siddharthteotia edited a comment on issue #4547: Indexed table URL: https://github.com/apache/incubator-pinot/pull/4547#issuecomment-523246556 I think we should implement this in a generic manner -- something like a container of columns to pass a columnar data batch between operators. The batch size can be fixed (say 4K or 10K) and each time a parent operator calls next, this batch is passed onto to parent operator from child operator. We should do this independent of sort query or a selection query or an aggregation query. For example, a simple query with SELECT -> PROJECT -> FILTER -> SCAN as the operator tree will also use as the record batch container during the execution or is that not the goal?
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@pinot.apache.org For additional commands, e-mail: commits-h...@pinot.apache.org
