Yes, I can provide the core. How should I share it? I'll see about setting
the (un)summarized_metrics options. Is there a good way to see which are
used or not?
As for rrdcached this is how we have it running:
/usr/bin/rrdcached -l unix:/var/run/rrdcached/sock -j
/var/lib/rrdcached/journal/ -F
There's a lot less locking when rrdcached runs on tcp for various
reasons. I switched to spinlocks because in the general case there
aren't many metrics that people are interested in summarizing, which
is why the CPU goes so high for you. I think that using
(?:un)?summarized_metrics will
I'm trying to setup the tcp listener for rrdcached but getting this error
absolute path names not allowed when talking to a remote daemon. Should I
be setting rrd_rootdir to something else besides defaults?
-gary
On Fri, Sep 12, 2014 at 3:12 PM, Devon H. O'Dell devon.od...@gmail.com
wrote:
If you can provide the core file of the
segfault that would be helpful.
Problem may be with metric summarization where it's locking. One
thing to do is provide a list of metrics to summarize e.g. I got
these options turned on in gmetad.conf