[squid-users] config trouble moving to squid 3.1

From: Preller, Markus <Markus.Preller_at_uk-erlangen.de>
Date: Wed, 29 Feb 2012 13:16:22 +0100

Hi,
we've been running squid 2.5 and apache 2.x on one box for years now without a problem.

Server IP: 192.168.10.21
DNS-entry: proxy.mydom.de

Service IP: 192.168.10.22
DNS-entry: cms.mydom.de

Squid and Apache are set up to only bind to 192.168.10.22.

So squid was set up as a reverse proxy/accelerator using the following
parameters in squid.conf:
httpd_port 192.168.10.22:80
httpd_accel_host virtual # we're using apache name-based vhosts
httpd_accel_port 81 # apache listens on 192.168.10.22:81
httpd_accel_with_proxy on
httpd_accel_uses_host_header on

In httpd.conf you find:
Listen 192.168.10.22:81
NameVirtualHost 192.168.10.22:81

and dozens of

<VirtualHost 192.168.10.22:81>
    ServerName www.anyname.dom
    ...
    ...
</VirtualHost>

Our DNS defines cms.mydom.de as an alias for each ServerName used in a VirtualHost entry.
Now I'm trying to build the same setup with squid 3.1 on a CentOS 6.2 system while leaving
the apache config untouched.

So I replaced the lines from squid 2.5

...
httpd_port 192.168.10.22:80
httpd_accel_*
...

with

...
http_port 192.168.10.22:80 accel defaultsite=192.168.10.22:81 vhost
...

which gives me a TCP_MISS/403 in squid access.log. When I compare
the logs from squid 2.5 with squid 3.1 I can see that the GET references
differ between the logs:

in the 2.5 logs I find: ... GET http:// cms.mydom.de:81/...
in the 3.1 logs I find: ... GET http:// cms.mydom.de/...

Is there something missing in my squid 3.1 config?
Where is my fault? Your help would be appreciated.
 

best regards
Markus Preller
 
Received on Wed Feb 29 2012 - 12:16:27 MST

This archive was generated by hypermail 2.2.0 : Wed Feb 29 2012 - 12:00:06 MST