Dear Vladimir,
We're not using rrdcached. I'll look into this tomorrow (we have a
maintenance today).
After 24 hours, rrdcached seems to have solved it.
Thanks for you advice, and also to Mozammil for his.
Filipe
--
Filipe Bonjour
In theory there is no difference between theory
Hello,
I am fairly new to Ganglia, and have a problem with Ganglia 3.6.0 / Ganglia
Web 3.5.10: In one of my clusters, after I add approximately 55 hosts, the
graphs go blank. I think it's very similar to
http://www.mail-archive.com/ganglia-general%40lists.sourceforge.net/msg07852.html,
but that
What kind of storage are you using ?
Are you using rrdcached?
Vladimir
On 03/16/2014 11:17 AM, Filipe Bonjour wrote:
Hello,
I am fairly new to Ganglia, and have a problem with Ganglia
3.6.0 /
Dear Vladimir,
What kind of storage are you using ? Are you using rrdcached?
Vladimir
We're using a parallel filesystem (GPFS). I agree that it's not very
fast, and I was tempted to move the RRDs to faster disk or tmpfs. But if
the problem was slow storage or network, wouldn't the other
I had past experience with Ganglia setup having more than 100 nodes. Since the
setup was in Amazon AWS, I was bond to use unicast mode to communicate between
gmond and gmetad and I personally like unicast which somewhere or the other
saves network bandwidth.
The way I had organized the setup,
5 matches
Mail list logo
