Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1642664

Re: [PATCH v2] perf report: fix off-by-one for non-activation frames

Show all headers | View raw

[Multipart message — attachments visible in raw view] - view raw

On Dienstag, 16. Mai 2017 18:17:26 CEST Milian Wolff wrote:
> On Dienstag, 16. Mai 2017 16:38:29 CEST Namhyung Kim wrote:
> > On Tue, May 16, 2017 at 10:59:51AM +0200, Milian Wolff wrote:
> > > As the documentation for dwfl_frame_pc says, frames that
> > > are no activation frames need to have their program counter
> > > decremented by one to properly find the function of the caller.
> > > 
> > > This fixes many cases where perf report currently attributes
> > > the cost to the next line. I.e. I have code like this:
> > > 
> > > ~~~~~~~~~~~~~~~
> > > 
> > >   #include <thread>
> > >   #include <chrono>
> > >   
> > >   using namespace std;
> > >   
> > >   int main()
> > >   {
> > >   
> > >     this_thread::sleep_for(chrono::milliseconds(1000));
> > >     this_thread::sleep_for(chrono::milliseconds(100));
> > >     this_thread::sleep_for(chrono::milliseconds(10));
> > >     
> > >     return 0;
> > >   
> > >   }
> > > 
> > > ~~~~~~~~~~~~~~~
> > 
> > It'd be nice if the test program has a signal frame for verification.
> 
> I have pretty much zero experience about signals. Would it be enough to add
> a signal handler for, say, SIGUSR1 to my test application and then trigger
> a sleep when that signal is delivered? If that should be enough, I'll write
> and test it out.

~~~~~~~~~~~~~~~
#include <thread>
#include <chrono>
#include <signal.h>

using namespace std;

volatile bool run_loop = true;

void my_handler(int signum)
{
    this_thread::sleep_for(chrono::milliseconds(1000));
    this_thread::sleep_for(chrono::milliseconds(100));
    this_thread::sleep_for(chrono::milliseconds(10));
    run_loop = false;
}

int main()
{
    signal(SIGUSR1, my_handler);

    while (run_loop) {}

    return 0;
}
~~~~~~~~~~~~~~~

This does not properly unwind neither before nor after this patch. I only ever 
get:

   100.00%  core.c:0
            |
            ---__schedule core.c:0
               schedule
               do_nanosleep hrtimer.c:0
               hrtimer_nanosleep
               sys_nanosleep
               entry_SYSCALL_64_fastpath .tmp_entry_64.o:0
               __nanosleep_nocancel .:0
               std::this_thread::sleep_for<long, std::ratio<1l, 1000l> > 
thread:323

So... should this work? Please tell me how to test this properly.

Thanks
-- 
Milian Wolff | milian.wolff@kdab.com | Software Engineer
KDAB (Deutschland) GmbH&Co KG, a KDAB Group company
Tel: +49-30-521325470
KDAB - The Qt Experts

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v2] perf report: fix off-by-one for non-activation frames Milian Wolff <milian.wolff@kdab.com> - 2017-05-16 11:10 +0200
  Re: [PATCH v2] perf report: fix off-by-one for non-activation frames Namhyung Kim <namhyung@kernel.org> - 2017-05-16 16:50 +0200
    Re: [PATCH v2] perf report: fix off-by-one for non-activation frames Milian Wolff <milian.wolff@kdab.com> - 2017-05-16 18:20 +0200
      Re: [PATCH v2] perf report: fix off-by-one for non-activation frames Milian Wolff <milian.wolff@kdab.com> - 2017-05-16 18:30 +0200
        Re: [PATCH v2] perf report: fix off-by-one for non-activation frames Namhyung Kim <namhyung@kernel.org> - 2017-05-17 07:20 +0200
          Re: [PATCH v2] perf report: fix off-by-one for non-activation frames Milian Wolff <milian.wolff@kdab.com> - 2017-05-18 10:20 +0200

csiph-web