All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	LKML <linux-kernel@vger.kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Ingo Molnar <mingo@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Li Zhong <zhong@linux.vnet.ibm.com>,
	"Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>,
	Anish Singh <anish198519851985@gmail.com>
Subject: Re: [PATCH 4/6] watchdog: Boot-disable by default on full dynticks
Date: Fri, 14 Jun 2013 11:35:50 -0400	[thread overview]
Message-ID: <1371224150.9844.327.camel@gandalf.local.home> (raw)
In-Reply-To: <20130614134947.GB133453@redhat.com>

On Fri, 2013-06-14 at 09:49 -0400, Don Zickus wrote:
>  
> > The concept behind full dynamic ticks is very easy. When you set a given
> > CPU(s) to dynamic tick, when it only has a single task scheduled on that
> > CPU, it disables the periodic tick. This removes essentially *all*
> > latency from the kernel! That is, if the task is doing some complex
> 
> Including SMMi latency? ;-)

When you have SMI latencies, it's time to bitch at your vendor, not
us. ;-)


> > 
> > Now removing the periodic tick is not a trivial task, and this is where
> > all our issues come from. In fact, we can not even completely remove the
> > tick yet, we just move it to 1 HZ instead of whatever the CONFIG_HZ is
> > set to. We have to handle everything that depends on that tick, which
> > includes perf, among other things.
> 
> Which part of perf is dependent on the tick?  Just curious.

I'm not the one to answer this question, but it seems that it uses the
tick whenever perf is active. I had to disable watchdog when dynamic
tick was configured because it would permanently disable dynamic ticks
without letting the user know why. This is because watchdog uses perf
and enables it on boot and keeps it enabled.

-- Steve



  reply	other threads:[~2013-06-14 15:35 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-12 14:02 [PATCH 0/6] timers nohz updates preview for 3.11 Frederic Weisbecker
2013-06-12 14:02 ` [PATCH 1/6] sched: Disable lb_bias feature for full dynticks Frederic Weisbecker
2013-06-12 14:02 ` [PATCH 2/6] nohz: Warn if the machine can not perform nohz_full Frederic Weisbecker
2013-06-12 14:02 ` [PATCH 3/6] watchdog: Register / unregister watchdog kthreads on sysctl control Frederic Weisbecker
2013-06-12 14:02 ` [PATCH 4/6] watchdog: Boot-disable by default on full dynticks Frederic Weisbecker
2013-06-12 17:03   ` Don Zickus
2013-06-13 13:10     ` Frederic Weisbecker
2013-06-13 14:02       ` Don Zickus
2013-06-13 14:22         ` Frederic Weisbecker
2013-06-13 14:45           ` Don Zickus
2013-06-13 14:56             ` Frederic Weisbecker
2013-06-13 15:20               ` Don Zickus
2013-06-13 15:48                 ` Steven Rostedt
2013-06-13 16:21                   ` anish singh
2013-06-13 17:16                     ` Steven Rostedt
2013-06-14  4:17                       ` anish singh
2013-06-14 12:26                         ` Paul E. McKenney
2013-06-14 16:03                           ` anish singh
2013-06-14 16:12                             ` Steven Rostedt
2013-06-14 16:22                               ` anish singh
2013-06-14 13:49                   ` Don Zickus
2013-06-14 15:35                     ` Steven Rostedt [this message]
2013-06-18 10:36         ` Peter Zijlstra
2013-06-18 12:04           ` Frederic Weisbecker
2013-06-18 12:53             ` Peter Zijlstra
2013-06-12 14:02 ` [PATCH 5/6] rcu: Prevent CPU from stopping tick if awaited for quiescent state report Frederic Weisbecker
2013-06-12 14:02 ` [PATCH 6/6] nohz: Remove obsolete check for full dynticks CPUs to be RCU nocbs Frederic Weisbecker

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=1371224150.9844.327.camel@gandalf.local.home \
    --to=rostedt@goodmis.org \
    --cc=akpm@linux-foundation.org \
    --cc=anish198519851985@gmail.com \
    --cc=dzickus@redhat.com \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=srivatsa.bhat@linux.vnet.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=zhong@linux.vnet.ibm.com \
    --subject='Re: [PATCH 4/6] watchdog: Boot-disable by default on full dynticks' \
    /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

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.