mixermt commented on pull request #32826: URL: https://github.com/apache/spark/pull/32826#issuecomment-1030764526
Thanks @dongjoon-hyun for your quick reply 🙏 Another small question regarding benchmarks, is there any benchmarks were done with different number of workers defined by `parquet.compression.codec.zstd.workers` ? Unfortunately, I can't find any benchmarks regarding this. In our production tests, we see a significant degradation while using, other than default, number of workers, although by description it should improve speed. We provide plenty of memory to executors. <img width="1018" alt="image" src="https://user-images.githubusercontent.com/695850/152670555-41fb5324-480f-4426-8f60-b65f64aee21a.png";> -- 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]
![https://user-images.githubusercontent.com/695850/152670555-41fb5324-480f-4426-8f60-b65f64aee21a.png"](https://user-images.githubusercontent.com/695850/152670555-41fb5324-480f-4426-8f60-b65f64aee21a.png"){kind=link}