This was definitely not caused by too many connections or the conntrack
table being full. In my test setup there were only five people trying to
connect... two people who were having the problem and three of us that it
worked fine for. Still the strange thing is the exact same iptables setup
work
Is there a way to configure haproxy so it deals with available backends
ressources (number of active connexions) as "sharable quotas", a bit like
Linux IP QoS can do for traffic shaping ?
ie. do a best effort to attribute a minimum number of active cnx for a
frontend when there are that much requ
Hey,
Attached, and linked here:
http://consoleninja.net/p/haproxy_intel_hash.diff
... is a patch to HAProxy 1.3.22 that uses intel's nehalem hardware CRC32
instruction for the URI hashing.
I did some tests here:
http://dormando.livejournal.com/522027.html
With this bench tool:
http://consoleninja
> I did some tests here:
> http://dormando.livejournal.com/522027.html
> With this bench tool:
> http://consoleninja.net/p/intel_hash_bench.c
> ... which I hadn't even compiled with -O2 during my tests.
For what it's worth, compiled with -O2:
haproxy, without extra tests:
0m16.883s (though it wav
I'm a little confused about multipart ACLs. Are conditions ORed or ANDed
together as they're added on?
For example, what should happen when I set up the following?
acl my_cond hdr_dom(host) site1.com
acl my_cond path_beg /special-case
use_backend www2 if my_cond
default_backend www1
Should my
On Sun, Dec 20, 2009 at 11:26:43PM -0500, Ben Koski wrote:
> I'm a little confused about multipart ACLs. Are conditions ORed or ANDed
> together as they're added on?
>
> For example, what should happen when I set up the following?
>
> acl my_cond hdr_dom(host) site1.com
> acl my_cond path_beg /s
6 matches
Mail list logo