On Fri, 2 Jul 2021 06:20:29 GMT, Markus KARG <github.com+1701815+mk...@openjdk.org> wrote:
>> This PR-*draft* is **work in progress** and an invitation to discuss a >> possible solution for issue >> [JDK-8265891](https://bugs.openjdk.java.net/browse/JDK-8265891). It is *not >> yet* intended for a final review. >> >> As proposed in JDK-8265891, this PR provides an implementation for >> `Channels.newInputStream().transferTo()` which provide superior performance >> compared to the current implementation. The changes are: >> * Prevents transfers through the JVM heap as much as possibly by offloading >> to deeper levels via NIO, hence allowing the operating system to optimize >> the transfer. >> * Using more JRE heap in the fallback case when no NIO is possible (still >> only KiBs, hence mostl ynegligible even on SBCs) to better perform on modern >> hardware / fast I/O devides. >> >> Using JMH I have benchmarked both, the original implementation and this >> implementation, and (depending on the used hardware and use case) >> performance change was approx. doubled performance. So this PoC proofs that >> it makes sense to finalize this work and turn it into an actual OpenJDK >> contribution. >> >> I encourage everybody to discuss this draft: >> * Are there valid arguments for *not* doing this change? >> * Is there a *better* way to improve performance of >> `Channels.newInputStream().transferTo()`? >> * How to go on from here: What is missing to get this ready for an actual >> review? > > Markus KARG has refreshed the contents of this pull request, and previous > commits have been removed. The incremental views will show differences > compared to the previous content of the PR. Sorry for the delay. I now have pushed a first draft of the test. IIUC then five implementation have to be tested just for the actualy API, i. e. whether they throws NPE when `out` is `null`, and whether they transfer small, single turn, and multiple turn loads correctly. The tests are taken from `InputStream/TransferTo.java` as you proposed, and I am not using mocking but instead use `Channels.new*` as the existing tests you proposed as a blueprint. I hope I understood your requests and proposals correctly, if not please tell me. The tests pass well and proof that the new implementations work as expected and API-compliant. ------------- PR: https://git.openjdk.java.net/jdk/pull/4263