[squid-users] xcalloc error when installing squid in container on CentOS 9 host

[Alex Rousskov]

On 8/2/22 04:22, Frank Ansari wrote:
> Hi,
> 
> I have found a weird issue with CentOS 9.
> 
> So far I had squid running on a CentOS 8 system within an Alpine Linux 
> Container and this has worked.
> 
> Now I installed CentOS 9 and also latest Alpine Linux with squid 5.5.
> 
> Squid refuses to start and when I run "squid -z" I get this error:
> 
> [root at 324ae7d5e4db /]# 2022/08/01 08:01:47| FATAL: xcalloc: Unable to 
> allocate 1073741816 blocks of 432 bytes!

Sounds like https://bugs.launchpad.net/ubuntu-docker-images/+bug/1978272

You may need to set max_filedescriptors or otherwise reconfigure your OS 
so that Squid does not try to allocate 1073741816 432-byte descriptor 
structures based on your current OS settings.

I do not know whether that allocation is a Squid bug (e.g., Squid is 
misinterpreting some negative "no limit" number as a positive 1073741816 
number).

Alex.


> 2022/08/01 08:01:47| Squid Cache (Version 5.5): Terminated abnormally.
> CPU Usage: 0.002 seconds = 0.000 user + 0.002 sys
> Maximum Resident Size: 31744 KB
> Page faults with physical i/o: 0
> 
> My question: has anybody the same issue? Why is squid asking for 432 GB?
> 
> This seems to have nothing to do with my squid.conf. Whatever I change 
> there has no effect at all.
> 
> The CentOS 9 VM is running on Proxmox and has 4 GB RAM.
> 
> I also tried to install Debian 11 and Ubuntu 20 and 22 containers and 
> similar errors.
> 
> My last try was to install a CentOS 9 conatiner on the CentOS 9 host and 
> also this gives the same error.
> 
> I have now installed squid 5.5 directly on the OS but I still curios why 
> it refuses to run in any kind of container.
> 
> 
> 
> _______________________________________________
> squid-users mailing list
> squid-users at lists.squid-cache.org
> http://lists.squid-cache.org/listinfo/squid-users