[lkml]   [2011]   [Apr]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH -tip v3 3/6] perf branch trace: print pid and command
On Fri, Apr 01, 2011 at 11:11:10AM -0600, David Ahern wrote:
> On 04/01/11 09:13, Frederic Weisbecker wrote:
> > On Mon, Mar 28, 2011 at 08:31:23AM -0600, David Ahern wrote:
> >> On 03/28/11 04:34, Akihiro Nagai wrote:
> >>>> from is sample->ip? to is sample->addr? In the above example
> >>>> 0x39d3015260 is the value from sample->addr, 1526f is sample->ip which
> >>>> resolves to _dl_next_ld_env_entry from /lib64/
> >>> Yes.
> >>> In this example, resolved address is only sample->ip (branch from).
> >>> We need the resolved address of sample->addr (branch to) too, because
> >>> both of them are addresses of execution code.
> >>
> >> Ok, now I understand. In that case add conversion of sample->addr to
> >> symbols to perf-script.
> >
> > I agree that we should rather use perf script for branch dumps.
> > Sorry Akihiro, I think we suggested you to create this dedicated
> > perf branch by the past. But then perf script became the vanilla dump
> > tool in the middle and it seems more suitable today.
> >
> > We can still create a perf branch later in order to produce some more
> > advanced post-processing tools. But for sample dumps perf script (which starts
> > to show itself as a misnomer BTW) seems to be the right place.
> perf-dump?

Yeah. We could make it an alias of perf-script.

> >
> > So, in this context, if we have PERF_SAMPLE_ADDR, we are going to always
> > follow the ip with a "=>" and then resolve the address, etc...
> >
> > Yeah it makes sense for this default mode. But what about when we'll want
> > a function graph kind of output? This will require a totally different
> > layout. Also PERF_SAMPLE_ADDR may be used for different context in the
> > future.
> >
> > Perhaps we want a kind of per evsel callback that makes its own
> > interpretation of the pid/tid/dso/sym/etc... options asked by the
> > user?
> The print addr function can take the evsel as an input. It includes the
> event type which can be used to decide what the address means.

Also yeah. But once we'll have the graph output, that may become
a real mess.

> >
> > But well, we can start simple and make and just do the => trick
> > if we have PERF_SAMPLE_ADDR and resolve addr if the user asked
> > the sym. Then when we have the graph output, have these per evsel
> > display callbacks.
> There is another email thread about page faults. The user wants sample
> address resolved to symbols. I was going to look into it next week when
> I get back from vacation.

What we seem to need for that is to bring a pagefault tracepoint. We had
propositions for that in the past, but work on this is in pause mode it

 \ /
  Last update: 2011-04-06 14:17    [W:0.115 / U:1.232 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site