lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-2345] Hoodie columns sort partitioner for bulk insert (#3523)

Browse Source 
Co-authored-by: yuezhang <yuezhang@freewheel.tv>
This commit is contained in:
zhangyue19921010
2021-08-24 21:45:17 +08:00
committed by GitHub
parent 05e6f44d53
commit de94787a85
5 changed files with 83 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieWriteConfig.java
View File

@@ -158,11 +158,18 @@ public class HoodieWriteConfig extends HoodieConfig {
.withDocumentation("For large initial imports using bulk_insert operation, controls the parallelism to use for sort modes or custom partitioning done"
+ "before writing records to the table.");
public static final ConfigProperty<String> BULKINSERT_USER_DEFINED_PARTITIONER_SORT_COLUMNS = ConfigProperty
.key("hoodie.bulkinsert.user.defined.partitioner.sort.columns")
.noDefaultValue()
.withDocumentation("Columns to sort the data by when use org.apache.hudi.execution.bulkinsert.RDDCustomColumnsSortPartitioner as user defined partitioner during bulk_insert. "
+ "For example 'column1,column2'");
public static final ConfigProperty<String> BULKINSERT_USER_DEFINED_PARTITIONER_CLASS_NAME = ConfigProperty
.key("hoodie.bulkinsert.user.defined.partitioner.class")
.noDefaultValue()
.withDocumentation("If specified, this class will be used to re-partition records before they are bulk inserted. This can be used to sort, pack, cluster data"
+ " optimally for common query patterns.");
+ " optimally for common query patterns. For now we support a build-in user defined bulkinsert partitioner org.apache.hudi.execution.bulkinsert.RDDCustomColumnsSortPartitioner"
+ " which can does sorting based on specified column values set by " + BULKINSERT_USER_DEFINED_PARTITIONER_SORT_COLUMNS.key());
public static final ConfigProperty<String> UPSERT_PARALLELISM_VALUE = ConfigProperty
.key("hoodie.upsert.shuffle.parallelism")
@@ -894,6 +901,10 @@ public class HoodieWriteConfig extends HoodieConfig {
return getString(BULKINSERT_USER_DEFINED_PARTITIONER_CLASS_NAME);
}
public String getUserDefinedBulkInsertPartitionerSortColumns() {
return getString(BULKINSERT_USER_DEFINED_PARTITIONER_SORT_COLUMNS);
}
public int getInsertShuffleParallelism() {
return getInt(INSERT_PARALLELISM_VALUE);
}
@@ -1832,6 +1843,11 @@ public class HoodieWriteConfig extends HoodieConfig {
return this;
}
public Builder withUserDefinedBulkInsertPartitionerSortColumns(String columns) {
writeConfig.setValue(BULKINSERT_USER_DEFINED_PARTITIONER_SORT_COLUMNS, columns);
return this;
}
public Builder withDeleteParallelism(int parallelism) {
writeConfig.setValue(DELETE_PARALLELISM_VALUE, String.valueOf(parallelism));
return this;