Jesse Becker wrote: > Markus Reusch wrote: >> Hi list(eners), >> >> we are using Ganglia for about 20-30 AIX-Systems. All data is >> collected on 2 LPARs which run gmetad, rrdtool and the Apache, so >> it's accessible for the users with the supplied PHP web frontend. >> Our rrd-database has currently a size of about 400 MB and consists of >> about 4800 files. I have no idea if this size or number of files is a >> problem at all. > > That actually seems high. On a cluster with 88 computers, there are > 3238 files in about 40MB. The total size should scale proportionally > to the number of hosts and metrics. > It seems very high for default Ganglia, and what you say is true about scaling to hosts and metrics, but it also scales based on the RRA configuration (and if the RRA configuration is done automatically, it depends on the update interval). So I would ask, did Markus change the default metrics, the default update interval in gmetad.conf, or the default RRA configuration?
>> Every day, several users connect to the web frontend and open those >> graphs, which results in some rrdtool calls, exhausting all the >> available CPU time of the machine. No matter if it's just 4 rrdtool >> processes or 20 of them. The machine is already at it's limit when > > What version of rrdtool? There was a recent discussion about this in > the mailing list. I think that versiosn 1.2.21 has a problem. There > should be one rrdtool process called per graph, and it should be > fairly short-lived. > I agree that an rrdtool update is probably in order. -Matt ------------------------------------------------------------------------- SF.Net email is sponsored by: Check out the new SourceForge.net Marketplace. It's the best place to buy or sell services for just about anything Open Source. http://sourceforge.net/services/buy/index.php _______________________________________________ Ganglia-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/ganglia-general
