LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>,
	viresh kumar <viresh.kumar@linaro.org>,
	Ingo Molnar <mingo@redhat.com>,
	linaro-kernel@lists.linaro.org,
	LKML <linux-kernel@vger.kernel.org>,
	Steven Miao <realmz6@gmail.com>,
	shashim@codeaurora.org, Frederic Weisbecker <fweisbec@gmail.com>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	cl@kernel.org
Subject: Re: [PATCH 1/2] timer: Avoid waking up an idle-core by migrate running timer
Date: Sat, 25 Apr 2015 11:37:30 -0700	[thread overview]
Message-ID: <1429987050.22254.187.camel@edumazet-glaptop2.roam.corp.google.com> (raw)
In-Reply-To: <alpine.DEB.2.11.1504231439300.13914@nanos>

On Thu, 2015-04-23 at 14:45 +0200, Thomas Gleixner wrote:

> You definitely have a point from the high throughput networking
> perspective.
> 
> Though in a power optimizing scenario with minimal network traffic
> this might be the wrong decision. We have to gather data from the
> power maniacs whether this matters or not. The FULL_NO_HZ camp might
> be pretty unhappy about the above.

Sure, I understand.


To make this clear, here the profile on a moderately loaded TCP server,
pushing ~20Gbits of data. Most of TCP output is ACK clock driven (thus
from softirq context).

(using regular sendmsg() system calls, that why the
get_nohz_timer_target() is 'only' second in the profile, but add the
find_next_bit() to it and this is very close being at first position)



   PerfTop:    4712 irqs/sec  kernel:96.7%  exact:  0.0% [4000Hz cycles],  (all, 72 CPUs)
-----------------------------------------------------------------------------------------
    10.16%  [kernel]          [k] copy_user_enhanced_fast_string            
     5.66%  [kernel]          [k] get_nohz_timer_target                     
     5.59%  [kernel]          [k] _raw_spin_lock                            
     2.53%  [kernel]          [k] __netif_receive_skb_core                  
     2.27%  [kernel]          [k] find_next_bit                             
     1.90%  [kernel]          [k] tcp_ack                                   

Maybe a reasonable heuristic would be to
change /proc/sys/kernel/timer_migration default to 0 on hosts with more
than 32 cpus.

profile with timer_migration = 0

   PerfTop:    3656 irqs/sec  kernel:94.3%  exact:  0.0% [4000Hz cycles],  (all, 72 CPUs)
-----------------------------------------------------------------------------------------
    13.95%  [kernel]          [k] copy_user_enhanced_fast_string            
     4.65%  [kernel]          [k] _raw_spin_lock                            
     2.57%  [kernel]          [k] __netif_receive_skb_core                  
     2.33%  [kernel]          [k] tcp_ack               

Thanks.



  reply	other threads:[~2015-04-25 18:37 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-31  6:55 [PATCH 0/2] timer: Migrate running timers Viresh Kumar
2015-03-31  6:55 ` [PATCH 1/2] timer: Avoid waking up an idle-core by migrate running timer Viresh Kumar
2015-03-31 14:53   ` Peter Zijlstra
2015-04-14 23:13   ` Thomas Gleixner
2015-04-17  8:12     ` viresh kumar
2015-04-17  8:32       ` Ingo Molnar
2015-04-21 21:32       ` Thomas Gleixner
2015-04-21 21:54         ` Eric Dumazet
2015-04-22 15:29           ` Peter Zijlstra
2015-04-22 16:02             ` Eric Dumazet
2015-04-22 18:56               ` Thomas Gleixner
2015-04-22 19:59                 ` Eric Dumazet
2015-04-22 21:56                   ` Thomas Gleixner
2015-04-23  6:57                     ` Eric Dumazet
2015-04-23 12:45                       ` Thomas Gleixner
2015-04-25 18:37                         ` Eric Dumazet [this message]
2015-05-05 13:00                           ` Thomas Gleixner
2015-05-06 16:33                             ` Eric Dumazet
2015-04-15 15:54   ` Thomas Gleixner
2015-03-31  6:55 ` [PATCH 2/2] timer: Replace base-> 'running_timer' with 'busy' Viresh Kumar
2015-03-31 15:01 ` [PATCH 0/2] timer: Migrate running timers Viresh Kumar

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=1429987050.22254.187.camel@edumazet-glaptop2.roam.corp.google.com \
    --to=eric.dumazet@gmail.com \
    --cc=cl@kernel.org \
    --cc=fweisbec@gmail.com \
    --cc=linaro-kernel@lists.linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=realmz6@gmail.com \
    --cc=shashim@codeaurora.org \
    --cc=tglx@linutronix.de \
    --cc=viresh.kumar@linaro.org \
    --subject='Re: [PATCH 1/2] timer: Avoid waking up an idle-core by migrate running timer' \
    /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 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).