[squid-users] tcp_outgoing_address and ICAP server

[Amos Jeffries]

On 25/01/2015 11:43 p.m., Marcus Kool wrote:
> 
> 
> On 01/24/2015 11:24 PM, Amos Jeffries wrote:
>> On 25/01/2015 9:39 a.m., Marcus Kool wrote:
>>>
>>>
>>> On 01/24/2015 10:15 AM, Amos Jeffries wrote:
>>>> On 22/01/2015 10:11 a.m., Marcus Kool wrote:
>>>>> I am using Squid 3.4.9 and have an issue with tcp_outgoing_address.
>>>>>
>>>>> The Squid server is connceted to the internet with multiple NICs and
>>>>> uses
>>>>>      tcp_outgoing_address a.public.IP.address
>>>>>
>>>>> and also want to use an ICAP server on the same host using
>>>>>
>>>>> icap_service  reqmod_urlfilterdb   reqmod_precache
>>>>> icap://a.local.ip.address:1344/reqmod_icapd  bypass=off  routing=on
>>>>> on-overload=wait ipv6=off
>>>>>
>>>>> It seems that Squid binds the connection to the ICAP server the
>>>>> same way
>>>>> it binds
>>>>> connections to webservers using the rule with tcp_outgoing_address
>>>>> and that it not desired nor workable.
>>>>>
>>>>> I tried
>>>>>
>>>>> acl myicaphost dst a.local.ip.address
>>>>> tcp_outgoing_address a.public.IP.address !myicaphost
>>>>>
>>>>> but Squid issues the following errors:
>>>>> 2015/01/21 21:58:32 kid1| WARNING: myicaphost ACL is used in context
>>>>> without an HTTP request. Assuming mismatch.
>>>>> 2015/01/21 21:58:32 kid1| commBind: Cannot bind socket FD 10 to
>>>>> XX.XX.XX.XX: (99) Cannot assign requested address
>>>>> 2015/01/21 21:58:32 kid1| essential ICAP service is down after an
>>>>> options fetch failure: icap://XX.XX.XX.XX:1344/reqmod_icapd
>>>>> [down,!opt]
>>>>>
>>>>> So the question is how to send web traffic over a specific NIC and
>>>>> traffic to the ICAP server over an other (default?) NIC ?
>>>>
>>>>
>>>> Please try the attached patch against Squid-3.4. It should make your
>>>> config work.
>>>>
>>>> Amos
>>>
>>> Thank you for the patch.
>>> It resolves 1 issue: there is no longer the warning
>>>     WARNING: myicaphost ACL is used in context without an HTTP request.
>>> Assuming mismatch.
>>>
>>> But the binding to the wrong NIC with the external IP still happens:
>>>
>>> 2015/01/24 17:19:48.027 kid1| Xaction.cc(133) openConnection:
>>> Adaptation::Icap::OptXact opens connection to 10.10.0.6:1344
>>> 2015/01/24 17:19:48.027 kid1| AsyncCall.cc(18) AsyncCall: The AsyncCall
>>> Adaptation::Icap::Xaction::noteCommConnected constructed, this=0x1d9d7e0
>>> [call53]
>>> 2015/01/24 17:19:48.027 kid1| comm.cc(549) comm_openex: comm_openex:
>>> Attempt open socket for: a.public.IP.address
>>> 2015/01/24 17:19:48.027 kid1| comm.cc(590) comm_openex: comm_openex:
>>> Opened socket local=a.public.IP.address remote=[::] FD 10 flags=1 :
>>> family=2, type=1, protocol=6
>>>
>>> The firewall and routing was changed to allow traffic from the external
>>> IP to
>>> the internal IP so for us the urgency of the issue is low, but
>>> the binding remains on the external IP despite the ACL saying not to
>>> do it.
>>
>> Aha, conceptual problem.
>>
>> tcp_outgoing_address does not forbid things. There is no "allow/deny"
>> action, just a set-IP action. It either sets the IP or it leaves it
>> alone.
> 
> Do you agree that the binding should not take place if a socket
> is created with a destination address 'myicaphost' ?  The myicaphost is
> 10.10.0.6 and the comm debug output above shows that the socket *is* bound.

I cant agree because I dont know why it was binding. Squid only uses
bind() if there is an explicit outgoing address required to be used.


> 
>> Your rule sets the IP when the dst is non-myicaphost. So what
>> tcp_outgoing_address rule or OS level routing rule matches when it *is*
>> myicaphost?
> 
> Sorry, I don't know which routing decision is taken. All I know is that
> the routing has been changed to make the connection to the ICAP server
> work.
> 
> I tried to show with the comm debug output that the connection to the
> ICAP server (10.10.0.6) is still bound.  I replaced the public IP address
> with "a.public.IP.address"  (I do not want to show the real IP but
> it is definitely a public IP address).

That obfuscation is fine, as long as its clear which IP is which.

Perhapse a new debug trace after applying the patch will help resolve
what the remaining problem is?

Amos