W3C home > Mailing lists > Public > ietf-http-wg@w3.org > July to September 2014

Re: Large Frame Proposal

From: Jason Greene <jason.greene@redhat.com>
Date: Wed, 9 Jul 2014 21:36:14 -0500
Cc: Mark Nottingham <mnot@mnot.net>, Greg Wilkins <gregw@intalio.com>, David Krauss <potswa@gmail.com>, Patrick McManus <pmcmanus@mozilla.com>, Poul-Henning Kamp <phk@phk.freebsd.dk>, HTTP Working Group <ietf-http-wg@w3.org>
Message-Id: <55861623-9622-48F6-AD94-C506A55DC778@redhat.com>
To: Roberto Peon <grmocg@gmail.com>

On Jul 9, 2014, at 8:03 PM, Roberto Peon <grmocg@gmail.com> wrote:

> Will double-bleh do?
> 
> Nope? I thought not.
> 
> The proposal will work just fine so long as you don't get a pair of entites on the path that do the stupid together.
> Hopefully this isn't something that would happen today, but who knows.
> With a smaller max frame size and continuations, you need implementations that screwed up by more than just setting a single variable too big in order to screw with latency.

For this to be accurate continuations would have to be improved to allow multiplexing. If they donít they are equivalent to a large jumbo frame, just written in chunks.

> 
> So, how much do we want to empower folks to shoot themselves in the head in order to deal with the 0.02% usecase?
> 
> -=R

--
Jason T. Greene
WildFly Lead / JBoss EAP Platform Architect
JBoss, a division of Red Hat
Received on Thursday, 10 July 2014 02:36:56 UTC

This archive was generated by hypermail 2.3.1 : Wednesday, 30 March 2016 09:57:09 UTC