the-other-tim-brown commented on code in PR #13976:
URL: https://github.com/apache/hudi/pull/13976#discussion_r2389681694
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/StreamingMetadataWriteHandler.java:
##########
@@ -47,21 +54,24 @@ public class StreamingMetadataWriteHandler {
* @param table The {@link HoodieTable} instance for data
table of interest.
* @param dataTableWriteStatuses The {@link WriteStatus} from data table
writes.
* @param instantTime The instant time of interest.
+ * @param enforceCoalesceWithRepartition true when repartition has to be
added to dag to coalesce data table write statuses to 1. false otherwise.
Review Comment:
Update javadoc with new divisor param
##########
hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/client/TestCoalescingPartitioner.java:
##########
@@ -0,0 +1,63 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.client;
+
+import org.apache.hudi.common.data.HoodieData;
+import org.apache.hudi.data.HoodieJavaRDD;
+import org.apache.hudi.testutils.HoodieClientTestBase;
+
+import org.junit.jupiter.api.Test;
+
+import java.util.stream.Collectors;
+import java.util.stream.IntStream;
+
+import static org.junit.jupiter.api.Assertions.assertEquals;
+
+public class TestCoalescingPartitioner extends HoodieClientTestBase {
Review Comment:
Should there be some test that applies the partitioner to an RDD?
Specifically something to simulate the use case for the streaming writes.
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/StreamingMetadataWriteHandler.java:
##########
@@ -87,12 +97,24 @@ public void commitToMetadataTable(HoodieTable table,
private HoodieData<WriteStatus>
streamWriteToMetadataTable(HoodieData<WriteStatus> dataTableWriteStatuses,
HoodieTableMetadataWriter metadataWriter,
HoodieTable table,
- String
instantTime) {
- HoodieData<WriteStatus> allWriteStatus = dataTableWriteStatuses;
+ String
instantTime,
+ boolean
enforceCoalesceWithRepartition,
+ int
coalesceDividentForDataTableWrites) {
HoodieData<WriteStatus> mdtWriteStatuses =
metadataWriter.streamWriteToMetadataPartitions(dataTableWriteStatuses,
instantTime);
- allWriteStatus = allWriteStatus.union(mdtWriteStatuses);
- allWriteStatus.persist("MEMORY_AND_DISK_SER", table.getContext(),
HoodieData.HoodieDataCacheKey.of(table.getMetaClient().getBasePath().toString(),
instantTime));
- return allWriteStatus;
+ mdtWriteStatuses.persist("MEMORY_AND_DISK_SER", table.getContext(),
HoodieData.HoodieDataCacheKey.of(table.getMetaClient().getBasePath().toString(),
instantTime));
+ HoodieData<WriteStatus> coalescedDataWriteStatuses;
+ int coalesceParallelism = Math.max(1,
dataTableWriteStatuses.getNumPartitions() / coalesceDividentForDataTableWrites);
+ if (enforceCoalesceWithRepartition) {
+ // with bulk insert and NONE sort mode, simple coalesce on datatable
write statuses also impact record key generation stages.
+ // and hence we are adding a partitioner to cut the chain so that
coalesce(1) here does not impact record key generation stages.
+ coalescedDataWriteStatuses =
HoodieJavaRDD.of(HoodieJavaRDD.getJavaRDD(dataTableWriteStatuses)
+ .mapToPair((PairFunction<WriteStatus, Boolean, WriteStatus>)
writeStatus -> new Tuple2(true, writeStatus))
Review Comment:
Does the partitioner apply the partition calculation to the key? If so, then
we need a new key here.
--
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]
