Normally if a client is starting to see latency in an app, I use perfstat for a snapshot measurement and consider changes if disk utilization starts creeping up towards 80%.
DFM/OM or SNMP-based monitoring tools have been useful in alerting on sustained high disk utilization or volume latency.
Christopher Mende Sr Solutions Architect Peak UpTime +1 913 523 4263
________________________________ From: Hadrian Baron Hadrian.Baron@vegas.com Sent: Tuesday, June 10, 2008 13:39 To: toasters@mathworks.com toasters@mathworks.com Subject: At which point does high disk utilization impact IO requests?
When average disk utilization across all disks in an aggregate becomes high, IO requests are delayed.
My question is what should this threshold be?
I’ve heard from one performance consultant that 40% disk utilization is where you start seeing latency (this was in regards to a HDS array).
The Netapp Storage Performance Management using DFM TR-3525 says 70% is the industry accepted disk utilization threshold. http://www-download.netapp.com/edm/TOT/docs/3525.pdf (page 17)
Here is some interesting EMC FUD comparing a 3050 and a CX3-40 which says the Netapp beats the CX3 until disk utilization passes 20% then latency increases dramatically (page 7). http://www.dell.com/downloads/global/products/pvaul/en/netapp_performance_sa... (page 7)
Every environment is different, so the proper answer is of course – It depends – and you should test for yourself. It depends on whether you can accept 5ms more latency, or 50ms more. It depends on what kind of IO you do. But my question is what *your* threshold is, and how can you automate the monitoring of disk utilization?
TIA,
Hadrian