lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-4316] Support for spillable diskmap configuration when constructing HoodieMergedLogRecordScanner (#5959)

Browse Source
This commit is contained in:
cxzl25
2022-06-27 11:09:30 +08:00
committed by GitHub
parent 7a6eb0f6e1
commit 72fa19bcc9
5 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
hudi-client/hudi-java-client/src/main/java/org/apache/hudi/client/clustering/run/strategy/JavaExecutionStrategy.java
View File

@@ -191,6 +191,8 @@ public abstract class JavaExecutionStrategy<T extends HoodieRecordPayload<T>>
.withBufferSize(config.getMaxDFSStreamBufferSize())
.withSpillableMapBasePath(config.getSpillableMapBasePath())
.withPartition(clusteringOp.getPartitionPath())
.withDiskMapType(config.getCommonConfig().getSpillableDiskMapType())
.withBitCaskDiskMapCompressionEnabled(config.getCommonConfig().isBitCaskDiskMapCompressionEnabled())
.build();
Option<HoodieFileReader> baseFileReader = StringUtils.isNullOrEmpty(clusteringOp.getDataFilePath())

2
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/clustering/run/strategy/MultipleSparkJobExecutionStrategy.java
View File

@@ -221,6 +221,8 @@ public abstract class MultipleSparkJobExecutionStrategy<T extends HoodieRecordPa
.withBufferSize(config.getMaxDFSStreamBufferSize())
.withSpillableMapBasePath(config.getSpillableMapBasePath())
.withPartition(clusteringOp.getPartitionPath())
.withDiskMapType(config.getCommonConfig().getSpillableDiskMapType())
.withBitCaskDiskMapCompressionEnabled(config.getCommonConfig().isBitCaskDiskMapCompressionEnabled())
.build();
Option<HoodieFileReader> baseFileReader = StringUtils.isNullOrEmpty(clusteringOp.getDataFilePath())

2
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/sink/clustering/ClusteringOperator.java
View File

@@ -269,6 +269,8 @@ public class ClusteringOperator extends TableStreamOperator<ClusteringCommitEven
.withReverseReader(writeConfig.getCompactionReverseLogReadEnabled())
.withBufferSize(writeConfig.getMaxDFSStreamBufferSize())
.withSpillableMapBasePath(writeConfig.getSpillableMapBasePath())
.withDiskMapType(writeConfig.getCommonConfig().getSpillableDiskMapType())
.withBitCaskDiskMapCompressionEnabled(writeConfig.getCommonConfig().isBitCaskDiskMapCompressionEnabled())
.build();
HoodieTableConfig tableConfig = table.getMetaClient().getTableConfig();

1
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/table/format/FormatUtils.java
View File

@@ -136,6 +136,7 @@ public class FormatUtils {
.withBufferSize(writeConfig.getMaxDFSStreamBufferSize())
.withMaxMemorySizeInBytes(split.getMaxCompactionMemoryInBytes())
.withDiskMapType(writeConfig.getCommonConfig().getSpillableDiskMapType())
.withBitCaskDiskMapCompressionEnabled(writeConfig.getCommonConfig().isBitCaskDiskMapCompressionEnabled())
.withSpillableMapBasePath(writeConfig.getSpillableMapBasePath())
.withInstantRange(split.getInstantRange())
.withOperationField(flinkConf.getBoolean(FlinkOptions.CHANGELOG_ENABLED))

9
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieMergeOnReadRDD.scala
View File

@@ -25,7 +25,7 @@ import org.apache.hadoop.fs.Path
import org.apache.hadoop.mapred.JobConf
import org.apache.hudi.HoodieConversionUtils.{toJavaOption, toScalaOption}
import org.apache.hudi.HoodieMergeOnReadRDD.{AvroDeserializerSupport, collectFieldOrdinals, getPartitionPath, projectAvro, projectAvroUnsafe, projectRowUnsafe, resolveAvroSchemaNullability}
import org.apache.hudi.common.config.HoodieMetadataConfig
import org.apache.hudi.common.config.{HoodieCommonConfig, HoodieMetadataConfig}
import org.apache.hudi.common.engine.HoodieLocalEngineContext
import org.apache.hudi.common.fs.FSUtils
import org.apache.hudi.common.fs.FSUtils.getRelativePartitionPath
@@ -361,7 +361,12 @@ private object HoodieMergeOnReadRDD {
.withSpillableMapBasePath(
hadoopConf.get(HoodieRealtimeConfig.SPILLABLE_MAP_BASE_PATH_PROP,
HoodieRealtimeConfig.DEFAULT_SPILLABLE_MAP_BASE_PATH))
.withDiskMapType(
hadoopConf.getEnum(HoodieCommonConfig.SPILLABLE_DISK_MAP_TYPE.key,
HoodieCommonConfig.SPILLABLE_DISK_MAP_TYPE.defaultValue))
.withBitCaskDiskMapCompressionEnabled(
hadoopConf.getBoolean(HoodieCommonConfig.DISK_MAP_BITCASK_COMPRESSION_ENABLED.key(),
HoodieCommonConfig.DISK_MAP_BITCASK_COMPRESSION_ENABLED.defaultValue()))
if (logFiles.nonEmpty) {
logRecordScannerBuilder.withPartition(
getRelativePartitionPath(new Path(tableState.tablePath), logFiles.head.getPath.getParent))