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

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
access_log /dev/null
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?

Regards
Jinge
Received on Fri Jul 05 2013 - 06:27:02 MDT