2010YOUY01 commented on PR #18262: URL: https://github.com/apache/datafusion/pull/18262#issuecomment-3442590675
Thank you! Here the `elpased_compute` metric doesn't seem correct. It should represent the time operator using the CPU and do the actual work, so it must be larger than the `repartition_time`. I think it's mostly `repartition_time` plus time doing spilling writes and reads. In this line `elapsed_compute` is smaller than `repartition_time` ``` | | RepartitionExec: partitioning=Hash([v1@0], 11), input_partitions=11, metrics=[output_rows=100, elapsed_compute=5.418µs, spill_count=0, spilled_bytes=0.0 B, spilled_rows=0, fetch_time=5.720625ms, repartition_time=539.261µs, send_time=18.568µs] | ``` Besides I suggest to wait until https://github.com/apache/datafusion/pull/18207 is merged, there seem to be a lot of conflict. -- 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]
