On Wed, Oct 21, 2015 at 12:23 PM, Arnaldo Carvalho de Melo <arnaldo.m...@gmail.com> wrote: > Em Wed, Oct 21, 2015 at 11:28:54AM -0700, Brendan Gregg escreveu: >> On Tue, Oct 20, 2015 at 7:21 PM, Chandler Carruth <chandl...@gmail.com> >> wrote: >> > Since Arnaldo asked, I thought I should actually try to respond >> > specifically >> > to the question of why I favor the 'caller' view as the default. >> > >> > On Tue, Oct 20, 2015 at 3:06 AM Arnaldo Carvalho de Melo >> > <arnaldo.m...@gmail.com> wrote: >> >> >> >> > IMHO changing that order is not a good idea. Unless many users >> >> > complained >> >> > about it. >> >> >> >> Perhaps there are not that many users of callchains because the default >> >> is not what they're used to see? >> >> >> >> Motivation for the change came from a video from Chandler, that >> >> resurfaced the callchain default issue, Chandler? >> > >> > >> > So, first and foremost, thanks for fixing some of my gripes about the >> > usability of the perf tool, I'm super excited about the changes you're >> > making, even if this one isn't among them. >> > >> > I think the default of caller vs. callee is probably the hardest judgement >> > call to make about the right defaults. I can see it going both ways. >> > >> > When profiling my *system*, or a diverse group of programs or tasks, I >> > often >> > find callee useful. Were I a kernel developer, I suspect callee would be >> > *dramatically* more common than caller. >> > >> > For me, what makes the caller view much more frequently desired is that I'm >> > usually profiling a fairly isolated application, or benchmark for an >> > isolated library. While I always start off with some more system-level >> > performance problem, I rarely need a detailed profile to get a reasonable >> > idea of what subsystem to stare at, and then I spend days looking at a >> > relatively isolated reproduction. >> > >> > Anyways, for profiling user-land applications, I suspect from my >> > conversations with users that "caller" is the more common expectation. >> [...] >> >> I would have said callee is the more common expectation, certainly for >> system profilers. I quickly checked various tools to see what their >> defaults are: >> >> callee: >> >> gdb >> lldb >> pstack >> jstack >> perf >> stap >> ktap >> dtrace >> kernel oops message >> jvm crash >> node.js/v8 crash >> >> caller: >> >> python traceback > > sysprof -> http://sysprof.com/screen-shot-4.png
Right, GUIs with tree views do this. I've thought about it more, and how does the following 3 changes sound?: 1. perf top: change to caller default - Since it's dumping a tree view, this ordering is intuitive, and this is the convention from other interactive GUIs that do tree views. Optionally add a hotkey to change it live. Could also add -G from perf report (--inverted) to easily call the old behavior. 2. perf report: change to caller default - I'd like to leave it callee, but as Ingo said, "top" and "report" should be unified. I can always run -G, or -g, or edit ~/.perfconfig. 3. perf script: leave callee default. - Since it's dumping a full stack, that's the convention with other tools that dump full stacks (as I listed), and I think that's useful ordering anyway when reading a full stack: show me event context first, followed by history next. "perf script" should have -G and -g added, to adjust behavior. I'd also like different UIs from perf report (folded and json), but that's a different thread. :) Brendan -- 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/
