W3C home > Mailing lists > Public > ietf-http-wg@w3.org > July to September 2012

Re: HTTP 2.0 and a Faster, more Mobile-friendly web

From: James M Snell <jasnell@gmail.com>
Date: Tue, 31 Jul 2012 12:59:52 -0700
Message-ID: <CABP7RbeugXO1P+gcyYPBA4KEszu2fzEZ=mEprqLWO1=zVsCrdw@mail.gmail.com>
To: Henrik Frystyk Nielsen <henrikn@microsoft.com>
Cc: "ietf-http-wg@w3.org" <ietf-http-wg@w3.org>, Gabriel Montenegro <Gabriel.Montenegro@microsoft.com>, Rob Trace <Rob.Trace@microsoft.com>, "Adalberto Foresti (MS OPEN TECH)" <aforesti@microsoft.com>
Excellent to see this kind of analysis being performed. A few comments
inline..

On Sun, Jul 29, 2012 at 1:14 PM, Henrik Frystyk Nielsen <
henrikn@microsoft.com> wrote:
[snip]

> The SPDY proposal has been great for raising awareness of Web performance.
> It takes a “clean slate” approach to improving HTTP.
>
> To compare the performance of SPDY with HTTP/1.1 we have run tests
> comparing download times of several public web sites using a controlled
> tested study. The test uses publically available software run with mostly
> default configurations while applying all the currently available
> optimizations to HTTP/1.1. You can find a preliminary report on the test
> results here: http://research.microsoft.com/apps/pubs/?id=170059. The
> results mirror other data (
> http://www.guypo.com/technical/not-as-spdy-as-you-thought) that indicate
> mixed results with SPDY performance.
>
> Our results indicate almost equal performance between SPDY and HTTP/1.1
> when one applies all the known optimizations to HTTP/1.1. SPDY’s
> performance improvements are not consistent and significant. We will
> continue our testing, and we welcome others to publish their results so
> that HTTP/2.0 can choose the best changes and deliver the best possible
> performance and scalability improvements compared to HTTP/1.1.****
>
> **
>
One of the frustrating issues for me, so far, is that nearly all of the
discussion around HTTP/2.0 to date has centered around the requirements for
browser clients; given the ever growing use HTTP as an enabler for
integration APIs and the ever increasing number of non-browser HTTP client
applications, it would be very interesting to formally compare and analyze
the performance of SPDY vs. current HTTP/1.1 for *API* clients and servers.
In my informal testing, I have seen very little difference, if any, between
using SPDY* and a client using persistent HTTP/1.1 connections with
pipelined API requests.
  * with the current http mapping defined in the spdy spec

With a few tweaks here and there to the SPDY+HTTP mapping (e.g. the binary
header encoding I had kicked around previously) I was able to squeeze a bit
more out the SPDY option but the results were certainly not conclusive.

This, of course, was not a formal study and my methodology was far from
rigorous. A more thorough analysis would be required.

- James
Received on Tuesday, 31 July 2012 20:00:40 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Tuesday, 31 July 2012 20:00:50 GMT