Em Fri, Jun 26, 2015 at 04:47:39PM +0300, Adrian Hunter escreveu: > On 26/06/15 16:41, Arnaldo Carvalho de Melo wrote: > >> Another thing, the intel_bts implementation does not support > >> "instructions" samples because there is no timing information to > >> use to create periodic samples. But callchains are added only > >> to "instructions" samples so there are no callchains in 'perf report' > >> for intel_bts. The call information is still available for > > > > Humm, so IOW, what you say is that we should refuse to run 'record' when > > asking for callchains and intel_bts? > > 'record' can record other events at the same time which can have callchains. > e.g. > > perf record -g --per-thread -e intel_bts//u,branch-misses:u ls
Right, what I was trying to say is that there are combinations where one can ask for a callchain in record, it will act as if it did what was asked for but then when report runs, no callchain will be available. I guess we can check for that situation and warn the user. - Arnaldo -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
