Re: [squid-users] My my squid hit ratio so low?

On 5/07/2013 6:26 p.m., jinge wrote:
> Hi, all.
>
> We use squid for a long time. And recently we upgrade our squid to 3.3.4 and begin to use SMP and rock.
>
> This is our related configure.
>
> include /usr/local/etc/squid/commonbk/bk.global-options.conf
> include /usr/local/etc/squid/commonbk/bk.refresh-pattern.conf
> include /usr/local/etc/squid/commonbk/bk.acl-define.conf
> include /usr/local/etc/squid/commonbk/bk.acl-action.conf
> #include /usr/local/etc/squid/squid.conf
> cache_dir rock /cache1/rock 48000 max-size=31000 max-swap-rate=300 swap-timeout=300
> cache_dir rock /cache2/rock 48000 max-size=31000 max-swap-rate=300 swap-timeout=300
> workers 3
> cpu_affinity_map process_numbers=1,2,3 cores=3,5,7
> if ${process_number} = 1
> include /usr/local/etc/squid/commonbk/backend5a.conf
> endif
> if ${process_number} = 2
> include /usr/local/etc/squid/commonbk/backend5b.conf
> endif
> if ${process_number} = 3
> include /usr/local/etc/squid/commonbk/backend5c.conf
> endif

Lot of sub-config files there. What do they contain?

> access_log /dev/null

Do not waste rsources formatting log lines only to send them to /dev/null.

"access_log none" does what you want in a far more efficient way.

> cache_log /var/log/squid/cache.log
>
>
> and our machine
>
> No LSB modules are available.
> Distributor ID: Ubuntu
> Description: Ubuntu Raring Ringtail (development branch)
> Release: 13.04
> Codename: raring
>
> total used free shared buffers cached
> Mem: 15G 14G 1.5G 0B 27M 6.7G
> -/+ buffers/cache: 7.5G 8.1G
> Swap: 16G 0B 16G
>
> Linux 3.8.0-16-generic #26-Ubuntu SMP Mon Apr 1 19:52:57 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux
>
> /dev/sdb1 137G 13G 125G 9% /cache1
> /dev/sdc1 69G 13G 57G 18% /cache2
> /dev/sdd1 69G 37G 33G 54% /cache3
> /dev/sde1 69G 31G 38G 45% /cache4
> /dev/sdf1 69G 31G 39G 45% /cache5
>
> we found that the Rock won't fill the cache_dir in 48GB. And our ratio is so low
>
> Hits as % of all requests: 5min: 4.3%, 60min: 4.3%
> Hits as % of bytes sent: 5min: 3.3%, 60min: 3.3%
> Memory hits as % of hit requests: 5min: 33.7%, 60min: 32.1%
> Disk hits as % of hit requests: 5min: 8.5%, 60min: 9.0%
>
>
> Can anyone tell me what's wrong with my squid?

Not from just those numbers. This is where an access.log comes in handy.
For identifying where the MISSes are and if any should have been HITs.

>
>
>
>
>
>
>
> Regards
> Jinge
>
>
>
Received on Fri Jul 05 2013 - 06:39:57 MDT