BruceKellan commented on issue #8685:
URL: https://github.com/apache/hudi/issues/8685#issuecomment-1543321785
That my flink DDL:
```sql
create table sink_table (
uniqueKey string,
key string,
`offset` bigint,
`time` bigint,
sid int,
plat string,
pid string,
gid string,
account string,
playerid string,
kafka_ts bigint,
consume_ts bigint,
prop map<string, string>,
`day` string,
`type` string
) partitioned by (`day`, `type`) with (
'connector' = 'hudi',
'path' = 'xxxxx',
'table.type' = 'COPY_ON_WRITE',
'write.operation' = 'insert',
'write.tasks' = '12',
'write.task.max.size' = '1024',
'hive_sync.partition_fields' = 'day,type',
'hive_sync.partition_extractor_class' =
'org.apache.hudi.hive.MultiPartKeysValueExtractor',
'hadoop.io.compression.codec.zstd.level' = '3',
'hadoop.parquet.compression.codec.zstd.level' = '3',
'hoodie.datasource.write.recordkey.field' = 'uniqueKey',
'hoodie.datasource.write.partitionpath.field' = 'day,type',
'hoodie.datasource.write.hive_style_partitioning' = 'true',
'hoodie.datasource.write.keygenerator.type' = 'COMPLEX',
'hoodie.parquet.compression.codec' = 'zstd',
'hoodie.parquet.dictionary.enabled' = 'true',
'write.insert.cluster' = 'false',
'clean.retain_commits' = '30',
'clustering.schedule.enabled' = 'true',
'clustering.delta_commits' = '8',
'clustering.async.enabled' = 'true',
'clustering.plan.strategy.target.file.max.bytes' = '104857600',
'clustering.plan.strategy.small.file.limit' = '30',
'clustering.plan.strategy.max.num.groups' = '1500',
'hoodie.clustering.plan.strategy.single.group.clustering.enabled' =
'false',
'hoodie.archive.merge.enable' = 'true',
'hoodie.archive.merge.small.file.limit.bytes' = '536870912',
'metadata.enabled' = 'false'
)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
