[UGLY HACK] Proof of concept multipart/byteranges support and connection sharing

[Michael Ellerman]

On Mon, 2006-05-22 at 08:32 -0500, John Arbash Meinel wrote:
> Michael Ellerman wrote:
> > As another data point, doing the byterange stuff without the connection
> > sharing gets me these rough numbers:
> > 
> > real    29m8.436s
> > real    31m13.397s
> > real    29m5.429s
> > 
> > So it's definitely helping, although the bulk of the improvement is the
> > byterange stuff.
> 
> Well, what I saw was this:
> current urllib 50m, pycurl 50m, byterange 30m, byterange + sharing 20m.
> Is that about right?

Yep, that's right.

> In general, thanks for looking into this. It looks like a lot of
> potential. (And we still haven't had to do anything custom on the server
> side.)

No worries. I think it'd be really great to not need a smart server, so
anything we can do to make regular HTTP performance better is a good
thing IMHO.

Having said that 20 minutes is still a long way from fast. I can wget
30MB of data from bazaar-vcs.org (roughly equivalent to what a branch is
doing), in 2m38s. So we're a long way from being limited by the network.

cheers

-- 
Michael Ellerman
IBM OzLabs

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 191 bytes
Desc: This is a digitally signed message part
Url : https://lists.ubuntu.com/archives/bazaar/attachments/20060523/2dd63268/attachment.pgp