Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Alexander Zimmermann <alexander.zimmermann@comsys.rwth-aachen.de>
Cc: netdev <netdev@vger.kernel.org>, Jerry Chu <hkchu@google.com>,
	Lukowski Damian <damian@tvk.rwth-aachen.de>,
	Hannemann Arnd <arnd@arndnet.de>
Subject: Re: [BUG] tcp : how many times a frame can possibly be retransmitted ?
Date: Wed, 24 Aug 2011 21:45:32 +0200	[thread overview]
Message-ID: <1314215132.2506.7.camel@edumazet-laptop> (raw)
In-Reply-To: <3482698A-C35B-4BED-AEEF-EBA135991705@comsys.rwth-aachen.de>

Le mercredi 24 août 2011 à 21:03 +0200, Alexander Zimmermann a écrit :
> Hi Eric,
> 
> Am 24.08.2011 um 18:21 schrieb Eric Dumazet:
> 
> > On one dev machine running net-next, I just found strange tcp sessions
> > that retransmit a frame forever (The other peer disappeared)
> 
> not forever...
> If remember correctly you will stop after 120s.
> 

Hi Alexander

I just tried again one session, and got much more delay than that.

It stops because of a side effect, "icsk_retransmits" being a 8bit
field.

Every 256 retransmits, it becomes 255+1 -> 0

retransmits_timed_out() immediately returns false.

And backoff increases at this time.

Eventually, we retransmit 256*15 times, process 256*15 ICMP messages.

Thanks

  parent reply	other threads:[~2011-08-24 19:45 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-08-24 16:21 [BUG] tcp : how many times a frame can possibly be retransmitted ? Eric Dumazet
2011-08-24 19:03 ` Alexander Zimmermann
2011-08-24 19:39   ` Jerry Chu
2011-08-24 19:45   ` Eric Dumazet [this message]
2011-08-24 22:44 ` Ilpo Järvinen
2011-08-24 23:00   ` Eric Dumazet
2011-08-24 23:41     ` [PATCH] tcp: bound RTO to minimum Hagen Paul Pfeifer
2011-08-24 23:43       ` Hagen Paul Pfeifer
2011-08-25  1:50       ` Yuchung Cheng
2011-08-25  5:28         ` Eric Dumazet
2011-08-25  7:28           ` Alexander Zimmermann
2011-08-25  8:26             ` Eric Dumazet
2011-08-25  8:44               ` Alexander Zimmermann
2011-08-25  8:46               ` Arnd Hannemann
2011-08-25  9:09                 ` Eric Dumazet
2011-08-25  9:46                   ` Arnd Hannemann
2011-08-25 10:02                     ` Eric Dumazet
2011-08-25 10:14                       ` Ilpo Järvinen
2011-08-25 10:15                       ` Arnd Hannemann
2011-08-25  8:56     ` [BUG] tcp : how many times a frame can possibly be retransmitted ? Ilpo Järvinen
2011-08-25  9:40       ` Eric Dumazet
2011-08-25 10:07         ` Ilpo Järvinen

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=1314215132.2506.7.camel@edumazet-laptop \
    --to=eric.dumazet@gmail.com \
    --cc=alexander.zimmermann@comsys.rwth-aachen.de \
    --cc=arnd@arndnet.de \
    --cc=damian@tvk.rwth-aachen.de \
    --cc=hkchu@google.com \
    --cc=netdev@vger.kernel.org \
    /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