gperftools VS tracy

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

> First, this isn't really true. You might typically have a window, a container, a layout object and then your gui components.

Any non-trivial UI will include many complicated workflows and layouts. "GUI components" themselves will often be combinations of other, more primitive, GUI components.

> Second you don't need nested calls, you just add one component to another.

You're just describing currying here (function application or nesting hierarchies are the same thing), and both are equally annoying when building interfaces.

> Why would that be true?

Because you will want certain things to be reusable, it's a pretty common pattern.

> This is a bizarre way to make a GUI let alone thinking it's necessary. Where is this idea coming from?

It's a pretty common pattern for building GUIs. Take a look at tracy[1], built using ImGUI. All the different components are split up in their own file, I'm not sure what the alternative would be, like a 100,000-line "master UI" file? Seems like a much worse idea. Looking at the tracy code, it's very well-written, but also super weird to follow. For example, color defaults seem to be located in header files[2]. I mean, yuck.

[1] https://github.com/wolfpld/tracy/tree/master/profiler/src/pr...

[2] https://github.com/wolfpld/tracy/blob/master/profiler/src/pr...

While it doesn't capture every syscall, you can get pretty far with the (seemingly little known) Endpoint Security Framework: https://developer.apple.com/documentation/endpointsecurity

I cobbled together a little tool at my previous job that would capture a full trace of all process fork+exec and file opens, which would then present all of these events in the usual tracing UI (like you'd get when view a trace of a single program with Tracy[1] or Perfetto[2]).

We had a massive monorepo built with bazel and a heap of shell, and it wasn't clear which part of our code base was responsible for generating some mis-generated file. This tool gave me the whole inter-process call stack, complete with arguments and environment variables, letting me quickly find where and how to fix the problem.

It's such a nice tool to have that it kinda blows my mind that no one has openly published anything like it. By leveraging eBPF on Linux, the same UI could be used on both macOS and Linux. If I had more time and energy, I'd do it myself.

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

[2]: https://perfetto.dev/

https://github.com/wolfpld/tracy/issues/887

MSVC changed the mutex constructor to constexpr, breaking binary backward compatibility. They say WONTFIX, you must use the latest MSVCRT with the latest MSVC. But I have the latest MSVCRT installed? Whatever - a workaround was pushed to master yesterday.

I consider Tracy the state of the art for profiling C++ applications. It’s straightforward to integrate, toggle, gather data, analyze, and respond. It’s also open source, but rivals any product you’d have to pay for:

https://github.com/wolfpld/tracy

For C++ applications, nothing beats Tracy’s flame graphs in value per dollar. We are using it at Adobe with great effect. It can handle mutex lock contention, runtime values and notes, arbitrary value graphs, and more. Highly recommended: https://github.com/wolfpld/tracy

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.