Messages in this thread | | | Date | Tue, 19 May 2015 17:18:54 -0300 | From | Arnaldo Carvalho de Melo <> | Subject | Re: [PATCH 35/40] perf record: Synthesize COMM event for a command line workload |
| |
Em Tue, May 19, 2015 at 09:49:03PM +0200, Jiri Olsa escreveu: > On Wed, May 20, 2015 at 12:12:45AM +0900, Namhyung Kim wrote: > > SNIP > > > > > > > > > > > This looks reasonable, but I think it probably needs to be done > > > > > somewhere in perf_evlist__prepare_workload() or > > > > > perf_evlist__start_workload(), as this affects other tools as well, like > > > > > 'top', 'trace' and any other that may want to do this start-workload use > > > > > case. > > > > > > > > Hmm.. I need to look at this again as it only affects on processing > > > > indexed data files which used to have a separate missing threads tree. > > > > > > Humm, you're thinking about where you managed to reproduce the problem, > > > I am thinking outside indexing, etc, i.e. by definition we either enable > > > the event before we fork, so that we get the PERF_RECORD_FORK/COMM or we > > > synthesize it either from /proc or directly (preferred) if we decide to > > > do it after the fork/exec, right? > > > > But as I said before, later COMM event will override thread->comm to a > > proper string as long as it can find a matching thread. So I think it > > has no problem in the current code.
> I can see the issue in the current script code and the patch cured it ;-)
Exactly, this is my point, this is not something new :-)
- Arnaldo
> before: > > [jolsa@krava perf]$ ./perf record -o - true | ./perf script > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 0.000 MB - ] > :29236 29236 350869.479255: 1 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > :29236 29236 350869.479260: 1 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > :29236 29236 350869.479261: 7 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > :29236 29236 350869.479263: 122 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > :29236 29236 350869.479264: 2303 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > :29236 29236 350869.479266: 49582 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > true 29236 350869.479283: 1041734 cycles: ffffffff81190a4a perf_output_begin ([kernel.kallsyms]) > > after: > > [jolsa@krava perf]$ ./perf record -o - true | ./perf script > [ perf record: Woken up 1 times to write data ] > [ perf record: Captured and wrote 0.000 MB - ] > perf 28041 350801.438466: 1 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > perf 28041 350801.438471: 1 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > perf 28041 350801.438472: 7 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > perf 28041 350801.438473: 140 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > perf 28041 350801.438475: 3721 cycles: ffffffff8105e8aa native_write_msr_safe ([kernel.kallsy > perf 28041 350801.438476: 94744 cycles: ffffffff8118e270 perf_event_comm ([kernel.kallsyms]) > true 28041 350801.438508: 1604677 cycles: ffffffff811d0781 do_mmap_pgoff ([kernel.kallsyms]) > > jirka
| |