Want to protect your cyber security and still get fast solutions? Ask a secure question today.Go Premium

x
  • Status: Solved
  • Priority: Medium
  • Security: Public
  • Views: 3969
  • Last Modified:

ESX Server Disk Performance - Interpreting the data

I am trying to interpret storage utilization data from our ESX servers but I am not sure what
counters to look at, and when I get that data determining exactly what it means.  

Currently I am going through Virtual Center and looking at the performance tab.  I have Disk Usage (Avg)  pulled up and it shows a maximum of 9,279 KBps with an average of 2,022KBps.  I truthfully dont know if those are high numbers or not, or if ESX storage counters need to be interpreted with a formula based on hardware.
This server is a local storage server with (6) 15,000RPM SAS drives.  

What data should I be looking at for the counters to determine a disk io problem, and at what point in time should I be concerned that I have overloaded the server and need to migrate to another storage device or server ?

Attached: Stacked Graph of  Disk usage (average) over the past week.
vmware-disk-utilization.JPG
0
heliontech
Asked:
heliontech
2 Solutions
 
Duncan MeyersCommented:
Broadly speaking, disk bandwidth is a spectacularly useless metric to look at in a VMware environment. Disk bandwidth is high where you have a sequential I/O load, and low where the workload is largely random in nature. ESX Server, by its nature, presents a highly random workload to disk, so take a look at Disk Read Requests and Disk Write Requests. The total of Read + Write shouldn't exceed about 1200 - 2400 (give or take, depending on RAID config etc etc etc).

An important thing to monitor is response time, which should be less than 20ms at worst, less than 10ms in your config. High response times indicate either a heavy workload or a configuration issue.
0
 
larstrCommented:
There are several factors that will impact your disk performance such as your disk controller type, raid level, the amount of ram on your controller and whether it has a onboard battery or not. With directly attached storage (das) you should normally not have too high latency (response time), but it also depends on how powerfull your disk controller is.

For measuring latency you can use esxtop from the esx console.

A better way of measuring the performance of your disk system is to use iometer and compare your results with what other people have gotten. I did some testing here after following this thread.

Good luck!

Lars
0

Featured Post

Get your problem seen by more experts

Be seen. Boost your question’s priority for more expert views and faster solutions

Tackle projects and never again get stuck behind a technical roadblock.
Join Now