ashoka1981 commented on PR #68666: URL: https://github.com/apache/doris/pull/68666#issuecomment-5903706695
@linrrzqqq this builds directly on the per-block batching from #62494 — batches of a block are now executed through a bounded streaming scheduler when the AI resource sets `ai.max_concurrency` (default 1 = today's sequential loop). Design notes, alternatives considered (planner-side change, session variable, waves vs streaming) and measurements are in the description; happy to adjust the knob's placement or defaults if you'd prefer otherwise. Tracking issue: #68626. -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
