RE: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Liang, Kan
> On Wed, Nov 05, 2014 at 04:22:09PM +, Liang, Kan wrote: > > > > >> > > > > > > So if I take all except 11,13,16,17 but instead do something like > > > the below, everything will work just fine, right? > > > > > > Or am I missing something? > > > > > > > Yes, it should work. Then LBR

Re: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Peter Zijlstra
On Wed, Nov 05, 2014 at 04:22:09PM +, Liang, Kan wrote: > > >> > > > > So if I take all except 11,13,16,17 but instead do something like the below, > > everything will work just fine, right? > > > > Or am I missing something? > > > > Yes, it should work. Then LBR callstack will rely on

RE: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Liang, Kan
>> > > So if I take all except 11,13,16,17 but instead do something like the below, > everything will work just fine, right? > > Or am I missing something? > Yes, it should work. Then LBR callstack will rely on user to enable it. But user never get the LBR callstack data if it's available.

Re: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Peter Zijlstra
So if I take all except 11,13,16,17 but instead do something like the below, everything will work just fine, right? Or am I missing something? --- arch/x86/kernel/cpu/perf_event.h |8 arch/x86/kernel/cpu/perf_event_intel_lbr.c |8

Re: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Peter Zijlstra
So if I take all except 11,13,16,17 but instead do something like the below, everything will work just fine, right? Or am I missing something? --- arch/x86/kernel/cpu/perf_event.h |8 arch/x86/kernel/cpu/perf_event_intel_lbr.c |8

RE: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Liang, Kan
So if I take all except 11,13,16,17 but instead do something like the below, everything will work just fine, right? Or am I missing something? Yes, it should work. Then LBR callstack will rely on user to enable it. But user never get the LBR callstack data if it's available. I'm

Re: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Peter Zijlstra
On Wed, Nov 05, 2014 at 04:22:09PM +, Liang, Kan wrote: So if I take all except 11,13,16,17 but instead do something like the below, everything will work just fine, right? Or am I missing something? Yes, it should work. Then LBR callstack will rely on user to enable it.

RE: [PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-05 Thread Liang, Kan
On Wed, Nov 05, 2014 at 04:22:09PM +, Liang, Kan wrote: So if I take all except 11,13,16,17 but instead do something like the below, everything will work just fine, right? Or am I missing something? Yes, it should work. Then LBR callstack will rely on user to

[PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-04 Thread Kan Liang
For many profiling tasks we need the callgraph. For example we often need to see the caller of a lock or the caller of a memcpy or other library function to actually tune the program. Frame pointer unwinding is efficient and works well. But frame pointers are off by default on 64bit code (and on

[PATCH V7 00/17] perf, x86: Haswell LBR call stack support

2014-11-04 Thread Kan Liang
For many profiling tasks we need the callgraph. For example we often need to see the caller of a lock or the caller of a memcpy or other library function to actually tune the program. Frame pointer unwinding is efficient and works well. But frame pointers are off by default on 64bit code (and on