From: Matt Mackall <mpm@selenic.com>
Date: Thu, 05 May 2005 20:36:58 GMT
Subject: Re: Mercurial v0.4d
Message-ID: <20050505203658.GG22038@waste.org>
In-Reply-To: <427A6E3F.5090904@pobox.com>

On Thu, May 05, 2005 at 03:04:31PM -0400, Jeff Garzik wrote:
> Matt Mackall wrote:
> >The web protocol is painfully slow, mostly because it makes an http
> >round trip per file revision to pull. I'm about to start working on a
> >replacement that minimizes round trips.
> 
> Can you make it do HTTP 1.1 pipelining?

Yes, a zsync-like protocol ought to be doable. But you'll still
potentially be doing 16k requests to pull something the size of the
kernel, which isn't very friendly to a web server. So I'm working on a
stand-alone or possibly CGI-based replacement.

My goal is to do something like this:

client                             server
I last saw change N from you 
                                   W, X, Y, and Z are newer here
Send me X, Y, and Z relative to N
                                   Here you go, deltas from N to X to
				   Y to Z, sorted by file

So not only can we be efficient in number of round trips and data
transferred, we can reduce seeks by applying all per-file changes together.
We can also usually avoid decompress/recompress and patch/diff because
both ends will end up storing the same delta.

-- 
Mathematics is the supreme nostalgia of our time.