Re: [squid-users] 'squid -k reconfigure' and connectivity breaking

From: Eliezer Croitoru <eliezer_at_ec.hadorhabaac.com>
Date: Fri, 22 Apr 2011 16:47:55 +0300

On 22/04/2011 09:12, Eugene M. Zheganin wrote:

> Hi.
>
> On 20.04.2011 13:48, Helmut Hullen wrote:
>>> # stat swap.state
>>> 95 4012314 -rw-r----- 1 squid squid 16326000 10203960 "Apr 19
>>> 14:02:21 2011" "Apr 20 10:53:45 2011" "Apr 20 10:53:45 2011" "Apr 19
>>> 14:02:21 2011" 16384 19968 0 swap.state
>> What about deleting the old cache and restarting with
>>
>> squid -z
> Yeah. Thanks. Actually, I should think about this myself and it was
> really stupid not to recreate the cache after upgrade between major
> versions.
> It helped against LFS v1.
>
> But reconfigure still takes 4 seconds between first "Closing HTTP
> connection" and final "Ready to serve requests".
> I really hope this soft reconfiguring will be implemented in close
> future.
>
> Thanks.
> Eugene.

i was thinking about a similar problem before.
i have clients using the squid proxy and i cant just break their
connection using a reconfigure.
so i was thinking about another way to do a "long reconfigure steps".
as a production proxy i added a second squid instance on the same
machine with the new config but on other ports and ip.
then i used the linux iptables to change the ruleset of every new
connection intercepted and not established to be routed\redirected
to the second working proxy.
then after couple of minutes when all the old connections of the clients
ended i can reconfigure the main instance wait and see that it's ready
and working
(all done by bash script) and the same as the first step returning all
the clients to the main proxy.

it's not a solution for soft reconfigure but it's better then anything
else i could think of to make sure that my clients wont have problems
while i'm doing a reconfigure.

Regards
Eliezer
Received on Fri Apr 22 2011 - 13:48:00 MDT

This archive was generated by hypermail 2.2.0 : Sat Apr 23 2011 - 12:00:04 MDT