Re: [squid-users] cache_peer_domain with file list

Waitman Gobble wrote:
> Waitman Gobble wrote:
>> Amos Jeffries wrote:
>>> ?huh? your example omits cache_peer order.
>>> Which is half the critical config for failover sequencing.
>>> {important stuff in previous email}
>>> Amos
>>>
>
>
> ok this squid.conf seems to be working for me. sans cache-mgr stuff.
>
>
> http_port 80 accel defaultsite=waitman.net vhost
> access_log /usr/local/squid/var/logs/access.log squid
> cache_store_log none
> cache_mgr {email}
> cachemgr_passwd {assword} all
>
> cache_dir ufs /cache 307200 16 256
> maximum_object_size 65536 KB
> cache_mem 1208 MB
> cache_effective_user squid
> cache_effective_group squid
> coredump_dir /cache
>
> acl s1 dstdomain "/usr/local/squid/etc/s1"
> http_access allow s1
> acl s2 dstdomain "/usr/local/squid/etc/s2"
> http_access allow s2
> http_access deny all
>
> cache_peer 172.16.10.5 parent 80 0 no-query originserver name=server_s1
> login=PASS
> cache_peer_access server_s1 allow s1
>
> cache_peer 172.16.10.7 parent 80 0 no-query originserver name=server_s2
> login=PASS
> cache_peer_access server_s2 allow s2
>
> cache_peer 172.16.10.5 parent 80 0 no-query originserver name=bu_s1
> login=PASS
> cache_peer_access bu_s1 allow s2
>
> cache_peer 172.16.10.7 parent 80 0 no-query originserver name=bu_s2
> login=PASS
> cache_peer_access bu_s2 allow s1
>
>
>
> Basically I wanted an inexpensive solution for redundancy, hosting many
> sites on inexpensive equipment. The current test: With four servers, 2
> squid machines and 2 main servers - if one goes down everything still
> works. If a squid machine and a main server goes down at the same time
> then everything still works. If both squid machines or both main servers
> go down, then I'm SOL but that's unlikely... They're spread out
> geographically so it would 'prolly take something like a nuclear war for
> that to happen. (crossing fingers).
>
> The squid machines are also ns servers, which say 'i'm master of domain
> x, i serve http for domain x' - the domain in question. So the
> redundancy begins at the nameserver field in the domain record.
>
> So it seems to work so far with my limited test, I'll see what happens
> if I set up a bunch of domains. It also seems scalable.
>
> However, you mentioned "cache_peer order" - it seems to go in the order
> specified in squid.conf - i've reviewed the docs - i don't see a
> parameter to set the order?? just checking. maybe i missed something.
>

Yes I meant order of lines in squid.conf.

You have made a basic (common?) CDN configuration.
It scales vertically very well for a small number of domains. But as the
domains increase its gets limited by how fast you can change the domains
  list on all Squid.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE6 or 3.0.STABLE18
   Current Beta Squid 3.1.0.13