Question

I am doing profiling of a process.
I have to profile cpu time,I/O blocking time .. and # of cache misses.
But I don’t know how to get cache misses.
I am analysing kernel source code, but I don’t know how to do. I know where source code about run queue is.
How can I get number of cache misses of a process?
I think it may be specific or technical question.
So, If you hesitate answering directly, please give me some hints or recommend book about how to get number of caches misses.
Answering directly is BEST.
Thank you in advance.

Answer 1

perf, cachegrind, oprofile, PTU, CodeAnalyst, and Zoom are a few options

perf stat \
  --repeat 10 \
  -e cycles:u \
  -e instructions:u \
  -e l1-dcache-loads:u \
  -e l1-dcache-load-misses:u \
  -e l1-icache-loads:u \
  -e l1-icache-load-misses:u \
  -e llc-loads:u \
  -e llc-load-misses:u \
  a.out

perf options: https://perf.wiki.kernel.org/articles/t/u/t/Tutorial.html