Re: Re: [PATCH perf/core v3 3/3] [BUGFIX] perf probe: Show usage even if the last event is skipped

[Arnaldo Carvalho de Melo]

Em Wed, Jun 17, 2015 at 11:58:18PM +0900, Masami Hiramatsu escreveu:
> On 2015/06/17 14:31, Masami Hiramatsu wrote:
> >> > I.e. the only problem I found was this:
> >> > 
> >> > [root@zoo ~]# time perf probe -l > /dev/null
> >> > 
> >> > real	0m15.408s
> >> > user	0m14.892s
> >> > sys	0m0.534s
> >> > [root@zoo ~]# 
> >> > [root@zoo ~]# perf stat perf probe -l > /dev/null
> >> > 
> >> >  Performance counter stats for 'perf probe -l':
> >> > 
> >> >       15256.588897      task-clock (msec)         #    1.001 CPUs utilized          
> >> >                116      context-switches          #    0.008 K/sec                  
> >> >                  4      cpu-migrations            #    0.000 K/sec                  
> >> >            230,720      page-faults               #    0.015 M/sec                  
> >> >     47,830,405,530      cycles                    #    3.135 GHz                    
> >> >     43,974,134,505      stalled-cycles-frontend   #   91.94% frontend cycles idle   
> >> >    <not supported>      stalled-cycles-backend   
> >> >     11,540,587,038      instructions              #    0.24  insns per cycle        
> >> >                                                   #    3.81  stalled cycles per insn
> >> >      2,807,769,592      branches                  #  184.037 M/sec                  
> >> >         20,087,075      branch-misses             #    0.72% of all branches        
> >> > 
> >> >       15.240796324 seconds time elapsed
> >> > 
> >> > [root@zoo ~]#
> >> > 
> >> > Can you check why it takes so long and check the need for this patch?
> > It is because perf probe -l is not optimized to show a lot of probes yet.
> > It initializes and loads debuginfo for each probe. I guess we can reuse
> > debuginfo among them. let me try...
> > 
> 
> OK, I've ensured that's true,
> 
> [root@localhost perf]# time  ./perf probe -l &> /dev/null
> 
> real    0m25.376s
> user    0m24.381s
> sys     0m1.012s
> 
> [root@localhost perf]# time  ./perf probe --no-dwarf -l &> /dev/null
> 
> real    0m0.059s
> user    0m0.039s
> sys     0m0.020s
> 
> (Note that --no-dwarf is my local patch for debugging, not sending yet)
> 
> So, the problem is on the debuginfo processing. I've also fixed that
> by caching the last used debuginfo. :)
> 
> [root@localhost perf]#  time  ./perf probe -l &> /dev/null
> 
> real    0m0.161s
> user    0m0.136s
> sys     0m0.025s
> 
> I'll send the patch asap.

Thanks! I really need to go thru builtin-probe.c looking at how it uses
the symbol functions, to see what I can change in symbol*.[ch] to help
it with its needs.

Till then tho, please send the patch, that is a really great speedup! :-)

- Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/