progval opened a new issue, #12584:
URL: https://github.com/apache/datafusion/issues/12584
### Is your feature request related to a problem or challenge?
For Parquet files, the `time_elapsed_opening` metric encompasses all of (in
execution order):
1. Reading and parsing the footer/metadata (which is usually negligeable
unless the page index is enabled, no metric either way)
2. Applying the row-level pushdown filter (`pushdown_eval_time` metric)
3. Parsing statistics and using them to prune (no metric)
4. Parsing Bloom Filters and using them to prune (no metric)
5. Pruning using the page filter (`page_filter_eval_time` metric)
6. Selecting columns and projecting (no metric, negligeable time)
### Describe the solution you'd like
1. Add missing metrics:
* `metadata_load_time` for part 1
* `statistics_eval_time` for part 3
* `bloom_filter_eval_time`for part 4
3. Rename `pushdown_eval_time` to `row_pushdown_eval_time`, because
statistics and eval time are also pushdown filters
### Describe alternatives you've considered
Split `statistics_eval_time` and `bloom_filter_eval_time` each into two
metrics, one for load time and one for eval time. But eval time is negligeable
for both, so probably not worth it.
### Additional context
_No response_
--
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]
