[svn.haxx.se] · SVN Dev · SVN Users · SVN Org · TSVN Dev · TSVN Users · Subclipse Dev · Subclipse Users · this month's index

Re: 1.7 Performance via HTTP

From: Justin Erenkrantz <justin_at_erenkrantz.com>
Date: Thu, 12 May 2011 12:24:54 -0700

On Thu, May 12, 2011 at 11:49 AM, Mark Phippard <markphip_at_gmail.com> wrote:
> For Neon, I think it is significant. In my case, 1.7 Neon issued 6,308
> fewer HTTP requests.  My latency is .2 seconds.  So that lopped around
> 21 minutes off the total test time when comparing Neon to Neon.  I
> realize with Serf it is less of an issue.

Yes - for ra_neon, the request count does matter...a lot. =)

FWIW, I found some silliness in serf about how it gathers data to be
put on to the socket - being more efficient at the socket level by
using iovec's more should help reduce socket writes tremendously and
should hopefully bring ra_serf inline with ra_neon over HTTPS. --
justin
Received on 2011-05-12 21:25:23 CEST

This is an archived mail posted to the Subversion Dev mailing list.

This site is subject to the Apache Privacy Policy and the Apache Public Forum Archive Policy.