Re: [squid-users] Multiple parents

From: Henrik Nordstrom <hno@dont-contact.us>
Date: Wed, 16 May 2001 22:57:55 +0200

As you say it might be a DNS thing. Try configuring the peers using IP
addresses instead.

The connect-timeout argument to cache_peer works once Squid has found
the IP of the peer, and so do the global option.

And if you have never_direct enabled (allow) then Squid-2.4 should add
all of the peers to the list of peers to try before sending an error to
the client.

--
Henrik Nordstrom
Squid Hacker
Andrei B. wrote:
> 
> I have a satellite reception dish with an Europe Online account.
> 
> As Henrik suggested in a previous discussion :
> 
> cache_peer proxy.113.europeonline.net parent 8080 7 no-query login[...]
> cache_peer proxy.114.europeonline.net parent 8080 7 no-query login[...]
> cache_peer proxy.115.europeonline.net parent 8080 7 no-query login[...]
> cache_peer proxy.103.europeonline.net parent 8080 7 no-query login[...]
> 
> All are activated. He told me that squid will see that if a peer is
> down, it will switch to another one with a delay until a dead peer is
> detected.
> 
> Due to the nature of the link, only one of these parent caches can be
> active at any one time. I wanted to put them all active, so that I
> don't have to edit squid.conf and reload config everytime I bring the
> link up (modem is used for upload).
> 
> The following thing (and it's annoying) happens:
> - client issues a request.
> - squid attempts to use the first parent in the above list (which is
> down, by the way)
> - after a very long time, similar to that of a failed DNS lookup or
> failed to connect on a direct path, I get the message "peer cache is
> down"
> - client issues a reload on the URL
> - squid tries the second peer, and if down, the same thing happens.
> 
> Suppose 103 is up, the rest are down. It takes the client a request and
> 3 subsequent reloads on an error page until squid gets to use the last
> peer in the list and navigation starts to work. Pretty nasty.
> 
> Any suggestions on how to change this behaviour? (If possible)
> 
> I set connect-timeout=5 (seconds) on the cache_peer line, with no
> results.
> 
> dead_peer_timeout is not usefull, it's a TCP connection.
> 
> connect_timeout seems to influence this, but also gives timeout errors
> on slow servers.
> 
> peer_connect_timeout, although by description it should address this,
> seems to have no effect. I set it to 5 seconds, and my connect still
> waits about 2 minutes to timeout, then for the next request, peer is
> changed.
> 
> ANy help is welcome. Thanks.
> 
> =====
> ing. Andrei Boros
> Centrul pt. Tehnologia Informatiei
> Societatea Romana de Radiodifuziune
> 
> __________________________________________________
> Do You Yahoo!?
> Yahoo! Auctions - buy the things you want at great prices
> http://auctions.yahoo.com/
Received on Wed May 16 2001 - 16:09:29 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:00:09 MST