Re: [squid-users] Web server acceleration with squid and clustering with high availability

Henrik Nordstrom wrote:
> sön 2007-01-07 klockan 15:58 +0200 skrev Forse:
>
>
>> o Setup squid 1 (one that is running on same machine as web server) so
>> it uses squid2 (one on VPS) as sibling and forwards all media requests
>> to it.
>> o Squid2 in turn will fetch media content when asked from squid1 and
>> then serve it from own cache
>> o Squid1 monitors squid2 and if it goes down will serve media requests
>> itself until squid2 comes back online.
>>
>
> This is a parent relation with the default option, and with the origin
> server as secondary parent without the default option.
>

But won't this still push all the traffic through Squid 1*? Shouldn't
the origin server be performing service monitoring on Squid 2 and
sending 302's (redirecting requests directly to Squid 2) when it's up
and serving traffic natively when it's not?

> Regards
> Henrik
>

As always, correct me when I'm wrong. It happens much more frequently
then I would like.

Chris

* I'm assuming here that you are suggesting these settings on Squid 1.
Always sending media requests to Squid 2 and specifying Squid 1 as the
default parent etc. would not allow failure of Squid 2.
Received on Tue Jan 09 2007 - 11:35:31 MST