XiangpengHao opened a new pull request, #11684:
URL: https://github.com/apache/datafusion/pull/11684
## Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases. You can
link an issue to this PR using the GitHub syntax. For example `Closes #123`
indicates that this PR will close issue #123.
-->
Related to #7000.
## Rationale for this change
I get some time to implement the multi-column aggregation with StringView,
the implementation is inspired by @jayzhan211 's #10976.
<!--
Why are you proposing this change? If this is already explained clearly in
the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand your
changes and offer better suggestions for fixes.
-->
However, the performance is mixed, I see almost no performance diff with
ClickBench query 18:
```sql
SELECT "UserID", extract(minute FROM to_timestamp_seconds("EventTime")) AS
m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase"
ORDER BY COUNT(*) DESC LIMIT 10;
```
This is becuase the average size of `SearchPhrase` is only 4, meaning the
string is always inlined to view and thus not being reused.
However, I made this query (q14, changed `SearchPhrase` to `URL`)
```sql
SELECT "SearchEngineID", "URL", COUNT(*) AS c FROM hits WHERE "URL" <> ''
GROUP BY "SearchEngineID", "URL" ORDER BY c DESC LIMIT 10;
```
Without this patch, it takes 7.4s; with this patch, it takes 5.9s, a 20%
improvement.
With this patch, the output string will reuse the string values in the
buffer, so it is good.
However, when `intern`ing the values, we need to hash twice: (1) the string
itself to build `BytesViewMap` (2) the group index - `u32`, which adds overhead.
## What changes are included in this PR?
Things not implemented yet:
- `EmtiTo::First(n)`: I need to think a bit more about how to efficiently
reuse the `BytesViewBuilder`
<!--
There is no need to duplicate the description in the issue here but it is
sometimes worth providing a summary of the individual changes in this PR.
-->
## Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example, are
they covered by existing tests)?
-->
## Are there any user-facing changes?
No
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
-->
<!--
If there are any breaking changes to public APIs, please add the `api
change` label.
-->
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
