You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@flink.apache.org by GitBox <gi...@apache.org> on 2022/03/21 04:05:42 UTC

[GitHub] [flink] fredia edited a comment on pull request #19033: [FLINK-21321][Runtime/StateBackends] improve RocksDB incremental rescale performance by using deleteRange operator

fredia edited a comment on pull request #19033:
URL: https://github.com/apache/flink/pull/19033#issuecomment-1073462371


   @Aitozi Thank you for your interest. As you mentioned, 
   > we could always choose one as the base db, since the DeleteRange can finish in no time. 
   
   In theory, setting the default value to 0 is most suitable, since `deleteRange()` takes less time than creating a new RocksDB instance and then scan-and-put the data. We did some experiments with different thresholds, and create a ticket https://issues.apache.org/jira/browse/FLINK-26757 about this, please take a look.


-- 
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: issues-unsubscribe@flink.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org