snazy opened a new pull request, #4071: URL: https://github.com/apache/polaris/pull/4071
The current implementation of reusing scratch `ByteBuffer`s is correct, but can become inefficient over time. It would also be immediately inefficient with virtual threads (which we're not using though). This change addresses the "pref regression over runtime" and the virtual-thread concern at the same time, while keeping the performance on-par with the current implementation. This has been validated using the existing JMH benchmarks running with JMH's `gc` and `prov` profiles. The remaining differences are rather noise or really marginal performance footprint differences. -- 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]
