korowa commented on issue #8393: URL: https://github.com/apache/arrow-datafusion/issues/8393#issuecomment-1989261154
Disregarding IEJoin -- `time` output from the issue description seems to show that both DuckDB and DF spend +- same cputime (user + system) and the only difference is parallelism (shown by real time), which, how @simonvandel noticed, depends on left/right input + join type)-- this makes me think that the x8 slowdown is not related to how join performed internally, but more like caused by physical optimizer skipping join reordering for `NestedLoopJoin`. So, if i'm not mistaken, this issue is mostly about covering NLJoin in [join_selection.rs](https://github.com/apache/arrow-datafusion/blob/abb0c1f62bf622bd0e40769560cf0804dac2ecbf/datafusion/core/src/physical_optimizer/join_selection.rs). -- 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]
