Rich-T-kid commented on PR #26789: URL: https://github.com/apache/datafusion/pull/26789#issuecomment-6450689131
Clarification on the benchmark results above: they compare merge-base `c18e5d9` with PR SHA `523969b7c`, with `DATAFUSION_EXECUTION_PARQUET_ENABLE_RLE_TO_DICTIONARY=true` on both sides. The baseline therefore reads eligible Parquet strings as `Dictionary<Int32, Utf8>`, not through the default `Utf8View` path. Those runs isolate the effect of the new physical optimizer rule within dictionary-enabled execution; they do not show whether dictionary reads plus this rule outperform the default main configuration. I am running a follow-up comparison with dictionary reads disabled on the main baseline and enabled on the PR side, so the baseline uses `Utf8View` and the changed side exercises the new rule. -- 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]
