linux-doc.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Changbin Du <changbin.du@gmail.com>
To: rostedt@goodmis.org
Cc: mingo@redhat.com, corbet@lwn.net, linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org, Changbin Du <changbin.du@gmail.com>
Subject: [PATCH 3/5] sched/tracing: Put a margin between flags and duration for wakeup tracers
Date: Tue,  1 Jan 2019 23:46:12 +0800	[thread overview]
Message-ID: <20190101154614.8887-4-changbin.du@gmail.com> (raw)
In-Reply-To: <20190101154614.8887-1-changbin.du@gmail.com>

Don't mix context flags with function duration info. Now the output looks
like this:

\# tracer: wakeup
\#
\# wakeup latency trace v1.1.5 on 4.20.0+
\# --------------------------------------------------------------------
\# latency: 593 us, #674/674, CPU#0 | (M:desktop VP:0, KP:0, SP:0 HP:0 #P:4)
\#    -----------------
\#    | task: kworker/0:1H-339 (uid:0 nice:-20 policy:0 rt_prio:0)
\#    -----------------
\#
\#                                      _-----=> irqs-off
\#                                     / _----=> need-resched
\#                                    | / _---=> hardirq/softirq
\#                                    || / _--=> preempt-depth
\#                                    ||| /
\#  REL TIME      CPU  TASK/PID       ||||     DURATION                  FUNCTION CALLS
\#     |          |     |    |        ||||      |   |                     |   |   |   |
        0 us |   0)    <idle>-0    |  dNs. |               |  /*      0:120:R   + [000]   339:100:R kworker/0:1H */
        3 us |   0)    <idle>-0    |  dNs. |   0.000 us    |            (null)();
       67 us |   0)    <idle>-0    |  dNs. |   0.721 us    |  ttwu_stat();
       69 us |   0)    <idle>-0    |  dNs. |   0.607 us    |  _raw_spin_unlock_irqrestore();
       71 us |   0)    <idle>-0    |  .Ns. |   0.598 us    |  _raw_spin_lock_irq();
       72 us |   0)    <idle>-0    |  .Ns. |   0.584 us    |  _raw_spin_lock_irq();
       73 us |   0)    <idle>-0    |  dNs. | + 11.118 us   |  __next_timer_interrupt();
       75 us |   0)    <idle>-0    |  dNs. |               |  call_timer_fn() {
       76 us |   0)    <idle>-0    |  dNs. |               |    delayed_work_timer_fn() {
       76 us |   0)    <idle>-0    |  dNs. |               |      __queue_work() {
       ...

Signed-off-by: Changbin Du <changbin.du@gmail.com>
---
 kernel/trace/trace_functions_graph.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 16ebbdd7b22e..69ebf3c2f1b5 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -380,6 +380,7 @@ static void print_graph_lat_fmt(struct trace_seq *s, struct trace_entry *entry)
 {
 	trace_seq_putc(s, ' ');
 	trace_print_lat_fmt(s, entry);
+	trace_seq_puts(s, " | ");
 }
 
 /* If the pid changed since the last trace, output this event */
@@ -1153,7 +1154,7 @@ static void __print_graph_headers_flags(struct trace_array *tr,
 	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_puts(s, "  TASK/PID       ");
 	if (lat)
-		seq_puts(s, "||||");
+		seq_puts(s, "||||   ");
 	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_puts(s, "  DURATION   ");
 	seq_puts(s, "               FUNCTION CALLS\n");
@@ -1169,7 +1170,7 @@ static void __print_graph_headers_flags(struct trace_array *tr,
 	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_puts(s, "   |    |        ");
 	if (lat)
-		seq_puts(s, "||||");
+		seq_puts(s, "||||   ");
 	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_puts(s, "   |   |      ");
 	seq_puts(s, "               |   |   |   |\n");
-- 
2.17.1


  parent reply	other threads:[~2019-01-01 15:47 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-01 15:46 [PATCH 0/5] Improve the latency tracers Changbin Du
2019-01-01 15:46 ` [PATCH 1/5] function_graph: Support displaying relative timestamp Changbin Du
2019-01-01 15:46 ` [PATCH 2/5] sched/tracing: Show more info for funcgraph wakeup tracers Changbin Du
2019-01-01 15:46 ` Changbin Du [this message]
2019-01-01 15:46 ` [PATCH 4/5] sched/tracing: Show stacktrace for " Changbin Du
2019-01-16  3:25   ` Steven Rostedt
2019-01-16 16:04     ` Changbin Du
2019-01-01 15:46 ` [PATCH 5/5] trace/doc: Add latency tracer funcgraph example Changbin Du
2019-01-12  4:05 ` [PATCH 0/5] Improve the latency tracers Changbin Du
2019-01-14 15:00   ` Steven Rostedt

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=20190101154614.8887-4-changbin.du@gmail.com \
    --to=changbin.du@gmail.com \
    --cc=corbet@lwn.net \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --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;
as well as URLs for NNTP newsgroup(s).