Re: [squid-users] 2 questions about proxy hierarchy

From: Eugene M. Zheganin <emz_at_norma.perm.ru>
Date: Fri, 08 Jun 2012 15:26:49 +0600

On 07.06.2012 17:19, Amos Jeffries wrote:
> On 7/06/2012 10:48 p.m., Eugene M. Zheganin wrote:
>> Hi.
>>
>> Happy world ipv6 launch day to everybody. :P
>>
>> squid/3.1.12, FreeBSD 8.x|9.x
>>
>> a) why when using ipv6 address, like fd00::316 or, no matter
>> [fd00::316], squid detects that configuration file is corrent, but
>> then I'm immidiately getting "TCP connection to fd00::316/3128
>> failed", but, in the same time, I CAN telnet to the fd00::316 port
>> 3128 ?
>
> More to the point *what* is failing to connect to your Squid and from
> where?
Assume I get one parent squid A, and one child squid, B.
B's IP (v6) is in the parent's config file, like

acl children src fd00::d02/128

B's config has the line like

cache_peer fd00::316 3128 3130 default

or

cache_peer [fd00:316] 3128 3130 default

and some lines like

always_direct deny some-domain-based-acl
always_direct allow all
never_direct allow some-domain-based-acl
never_direct deny all

In this situation I'm starting to get these lines on B:

TCP connection to fd00::316/3128 failed

In the same time I can connect from B's console (telnet fd00::316 3128).
>
>>
>> b) more long story. I think I'm just not getting something. From the
>> 2.6 version I always had to use no-query option for parents. That is
>> because the cold
ZOMG. Did I write this ? I mean 'children'.
>> squid is always detecting the parent proxy as dead, but the weird
>> thing is, it's still capable of communicating to them. I mean I see
>> udp/3130 packets in tcpdump going both ways, and UDP_HIT/000
>> UDP_MISS/000 ICP queries from children on parent proxies.
>> Why is that ?
>
> bugs?
That's too easy to explain. I think the situation when I discover and
report this bug first time for like 10 years is quite impossible.

Eugene.
Received on Fri Jun 08 2012 - 09:27:05 MDT

This archive was generated by hypermail 2.2.0 : Fri Jun 08 2012 - 12:00:02 MDT