General list for discussing Bufferbloat
 help / color / mirror / Atom feed
From: Rick Jones <rick.jones2@hp.com>
To: "Toke Høiland-Jørgensen" <toke@toke.dk>
Cc: Paolo Valente <paolo.valente@unimore.it>,
	codel@lists.bufferbloat.net, cerowrt-devel@lists.bufferbloat.net,
	bloat <bloat@lists.bufferbloat.net>,
	paulmck@linux.vnet.ibm.com, John Crispin <blogic@openwrt.org>
Subject: Re: [Bloat] [Codel] FQ_Codel lwn draft article review
Date: Mon, 26 Nov 2012 13:05:53 -0800	[thread overview]
Message-ID: <50B3D9B1.9050804@hp.com> (raw)
In-Reply-To: <87a9u7amon.fsf@toke.dk>

On 11/23/2012 04:07 PM, Toke Høiland-Jørgensen wrote:
> "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> writes:

>> Also, I know what ICMP is, but the UDP variants are new to me.  Could
>> you please expand the "EF", "BK", "BE", and "CSS" acronyms?
>
> The UDP ping times are simply roundtrips/second (as measured by netperf)
> converted to ping times. The acronyms are diffserv markings, i.e.
> EF=expedited forwarding, BK=bulk (CS1 marking), BE=best effort (no
> marking). The UDP ping tests tend to not work so well on a loaded link,
> however, since netperf stops sending packets after detecting
> (excessive(?)) loss. Which is why you see only see the UDP ping times on
> the first part of the graph.

In a "classic" netperf UDP_RR test, where there is only one 
request/response (transaction) in flight at one time, the test will come 
to a halt on the first packet loss - of either a request or a response. 
  Netperf has no retransmission mechanism for UDP.

If one is using "burst mode" then the test will continue so long as 
there is at least one "transaction" outstanding.  However, one cannot 
then simply invert transactions per second to get seconds per transaction.

That is why I tend to use TCP_RR - the retransmission mechanism of TCP 
will kick-in to keep the test going.

In theory, netperf could be tweaked to set SO_RCVTIMEO at some 
high-but-not-too-high level (from the command line?).  It could then 
keep the test limping along I suppose (with gaps), but I don't want 
anything terribly complicated going-on in netperf - otherwise one might 
as well use TCP_RR anyway.

rick jones

  parent reply	other threads:[~2012-11-26 21:06 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CAA93jw5yFvrOyXu2s2DY3oK_0v3OaNfnL+1zTteJodfxtAAzcQ@mail.gmail.com>
2012-11-23  8:57 ` [Bloat] " Dave Taht
2012-11-23 22:18   ` Paul E. McKenney
2012-11-24  0:07     ` Toke Høiland-Jørgensen
2012-11-24 16:19       ` Dave Taht
2012-11-24 16:36         ` [Bloat] [Cerowrt-devel] " dpreed
2012-11-24 19:57         ` [Bloat] [Codel] " Andrew McGregor
2012-11-26 21:13         ` Rick Jones
2012-11-26 21:19           ` Dave Taht
2012-11-26 22:16         ` [Bloat] " Toke Høiland-Jørgensen
2012-11-26 23:21           ` Toke Høiland-Jørgensen
2012-11-26 23:39             ` [Bloat] [Cerowrt-devel] " dpreed
2012-11-26 23:58               ` Toke Høiland-Jørgensen
2012-11-27 16:41                 ` Oliver Hohlfeld
2012-11-28  0:51                   ` Toke Høiland-Jørgensen
2012-11-28 19:21                     ` Greg White
2012-11-28 19:45                       ` Simon Barber
2012-11-28 20:01                         ` Oliver Hohlfeld
2012-11-28 21:40                         ` Greg White
2012-11-28 20:09                       ` Oliver Hohlfeld
2012-11-28 21:45                         ` Greg White
2012-11-26 17:20       ` [Bloat] " Paul E. McKenney
2012-11-26 21:05       ` Rick Jones [this message]
2012-11-26 23:18         ` [Bloat] [Codel] " Rick Jones
2012-11-27 22:03     ` [Bloat] [Cerowrt-devel] " Jim Gettys
2012-11-27 22:31       ` David Lang
2012-11-27 22:54         ` Paul E. McKenney
2012-11-27 23:15           ` [Bloat] [Codel] " Andrew McGregor
2012-11-28  0:51             ` Paul E. McKenney
2012-11-28 17:36             ` Paul E. McKenney
2012-11-28 14:06         ` [Bloat] " Michael Richardson
2012-11-27 22:49       ` Paul E. McKenney
2012-11-27 23:53         ` [Bloat] [Codel] " Greg White
2012-11-28  0:27           ` Paul E. McKenney
2012-11-28  3:43             ` Kathleen Nichols
2012-11-28  4:38               ` Paul E. McKenney
2012-11-28 16:01                 ` Paul E. McKenney
2012-11-28 16:16                   ` Jonathan Morton
2012-11-28 17:44                     ` Paul E. McKenney
2012-11-28 18:37                       ` Michael Richardson
2012-11-28 18:51                         ` Eric Dumazet
2012-11-28 21:44                           ` Michael Richardson
2012-11-28 19:00                       ` Eric Dumazet
     [not found]                         ` <87vcckb0el.fsf@toke.dk>
2012-12-02 21:47                           ` Andrew McGregor
2012-12-03  8:04                             ` Dave Taht
2012-12-02 22:07                           ` Eric Dumazet
     [not found]                             ` <87lidgaynn.fsf@toke.dk>
2012-12-02 22:30                               ` Eric Dumazet
2012-11-28 17:20       ` [Bloat] " Paul E. McKenney
     [not found]         ` <20121202230635.GA16359@linux.vnet.ibm.com>
     [not found]           ` <87obib5qf8.fsf@toke.dk>
2012-12-03 11:31             ` Dave Taht
     [not found]               ` <87fw3n5m9g.fsf@toke.dk>
2012-12-03 14:58                 ` Paul E. McKenney
2012-12-03 15:49                   ` [Bloat] [Codel] " Eric Dumazet
2012-12-03 15:03               ` [Bloat] " Paul E. McKenney
2012-12-03 15:58               ` David Woodhouse
2012-12-04  3:13                 ` [Bloat] [Codel] " Dan Siemon
2012-12-04  9:23                   ` Alex Burr
2012-12-05  3:41                     ` Dan Siemon
2012-12-05 20:33                       ` Alex Burr
2012-12-06  4:12                         ` Dan Siemon
2012-12-06 23:41                           ` Alex Burr
2012-12-05  0:01                   ` Sebastian Moeller
2012-11-30  1:09       ` [Bloat] " Dan Siemon
2013-01-01 20:50         ` Dan Siemon

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

  List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=50B3D9B1.9050804@hp.com \
    --to=rick.jones2@hp.com \
    --cc=bloat@lists.bufferbloat.net \
    --cc=blogic@openwrt.org \
    --cc=cerowrt-devel@lists.bufferbloat.net \
    --cc=codel@lists.bufferbloat.net \
    --cc=paolo.valente@unimore.it \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=toke@toke.dk \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox