alamb commented on PR #16690: URL: https://github.com/apache/datafusion/pull/16690#issuecomment-3063739024
> * Doing (some of the) merge algorithm itself in parallel - I am not sure what would the best way forward here, but it seems it could give the largest gains, as merging is currently done in a single thread. Here is a related idea; - https://github.com/apache/datafusion/issues/7181 > * Doing conversion to `Row` format in parallel - it seems currently this is done in a single thread, it should give some (smaller) speedup This is an interesting idea and I think it may make a significant difference -- the core merge is a single threaded operation, so the less time that thread has to wait (for example, to fetch the next cursor of rows) will contribute directly to the overall speed of the query -- 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: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
