On Thu, May 12, 2011 at 11:49 AM, Mark Phippard <markp...@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
