alamb opened a new pull request, #24426: URL: https://github.com/apache/datafusion/pull/24426
## Which issue does this PR close? - Part of https://github.com/apache/datafusion/issues/24393 - Part of https://github.com/apache/datafusion/issues/20324 **Note: this is a benchmarking prototype and is NOT intended for merge or review.** Stacked on https://github.com/apache/datafusion/pull/24395 (the `progressive_io` option). ## Rationale for this change Measure whether enabling `pushdown_filters` by default can now match or beat today's ClickBench performance when the I/O pattern is kept the same as today (one request per row group), i.e. with `progressive_io = false` (the default introduced in #24395). ## What changes are included in this PR? - The `progressive_io` commit from #24395 - Flips the default of `datafusion.execution.parquet.pushdown_filters` to `true` (`progressive_io` stays `false`, so scans still fetch each row group's data in a single request) ## Are these changes tested? Benchmark runs only (`clickbench_partitioned`, with and without simulated object store latency); results to be posted below. Other tests that encode the pushdown-off default are expected to fail and are not being fixed in this prototype. ## Are there any user-facing changes? Not intended for merge as-is. -- 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]
