Re: [squid-users] How to reduce cache_swap after cache disk is full

On 02.04 19:49, Seewo Chen wrote:
> > cache_replacement_policy heap LFUDA
> > cache_swap_low 93
> > cache_swap_high 95
> >
> > question: Why the cache swap don't reduce to 93% after reached 95%?
> > What can I do under those case?

it is probably because those numbers are too close to each other.
You probably should use 95 and 90. Or 90 and 80.

> >>You are using LFUDA to cache maximum size of objects
> >>so that what is your minimum_object_size TAG
> >>configuration? May be because of BIG sized object get
> >>stored in cache so that cache_dir is not maintained to
> >>the 93% to 95%.
>
> maximum_object_size 20480 KB
> minimum_object_size is default , set to 0 KB
>
> now I do the following:
> rm -rf /cache1
> rm -rf /cache2

not needed to remove whole cache, it should be enough to decrease cache
size and let squid to sipe it by itself.

> /etc/rc.d/init.d/squid -z
> reboot
>
> How to prevent this case again?

decrease cache size (9GB?) and make cache_swap_low and cache_swap_high differ a
bit more. 2% is too low.

Also, looking at it, you are running two caches on the same drive. it is
just waste of resources. I recommend you creating one bigger partition and
use one cache_dir. not 20GB, I'd try 18 (with cache_swap_* 95 and 90) or
19 (with cache_swap 90 and 80) GB.

-- 
Matus UHLAR - fantomas, uhlar@fantomas.sk ; http://www.fantomas.sk/
Warning: I wish NOT to receive e-mail advertising to this address.
Varovanie: na tuto adresu chcem NEDOSTAVAT akukolvek reklamnu postu.
Depression is merely anger without enthusiasm.