jihoonson commented on issue #8061: Native parallel batch indexing with shuffle URL: https://github.com/apache/incubator-druid/issues/8061#issuecomment-517850801 > Keeping MM simple would optionally keep us open to expanding our TaskRunners to directly leverage modern container orchestration platforms like kubernetes, marathon, Yarn, Yunicorn etc, where TaskRunners schedule peons directly in e.g. a kubernetes cluster. Thinking more about this, it could be easier and more useful for these users if intermediary data is stored in deep storage. I think we can make this pluggable, like using MM or deep storage for intermediary data depending on the configuration. Does this make sense?
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
