Re: [SQU] Run away memory problem

There are some patches for such problems on my Squid-2.3 patch page. See
http://squid.sourceforge.net/hno/patch-2.3.html

Or try the current Squid-2.4 development release. All those patches and
a lot more is in Squid-2.4.

--
Henrik Nordstrom
Squid hacker
Schuster, Dan wrote:
> 
> We have three Squid servers configured the same that are running
> squid-2.3.STABLE4 on RH Linux 2.2.12-20smp,  256MB of RAM and 4G for squid
> cache.
> 
> We have our cache_mem set to 16 MB, and memory_pools turned off.  We have
> used both Linux mallac and dl-malloc with the same results.  We are
> currently using replacement_policy LFUDA.
> 
> The problem is that every day one of our three servers starts to use up all
> of the memory and go into swap space.  When looking at the Memory
> Utilization section in the Cache Manager the "Store Mem Buffer" is taking up
> all the memory around 200MB.    (Store Mem Buffer 4096 49456 197824 197824)
> Shouldn't the cache_mem parameter limit this section of memory to 16MB?
> 
> Anther oddity is that when this happens the Byte Hit Ratios goes negative on
> the General Runtime Information page:
>         Byte Hit Ratios: 5min: -37.1%, 60min: -32.3%
> 
> Also, when we shutdown squid (via squid -k shutdown) to clear up this
> problem squid will not stop.  We have manually shut squid down via kill.
> 
> Has this happened to anyone else?  and is there anything else I can do to
> figure out what is going on?
> 
> Thanks,
> -Dan
> 
> --
> To unsubscribe, see http://www.squid-cache.org/mailing-lists.html
--
To unsubscribe, see http://www.squid-cache.org/mailing-lists.html