Varnish restarting sporadically... losing entire cache...

[Ben Nowacky]

Okay, so there has to be something I'm doing wrong still.. I know I'm on a 32 bit system (centos), but even lowering threads, ulimit -s to all values between 32 and 1024, and even trying to adjust thread_pool_stack, I can't keep varnish running for more than 10 minutes at a time under load.

There /has/ to be something I"m doing wrong. For some reason, even though they are running, i don't have anything in syslogs. Unfortunately, I'm not the linux pro i should be to enable and get a coredump of the daemon running.

- Is anyone else running varnish on a 32 bit OS? (centos / redhat)
- Is seg fault  and stop / start every 4-10 minutes normal in this case and should i just deal?
- If not, what startup commands are you using to keep things under control?

Just doesn't make sense that varnish is /this/ unstable in a 32 bit os... Seems that if it were this bad for everyone, it would be completely unusable on anything BUT 64 bit architecture.

(our servers are all remote, or we would have upgraded already. Doing a remote upgrade on live production servers is a bit scary as we're concerned about other libraries not functions with a new kernel, and how much debugging and fixing are we going to have to be doing!).

Thanks in advance !

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.varnish-cache.org/lists/pipermail/varnish-misc/attachments/20100706/9b3a0f27/attachment-0003.html>