Re: [squid-users] Squid 3.2.0.11 FATAL: kid2 registration timed out

On 14/09/11 20:58, Saleh Madi wrote:
> Hi,
>
> My squid configuration is
>
> workers 3
> cpu_affinity_map process_numbers=1,2,3 cores=4,10,12
>
> if ${process_number} = 1
> cache_dir aufs /cache1/squid1 100000 16 256
> cache_dir aufs /cache1/squid2 100000 16 256
> redirect_program /usr/bin/squidGuard -c /etc/squid/squidGuard.conf
> redirect_children 8
> redirector_bypass on
> endif
>
> if ${process_number} = 2
> cache_dir aufs /cache2/squid1 100000 16 256
> cache_dir aufs /cache2/squid2 100000 16 256
> redirect_program /usr/bin/squidGuard -c /etc/squid/squidGuard.conf
> redirect_children 8
> redirector_bypass on
> endif
>
>
> if ${process_number} = 3
> cache_dir aufs /cache3/squid1 100000 16 256
> cache_dir aufs /cache3/squid2 100000 16 256
> redirect_program /usr/bin/squidGuard -c /etc/squid/squidGuard.conf
> redirect_children 8
> redirector_bypass on
> endif
>
>
> $ ps -uax |grep squid-
> proxy 24131 0.0 0.3 38208 13036 ? S 10:30 0:00
> (squid-coord-4) -YC -f /etc/squid3/squid.conf
> proxy 24132 4.9 3.4 158528 125876 ? Sl 10:30 0:22
> (squid-3) -YC -f /etc/squid3/squid.conf
> proxy 24193 3.5 3.5 160144 127424 ? Sl 10:30 0:15
> (squid-1) -YC -f /etc/squid3/squid.conf
>
> But when I stop squid and restart again the squid-2 process not started
> and become this error "FATAL: kid2 registration timed out", how I can
> fix this problem.

Is your shutdown_lifetime timeout sufficiently long for each worker to
send its ~2GB of cache index to disk?
  If not, the index storage will be incomplete and workers will hang
while re-indexing the entire 200GB cache object by object before
completing the registration. This could take hours.

This bug is being tracked at
http://bugs.squid-cache.org/show_bug.cgi?id=3268 where you will also
find a workaround code alteration that can be made.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE9 or 3.1.15
   Beta testers wanted for 3.2.0.11