1
0

[HUDI-3612] Clustering strategy should create new TypedProperties when modifying it (#5027)

This commit is contained in:
RexAn
2022-03-26 18:46:03 +08:00
committed by GitHub
parent 0c09a973fb
commit 57b4f39c31
5 changed files with 20 additions and 22 deletions

View File

@@ -37,7 +37,6 @@ import org.apache.log4j.Logger;
import java.util.List;
import java.util.Map;
import java.util.Properties;
/**
* Clustering Strategy based on following.
@@ -60,13 +59,12 @@ public class JavaSortAndSizeExecutionStrategy<T extends HoodieRecordPayload<T>>
final String instantTime, final Map<String, String> strategyParams, final Schema schema,
final List<HoodieFileGroupId> fileGroupIdList, final boolean preserveHoodieMetadata) {
LOG.info("Starting clustering for a group, parallelism:" + numOutputGroups + " commit:" + instantTime);
Properties props = getWriteConfig().getProps();
props.put(HoodieWriteConfig.BULKINSERT_PARALLELISM_VALUE.key(), String.valueOf(numOutputGroups));
// We are calling another action executor - disable auto commit. Strategy is only expected to write data in new files.
props.put(HoodieWriteConfig.AUTO_COMMIT_ENABLE.key(), Boolean.FALSE.toString());
props.put(HoodieStorageConfig.PARQUET_MAX_FILE_SIZE.key(), String.valueOf(getWriteConfig().getClusteringTargetFileMaxBytes()));
HoodieWriteConfig newConfig = HoodieWriteConfig.newBuilder()
.withEngineType(EngineType.JAVA).withProps(props).build();
.withBulkInsertParallelism(numOutputGroups)
.withEngineType(EngineType.JAVA)
.withProps(getWriteConfig().getProps()).build();
newConfig.setValue(HoodieStorageConfig.PARQUET_MAX_FILE_SIZE, String.valueOf(getWriteConfig().getClusteringTargetFileMaxBytes()));
return (List<WriteStatus>) JavaBulkInsertHelper.newInstance().bulkInsert(inputRecords, instantTime, getHoodieTable(), newConfig,
false, getPartitioner(strategyParams, schema), true, numOutputGroups, new CreateHandleFactory(preserveHoodieMetadata));
}

View File

@@ -19,6 +19,7 @@
package org.apache.hudi.table.action.commit;
import org.apache.hudi.client.WriteStatus;
import org.apache.hudi.common.config.TypedProperties;
import org.apache.hudi.common.model.HoodieKey;
import org.apache.hudi.common.model.HoodieRecord;
import org.apache.hudi.common.model.HoodieRecordPayload;
@@ -111,7 +112,7 @@ public class JavaBulkInsertHelper<T extends HoodieRecordPayload, R> extends Base
FileIdPrefixProvider fileIdPrefixProvider = (FileIdPrefixProvider) ReflectionUtils.loadClass(
config.getFileIdPrefixProviderClassName(),
config.getProps());
new TypedProperties(config.getProps()));
List<WriteStatus> writeStatuses = new ArrayList<>();