All of lore.kernel.org
 help / color / mirror / Atom feed
From: Changbin Du <changbin.du@gmail.com>
To: Changbin Du <changbin.du@gmail.com>
Cc: rostedt@goodmis.org, mingo@redhat.com, corbet@lwn.net,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 0/5] Improve the latency tracers
Date: Sat, 12 Jan 2019 12:05:33 +0800	[thread overview]
Message-ID: <20190112040531.w7wvt5x6ztxb6qcg@mail.google.com> (raw)
In-Reply-To: <20190101154614.8887-1-changbin.du@gmail.com>

Hi Steven, Have you checked this serias yet? :)

On Tue, Jan 01, 2019 at 11:46:09PM +0800, Changbin Du wrote:
> Happy new year!
> 
> This series make some improments for the kernel latency tracers, especilly
> for the wakeup tracers. The latency tracers will show us more useful
> information. With this series, the wakeup tracers look like this
> when display-graph is enabled:
> 
> # 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)();
>   <idle>-0       0dNs.   66us : <stack trace>
>  => try_to_wake_up
>  => __queue_work
>  => queue_work_on
>  => call_timer_fn
>  => run_timer_softirq
>  => __do_softirq
>  => irq_exit
>  => smp_apic_timer_interrupt
>  => apic_timer_interrupt
>  => native_safe_halt
>  => default_idle
>  => default_idle_call
>  => do_idle
>  => cpu_startup_entry
>  => start_kernel
>  => secondary_startup_64
>        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. |   1.125 us    |  __next_timer_interrupt();
>        75 us |   0)    <idle>-0    |  dNs. |               |  call_timer_fn() {
>        76 us |   0)    <idle>-0    |  dNs. |               |    delayed_work_timer_fn() {
>       [...]
>       564 us |   0)   kworker-13   |  d... |               |      set_next_entity() {
>       565 us |   0)   kworker-13   |  d... |   0.524 us    |        __update_load_avg_se();
>       566 us |   0)   kworker-13   |  d... |   0.562 us    |        __update_load_avg_cfs_rq();
>       567 us |   0)   kworker-13   |  d... |   2.765 us    |      }
>       568 us |   0)   kworker-13   |  d... | + 10.077 us   |    }
>       569 us |   0)   kworker-13   |  d... |   0.000 us    |  __schedule();
> kworker/-13      0d...  593us : <stack trace>
>  => schedule
>  => worker_thread
>  => kthread
>  => ret_from_fork
>       593 us |   0)   kworker-13   |  d... |               |  /*     13:120:I ==> [000]   339:100:R kworker/0:1H */
> 
> Changbin Du (5):
>   function_graph: Support displaying relative timestamp
>   sched/tracing: Show more info for funcgraph wakeup tracers
>   sched/tracing: Put a margin between flags and duration for wakeup
>     tracers
>   sched/tracing: Show stacktrace for wakeup tracers
>   trace/doc: Add latency tracer funcgraph example
> 
>  Documentation/trace/ftrace.rst       | 51 ++++++++++++++++++++++++++++
>  kernel/trace/trace.h                 |  9 ++---
>  kernel/trace/trace_functions_graph.c | 30 ++++++++++++++--
>  kernel/trace/trace_irqsoff.c         |  2 +-
>  kernel/trace/trace_sched_wakeup.c    | 11 ++++--
>  5 files changed, 94 insertions(+), 9 deletions(-)
> 
> -- 
> 2.17.1
> 

-- 
Cheers,
Changbin Du

  parent reply	other threads:[~2019-01-12  4:05 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 ` [PATCH 3/5] sched/tracing: Put a margin between flags and duration for " Changbin Du
2019-01-01 15:46 ` [PATCH 4/5] sched/tracing: Show stacktrace " 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 ` Changbin Du [this message]
2019-01-14 15:00   ` [PATCH 0/5] Improve the latency tracers 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=20190112040531.w7wvt5x6ztxb6qcg@mail.google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.