dongjoon-hyun commented on PR #1756: URL: https://github.com/apache/orc/pull/1756#issuecomment-1901003299
Thank you for double-check. Ya, it seems that our implementation has some limitations or bug. Apache Spark also has the ZStandardCodec implementation based on this `zstd-jni` and it shows 30% or 40% improvement in the micro-bencharmk. - https://github.com/apache/spark/blob/39f8e1a5953b5897f893151d24dc585a80c0c8a0/core/benchmarks/ZStandardBenchmark-results.txt#L27-L47 I'm still digging this because I believe this should be a part of Apache ORC 2.0.0 -- 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]
