mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung.kim@lge.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Jiri Olsa <jolsa@redhat.com>, David Ahern <dsahern@gmail.com>,
	Stephane Eranian <eranian@google.com>,
	Jeremy Eder <jeder@redhat.com>
Subject: [PATCH 17/17] perf ftrace: Tidy up the function graph output of 'show' subcommand
Date: Tue, 30 Jul 2013 18:19:14 +0900	[thread overview]
Message-ID: <1375175954-798-18-git-send-email-namhyung@kernel.org> (raw)
In-Reply-To: <1375175954-798-1-git-send-email-namhyung@kernel.org>

From: Namhyung Kim <namhyung.kim@lge.com>

Now it doesn't call pevent_print_event() but prints context info in
itself using print_graph_duration().  Make it compact by only print
cpu number and duration:

  # perf ftrace show
  ...
   10)   0.065 us |  __fsnotify_parent();
   10)            |  fsnotify() {
   10)   0.060 us |    __srcu_read_lock();
   10)   0.040 us |    __srcu_read_unlock();
   10)   0.652 us |  }
   10)   0.040 us |  fput();
   10)            |  __audit_syscall_exit() {
   10)            |    path_put() {
   10)   0.037 us |      dput();
   10)   0.032 us |      mntput();
   10)   0.563 us |    }
   10)   0.035 us |    unroll_tree_refs();
   10)   0.035 us |    kfree();
   10)   1.284 us |  }
   10)            |  __audit_syscall_entry() {
   10)   0.029 us |    current_kernel_time();
   10)   0.239 us |  }

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-ftrace.c | 35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 8d4ec20e3854..9e78ec19caeb 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -879,6 +879,27 @@ static struct pevent_record *get_ordered_record(struct perf_ftrace *ftrace);
 
 static struct event_format *fgraph_exit_event;
 
+static void
+print_graph_duration(struct trace_seq *s, struct event_format *event,
+		     struct pevent_record *record)
+{
+	unsigned long long duration;
+	unsigned long long rettime, calltime;
+	unsigned long usec, nsec;
+
+	if (pevent_get_field_val(s, event, "rettime", record, &rettime, 1))
+		return;
+
+	if (pevent_get_field_val(s, event, "calltime", record, &calltime, 1))
+		return;
+
+	duration = rettime - calltime;
+	usec = duration / 1000;
+	nsec = duration % 1000;
+
+	trace_seq_printf(s, "%3d) %3lu.%03lu us |  ", record->cpu, usec, nsec);
+}
+
 static int
 fgraph_ent_handler(struct trace_seq *s, struct pevent_record *record,
 		   struct event_format *event, void *context)
@@ -911,9 +932,14 @@ fgraph_ent_handler(struct trace_seq *s, struct pevent_record *record,
 	if (next && next->cpu == record->cpu &&
 	    pevent_data_type(event->pevent, next) == fgraph_exit_event->id) {
 		is_leaf = true;
+
+		print_graph_duration(s, fgraph_exit_event, next);
+
 		/* consume record */
 		get_ordered_record(ftrace);
 		free(next);
+	} else {
+		trace_seq_printf(s, "%3d) %*s |  ", record->cpu, 10, "");
 	}
 
 nested:
@@ -954,6 +980,8 @@ fgraph_ret_handler(struct trace_seq *s, struct pevent_record *record,
 	unsigned long long depth;
 	int i;
 
+	print_graph_duration(s, event, record);
+
 	if (pevent_get_field_val(s, event, "depth", record, &depth, 1))
 		return trace_seq_putc(s, '!');
 
@@ -1265,9 +1293,12 @@ static int do_ftrace_show(struct perf_ftrace *ftrace)
 			continue;
 		}
 
-		pevent_print_event(ftrace->pevent, &seq, record);
-		trace_seq_do_printf(&seq);
+		if (!strcmp(ftrace->tracer, "function_graph"))
+			pevent_event_info(&seq, event, record);
+		else
+			pevent_print_event(ftrace->pevent, &seq, record);
 
