lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-1951] Add bucket hash index, compatible with the hive bucket (#3173)

Browse Source 
* [HUDI-2154] Add index key field to HoodieKey

* [HUDI-2157] Add the bucket index and its read/write implemention of Spark engine.
* revert HUDI-2154 add index key field to HoodieKey
* fix all comments and introduce a new tricky way to get index key at runtime
support double insert for bucket index
* revert spark read optimizer based on bucket index
* add the storage layout
* index tag, hash function and add ut
* fix ut
* address partial comments
* Code review feedback
* add layout config and docs
* fix ut
* rename hoodie.layout and rebase master

Co-authored-by: Vinoth Chandar <vinoth@apache.org>
This commit is contained in:
Shawy Geng
2021-12-31 04:38:26 +08:00
committed by GitHub
parent 0f0088fe4b
commit a4e622ac61
46 changed files with 1335 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/DataSourceUtils.java
View File

@@ -44,7 +44,6 @@ import org.apache.hudi.exception.HoodieNotSupportedException;
import org.apache.hudi.exception.TableNotFoundException;
import org.apache.hudi.hive.HiveSyncConfig;
import org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor;
import org.apache.hudi.index.HoodieIndex.IndexType;
import org.apache.hudi.table.BulkInsertPartitioner;
import org.apache.hudi.util.DataTypeUtils;
import org.apache.log4j.LogManager;
@@ -185,7 +184,6 @@ public class DataSourceUtils {
}
return builder.forTable(tblName)
.withIndexConfig(HoodieIndexConfig.newBuilder().withIndexType(IndexType.BLOOM).build())
.withCompactionConfig(HoodieCompactionConfig.newBuilder()
.withPayloadClass(parameters.get(DataSourceWriteOptions.PAYLOAD_CLASS_NAME().key()))
.withInlineCompaction(inlineCompact).build())
@@ -309,6 +307,10 @@ public class DataSourceUtils {
DataSourceWriteOptions.HIVE_SKIP_RO_SUFFIX_FOR_READ_OPTIMIZED_TABLE().defaultValue()));
hiveSyncConfig.supportTimestamp = Boolean.valueOf(props.getString(DataSourceWriteOptions.HIVE_SUPPORT_TIMESTAMP_TYPE().key(),
DataSourceWriteOptions.HIVE_SUPPORT_TIMESTAMP_TYPE().defaultValue()));
hiveSyncConfig.bucketSpec = props.getBoolean(DataSourceWriteOptions.HIVE_SYNC_BUCKET_SYNC().key(),
(boolean) DataSourceWriteOptions.HIVE_SYNC_BUCKET_SYNC().defaultValue())
? HiveSyncConfig.getBucketSpec(props.getString(HoodieIndexConfig.BUCKET_INDEX_HASH_FIELD.key()),
props.getInteger(HoodieIndexConfig.BUCKET_INDEX_NUM_BUCKETS.key())) : null;
return hiveSyncConfig;
}

6
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala
View File

@@ -526,6 +526,12 @@ object DataSourceWriteOptions {
.noDefaultValue()
.withDocumentation("Mode to choose for Hive ops. Valid values are hms, jdbc and hiveql.")
val HIVE_SYNC_BUCKET_SYNC: ConfigProperty[Boolean] = ConfigProperty
.key("hoodie.datasource.hive_sync.bucket_sync")
.defaultValue(false)
.withDocumentation("Whether sync hive metastore bucket specification when using bucket index." +
"The specification is 'CLUSTERED BY (trace_id) SORTED BY (trace_id ASC) INTO 65536 BUCKETS'")
// Async Compaction - Enabled by default for MOR
val ASYNC_COMPACT_ENABLE: ConfigProperty[String] = ConfigProperty
.key("hoodie.datasource.compaction.async.enable")