jmh VS async-profiler

JMH for benchmarks

I would recommend using JMH instead.

Reflection is probably very roughly between 10 and 1000 times slower. Why don't you measure it yourself using JMH?

Aleksey Shipilev is another such leader, whom is especially knowledgeable about the internals of the JVM. His writings are invaluable. He is (was) the lead of the Java microbenchmark framework (JMH} which is how one would write small performance experiments in Java, and learn what really makes a difference or now.

In the last episode we implemented a parallelMap operation using streams, raw threads, a threadpool with futures, and coroutines. At first glance the raw threads was quickest, followed by futures, coroutines and then streams. In this, part 56 of an exploration of where a Test Driven Development implementation of the Gilded Rose stock control system might take us in Kotlin, we investigate the performance of the different functions further, in particular digging down into why coroutines seem to be slow and finding a way to speed them up. We also find a way to use a particular ForkJoinPool to run the streams code, making it as fast as the others (bar the raw threads). Frankly we only use very rough benchmarks here, with no statistical testing except 'it looks like'. That's OK for gross differences, but is highly suspect when deciding which of two similarly performant approaches is faster. For that check out JMH and you could watch my video from KotlinConf 2017

A few months ago, we started to use JMH in our project to test and find performance issues. The tool provides multiple modes and profilers, and we found this useful for our purposes.

We'll use async-profiler and flame graphs for profiling. To simplify the process, we'll run the code using JBang.

JIT'ed code is sadly poorly supported, but LLVM has had great hooks for noting each method that is produced and its address. So you can build a simple mixed-mode unwinder, pretty easily, but mostly in process.

I think Intel's DNN things dump their info out to some common file that perf can read instead, but because the *kernels* themselves reuse rbp throughout oneDNN, it's totally useless.

Finally, can any JVM folks explain this claim about DWARF info from the article:

> Doesn't exist for JIT'd runtimes like the Java JVM

that just sounds surprising to me. Is it off by default or literally not available? (Google searches have mostly pointed to people wanting to include the JNI/C side of a JVM stack, like https://github.com/async-profiler/async-profiler/issues/215).

debugging native calls in itself is also painful. I have switched to using async-profiler (https://github.com/async-profiler/async-profiler) instead of JFR for most of my usecases.

A. it tracks native calls by default

https://github.com/async-profiler/async-profiler#flame-graph...

Ok, Windows is not supported. But IntelliJ made a fork which works on Windows.

Hi, today I used async-profiler to check the CPU usage of my Spring Boot app (just a normal backend) in production. Surprisingly, Lettuce (Redis) + Mybatis (MySQL) take up most of the CPU time. I am not talking about wall time here, but CPU time, since I know database requests need to wait for milliseconds and thus wall time will be very long. Therefore, I wonder:

You can use async-profiler to see what is happening under the hood.

I have used visual vm quite a bit. https://github.com/async-profiler/async-profiler is also amazing... Throw the binary on the system and fire it up. It also profiles down into native code as well if you do that kind of thing.