lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-4319] Fixed Parquet's PLAIN_DICTIONARY encoding not being applied when bulk-inserting (#5966)

Browse Source 
* Fixed Dictionary encoding config not being properly propagated to Parquet writer (making it unable to apply it, substantially bloating the storage footprint)
This commit is contained in:
Alexey Kudinkin
2022-06-24 20:52:28 -07:00
committed by GitHub
parent 360df576a9
commit c86edfc28e
16 changed files with 50 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieAvroParquetWriter.java
View File

@@ -47,11 +47,11 @@ public class HoodieAvroParquetWriter<R extends IndexedRecord>
@SuppressWarnings({"unchecked", "rawtypes"})
public HoodieAvroParquetWriter(Path file,
HoodieAvroParquetConfig parquetConfig,
HoodieParquetConfig<HoodieAvroWriteSupport> parquetConfig,
String instantTime,
TaskContextSupplier taskContextSupplier,
boolean populateMetaFields) throws IOException {
super(file, (HoodieBaseParquetConfig) parquetConfig);
super(file, (HoodieParquetConfig) parquetConfig);
this.fileName = file.getName();
this.writeSupport = parquetConfig.getWriteSupport();
this.instantTime = instantTime;

2
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieBaseParquetWriter.java
View File

@@ -43,7 +43,7 @@ public abstract class HoodieBaseParquetWriter<R> extends ParquetWriter<R> {
private long lastCachedDataSize = -1;
public HoodieBaseParquetWriter(Path file,
HoodieBaseParquetConfig<? extends WriteSupport<R>> parquetConfig) throws IOException {
HoodieParquetConfig<? extends WriteSupport<R>> parquetConfig) throws IOException {
super(HoodieWrapperFileSystem.convertToHoodiePath(file, parquetConfig.getHadoopConf()),
ParquetFileWriter.Mode.CREATE,
parquetConfig.getWriteSupport(),

2
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/storage/HoodieFileWriterFactory.java
View File

@@ -77,7 +77,7 @@ public class HoodieFileWriterFactory {
Option<BloomFilter> filter = enableBloomFilter ? Option.of(createBloomFilter(config)) : Option.empty();
HoodieAvroWriteSupport writeSupport = new HoodieAvroWriteSupport(new AvroSchemaConverter(conf).convert(schema), schema, filter);
HoodieAvroParquetConfig parquetConfig = new HoodieAvroParquetConfig(writeSupport, config.getParquetCompressionCodec(),
HoodieParquetConfig<HoodieAvroWriteSupport> parquetConfig = new HoodieParquetConfig<>(writeSupport, config.getParquetCompressionCodec(),
config.getParquetBlockSize(), config.getParquetPageSize(), config.getParquetMaxFileSize(),
conf, config.getParquetCompressionRatio(), config.parquetDictionaryEnabled());

19
hudi-client/hudi-client-common/src/test/java/org/apache/hudi/testutils/HoodieWriteableTestTable.java
View File

@@ -19,6 +19,12 @@
package org.apache.hudi.testutils;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.generic.IndexedRecord;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hudi.avro.HoodieAvroUtils;
import org.apache.hudi.avro.HoodieAvroWriteSupport;
import org.apache.hudi.common.bloom.BloomFilter;
@@ -38,18 +44,11 @@ import org.apache.hudi.common.testutils.HoodieMetadataTestTable;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.collection.Pair;
import org.apache.hudi.config.HoodieStorageConfig;
import org.apache.hudi.io.storage.HoodieAvroParquetConfig;
import org.apache.hudi.io.storage.HoodieAvroParquetWriter;
import org.apache.hudi.io.storage.HoodieParquetConfig;
import org.apache.hudi.io.storage.HoodieOrcConfig;
import org.apache.hudi.io.storage.HoodieOrcWriter;
import org.apache.hudi.io.storage.HoodieAvroParquetWriter;
import org.apache.hudi.metadata.HoodieTableMetadataWriter;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.generic.IndexedRecord;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.log4j.LogManager;
import org.apache.log4j.Logger;
import org.apache.orc.CompressionKind;
@@ -110,7 +109,7 @@ public class HoodieWriteableTestTable extends HoodieMetadataTestTable {
if (HoodieTableConfig.BASE_FILE_FORMAT.defaultValue().equals(HoodieFileFormat.PARQUET)) {
HoodieAvroWriteSupport writeSupport = new HoodieAvroWriteSupport(
new AvroSchemaConverter().convert(schema), schema, Option.of(filter));
HoodieAvroParquetConfig config = new HoodieAvroParquetConfig(writeSupport, CompressionCodecName.GZIP,
HoodieParquetConfig<HoodieAvroWriteSupport> config = new HoodieParquetConfig<>(writeSupport, CompressionCodecName.GZIP,
ParquetWriter.DEFAULT_BLOCK_SIZE, ParquetWriter.DEFAULT_PAGE_SIZE, 120 * 1024 * 1024,
new Configuration(), Double.parseDouble(HoodieStorageConfig.PARQUET_COMPRESSION_RATIO_FRACTION.defaultValue()));
try (HoodieAvroParquetWriter writer = new HoodieAvroParquetWriter<>(