[Ganglia-developers] Dying data collection thread.

[Steven Wagner]

So, I come back from a meeting and one of my cluster graphs is empty (the 
meeting lasted about an hour).  The other two continue to be updated.

I'm not logging anymore so I don't know exactly what happened, but the data 
source is still active.  I restarted gmetad and it's updating just fine 
now.  I can only assume that something caused the data collecting thread 
for the source (the big pre-2.5.0 Linux cluster) to bomb out.

I notice there was one fix applied to CVS Friday afternoon that I didn't 
hear about.  If this happens again (i.e. if it wasn't a freak accident, 
like a downpour of herring), I'll apply that patch and give it another shot.

Is this a good time to suggest err_msg calls writing to an error log in 
addition to stdout in 2.5.1? :)