thinkharderdev commented on issue #12454: URL: https://github.com/apache/datafusion/issues/12454#issuecomment-2351561929
> It probably isn't feasible, but the ideal way to run such a query is to pre-partitioning the `data` table such that each distinct value of `fact_id` is only stored on one node. > > (this is how Vertica does this type of join, FWIW) That would essentially just be the hash partitioning right? Or do you mean actually storing the underlying table data so it is already partitioned and doesn't require a repartition during query execution? The latter wouldn't be possible in our case since we don't know the specific query patterns that are required up front. -- 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]
