lists.nanog.org
Sign In Sign Up
Manage this list Sign In Sign Up

Keyboard Shortcuts

Thread View

  • j: Next unread message
  • k: Previous unread message
  • j a: Jump to all threads
  • j l: Jump to MailingList overview
thread

None

None

12 Jul 2007 12 Jul '07
11:29 p.m.
...

I just don't understand how if there is 1 segment that gets lost how this coul d translate to such a catastrophic long period of slow-start. How can I minimize

h Microsoft SMTPSVC(6.0.3790.1830); Fri, 13 Jul 2007 00:14:59 +0100 Message-ID: <4696B55C.4090201@ukbroadband.com> Date: Fri, 13 Jul 2007 00:12:28 +0100 From: Leigh Porter <leigh.porter@ukbroadband.com> User-Agent: Thunderbird 2.0.0.4 (Macintosh/20070604) MIME-Version: 1.0 To: Philip Lavine <source_route@yahoo.com> CC: Stephen Wilcox <steve.wilcox@packetrade.com>, nanog <nanog@merit.edu> Subject: Re: TCP congestion References: <796919.42253.qm@web30811.mail.mud.yahoo.com> In-Reply-To: <796919.42253.qm@web30811.mail.mud.yahoo.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 12 Jul 2007 23:14:59.0400 (UTC) FILETIME=[77BAE480:01C7C4 DA] Sender: owner-nanog@merit.edu Precedence: bulk Errors-To: owner-nanog@merit.edu X-Loop: nanog X-Junkmail-Status: score=10/50, host=mozart.merit.edu X-Junkmail-SD-Raw: score=unknown, refid=str=0001.0A09020A.4696B969.0098:SCGAP167720,ss=1,fgs=0, ip=198.108.1.26, so=2006-09-22 03:48:54, dmn=5.3.14/2007-05-31 Status: RO X-Status: X-Keywords: NonJunk X-UID: 36 Come on folks, don't be afraid. We all know the beast is to blame for this, just don't say the name three times... Shub Internet Philip Lavine wrote: the impact of the inevitable segment loss/out of order over a WAN. Is QoS the only option?

...

----- Original Message ---- From: Stephen Wilcox <steve.wilcox@packetrade.com> To: Philip Lavine <source_route@yahoo.com> Cc: nanog <nanog@merit.edu> Sent: Thursday, July 12, 2007 1:09:24 PM Subject: Re: TCP congestion

Well, if its out of order its the same as if its lost or delayed, it needs to

see that missing segment before the window is full

...

As mentioned you need to get dumps from both ends, you will almost definitely

find that you have packet loss which tripped tcp's slow start mechanism.

...

Steve

On Thu, Jul 12, 2007 at 12:02:49PM -0700, Philip Lavine wrote:

...

Even if the segment was received out of order what would cause congestion avo

idance to starve the connection of legitimate traffic for 15 to 20 seconds? That is the core of the problem.

...
...

----- Original Message ---- From: Fred Baker <fred@cisco.com> To: Brian Knoll <Brian.Knoll@tradingtechnologies.com> Cc: Philip Lavine <source_route@yahoo.com>; nanog <nanog@merit.edu> Sent: Thursday, July 12, 2007 11:56:06 AM Subject: Re: TCP congestion

On Jul 12, 2007, at 11:42 AM, Brian Knoll ((TTNET)) wrote:

...

If the receiver is sending a DUP ACK, then the sender either never received the first ACK or it didn't receive it within the timeframe it expected.

or received it out of order.

Yes, a tcpdump trace is the first step.

_____________________________________________________________________________


...
...

Be a better Globetrotter. Get better travel answers from someone who knows. Y ahoo! Answers - Check it out. http://answers.yahoo.com/dir/?link=list&sid=396545469

______________________________________________________________________________


...

Pinpoint customers who are looking for what you sell. http://searchmarketing.yahoo.com/

0 0
Reply
Sign in to reply online Use email software

Back to the thread

Back to the list

HyperKitty Powered by HyperKitty version 1.3.12.