ziedbouf commented on issue #30: URL: https://github.com/apache/arrow-ballista/issues/30#issuecomment-1146597093
Hi everyone, first thanks for the great work on datafusion and ballista i am currently on @andygrove book for processing engine and it's pretty interesting as it help us to learn more about how processing engine works and take an extra steps on learning engine such spark. I am not an expert in this area, but i have few questions in mind as i am willing to explore how ballista answer these and help in production grade data processing engine. One of the things that i find interesting, is spark/redis integration that bump up spark performance due to the in memory nature of redis. However, i am not sure if that's already true in the context of ballista/datafusion due to the nature of Arrow an espcially with the integration of Plasma project in Arrow, made by Ray team, so i wonder guys if you can shed some lights on this. One more think, how does ballista compare to engine such as Ray and Dask in general, and does potentially ballista could be direct competitor of those frameworks. Finally as Ballista compares directly to spark, how do we see the implmentation of BALLISTA ML, Graph. Thanks everyone for the great works. -- 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...@arrow.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
