Originally Posted by syg00
Nothing seems too out of order there.You appear to have a problem with udevinfo, not with memory. I would also find it hard to believe that the memory is causing the udevinfo to go ballistic. Possible but unlikely.
Committed_AS: 676152 kB
This is a "best guess" of how much (total) memory you would currently need to satisfy all requests - including mallocs not actually used yet.
Kill the udevinfo, and chase that up. Relax about the memory (non-)usage.
As for the minimal swap usage, I don't know but I'd just ignore it. Happens over time anyway.
BTW - when posting output, use "code" tags so it formats properly.
I'm now confident its not a memory issue at all. When I kill udevinfo the machine runs like a charm. Do you have any idea what would be causing this to start and never stop? It happens when I migrate Squid or Groupwise over using Novell Cluster Services.
It's been running at 100% CPU utilization for 3 days now. If I reboot the machine it will run for about 20 minutes then finally stop. It's when I migrate a service it starts and never stops.
We have servers with the same exact hardware and OS in the cluster that don't have this problem. I'm not even sure where to begin. Any suggestions would be appreciated.