netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: John Heffner <jheffner@psc.edu>
To: David Miller <davem@davemloft.net>
Cc: rick.jones2@hp.com, ian.mcdonald@jandi.co.nz,
	netdev@vger.kernel.org, ilpo.jarvinen@helsinki.fi
Subject: Re: [PATCH] make _minimum_ TCP retransmission timeout configurable
Date: Wed, 29 Aug 2007 19:44:23 -0400	[thread overview]
Message-ID: <46D604D7.6090200@psc.edu> (raw)
In-Reply-To: <20070829.161528.38309258.davem@davemloft.net>

David Miller wrote:
> From: Rick Jones <rick.jones2@hp.com>
> Date: Wed, 29 Aug 2007 16:06:27 -0700
> 
>> I belive the biggest component comes from link-layer retransmissions. 
>> There can also be some short outtages thanks to signal blocking, 
>> tunnels, people with big hats and whatnot that the link-layer 
>> retransmissions are trying to address.  The three seconds seems to be a 
>> value that gives the certainty that 99 times out of 10 the segment was 
>> indeed lost.
>>
>> The trace I've been sent shows clean RTTs ranging from ~200 milliseconds 
>> to ~7000 milliseconds.
> 
> Thanks for the info.
> 
> It's pretty easy to generate examples where we might have some sockets
> talking over interfaces on such a network and others which are not.
> Therefore, if we do this, a per-route metric is probably the best bet.

This is exactly what I was thinking.  It might even help discourage 
users from playing with this setting who should not. ;)

   -John

  parent reply	other threads:[~2007-08-29 23:44 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-08-29 20:52 [PATCH] make _minimum_ TCP retransmission timeout configurable Rick Jones
2007-08-29 21:13 ` Eric Dumazet
2007-08-29 22:11   ` Rick Jones
2007-08-29 21:32 ` Ian McDonald
2007-08-29 21:46   ` David Miller
2007-08-29 22:10     ` Ian McDonald
2007-08-29 22:23       ` David Miller
2007-08-29 22:13     ` Stephen Hemminger
2007-08-29 22:28       ` David Miller
2007-08-29 22:51         ` Stephen Hemminger
2007-08-29 22:58           ` NCR, was " John Heffner
2007-08-29 22:59             ` David Miller
2007-08-29 22:32       ` Rick Jones
2007-08-29 22:29     ` Rick Jones
2007-08-29 22:35       ` David Miller
2007-08-29 22:48         ` John Heffner
2007-08-29 22:52           ` John Heffner
2007-08-29 22:53         ` Edgar E. Iglesias
2007-08-29 23:06         ` Rick Jones
2007-08-29 23:15           ` David Miller
2007-08-29 23:31             ` Rick Jones
2007-08-30  5:22               ` Krishna Kumar2
2007-08-30 17:10                 ` Rick Jones
2007-08-29 23:44             ` John Heffner [this message]
2007-09-05 19:04             ` Ilpo Järvinen
2007-09-06 20:39               ` David Miller
2007-08-29 22:09   ` Rick Jones
2007-08-29 22:20     ` David Miller
2007-08-29 22:33       ` Ian McDonald
2007-08-29 22:37         ` David Miller

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=46D604D7.6090200@psc.edu \
    --to=jheffner@psc.edu \
    --cc=davem@davemloft.net \
    --cc=ian.mcdonald@jandi.co.nz \
    --cc=ilpo.jarvinen@helsinki.fi \
    --cc=netdev@vger.kernel.org \
    --cc=rick.jones2@hp.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 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).