XiangpengHao commented on issue #9403: URL: https://github.com/apache/datafusion/issues/9403#issuecomment-2231018750
Want to share some of my findings here. My approach is very similar to #10976, except that it will emit `StringViewArray` and uses `ArrowBytesViewMap` in #11421 to build the hash idx of the string column. The performance is similar to (slightly slower) first converting to row-group then convert back. Flamegraph shows that building the `ArrowBytesViewMap` takes quite a lot of time (compute hash, hash lookup etc). -- 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]
