Re: [squid-users] Squid BUG?

On Tue, 21 Apr 2009 12:54:53 +1200 (NZST), "Amos Jeffries"
<squid3_at_treenet.co.nz> wrote:
[cut]
>> 2009/04/20 18:05:20| Store rebuilding is 822.48% complete

> what type of file system is in use?

ext3

> with what settings?

4x 300GB SAS disks

cache_swap_low 80
cache_swap_high 85

cache_dir aufs /var/cache/proxy/cache1 256000 256 256
cache_dir aufs /var/cache/proxy/cache2 256000 256 256
cache_dir aufs /var/cache/proxy/cache3 256000 256 256
cache_dir aufs /var/cache/proxy/cache4 256000 256 256

maximum_object_size 256 MB
minimum_object_size 1 KB

cache_replacement_policy heap LFUDA

Now (that's why does not work anymore):

/dev/sdb1 276G 262G 0 100% /var/cache/proxy/cache1
/dev/sdc1 276G 262G 0 100% /var/cache/proxy/cache2
/dev/sdd1 276G 262G 0 100% /var/cache/proxy/cache3
/dev/sde1 276G 262G 0 100% /var/cache/proxy/cache4

Before crash was 20 or 35% free disk space on each disk, and was like that
for 6 weeks (then reached the limits and was not growing anymore until the
upgrade to STABLE14 crashed the box).

> with what disk available?
> on what operating system?

BlueWhite64 (an unofficial 64 bits Slackware port).

> is it rebuilding after saying DIRTY or CLEAN cache?

CLEAN after upgrade, DIRTY after crashes.

> does deleting the swap.state file(s) when squid is stopped fix things?

I will try.

The stranger think was store rebuild reporting > 100%.

Thanks,

Herbert.
Received on Tue Apr 21 2009 - 00:15:05 MDT