From: willy tarreau <wtarreau@yahoo.fr>
To: Matti Aarnio <matti.aarnio@zmailer.org>,
Constantine Gavrilov <const-g@xpert.com>
Cc: willy tarreau <wtarreau@yahoo.fr>,
alan@lxorguk.ukuu.org.uk, linux-kernel@vger.kernel.org
Subject: Re: Linux 2.2.18pre21
Date: Fri, 10 Nov 2000 12:21:46 +0100 (CET) [thread overview]
Message-ID: <20001110112146.12035.qmail@web1103.mail.yahoo.com> (raw)
> I don't like to call it BONDING.
> "Bonding" is something where two (or more) channels
> carry data in between two participating systems.
> Like Multilink-PPP, and ISDN Channel Bonding. Often
> indeed data goes out somehow inter-leaved on the
> physical links. (Like ISDN Channel Bonding supplies
> a transparent 128 kbps link instead of two 64
> kbps links to the upper layers.)
this is *EXACTLY* what the old bonding driver does,
and what the new one does by default.
> EtherChannel does select the link (out of the group)
> by forming XOR of source and destination MAC
> addresses (their lowest bytes),
.../...
> This gives improved throughput on congested links
> in between two switches, or major server and core
> switches, while preserving data order over the
links.
OK, I've read about it because Thomas Davis asked me
if I would implement it. I didn't find it usefull for
the case of a Linux server directly connected to a
router or a level X switch (x>2) because in this case
only one link is getting used. Perhaps I'm wrong, but
I think this is the major use of the current Linux
bonding driver. However, the new driver is now ready
for such an implementation.
> Blind bonding-type "throw packets on links 0 and 1"
> MAY end up sending ethernet frames out of sequence,
> which for a few LAN based protocols is a great
source
> of upset.
probably, but do you have examples in mind ? if so, I
would add XOR to a next release, but I don't want to
add too much at a time. I consider this release
primarily as a bugfix (smp, security, oopses...), and
as an improvement which now supports link fail-over,
which is also a primary concern when implementing
multilinks.
> Beowulf systems have "bonding" in use for parallel
> Ethernet links in between two machines, however THAT
> is not EtherChannel compatible thing!
yes it is compatible ! compatible doesn't mean it does
not work the same way, but it works with. Both the
cisco and linux drivers agree to receive on each of
their trunk ports, so the difference only resides in
link optimization when sending frames.
> /Matti Aarnio
Willy
___________________________________________________________
Do You Yahoo!? -- Pour dialoguer en direct avec vos amis,
Yahoo! Messenger : http://fr.messenger.yahoo.com
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
next reply other threads:[~2000-11-10 11:22 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2000-11-10 11:21 willy tarreau [this message]
2000-11-10 11:42 ` compiling 2.4.0-test10 kernel Corisen
2000-11-10 16:23 ` Georg Nikodym
2000-11-10 17:23 ` Keith Owens
2000-11-10 18:25 ` Georg Nikodym
2000-11-10 18:44 ` Anton Altaparmakov
-- strict thread matches above, loose matches on Subject: below --
2000-11-13 9:47 Linux 2.2.18pre21 willy tarreau
2000-11-13 7:00 willy tarreau
2000-11-10 10:59 Arnaud S . Launay
2000-11-10 3:07 ` Alan Cox
2000-11-10 3:44 ` David S. Miller
2000-11-10 11:35 ` Benjamin Herrenschmidt
2000-11-10 15:34 ` David S. Miller
2000-11-10 15:42 ` Tom Rini
2000-11-10 10:52 ` David S. Miller
2000-11-16 14:07 ` Matthias Andree
2000-11-16 16:16 ` Andrea Arcangeli
2000-11-16 19:52 ` jesse
2000-11-16 21:40 ` Alan Cox
2000-11-18 10:07 ` Rogier Wolff
2000-11-18 17:32 ` kuznet
2000-11-18 17:34 ` Rogier Wolff
2000-11-18 17:47 ` kuznet
2000-11-18 17:51 ` Rogier Wolff
2000-11-16 22:56 ` Matthias Andree
2000-11-17 6:30 ` Peter Samuelson
2000-11-17 6:40 ` H. Peter Anvin
2000-11-17 11:22 ` Peter Samuelson
2000-11-17 17:35 ` H. Peter Anvin
2000-11-17 11:34 ` Matthias Andree
2000-11-17 19:23 ` jesse
2000-11-18 20:44 ` Pavel Machek
2000-11-18 1:38 ` Nix
2000-11-21 4:19 ` Peter Samuelson
2000-11-10 10:49 willy tarreau
2000-11-10 10:40 willy tarreau
2000-11-10 9:28 willy tarreau
2000-11-10 9:44 ` Matti Aarnio
2000-11-10 9:57 ` Constantine Gavrilov
2000-11-10 10:14 ` Matti Aarnio
2000-11-10 10:22 ` Constantine Gavrilov
2000-11-10 10:51 ` Matti Aarnio
2000-11-10 19:11 ` Thomas Davis
2000-11-10 10:18 ` Constantine Gavrilov
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=20001110112146.12035.qmail@web1103.mail.yahoo.com \
--to=wtarreau@yahoo.fr \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=const-g@xpert.com \
--cc=linux-kernel@vger.kernel.org \
--cc=matti.aarnio@zmailer.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
all inboxes | Powered by JetHome®