+		trace_seq_do_printf(&seq);
 		trace_seq_reset(&seq);
 
 		free(record);
-- 
1.7.11.7


  parent reply	other threads:[~2013-07-30  9:19 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-30  9:18 [PATCHSET 00/17] perf tools: Introduce new 'ftrace' command (v4) Namhyung Kim
2013-07-30  9:18 ` [PATCH 01/17] perf util: Save pid-cmdline mapping into tracing header Namhyung Kim
2013-07-30 13:28   ` Arnaldo Carvalho de Melo
2013-07-31  0:51     ` Namhyung Kim
2013-07-31 14:07       ` Arnaldo Carvalho de Melo
2013-08-05  7:17         ` Namhyung Kim
2013-08-07 13:44           ` David Ahern
2013-08-09  5:51             ` Namhyung Kim
2013-07-30  9:18 ` [PATCH 02/17] perf util: Add more debug message on failure path Namhyung Kim
2013-07-30 13:33   ` Arnaldo Carvalho de Melo
2013-07-30  9:19 ` [PATCH 03/17] perf tools: Introduce new 'ftrace' tool Namhyung Kim
2013-07-30  9:19 ` [PATCH 04/17] perf ftrace: Add support for --pid option Namhyung Kim
2013-07-30  9:19 ` [PATCH 05/17] perf ftrace: Add support for -a and -C option Namhyung Kim
2013-07-30  9:19 ` [PATCH 06/17] perf ftrace: Split "live" sub-command Namhyung Kim
2013-07-30  9:19 ` [PATCH 07/17] perf ftrace: Add 'record' sub-command Namhyung Kim
2013-07-30  9:19 ` [PATCH 08/17] perf ftrace: Add 'show' sub-command Namhyung Kim
2013-07-30  9:19 ` [PATCH 09/17] perf ftrace: Add 'report' sub-command Namhyung Kim
2013-07-30  9:19 ` [PATCH 10/17] perf ftrace: Add dump_printf() for low-level debugging Namhyung Kim
2013-07-30  9:19 ` [PATCH 11/17] perf ftrace: Use pager for displaying result Namhyung Kim
2013-07-30  9:19 ` [PATCH 12/17] perf ftrace: Cleanup using ftrace_setup/teardown() Namhyung Kim
2013-07-30  9:19 ` [PATCH 13/17] perf tools: Add document for perf-ftrace command Namhyung Kim
2013-07-30  9:19 ` [PATCH 14/17] perf ftrace: Add a signal handler for SIGSEGV Namhyung Kim
2013-07-30  9:19 ` [PATCH 15/17] perf ftrace: Add --clock option Namhyung Kim
2013-07-30  9:19 ` [PATCH 16/17] perf ftrace: Show leaf-functions as oneliner Namhyung Kim
2013-07-30  9:19 ` Namhyung Kim [this message]
2013-08-01 12:02 ` [PATCHSET 00/17] perf tools: Introduce new 'ftrace' command (v4) Jiri Olsa
2013-08-02  9:16   ` Ingo Molnar
2013-08-05  7:44     ` Namhyung Kim
     [not found]   ` <51FB2B90.6090602@gmail.com>
2013-08-02 13:33     ` [PATCH] perf tools: Renaming 'time' variable in perf_time_to_tsc due to name shadowing error Jiri Olsa
2013-08-03 19:23       ` Adrian Hunter
2013-08-05  7:47         ` Jiri Olsa
2013-08-09 10:23 ` [PATCHSET 00/17] perf tools: Introduce new 'ftrace' command (v4) Jiri Olsa
2013-08-13  2:20   ` Namhyung Kim
2013-08-28 14:57     ` Jeremy Eder
2013-08-29  2:56       ` Namhyung Kim
2013-08-09 10:25 ` Jiri Olsa
2013-08-09 10:30   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1375175954-798-18-git-send-email-namhyung@kernel.org \
    --to=namhyung@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@ghostprotocols.net \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jeder@redhat.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung.kim@lge.com \
    --cc=paulus@samba.org \
    --cc=rostedt@goodmis.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®