realno commented on pull request #1560: URL: https://github.com/apache/arrow-datafusion/pull/1560#issuecomment-1017072068
> > You mentioned your use case is mainly interactive queries. Out of curiosity, what does your current Spark deployment looks like? What are the biggest drivers (or pain points) for you to switch? > > Hi @realno, actually our team has customized the Spark to serve interactive queries. The Spark cluster is long running with thrift server for receiving query requests. The main pain point is it's not fast enough to serve queries within seconds. That's the main reason that we hope to utilize a native distributed compute engine with zero copy shuffling for our case. That makes a lot of sense @yahoNanJing. We have exact the same setup for one use case. How many executors do you guys run? -- 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]
