On Mon, 5 Oct 2015 21:26:39 +0200
Jesper Dangaard Brouer <brouer@xxxxxxxxxx> wrote:
> My only problem left, is I want a perf measurement that pinpoint these
> kind of spots. The difference in L1-icache-load-misses were significant
> (1,278,276 vs 2,719,158). I tried to somehow perf record this with
> different perf events without being able to pinpoint the location (even
> though I know the spot now). Even tried Andi's ocperf.py... maybe he
> will know what event I should try?
Using: 'ocperf.py -e icache_misses' and looking closer at the perf
annotate and considering "skid" I think I can see the icache misses
happening in the end of the function, due to the UD2 inst.
Annotation of kmem_cache_free_bulk (last/end of func):
│17b: test %r12,%r12
│ ↑ jne 2e
│184: pop %rbx
│ pop %r12
│ pop %r13
│ pop %r14
│ pop %r15
│ pop %rbp
│ ← retq
8.57 │18f: mov 0x30(%rdx),%rdx
5.71 │ ↑ jmp 116
│195: ud2
2.86 │197: mov %rdi,%rsi
│ mov %r11d,%r8d
│ mov %r10,%rcx
│ mov %rbx,%rdx
│ mov %r15,%rdi
│ → callq __slab_free
│ ↑ jmp 17b
2.86 │1ad: mov 0x30(%rdi),%rdi
│ ↑ jmpq 99
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href