All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: Julian Anastasov <ja@ssi.bg>, David Miller <davem@davemloft.net>,
	Yuchung Cheng <ycheng@google.com>,
	netdev <netdev@vger.kernel.org>,
	Neal Cardwell <ncardwell@google.com>,
	Larry Brakmo <brakmo@google.com>
Subject: Re: [PATCH v5 net-next] tcp: switch rtt estimations to usec resolution
Date: Mon, 24 Feb 2014 17:38:59 -0800	[thread overview]
Message-ID: <1393292339.2316.98.camel@edumazet-glaptop2.roam.corp.google.com> (raw)
In-Reply-To: <1393290667.2316.96.camel@edumazet-glaptop2.roam.corp.google.com>

On Mon, 2014-02-24 at 17:11 -0800, Eric Dumazet wrote:
> On Mon, 2014-02-24 at 15:51 -0800, Stephen Hemminger wrote:
> 
> > 
> > The original reason I kept ms resolution and added the flag was
> > that accessing high resolution time is expensive for systems where
> > TSC is not stable.  Google may live in a world of SMP systems with
> > good X86 CPUs with working TSC, but other architectures and system
> > config's may have non-working TSC.
> 
> Well, it seems we now have alternatives to ktime_get() that were
> probably not yet there at the time you made this choice ?
> 
> We only want a reasonable alternative to jiffies based measures,
> we do not need ultra precise and synchronized clocks.
> 
> I'll redo tests with hpet clocksource, and local_clock()

Interesting : Using current net-next kernel, before my patches I get
on a TCP_RR workload :

It seems nobody is seriously using hpet these days with recent kernels.


    29.98%  [kernel]      [k] read_hpet                     
     2.93%  [kernel]      [k] _raw_spin_lock                
     1.63%  [kernel]      [k] __schedule                    
     1.62%  [bnx2x]       [k] bnx2x_start_xmit              
     1.57%  [kernel]      [k] __netif_receive_skb_core      
     1.45%  [kernel]      [k] tcp_ack                       
     1.30%  [kernel]      [k] idle_cpu                      
     1.29%  [kernel]      [k] __switch_to                   
     1.28%  netperf       [.] send_omni_inner               
     1.05%  libc-2.15.so  [.] __libc_recv                   
     0.98%  [kernel]      [k] ipv4_dst_check                

  reply	other threads:[~2014-02-25  1:39 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-02-23  6:38 [PATCH net-next] tcp: switch rtt estimations to usec resolution Eric Dumazet
2014-02-23  7:36 ` Julian Anastasov
2014-02-23 17:55   ` Eric Dumazet
2014-02-23 18:50     ` [PATCH v2 " Eric Dumazet
2014-02-23 19:19       ` Yuchung Cheng
2014-02-23 21:41         ` Eric Dumazet
2014-02-24  4:42       ` [PATCH v3 " Eric Dumazet
2014-02-24 17:58         ` Eric Dumazet
2014-02-24 18:24         ` [PATCH v4 " Eric Dumazet
2014-02-24 20:47           ` Julian Anastasov
2014-02-24 22:13             ` Eric Dumazet
2014-02-24 23:01               ` Julian Anastasov
2014-02-24 23:31                 ` [PATCH v5 " Eric Dumazet
2014-02-24 23:51                   ` Stephen Hemminger
2014-02-25  0:15                     ` David Miller
2014-02-25  1:11                     ` Eric Dumazet
2014-02-25  1:38                       ` Eric Dumazet [this message]
2014-02-25  6:22                         ` [PATCH v6 net-next 1/2] net: add skb_mstamp infrastructure Eric Dumazet
2014-02-25  9:51                           ` David Laight
2014-02-25 12:21                             ` Eric Dumazet
2014-02-26 20:02                           ` David Miller
2014-02-26 20:29                             ` Eric Dumazet
2014-02-26 22:02                           ` [PATCH v7 " Eric Dumazet
2014-02-26 22:04                             ` David Miller
2014-02-25  6:22                         ` [PATCH v6 net-next 2/2] tcp: switch rtt estimations to usec resolution Eric Dumazet
2014-02-25 17:46                           ` Neal Cardwell
2014-02-25 18:17                             ` Eric Dumazet
2014-02-25 19:13                           ` Neal Cardwell
2014-02-26 22:02                           ` [PATCH v7 " Eric Dumazet
2014-02-26 22:04                             ` David Miller
2014-02-27  1:09                             ` Stephen Hemminger
2014-02-27  1:21                               ` Rick Jones
2014-02-27  9:57                                 ` David Laight
2014-02-27  2:25                               ` Eric Dumazet
2014-02-24 22:19           ` [PATCH v4 net-next] " Eric Dumazet
2014-02-28  5:20       ` [PATCH v2 " Andi Kleen
2014-02-28  6:14         ` Eric Dumazet
2014-02-28 13:31           ` Andi Kleen
2014-02-28 13:51             ` Eric Dumazet
2014-02-23 19:11     ` [PATCH " Julian Anastasov

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=1393292339.2316.98.camel@edumazet-glaptop2.roam.corp.google.com \
    --to=eric.dumazet@gmail.com \
    --cc=brakmo@google.com \
    --cc=davem@davemloft.net \
    --cc=ja@ssi.bg \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=stephen@networkplumber.org \
    --cc=ycheng@google.com \
    /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.