RFR: 8317538: Potential bottleneck in Provider::getService: specjvm2008::crypto.rsa have scalability issue for high vCPU numbers

[Anthony Scarpino]

On Fri, 25 Oct 2024 18:18:16 GMT, Vladimir Ivanov <vaivanov at openjdk.org> wrote:

> This patch remove access to the shared variable to fix scalability issue in the multithread environment. According to testing by the specjvm2008::crypto.rsa the one thread performance reduced for less than 1% while the score for the multithread run increased in ~2x. For the 2 socket system with Xeon 8480+ numbers looks as:
> •	1 thread: 643.15 for original version vs 642.54 for patched one;
> •	224 threads: 22446.19 for original vs 46147.41 for patched.
> The RSABench microbenchmark reports no score changes for the 1 thread (average for all testcases) and 2.4% improvement for the 224 threads.

I have some concerns that removing `previousKey` will cause other benchmarks to suffer because a `SecretKey` instance is generated every time.  Have you tried using ThreadLocal with `previousKey`?  That may allow a similar performance gain, while allowing repeated use of the same key saving object allocations costs.

-------------

PR Comment: https://git.openjdk.org/jdk/pull/21719#issuecomment-2444832234