Dans son courrier, du Thu, 04 Dec 1997 09:24:24 CST, Alex Rousskov
<rousskov@plains.NoDak.edu> ecrivez:
| On Thu, 4 Dec 1997, Bill Petersen wrote:
|
| > I am running Squid 1.1.18 I configure squid to
| >
| > cache_mem 8
| >
| > but find that over a week or so, squid uses over 100MB
| > of RAM. WHY?
|
| Read the documentation on "cache_mem" please. "cache_mem" does not specif
y
| the total memory requirement. "cache_mem" stands for the amount of RAM
| reserved for intransit and "hot" objects only.
|
| > Is there any way to limit how much RAM
| > squid will use?
|
| There is only one way, I guess: Limit your cache swap size. Release notes
| have a description on how to calculate Squid memory requirement given swa
p
| size.
It's not enough : we observe squid (1.1.18) ever growing tough the cache
swap size is stationary. Just after boot the size of the squid proc (vmsize
on linux) is about 90Mo and, 4 days later, is size is about 160Mo !
The only solution till now is to kill and reboot squid once per week...
May be the use of the memory_pools parameter solve that ?
Christian Claveleira - CRU/University of Rennes 1 (claveleira@cru.fr)
Received on Thu Dec 04 1997 - 08:24:14 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:37:50 MST