On Thu, 23 Apr 2026 16:24:53 GMT, Paul Hübner <[email protected]> wrote:
>> Hi all,
>>
>> The Java FF&M API includes functionality to both initialize and read from
>> thread-local data prior to and immediately after downcalls, respectively,
>> through the `Linker.Option::captureCallState` API. This is useful, as an
>> example, when setting or capturing `errno` when interfacing with C
>> functions. However, using this linker option introduces some invocation
>> overhead at runtime.
>>
>> This RFE introduces a JMH microbenchmark which quantifies this overhead. A
>> simple downcall to `strtoll` is measured with and without call state
>> capturing.
>>
>> Testing: GHA for sanity testing.
>>
>> # Benchmarking Results
>>
>> I have executed this benchmark on Oracle-supported platforms, the results
>> can be found below. For each platform, I've done two trials corresponding to
>> different JDKs: one being the current HEAD ("current", based on
>> 28506ca7a8f03cddb0903e4f58b4f38742f15606), and one with
>> [JDK-8378559](https://bugs.openjdk.org/browse/JDK-8378559) reverted
>> ("legacy", revert commit on top of
>> 28506ca7a8f03cddb0903e4f58b4f38742f15606). This one-off experiment is
>> insightful since [JDK-8378559](https://bugs.openjdk.org/browse/JDK-8378559)
>> increased the overhead of downcalls using state capturing by introducing
>> thread-local data initialization. The performance impact of this change was
>> previously unquantified.
>>
>> ## Linux x64
>>
>> **Current:**
>>
>> Benchmark Mode Cnt Score
>> Error Units
>> CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 39.261 ±
>> 0.025 ns/op
>> CaptureCallStateOverheadBench.useCaptureCallState avgt 30 45.539 ±
>> 0.653 ns/op
>>
>>
>> **Legacy:**
>>
>> Benchmark Mode Cnt Score
>> Error Units
>> CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 39.249 ±
>> 0.015 ns/op
>> CaptureCallStateOverheadBench.useCaptureCallState avgt 30 43.887 ±
>> 1.919 ns/op
>>
>>
>> ## Linux AArch64
>>
>> **Current:**
>>
>> Benchmark Mode Cnt Score
>> Error Units
>> CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 47.175 ±
>> 0.067 ns/op
>> CaptureCallStateOverheadBench.useCaptureCallState avgt 30 58.490 ±
>> 0.532 ns/op
>>
>>
>> **Legacy:**
>>
>> Benchmark Mode Cnt Score
>> Error Units
>> CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 47.396 ±
>> 0.217 ns/op
>> CaptureCallStateOverheadBench.useCaptureCall...
>
> Paul Hübner has updated the pull request incrementally with one additional
> commit since the last revision:
>
> Reviewer feedback.
Thanks for the reviews, everyone. As promised, I'll send the email out in a bit.
-------------
PR Comment: https://git.openjdk.org/jdk/pull/30719#issuecomment-4395230806
