1

I'm trying to profile a large multi-threaded Make-based system. I recently found GNU remake and was able to use it as a drop-in replacement for gmake.

Since my system is multi-threaded and also has many processes, remake generated a large amount of data ~30K callgrind files(10GB). I tried using kcachegrind to visualize the data, but it can load a maximum of 499 files which doesn't come close to the amount of data I have.

Are there any tools for visualizing profiling data of this magnitude?

Other tools I tried: gprof2dot

Another idea I had was to stitch multiple callgrind files together. But I didn't find any tools for this as well

Veena
  • 29
  • 2
  • Just a random thought: the only problem that I see that is worth investigating is if there are many idle CPUs sitting around and doing nothing. Otherwise, at least in my limited experience, the build time is completely determined by the compiler, not `make` itself. What are you trying to achieve? – Vroomfondel Jan 20 '23 at 09:49

0 Answers0