RFR: 8276054: JMH benchmarks for Fences [v3]

[Claes Redestad]

On Thu, 28 Oct 2021 07:50:55 GMT, Aleksey Shipilev <shade at openjdk.org> wrote:

>> While working on JDK-8252990, I realized there are no microbenchmarks for Fences. I would be good to add some. While technically we can benchmark `Unsafe` directly, I instead chose to use the public API, `VarHandles`, as this captures the real-world uses too.
>> 
>> Sample output for `make test TEST=micro:vm.fences` on `x86_64`:
>> 
>> 
>> Benchmark                      Mode  Cnt  Score    Error  Units
>> Multiple.acquire               avgt    9  0.408 ±  0.005  ns/op
>> Multiple.full                  avgt    9  4.694 ±  0.003  ns/op
>> Multiple.plain                 avgt    9  0.407 ±  0.004  ns/op
>> Multiple.release               avgt    9  0.407 ±  0.003  ns/op
>> Multiple.storeStore            avgt    9  0.409 ±  0.006  ns/op
>> MultipleWithLoads.acquire      avgt    9  4.600 ±  0.002  ns/op
>> MultipleWithLoads.full         avgt    9  8.322 ±  0.003  ns/op
>> MultipleWithLoads.plain        avgt    9  4.328 ±  0.001  ns/op
>> MultipleWithLoads.release      avgt    9  4.600 ±  0.002  ns/op
>> MultipleWithLoads.storeStore   avgt    9  4.600 ±  0.002  ns/op
>> MultipleWithStores.acquire     avgt    9  0.812 ±  0.001  ns/op
>> MultipleWithStores.full        avgt    9  5.291 ±  0.001  ns/op
>> MultipleWithStores.plain       avgt    9  0.812 ±  0.001  ns/op
>> MultipleWithStores.release     avgt    9  0.812 ±  0.001  ns/op
>> MultipleWithStores.storeStore  avgt    9  0.812 ±  0.001  ns/op
>> SafePublishing.plain           avgt    9  6.378 ±  0.011  ns/op
>> SafePublishing.release         avgt    9  6.368 ±  0.010  ns/op
>> SafePublishing.storeStore      avgt    9  6.376 ±  0.013  ns/op
>> Single.acquireFence            avgt    9  0.410 ±  0.009  ns/op
>> Single.fullFence               avgt    9  4.689 ±  0.002  ns/op
>> Single.plain                   avgt    9  0.409 ±  0.010  ns/op
>> Single.releaseFence            avgt    9  0.410 ±  0.006  ns/op
>> Single.storeStoreFence         avgt    9  0.410 ±  0.009  ns/op
>
> Aleksey Shipilev has updated the pull request incrementally with two additional commits since the last revision:
> 
>  - Consistent benchmark names: drop excess "Fence"
>  - Add loadLoad tests too

I think the general rule in OpenJDK projects is simply one reviewer approval. I have not seen a need to try and add any special rules. I'm also not even sure where special rules - like those enforced by the hotspot maintainers (two reviewers, 24hr grace time) - are written down.

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

PR: https://git.openjdk.java.net/jdk/pull/6138