[
https://issues.apache.org/jira/browse/IMPALA-15097?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18088542#comment-18088542
]
Aleksandr Efimov commented on IMPALA-15097:
-------------------------------------------
I kept the initial patch focused on showing runtime filter effectiveness from
scan-node counters without changing the graph when the profile does not have
enough information.
There are a few follow-up improvements that seem useful but probably deserve
separate JIRAs rather than expanding this patch:
- add a small legend/explanation for dashed runtime filter edges and
rejected/processed labels;
- improve runtime filter diagnostics around missing/late filters, e.g. make it
easier to see whether a filter arrived too late or simply rejected nothing;
- add broader regression coverage using real profile snippets for newer and
older runtime filter table formats.
If these sound useful, I can file separate follow-up JIRAs after this review.
> Show runtime filter effectiveness in plan-graph.py
> --------------------------------------------------
>
> Key: IMPALA-15097
> URL: https://issues.apache.org/jira/browse/IMPALA-15097
> Project: IMPALA
> Issue Type: Improvement
> Reporter: Quanlong Huang
> Assignee: Aleksandr Efimov
> Priority: Major
> Attachments: query-plan1.svg, rf_profile.txt
>
>
> When verbosity is larger than 0, plan-graph.py generates nodes and lines for
> runtime filters. It'd be helpful to show ineffective runtime filters, e.g.,
> by using dash lines.
> It'd be more helpful if we should how many files/rows, etc. are skipped by
> the filter.
> Uploaded an example profile and the generated svg file. The command is
> {code:java}
> bin/diagnostics/experimental/plan-graph.py -v1 rf_profile.txt | dot -T svg -o
> query-plan1.svg {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
