Hi, On Mon, Feb 27, 2006 at 08:21:15PM -0600, Christian Smyth wrote: > I am concerned about disk performance in the first place because the > application has nearly 4000 rrd's -- almost 30 GB worth -- and they are > all updated every 5 minutes. Actually, about 20% of them are updated > every minute. And oldbox is struggling under that read load.
For you to compare I am monitoring system activity of about 1000 servers. I have about 10000 rrds worth more than 60G on one centralized server. Every rrd is updated by a perl RRDs script every 10 minutes (with 10 minutes of 15s step data), and each rrd has 16 rras. The server is a IBM xseries 336 with two 3GHz Xeon CPUs, onboard 146G disk in Hardware RAID1 and 2G of RAM. The server's system activity looks like this when I take an average over the last week (4 CPUs seen as it's got Hyperthreading): CPU: 0.18 user 0.03 nice 0.04 system 1.32 iowait 2.40 idle LOAD: loadavg 1.33 Disk I/O : 0.3M read 0.7M write Ethernet: (data is sent via ssh from the clients) 73.7k in 15.6k out This could even be optimized somehow by improving my perl scripts. But overall you can see that the server is quite "cool" and could accept quite some additional rrds :) -- Unsubscribe mailto:[EMAIL PROTECTED] Help mailto:[EMAIL PROTECTED] Archive http://lists.ee.ethz.ch/rrd-users WebAdmin http://lists.ee.ethz.ch/lsg2.cgi
