tracy VS gperftools

i don't really think there is _anything_ that comes even close to tracy https://github.com/wolfpld/tracy.

on top of this, given google's penchant for dumping projects aka abandonware, this would be an easy pass.

The RemedyBG debugger (https://remedybg.handmade.network/) and the Tracy profiler (https://github.com/wolfpld/tracy) both use Dear ImGui and so far I've only read high praise from people who used those tools compared to the 'established' alternatives.

For tools like this, programmers are also just "normal users", and from the developer side, I'm sure they evaluated various alternatives with all their pros and cons before settling for Dear ImGui.

Not the person you asked, but generally you might want to look at "frame-based" profilers. These are typically used in video games, but the concept is general, and can apply to other applications. The "frame" could also be something like a request or transaction being processed. I like Tracy[1], myself.

Another latency metric that you'll see, often w/respect to web apps and microservices is "P99" and similar. This is the amount of time in which 99% of requests get their response. For a higher percentile, you get a better idea of worst-case performance.

[1] https://github.com/wolfpld/tracy

I've not actually used Superluminal, but I use Tracy for similar reasons. It's free though (and, importantly, open source).

For profiling, you can check tracy.

You could try Tracy

There is no such thing as overengineering in fun projects, so I've also adopted Tracy as profiling solution. Works quite nice and gonna save me plenty of times in the future debugging performance spikes on badly optimized math heavy operations.

I know about tools such as tracing, jaeger or tracy. While having a complete tracing could be a potential solution, these tools don't work with no_std.

For profiling you are right clang has no -pg that works. But there are options, since clang supports PGO the fprofile flags could be what you need. they will generated a profraw file for you. There is also gperf tools which work for more than just linux. https://github.com/gperftools/gperftools

Because we couldn't identify the issue using the results we got from Callgrind, we reached for another profiler, gperftools. It's a sampling profiler and therefor it has a smaller impact on the application's performance in exchange for less accurate call statistics. After filtering out the unimportant parts and visualizing the rest with pprof, it was evident that something strange was happening with the send function. It took only 71 milliseconds with the previous implementation and more than 900 milliseconds with the new implementation of our Bolt server. It was very suspicious, but based on Callgrind, its cost was almost the same as before. We were confused as the two results seemed to conflict with each other.

gprftools (https://github.com/gperftools/gperftools) can be easily plugged in using LD_PRELOAD and signal, and has nice go implemented visualization tool https://github.com/google/pprof.

Google's tcmalloc