[149150] in North American Network Operators' Group
RE: pontification bloat (was 10GE TOR port buffers (was Re: 10G
daemon@ATHENA.MIT.EDU (George Bonser)
Sun Jan 29 19:08:05 2012
From: George Bonser <gbonser@seven.com>
To: Jared Mauch <jared@puck.nether.net>
Date: Mon, 30 Jan 2012 00:07:00 +0000
In-Reply-To: <F96A401C-2632-4343-8BAF-0343BCA9AA3B@puck.nether.net>
Cc: North American Network Operators' Group <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
Additionally, ECN is just between hosts, end to end. If an flow is not ECN=
enabled (neither of the ECN bits set), then the routing gear does what it =
always has done, drop a packet. Only if one of the ECN bits is already set=
(meaning the flow is ECN aware, end to end) does the router set the other =
bit to signal congestion. So enabling this on routing gear would have no i=
mpact on user traffic except to allow a better experience for ECN aware flo=
ws.
In other words, allowing this option in the network gear would have no impa=
ct on non-ECN flows and only help flows that negotiated ECN end-to-end at c=
onnection setup. These flows would already be known to be trouble-free for=
ECN else they wouldn't have been able to negotiate it.
