[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20200625112122.v3gcd7xto7y4ste6@mail.google.com>
Date: Thu, 25 Jun 2020 19:21:22 +0800
From: Changbin Du <changbin.du@...il.com>
To: Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
Cc: Changbin Du <changbin.du@...il.com>, Jiri Olsa <jolsa@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
Steven Rostedt <rostedt@...dmis.org>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 10/19] perf ftrace: add support for trace option
funcgraph-tail
Hi Arnaldo,
First appologize for so long dealy! Maybe you have forgot the context of this
serias ;)
On Wed, May 20, 2020 at 06:05:09PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Sun, May 10, 2020 at 11:06:19PM +0800, Changbin Du escreveu:
> > This adds an option '--funcgraph-tail' for function graph tracer.
>
> And I think we should make these available in a compact way, as Intel PT
> has, i.e. instead of doing something like:
>
> --function-graph-options nosleep_time,noirqs,no_tail,long_info
>
> We could have:
>
> -G ns,ni,nt,li
>
> To save on typing, or something like that.
>
I just noticed that there is an existing graph tracer option:
--graph-depth <n>
Then our new option would be:
--graph-options depth=<n>,nosleep_time,noirqs,no_tail,long_info
This makes it a little complex to parse such options (need to parse key-vale
pairs).
So can we follow the existing style instead? I mean we can have below options:
-D --graph-depth <n>
-G --graph-funcs <func>
--graph-nosleep-time
--graph-noirqs
--graph-notail
--graph-longinfo
All graph tracer options are prefixed with '--graph-'.
> - Arnaldo
>
> > Signed-off-by: Changbin Du <changbin.du@...il.com>
> > ---
> > tools/perf/builtin-ftrace.c | 20 ++++++++++++++++++++
> > 1 file changed, 20 insertions(+)
> >
> > diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
> > index 20bc14d6c5fb..2ef5d1c4b23c 100644
> > --- a/tools/perf/builtin-ftrace.c
> > +++ b/tools/perf/builtin-ftrace.c
> > @@ -42,6 +42,7 @@ struct perf_ftrace {
> > bool func_stack_trace;
> > bool nosleep_time;
> > bool nofuncgraph_irqs;
> > + bool funcgraph_tail;
> > bool long_info;
> > unsigned tracing_thresh;
> > };
> > @@ -192,6 +193,7 @@ static void reset_tracing_options(struct perf_ftrace *ftrace __maybe_unused)
> > write_tracing_option_file("func_stack_trace", "0");
> > write_tracing_option_file("sleep-time", "1");
> > write_tracing_option_file("funcgraph-irqs", "1");
> > + write_tracing_option_file("funcgraph-tail", "0");
> > write_tracing_option_file("funcgraph-proc", "0");
> > write_tracing_option_file("funcgraph-abstime", "0");
> > write_tracing_option_file("irq-info", "0");
> > @@ -411,6 +413,17 @@ static int set_tracing_thresh(struct perf_ftrace *ftrace)
> > return 0;
> > }
> >
> > +static int set_tracing_funcgraph_tail(struct perf_ftrace *ftrace)
> > +{
> > + if (!ftrace->funcgraph_tail)
> > + return 0;
> > +
> > + if (write_tracing_option_file("funcgraph-tail", "1") < 0)
> > + return -1;
> > +
> > + return 0;
> > +}
> > +
> > static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
> > {
> > char *trace_file;
> > @@ -499,6 +512,11 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
> > goto out_reset;
> > }
> >
> > + if (set_tracing_funcgraph_tail(ftrace) < 0) {
> > + pr_err("failed to set tracing option funcgraph-tail\n");
> > + goto out_reset;
> > + }
> > +
> > if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
> > pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
> > goto out_reset;
> > @@ -638,6 +656,8 @@ int cmd_ftrace(int argc, const char **argv)
> > "Measure on-CPU time only (function_graph only)"),
> > OPT_BOOLEAN(0, "nofuncgraph-irqs", &ftrace.nofuncgraph_irqs,
> > "Ignore functions that happen inside interrupt (function_graph only)"),
> > + OPT_BOOLEAN(0, "funcgraph-tail", &ftrace.funcgraph_tail,
> > + "Show function tails comment (function_graph only)"),
> > OPT_BOOLEAN('l', "long-info", &ftrace.long_info,
> > "Show process names, PIDs, timestamps, irq-info if available"),
> > OPT_UINTEGER(0, "tracing-thresh", &ftrace.tracing_thresh,
> > --
> > 2.25.1
> >
>
> --
>
> - Arnaldo
--
Cheers,
Changbin Du
Powered by blists - more mailing lists