From: John Heffner <jheffner@psc.edu>
To: Andi Kleen <ak@muc.de>
Cc: "David S. Miller" <davem@davemloft.net>,
netdev@oss.sgi.com, akepner@sgi.com
Subject: Re: [RFC/PATCH] "strict" ipv4 reassembly
Date: Tue, 17 May 2005 14:57:38 -0400 [thread overview]
Message-ID: <200505171457.38719.jheffner@psc.edu> (raw)
In-Reply-To: <m1zmut7l5q.fsf@muc.de>
On Tuesday 17 May 2005 02:38 pm, Andi Kleen wrote:
> "David S. Miller" <davem@davemloft.net> writes:
> > From: Arthur Kepner <akepner@sgi.com>
> > Date: Tue, 17 May 2005 09:18:26 -0700 (PDT)
> >
> >> 1) Fragments must arrive in order (or in reverse order) -
> >> out of order fragments are dropped.
> >
> > Even the most simplistic flow over the real internet
> > can get slight packet reordering.
> >
> > Heck, reordering happens on SMP on any network.
> >
> > IP is supposed to be resilient to side effects of network
> > topology, and one such common side effect is packet reordering.
> > It's common, it's fine, and the networking stack deals with it
> > gracefully. Strict reassembly does not.
>
> If anything it would be better as a per route flag.
> Then you could set it only for your local network
> where you know Gigabit happens and reordering might
> be avoidable in some cases.
It would be better still to have a per-route packet reassembly timeout in
milliseconds. Expecting perfect ordering seems very fragile even for a LAN.
-John
next prev parent reply other threads:[~2005-05-17 18:57 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-05-17 16:18 [RFC/PATCH] "strict" ipv4 reassembly Arthur Kepner
2005-05-17 17:49 ` David S. Miller
2005-05-17 18:28 ` Arthur Kepner
2005-05-17 18:48 ` David S. Miller
2005-05-17 20:21 ` Arthur Kepner
2005-05-17 18:38 ` Andi Kleen
2005-05-17 18:45 ` Pekka Savola
2005-05-17 18:50 ` David S. Miller
2005-05-17 18:56 ` Rick Jones
2005-05-17 18:57 ` John Heffner [this message]
2005-05-17 19:09 ` David S. Miller
2005-05-17 19:21 ` Rick Jones
2005-05-17 19:26 ` Ben Greear
2005-05-17 20:48 ` Thomas Graf
2005-05-17 19:17 ` Andi Kleen
2005-05-17 19:56 ` David Stevens
2005-05-17 20:17 ` Andi Kleen
2005-05-17 20:22 ` David S. Miller
2005-05-17 20:27 ` Andi Kleen
2005-05-17 21:02 ` David S. Miller
2005-05-17 21:13 ` Andi Kleen
2005-05-17 21:24 ` David S. Miller
2005-05-17 21:25 ` Rick Jones
2005-05-17 22:06 ` Arthur Kepner
2005-05-17 22:18 ` Rick Jones
2005-05-17 22:40 ` David Stevens
2005-05-17 23:11 ` Herbert Xu
2005-05-17 23:20 ` Arthur Kepner
2005-05-17 23:25 ` Herbert Xu
2005-05-17 23:55 ` David Stevens
2005-05-18 0:00 ` Herbert Xu
2005-05-18 0:04 ` Andi Kleen
2005-05-18 0:09 ` Herbert Xu
2005-05-18 0:52 ` David S. Miller
2005-05-18 0:06 ` Nivedita Singhvi
2005-05-18 0:10 ` Herbert Xu
2005-05-18 0:51 ` David S. Miller
2005-05-18 1:05 ` Andi Kleen
2005-05-18 1:13 ` Herbert Xu
2005-05-18 1:09 ` John Heffner
2005-05-17 23:53 ` Rick Jones
2005-05-17 22:12 ` David S. Miller
2005-05-17 22:23 ` Rick Jones
2005-05-17 20:29 ` John Heffner
2005-05-17 19:01 ` Nivedita Singhvi
2005-05-17 19:13 ` Rick Jones
2005-05-17 19:25 ` Nivedita Singhvi
2005-05-17 19:31 ` John Heffner
2005-05-17 19:52 ` Nivedita Singhvi
2005-05-17 20:05 ` John Heffner
2005-05-17 20:12 ` Rick Jones
2005-05-17 19:33 ` Rick Jones
2005-05-17 19:53 ` Andi Kleen
2005-05-17 22:11 ` Herbert Xu
2005-05-17 22:13 ` David S. Miller
2005-05-17 23:08 ` Herbert Xu
2005-05-17 23:16 ` David S. Miller
2005-05-17 23:28 ` Herbert Xu
2005-05-17 23:36 ` Patrick McHardy
2005-05-17 23:41 ` Herbert Xu
2005-05-18 0:47 ` Thomas Graf
2005-05-18 1:06 ` Arthur Kepner
2005-05-18 1:16 ` Herbert Xu
2005-05-18 1:37 ` Thomas Graf
2005-05-18 1:52 ` Herbert Xu
2005-05-18 11:30 ` Thomas Graf
2005-05-18 11:40 ` Herbert Xu
2005-05-18 12:24 ` Thomas Graf
2005-05-18 16:21 ` Rick Jones
2005-05-18 17:40 ` Thomas Graf
2005-05-18 17:44 ` Thomas Graf
2005-05-18 21:46 ` Herbert Xu
2005-05-18 22:24 ` David Stevens
2005-05-18 22:39 ` Nivedita Singhvi
2005-05-18 23:31 ` Thomas Graf
2005-05-18 21:45 ` Herbert Xu
2005-05-19 12:23 ` Thomas Graf
2005-05-19 12:48 ` Herbert Xu
2005-05-19 15:19 ` Thomas Graf
2005-05-19 17:02 ` Rick Jones
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=200505171457.38719.jheffner@psc.edu \
--to=jheffner@psc.edu \
--cc=ak@muc.de \
--cc=akepner@sgi.com \
--cc=davem@davemloft.net \
--cc=netdev@oss.sgi.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).