progval commented on PR #12593: URL: https://github.com/apache/datafusion/pull/12593#issuecomment-2375197430
I remembered. The issue is that in this code: https://github.com/apache/arrow-rs/blob/62825b27e98e6719cb66258535c75c7490ddba44/parquet/src/arrow/async_reader/mod.rs#L212-L228 `ArrowReaderMetadata::load_metadata` does two expensive things: 1. call `AsyncFileReader::get_metadata()` to get a `ParquetMetadata`, which we can cache as per `advanced_parquet_index.rs` 2. instantiate and use [`parquet::MetadataLoader`](https://docs.rs/parquet/latest/parquet/arrow/async_reader/struct.MetadataLoader.html) to get **another** `ParquetMetadata` from the first one. And this new `ParquetMetadata` isn't cachable without my patch. in essence, it's enriching the `metadata` struct by doing: `let metadata = MetadataLoader::new(..., metadata).load_page_index(...).finish()` -- 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]
