Re: [squid-users] Clustering Accelerators

From: Christopher Arnold <chris@dont-contact.us>
Date: Fri, 24 Oct 2003 15:47:39 -0700

I finally figured out what the problem was I was experiencing. It had
to do with the following option:

# TAG: hierarchy_stoplist
# A list of words which, if found in a URL, cause the object to
# be handled directly by this cache. In other words, use this
# to not query neighbor caches for certain objects. You may
# list this option multiple times.
#
#We recommend you to use at least the following line.
hierarchy_stoplist cgi-bin ?

My origin server urls that are being accelerated by squid all have a ?
in them. :)

Took me a while to figure this out but my sibling peer relationship is
now functioning
correctly.

Henrik Nordstrom wrote:

>On Tue, 21 Oct 2003, Christopher Arnold wrote:
>
>
>
>>Is there a way to cluster reverse proxy accelerators so that the
>>seperate caches are not duplicating data but instead check with peers
>>first?
>>
>>
>
>Normal sibling cache peering are supposed to work for this purpose.
>
>
>
>>What is the recommended configuration for two accelerators communicating
>>via ICP?
>>
>>
>
>Same as for normal proxies. ICP is neutral.
>
>If your accelerator uses redirectors then the situation becomes somewhat
>messy and you need to remember to exlude requests from the other cache
>server from redirection (see redirector_access)
>
>Regards
>Henrik
>
>
>

-- 
Christopher Arnold
Systems Administrator                E-Mail:  Chris at Pictage.com 
Pictage, Inc. USA                       Tel:  (310) 525-1629 
Received on Fri Oct 24 2003 - 16:47:28 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:20:39 MST