cloud-fan commented on pull request #28780:
URL: https://github.com/apache/spark/pull/28780#issuecomment-647945904
shall we set `sorter.totalSpillBytes`, then we can update the metrics
correctly in `sort.spill`.
This is an
cloud-fan commented on pull request #28780:
URL: https://github.com/apache/spark/pull/28780#issuecomment-647288933
> number of in-memory bytes spilled
what's the difference between it and `spill (disk)`? IIUC `spill` means we
dump data from memory to disk.
cloud-fan commented on pull request #28780:
URL: https://github.com/apache/spark/pull/28780#issuecomment-644697788
I'm not familiar with this part. what does "spill (memory)" mean？
This is an automated message from the
