yihua commented on issue #6758: URL: https://github.com/apache/hudi/issues/6758#issuecomment-1258136314
@Zhangshunyu we leverage HFile format to speed up the point and range lookups, including the case based on partition path as the prefix for the record key in the metadata table. Do you see significant performance degradation when there are a large number of partitions? Based on [our benchmark](https://www.onehouse.ai/blog/introducing-multi-modal-index-for-the-lakehouse-in-apache-hudi), the lookup latency in MT scales well. -- 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]
