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 `strtol` 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
8357de88aa35ee998fefe321ee6dae9eb4993fa6), and one with
[JDK-8378559](https://bugs.openjdk.org/browse/JDK-8378559) reverted ("legacy",
revert commit on top of 8357de88aa35ee998fefe321ee6dae9eb4993fa6). 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 38.442 ±
0.016 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 45.425 ±
1.826 ns/op
**Legacy:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 39.224 ±
0.789 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 41.011 ±
0.058 ns/op
## Linux AArch64
**Current:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 45.396 ±
0.185 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 56.116 ±
0.463 ns/op
**Legacy:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 44.859 ±
0.183 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 51.721 ±
0.153 ns/op
## macOS x64
**Current:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 41.388 ±
0.547 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 46.102 ±
0.208 ns/op
**Legacy:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 40.929 ±
0.138 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 43.938 ±
0.385 ns/op
## macOS AArch64
**Current:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 16.892 ±
0.008 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 21.933 ±
0.016 ns/op
**Legacy:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 16.894 ±
0.008 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 19.083 ±
0.009 ns/op
## Windows x64
**Current:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 39.711 ±
0.031 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 63.534 ±
0.208 ns/op
**Legacy:**
Benchmark Mode Cnt Score
Error Units
CaptureCallStateOverheadBench.doNotUseCaptureCallState avgt 30 40.532 ±
0.544 ns/op
CaptureCallStateOverheadBench.useCaptureCallState avgt 30 50.759 ±
0.275 ns/op
---------
- [x] I confirm that I make this contribution in accordance with the [OpenJDK
Interim AI Policy](https://openjdk.org/legal/ai).
-------------
Commit messages:
- Different long sizes on different platforms.
- Use C standard library for the benchmark instead.
- Benchmark to measure call state capturing overhead.
Changes: https://git.openjdk.org/jdk/pull/30719/files
Webrev: https://webrevs.openjdk.org/?repo=jdk&pr=30719&range=00
Issue: https://bugs.openjdk.org/browse/JDK-8379630
Stats: 126 lines in 1 file changed: 126 ins; 0 del; 0 mod
Patch: https://git.openjdk.org/jdk/pull/30719.diff
Fetch: git fetch https://git.openjdk.org/jdk.git pull/30719/head:pull/30719
PR: https://git.openjdk.org/jdk/pull/30719
