RFR: 8275728: Add simple Producer/Consumer microbenchmark for Thread.onSpinWait
Evgeny Astigeevich
duke at openjdk.java.net
Wed Nov 10 18:16:04 UTC 2021
This is a microbenchmarks to demonstrate `Thread.onSpinWait` can be used to avoid heavy locks.
The microbenchmark differs from [Gil's original benchmark](https://github.com/giltene/GilExamples/tree/master/SpinWaitTest) and [Dmitry's variations](http://cr.openjdk.java.net/~dchuyko/8186670/yield/spinwait.html). Those benchmarks produce/consume data by incrementing a volatile counter. The latency of such operations is almost zero. They also don't use heavy locks. According to [Gil's SpinWaitTest.java](https://github.com/giltene/GilExamples/blob/master/SpinWaitTest/src/main/java/SpinWaitTest.java):
> This test can be used to measure and document the impact of Runtime.onSpinWait() behavior
> on thread-to-thread communication latencies. E.g. when the two threads are pinned to
> the two hardware threads of a shared x86 core (with a shared L1), this test will
> demonstrate an estimate the best case thread-to-thread latencies possible on the
> platform
Gil's microbenchmark targets SMT cases (x86 hyperthreading). As not all CPUs support SMT, the microbenchmarks cannot demonstrate benefits of `Thread.onSpinWait`. It is actually opposite. They show `Thread.onSpinWait` has negative impact on performance.
The microbenchmark from PR uses `BigInteger` to have 100 - 200 ns latencies for producing/consuming data. These latencies can cause either a producer or a consumer to wait each another. Waiting is implemented with `Object.wait`/`Object.notify` which are heavy. `Thread.onSpinWait` can be used in a spin loop to avoid them.
**ARM64 results**:
- No spin loop
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 0 avgt 75 1520.448 ± 40.507 us/op
- No `Thread.onSpinWait` intrinsic
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 125 avgt 75 1580.756 ± 47.501 us/op
- `ISB`-based `Thread.onSpinWait` intrinsic
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 125 avgt 75 617.454 ± 174.431 us/op
**X86_64 results**:
- No spin loop
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 125 avgt 75 1417.944 ± 1.691 us/op
- No `Thread.onSpinWait` intrinsic
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 125 avgt 75 1410.987 ± 2.093 us/op
- `PAUSE`-based `Thread.onSpinWait` intrinsic
Benchmark (maxNum) (spinNum) Mode Cnt Score Error Units
ThreadOnSpinWaitProducerConsumer.trial 100 125 avgt 75 217.054 ± 1.283 us/op
-------------
Commit messages:
- 8275728: Add simple Producer/Consumer microbenchmark for Thread.onSpinWait
Changes: https://git.openjdk.java.net/jdk/pull/6338/files
Webrev: https://webrevs.openjdk.java.net/?repo=jdk&pr=6338&range=00
Issue: https://bugs.openjdk.java.net/browse/JDK-8275728
Stats: 204 lines in 1 file changed: 204 ins; 0 del; 0 mod
Patch: https://git.openjdk.java.net/jdk/pull/6338.diff
Fetch: git fetch https://git.openjdk.java.net/jdk pull/6338/head:pull/6338
PR: https://git.openjdk.java.net/jdk/pull/6338
More information about the core-libs-dev
mailing list