On 09/28/2012 08:36 AM, Fred Leeflang wrote:
I just ran siege from the internal network to haproxy first; It would
seem that the issue doesn't happen here (earlier tests were to the
external IP on the BSD firewall, this one to the 10.x.x.x interface),
so it might be that the BSD firewall is causing issues here?
Hmm, I just realized that since this is from the internal network, I
hardcoded the server in /etc/hosts to one haproxy frontend. For
completeness, I also ran the check on the other haproxy which seems to
be working fine as well.
Going directly to nginx instead of haproxy results in about the same
number of transaction per second (approx. 200 which may or may not be a
limit caused by siege or simply the rest of the site) so I guess this
means haproxy is not the limiting factor here. I'm affraid the problem
may be mostly in the BSD firewall.
