using parallel varnishes

[David Birdsong]

On Thu, Jun 17, 2010 at 3:31 PM, Don Faulkner <dfaulkner at pobox.com> wrote:
> I would like to hear more about how you're combining varnish and haproxy, and what you're trying to achieve.
>
> I'm just getting started with varnish, but I've used haproxy before.
>
> I'm trying to construct a cluster of caching, load balancing, and ssl termination to sit in front of my web infrastructure. In thinking about this, I seem to be caught in an infinite loop.
>
> I've seen several threads suggesting that the "right" way to build the web pipeline is this:
>
> web server -> cache -> load balancer -> ssl endpoint -> (internet & clients)
>
> But, in this case, all I have the load balancer doing is balancing between the various caches.
Is there a something that you don't like about this setup?

> On the other hand, if I reverse this and put the cache in front, then I'm caching the output of the load balancers, and there's no load balancing for the caches.
>
> I obviously haven't thought this through enough. Could someone pry me out of my loop?
> --
> Don Faulkner, KB5WPM
> All that is gold does not glitter. Not all those who wander are lost.
>
> On Jun 17, 2010, at 1:50 PM, Ken Brownfield wrote:
>
>> Seems like that will do the job.
>>
>> You might also want to look into the consistent hash of haproxy, which should provide cache "distribution" over an arbitrary pool.  Doing it in varnish would get pretty complicated as you add more varnishes, and the infinite loop potential is a little unnerving (to me anyway :)
>>
>> We wanted redundant caches in a similar way (but for boxes with ~1T of cache) and set up a test config with haproxy that seems to work, but we haven't put real-world load on it yet.
>> --
>> Ken
>>
>> On Jun 17, 2010, at 6:54 AM, Martin Boer wrote:
>>
>>> Hello all,
>>>
>>> I want to have 2 servers running varnish in parallel so that if one fails the other still contains all cacheable data and the backend servers won't be overloaded.
>>> Could someone check to see if I'm on the right track ?
>>>
>>> This is how I figure it should be working.
>>> I don't know how large 'weight' can be, but with varnish caching > 90% that impact would be affordable.
>>> Regards,
>>> Martin Boer
>>>
>>>
>>> director via_other_varnish random {
>>> .retries = 5;
>>> {
>>>    .backend = other_server;
>>>    .weight = 9;
>>> }
>>> # use the regular backends if the other varnish instance fails.
>>> {
>>>    .backend = backend_1;
>>>    .weight = 1;
>>>  }
>>> {
>>>    .backend = backend_2;
>>>    .weight = 1;
>>>  }
>>> {
>>>    .backend = backend_3;
>>>    .weight = 1;
>>>  }
>>> }
>>>
>>> director via_backends random {
>>>  {
>>>    .backend = backend_1;
>>>    .weight = 1;
>>>  }
>>> {
>>>    .backend = backend_2;
>>>    .weight = 1;
>>>  }
>>> {
>>>    .backend = backend_3;
>>>    .weight = 1;
>>>  }
>>> }
>>>
>>>
>>> sub vcl_recv {
>>> if ( resp.http.X-through-varnish > 0 ) {
>>>    # other varnish forwarded the request already
>>>    # so forward to backends
>>>    set req.backend = via_backends;
>>>    remove resp.http.X-through-varnish;
>>> } else {
>>>    # try the other varnish
>>>    resp.http.X-through-varnish = 1;
>>>    set req.backend = via_other_varnish;
>>> }
>>> ..
>>>
>>>
>>> _______________________________________________
>>> varnish-misc mailing list
>>> varnish-misc at varnish-cache.org
>>> http://lists.varnish-cache.org/mailman/listinfo/varnish-misc
>>
>>
>> _______________________________________________
>> varnish-misc mailing list
>> varnish-misc at varnish-cache.org
>> http://lists.varnish-cache.org/mailman/listinfo/varnish-misc
>
>
> _______________________________________________
> varnish-misc mailing list
> varnish-misc at varnish-cache.org
> http://lists.varnish-cache.org/mailman/listinfo/varnish-misc
>