitioner that does local sorting for each spark partitions
after coalesce for bulk insert operation, corresponding to the {@code
BulkInsertSortMode.PARTITION_SORT} mode.
+ * A built-in partitioner that does local sorting w/in the Spark partition,
+ * corresponding to the {@code BulkInsertSortMode.PARTITION_SORT} mode.
*/
-public class PartitionSortPartitionerWithRows implements
BulkInsertPartitioner<Dataset<Row>> {
+public class PartitionSortPartitionerWithRows extends
RepartitioningBulkInsertPartitionerBase<Dataset<Row>> {
+
+ public PartitionSortPartitionerWithRows(HoodieTableConfig tableConfig) {
+ super(tableConfig);
+ }
@Override
- public Dataset<Row> repartitionRecords(Dataset<Row> rows, int
outputSparkPartitions) {
- return
rows.coalesce(outputSparkPartitions).sortWithinPartitions(HoodieRecord.PARTITION_PATH_METADATA_FIELD,
HoodieRecord.RECORD_KEY_METADATA_FIELD);
+ public Dataset<Row> repartitionRecords(Dataset<Row> dataset, int
outputSparkPartitions) {
+ Dataset<Row> repartitionedDataset;
+
+ // NOTE: Datasets being ingested into partitioned tables are additionally
re-partitioned to better
+ // align dataset's logical partitioning with expected table's
physical partitioning to
+ // provide for appropriate file-sizing and better control of the
number of files created.
+ //
+ // Please check out {@code GlobalSortPartitioner} java-doc for more
details
+ if (isPartitionedTable) {
+ repartitionedDataset = dataset.repartition(outputSparkPartitions, new
Column(HoodieRecord.PARTITION_PATH_METADATA_FIELD));
Review Comment:
Correct, we will be adding a new insertion mode. I've made the changes
locally and working on fixing the tests currently. Will update the PR once this
is done.
--
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]
