81cba796e6
I've always been confused by the strange behavior that I saw when working on #57304. Specifically, I saw switching from a bimorphic invocation to a monomorphic invocation to give us a 7%-15% performance bump. This felt *bonkers* to me. And, it also made me wonder whether it'd be worth looking into doing it everywhere. It turns out that, no, it isn't needed everywhere. This benchmark shows that a bimorphic invocation like: ``` LongKeyedBucketOrds ords = new LongKeyedBucketOrds.ForSingle(); ords.add(0, 0); <------ this line ``` is 19% slower than a monomorphic invocation like: ``` LongKeyedBucketOrds.ForSingle ords = new LongKeyedBucketOrds.ForSingle(); ords.add(0, 0); <------ this line ``` But *only* when the reference is mutable. In the example above, if `ords` is never changed then both perform the same. But if the `ords` reference is assigned twice then we start to see the difference: ``` immutable bimorphic avgt 10 6.468 ± 0.045 ns/op immutable monomorphic avgt 10 6.756 ± 0.026 ns/op mutable bimorphic avgt 10 9.741 ± 0.073 ns/op mutable monomorphic avgt 10 8.190 ± 0.016 ns/op ``` So the conclusion from all this is that we've done the right thing: `auto_date_histogram` is the only aggregation in which `ords` isn't final and it is the only aggregation that forces monomorphic invocations. All other aggregations use an immutable bimorphic invocation. Which is fine. Relates to #56487 |
||
|---|---|---|
| .. | ||
| src/main | ||
| README.md | ||
| build.gradle | ||
README.md
Elasticsearch Microbenchmark Suite
This directory contains the microbenchmark suite of Elasticsearch. It relies on JMH.
Purpose
We do not want to microbenchmark everything but the kitchen sink and should typically rely on our macrobenchmarks with Rally. Microbenchmarks are intended to spot performance regressions in performance-critical components. The microbenchmark suite is also handy for ad-hoc microbenchmarks but please remove them again before merging your PR.
Getting Started
Just run gradlew -p benchmarks run from the project root
directory. It will build all microbenchmarks, execute them and print
the result.
Running Microbenchmarks
Running via an IDE is not supported as the results are meaningless because we have no control over the JVM running the benchmarks.
If you want to run a specific benchmark class like, say,
MemoryStatsBenchmark, you can use --args:
gradlew -p benchmarks run --args ' MemoryStatsBenchmark'
Everything in the ' gets sent on the command line to JMH. The leading
inside the 's is important. Without it parameters are sometimes sent to
gradle.
Adding Microbenchmarks
Before adding a new microbenchmark, make yourself familiar with the JMH API. You can check our existing microbenchmarks and also the JMH samples.
In contrast to tests, the actual name of the benchmark class is not relevant to JMH. However, stick to the naming convention and
end the class name of a benchmark with Benchmark. To have JMH execute a benchmark, annotate the respective methods with @Benchmark.
Tips and Best Practices
To get realistic results, you should exercise care when running benchmarks. Here are a few tips:
Do
- Ensure that the system executing your microbenchmarks has as little load as possible. Shutdown every process that can cause unnecessary
runtime jitter. Watch the
Errorcolumn in the benchmark results to see the run-to-run variance. - Ensure to run enough warmup iterations to get the benchmark into a stable state. If you are unsure, don't change the defaults.
- Avoid CPU migrations by pinning your benchmarks to specific CPU cores. On Linux you can use
taskset. - Fix the CPU frequency to avoid Turbo Boost from kicking in and skewing your results. On Linux you can use
cpufreq-setand theperformanceCPU governor. - Vary the problem input size with
@Param. - Use the integrated profilers in JMH to dig deeper if benchmark results to not match your hypotheses:
- Add
-prof gcto the options to check whether the garbage collector runs during a microbenchmarks and skews your results. If so, try to force a GC between runs (-gc true) but watch out for the caveats. - Add
-prof perfor-prof perfasm(both only available on Linux) to see hotspots.
- Add
- Have your benchmarks peer-reviewed.
Don't
- Blindly believe the numbers that your microbenchmark produces but verify them by measuring e.g. with
-prof perfasm. - Run more threads than your number of CPU cores (in case you run multi-threaded microbenchmarks).
- Look only at the
Scorecolumn and ignoreError. Instead take countermeasures to keepErrorlow / variance explainable.