Skip to content

[HUDI-5484] Avoid using GenericRecord in HoodieColumnStatMetadata #7573

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
alexeykudinkin merged 7 commits into from
Jan 9, 2023
Merged

[HUDI-5484] Avoid using GenericRecord in HoodieColumnStatMetadata #7573

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
bfec3be
unwrap & wrap GenericRecord
cxzl25 Dec 28, 2022
7079635
trigger test
cxzl25 Dec 29, 2022
92b8c60
add ut
cxzl25 Jan 3, 2023
1ac267b
trigger test
cxzl25 Jan 3, 2023
0f68fae
comment
cxzl25 Jan 7, 2023
dae318c
Revert "add ut"
cxzl25 Jan 7, 2023
c595966
move ut
cxzl25 Jan 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions hudi-common/src/main/java/org/apache/hudi/metadata/HoodieMetadataPayload.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,8 +233,11 @@ public HoodieMetadataPayload(Option<GenericRecord> recordOpt) {
columnStatMetadata = HoodieMetadataColumnStats.newBuilder(METADATA_COLUMN_STATS_BUILDER_STUB.get())
.setFileName((String) columnStatsRecord.get(COLUMN_STATS_FIELD_FILE_NAME))
.setColumnName((String) columnStatsRecord.get(COLUMN_STATS_FIELD_COLUMN_NAME))
.setMinValue(columnStatsRecord.get(COLUMN_STATS_FIELD_MIN_VALUE))
.setMaxValue(columnStatsRecord.get(COLUMN_STATS_FIELD_MAX_VALUE))
// AVRO-2377 1.9.2 Modified the type of org.apache.avro.Schema#FIELD_RESERVED to Collections.unmodifiableSet.
// This causes Kryo to fail when deserializing a GenericRecord, See HUDI-5484.
// We should avoid using GenericRecord and convert GenericRecord into a serializable type.
.setMinValue(wrapStatisticValue(unwrapStatisticValueWrapper(columnStatsRecord.get(COLUMN_STATS_FIELD_MIN_VALUE))))
Copy link
Contributor

@alexeykudinkin alexeykudinkin Jan 6, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's add a comment explaining why we need to do that here

.setMaxValue(wrapStatisticValue(unwrapStatisticValueWrapper(columnStatsRecord.get(COLUMN_STATS_FIELD_MAX_VALUE))))
.setValueCount((Long) columnStatsRecord.get(COLUMN_STATS_FIELD_VALUE_COUNT))
.setNullCount((Long) columnStatsRecord.get(COLUMN_STATS_FIELD_NULL_COUNT))
.setTotalSize((Long) columnStatsRecord.get(COLUMN_STATS_FIELD_TOTAL_SIZE))
Expand Down
29 changes: 29 additions & 0 deletions hudi-spark-datasource/hudi-spark/src/test/java/org/apache/hudi/TestDataSourceUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,15 +22,18 @@
import org.apache.hudi.client.SparkRDDWriteClient;
import org.apache.hudi.common.config.HoodieStorageConfig;
import org.apache.hudi.common.config.TypedProperties;
import org.apache.hudi.common.model.HoodieColumnRangeMetadata;
import org.apache.hudi.common.model.HoodieRecord;
import org.apache.hudi.common.model.HoodieRecordPayload;
import org.apache.hudi.common.model.WriteOperationType;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.SerializationUtils;
import org.apache.hudi.common.util.collection.ImmutablePair;
import org.apache.hudi.config.HoodieClusteringConfig;
import org.apache.hudi.config.HoodieWriteConfig;
import org.apache.hudi.exception.HoodieException;
import org.apache.hudi.execution.bulkinsert.RDDCustomColumnsSortPartitioner;
import org.apache.hudi.metadata.HoodieMetadataPayload;
import org.apache.hudi.table.BulkInsertPartitioner;

import org.apache.avro.Conversions;
Expand All @@ -39,6 +42,7 @@
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericFixed;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.generic.IndexedRecord;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
Expand All @@ -59,6 +63,7 @@
import org.mockito.Mock;
import org.mockito.junit.jupiter.MockitoExtension;

import java.io.IOException;
import java.math.BigDecimal;
import java.time.LocalDate;
import java.util.ArrayList;
Expand Down Expand Up @@ -323,4 +328,28 @@ private static Stream<Arguments> testAutoModifyParquetWriteLegacyFormatParameter
{false, true, true}, {false, false, false}
}).map(Arguments::of);
}

@Test
public void testSerHoodieMetadataPayload() throws IOException {
String partitionPath = "2022/10/01";
String fileName = "file.parquet";
String targetColName = "c1";

HoodieColumnRangeMetadata<Comparable> columnStatsRecord =
HoodieColumnRangeMetadata.<Comparable>create(fileName, targetColName, 0, 500, 0, 100, 12345, 12345);

HoodieRecord<HoodieMetadataPayload> hoodieMetadataPayload =
HoodieMetadataPayload.createColumnStatsRecords(partitionPath, Collections.singletonList(columnStatsRecord), false)
.findFirst().get();

IndexedRecord record = hoodieMetadataPayload.getData().getInsertValue(null).get();
byte[] recordToBytes = HoodieAvroUtils.indexedRecordToBytes(record);
GenericRecord genericRecord = HoodieAvroUtils.bytesToAvro(recordToBytes, record.getSchema());

HoodieMetadataPayload genericRecordHoodieMetadataPayload = new HoodieMetadataPayload(Option.of(genericRecord));
byte[] bytes = SerializationUtils.serialize(genericRecordHoodieMetadataPayload);
HoodieMetadataPayload deserGenericRecordHoodieMetadataPayload = SerializationUtils.deserialize(bytes);

assertEquals(genericRecordHoodieMetadataPayload, deserGenericRecordHoodieMetadataPayload);
}
}