Dandandan commented on PR #2308: URL: https://github.com/apache/datafusion-ballista/pull/2308#issuecomment-5308112970
> Other DataFusion-based distributed engines, notably [DataFusion Distributed](https://datafusion-contrib.github.io/datafusion-distributed/) and [Sail](https://github.com/lakehq/sail), stream data between stages instead, and they are faster on interactive workloads as a result. Based on some experiments I did today, I was being able to recover (most) of the performance by keeping shuffle data in memory (RAM disk), this yields > 40% improvement on TPC-H, suggesting that most of the difference doesn't come from the blocking shuffle but from (avoiding) IO. -- 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]
