boneanxs commented on code in PR #8076:
URL: https://github.com/apache/hudi/pull/8076#discussion_r1155439841
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/clustering/run/strategy/SparkSingleFileSortExecutionStrategy.java:
##########
@@ -77,8 +78,11 @@ public HoodieData<WriteStatus>
performClusteringWithRecordsAsRow(Dataset<Row> in
// Since clustering will write to single file group using
HoodieUnboundedCreateHandle, set max file size to a large value.
newConfig.setValue(HoodieStorageConfig.PARQUET_MAX_FILE_SIZE,
String.valueOf(Long.MAX_VALUE));
- return HoodieDatasetBulkInsertHelper.bulkInsert(inputRecords, instantTime,
getHoodieTable(), newConfig,
- getRowPartitioner(strategyParams, schema), numOutputGroups,
shouldPreserveHoodieMetadata);
+ BulkInsertPartitioner<Dataset<Row>> partitioner =
getRowPartitioner(strategyParams, schema);
+ Dataset<Row> repartitionedRecords =
partitioner.repartitionRecords(inputRecords, numOutputGroups);
Review Comment:
Yes, I changed `HoodieDatasetBulkInsertHelper.bulkInsert`, deleting
repartition in that method. so adding repartition here and
`SparkSortAndSizeExecutionStrategy`
``` scala
// deleted
val repartitionedDataset = partitioner.repartitionRecords(dataset,
parallelism)
val arePartitionRecordsSorted = partitioner.arePartitionRecordsSorted
```
`BaseDatasetBulkCommitActionExecutor` would first call
`HoodieDatasetBulkInsertHelper.prepareForBulkInsert`, and then call
`HoodieDatasetBulkInsertHelper.bulkInsert` to perform write operation. And in
`HoodieDatasetBulkInsertHelper.prepareForBulkInsert`, it would do the
repartition work, so I delete the repartition in
`HoodieDatasetBulkInsertHelper.bulkInsert`. And it looks more reasonable,
`HoodieDatasetBulkInsertHelper.bulkInsert` should only perform the write
operation, it shouldn't change the records layout.
##########
hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/commit/DatasetBulkInsertActionExecutor.java:
##########
@@ -0,0 +1,91 @@
+/*
+ * 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.commit;
+
+import org.apache.hudi.HoodieSparkUtils;
+import org.apache.hudi.client.SparkRDDWriteClient;
+import org.apache.hudi.client.WriteStatus;
+import org.apache.hudi.common.data.HoodieData;
+import org.apache.hudi.common.model.WriteOperationType;
+import org.apache.hudi.config.HoodieInternalConfig;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.internal.DataSourceInternalWriterHelper;
+import org.apache.hudi.table.action.HoodieWriteMetadata;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SaveMode;
+
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+public class DatasetBulkInsertActionExecutor extends
BaseDatasetBulkCommitActionExecutor {
Review Comment:
make sense, will change
##########
hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/commit/BaseDatasetBulkCommitActionExecutor.java:
##########
@@ -0,0 +1,122 @@
+/*
+ * 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.commit;
+
+import org.apache.hudi.DataSourceUtils;
+import org.apache.hudi.DataSourceWriteOptions;
+import org.apache.hudi.HoodieDatasetBulkInsertHelper;
+import org.apache.hudi.client.HoodieWriteResult;
+import org.apache.hudi.client.SparkRDDWriteClient;
+import org.apache.hudi.client.WriteStatus;
+import org.apache.hudi.common.data.HoodieData;
+import org.apache.hudi.common.model.WriteOperationType;
+import org.apache.hudi.common.table.HoodieTableConfig;
+import org.apache.hudi.common.util.CommitUtils;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.config.HoodieWriteConfig;
+import org.apache.hudi.data.HoodieJavaRDD;
+import org.apache.hudi.exception.HoodieException;
+import
org.apache.hudi.execution.bulkinsert.BulkInsertInternalPartitionerWithRowsFactory;
+import org.apache.hudi.execution.bulkinsert.NonSortPartitionerWithRows;
+import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.hudi.table.HoodieTable;
+import org.apache.hudi.table.action.HoodieWriteMetadata;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+
+import java.io.Serializable;
+import java.util.Collections;
+import java.util.List;
+import java.util.Map;
+
+public abstract class BaseDatasetBulkCommitActionExecutor implements
Serializable {
Review Comment:
Yes, at first I tried to put this in `hudi-client-common`, but since
`BaseDatasetBulkCommitActionExecutor` needs to access `DataSourceUtils` and
`DataSourceWriteOptions`, not sure it's reasonable to move these classes there,
and I'm afraid there are other dependencies for these two classes, we may also
need to change those dependencies.
--
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]
