Linux-rt-users archive on lore.kernel.org
 help / color / Atom feed
From: Juri Lelli <juri.lelli@redhat.com>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: fweisbec@gmail.com, tglx@linutronix.de, mingo@kernel.org,
	linux-rt-users@vger.kernel.org, peterz@infradead.org,
	linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH] tick/sched: update full_nohz status after SCHED dep is cleared
Date: Tue, 16 Jun 2020 08:57:57 +0200
Message-ID: <20200616065757.GA446382@localhost.localdomain> (raw)
In-Reply-To: <20200615210743.GA21371@lenoir>

On 15/06/20 23:07, Frederic Weisbecker wrote:
> On Thu, May 21, 2020 at 07:00:20PM +0200, Juri Lelli wrote:

[...]

> >   sysjitter-2377  [004]   100.438495: sched_switch:         sysjitter:2377 [120] R ==> ksoftirqd/4:31 [120]
> > ksoftirqd/4-31    [004]   100.438497: softirq_entry:        vec=1 [action=TIMER]
> > ksoftirqd/4-31    [004]   100.438499: timer_cancel:         timer=0xffffffffa55a9d20
> > ksoftirqd/4-31    [004]   100.438501: timer_expire_entry:   timer=0xffffffffa55a9d20 function=clocksource_watchdog now=4294759824 baseclk=4294759824
> > ksoftirqd/4-31    [004]   100.438504: timer_start:          timer=0xffffffffa55a9d20 function=clocksource_watchdog expires=4294760322 [timeout=498] cpu=5 idx=113 flags=D|P|I

[...]

> > ksoftirqd/4-31    [004]   100.438509: hrtimer_cancel:       hrtimer=0xffff92e9df91fd20
> > ksoftirqd/4-31    [004]   100.438511: hrtimer_expire_entry: hrtimer=0xffff92e9df91fd20 now=92630515022 function=tick_sched_timer/0x0
> > ksoftirqd/4-31    [004]   100.438515: kernel_stack:         <stack trace>
> > => __ftrace_trace_stack (ffffffffa37da921)
> > => __raise_softirq_irqoff (ffffffffa36daf50)
> > => raise_softirq (ffffffffa36db0fe)
> > => rcu_sched_clock_irq (ffffffffa375af4a)
> > => update_process_times (ffffffffa3768fa4)
> > => tick_sched_handle (ffffffffa377aaa2)
> > => tick_sched_timer (ffffffffa377ad53)
> > => __hrtimer_run_queues (ffffffffa3769cf0)
> > => hrtimer_interrupt (ffffffffa376a58a)
> > => smp_apic_timer_interrupt (ffffffffa40028f8)
> > => apic_timer_interrupt (ffffffffa4001b7f)
> > => filter_pred_32 (ffffffffa37f3357)
> > => filter_match_preds (ffffffffa37f3510)
> > => trace_event_buffer_commit (ffffffffa37dc7eb)
> > => trace_event_raw_event_softirq (ffffffffa36dab77)
> > => __do_softirq (ffffffffa420025a)
> > => run_ksoftirqd (ffffffffa36dadc6)
> > => smpboot_thread_fn (ffffffffa36ffdb8)
> > => kthread (ffffffffa36f9fb7)
> > => ret_from_fork (ffffffffa4000215)
> > ksoftirqd/4-31    [004]   100.438516: softirq_raise:        vec=9 [action=RCU]
> > ksoftirqd/4-31    [004]   100.438520: kernel_stack:         <stack trace>
> > => __ftrace_trace_stack (ffffffffa37da921)
> > => __raise_softirq_irqoff (ffffffffa36daf50)
> > => raise_softirq (ffffffffa36db0fe)
> > => trigger_load_balance (ffffffffa371cb9c)
> > => update_process_times (ffffffffa3768fc7)
> > => tick_sched_handle (ffffffffa377aaa2)
> > => tick_sched_timer (ffffffffa377ad53)
> > => __hrtimer_run_queues (ffffffffa3769cf0)
> > => hrtimer_interrupt (ffffffffa376a58a)
> > => smp_apic_timer_interrupt (ffffffffa40028f8)
> > => apic_timer_interrupt (ffffffffa4001b7f)
> > => filter_pred_32 (ffffffffa37f3357)
> > => filter_match_preds (ffffffffa37f3510)
> > => trace_event_buffer_commit (ffffffffa37dc7eb)
> > => trace_event_raw_event_softirq (ffffffffa36dab77)
> > => __do_softirq (ffffffffa420025a)
> > => run_ksoftirqd (ffffffffa36dadc6)
> > => smpboot_thread_fn (ffffffffa36ffdb8)
> > => kthread (ffffffffa36f9fb7)
> > => ret_from_fork (ffffffffa4000215)
> > ksoftirqd/4-31    [004]   100.438520: softirq_raise:        vec=7 [action=SCHED]
> > ksoftirqd/4-31    [004]   100.438521: hrtimer_expire_exit:  hrtimer=0xffff92e9df91fd20
> > ksoftirqd/4-31    [004]   100.438523: hrtimer_start:        hrtimer=0xffff92e9df91fd20 function=tick_sched_timer/0x0 expires=92631512937 softexpires=92631512937
> > ksoftirqd/4-31    [004]   100.438525: local_timer_exit:     vector=236
> > ksoftirqd/4-31    [004]   100.438527: tick_stop:            success=0 dependency=SCHED

[...]

> > ksoftirqd/4-31    [004]   100.438530: softirq_exit:         vec=1 [action=TIMER]
> 
> Was there a corresponding softirq_enter? With timers expiring inside?

The one up above, at 100.438497.

[...]

> > 
> > Does this make sense and help in any way? Suggestions for debugging this
> > further? :-)
> 
> Let's see if I can reproduce it first. If not I'll need to bother you further :)

Sure. Let me know if you find anything.

Best,

Juri


  reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-20 14:04 Juri Lelli
2020-05-20 16:24 ` Frederic Weisbecker
2020-05-20 16:49   ` Juri Lelli
2020-05-20 17:02     ` Frederic Weisbecker
2020-05-20 18:47       ` Juri Lelli
2020-05-21  0:44         ` Frederic Weisbecker
2020-05-21 17:00           ` Juri Lelli
2020-06-15 15:05             ` Juri Lelli
2020-06-15 21:07             ` Frederic Weisbecker
2020-06-16  6:57               ` Juri Lelli [this message]
2020-06-16 20:46                 ` Frederic Weisbecker
2020-06-29 12:36                   ` Juri Lelli
2020-06-29 12:42                     ` Frederic Weisbecker
2020-06-29 12:53                       ` Juri Lelli

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=20200616065757.GA446382@localhost.localdomain \
    --to=juri.lelli@redhat.com \
    --cc=frederic@kernel.org \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rt-users@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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

Linux-rt-users archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rt-users/0 linux-rt-users/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rt-users linux-rt-users/ https://lore.kernel.org/linux-rt-users \
		linux-rt-users@vger.kernel.org
	public-inbox-index linux-rt-users

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rt-users


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git