up vote 3 down vote favorite
share [g+] share [fb]

How would your determine a max value to set an alarm on the I/O activity of a ubuntu/linux server hosting upto 4 sites running apache, mysql and upto 4 tomcats? Or in general (if there is one such) what is a suitable operational range for I/O read/write per second in a production server with a 7.2K SATA HDD?

What I'm trying to understand is the impact on the disks if read/writes per second peaks. What should I look for in the specification of the disks/drives to determine this?

As you can see, I'm "clearly" confused. Any help/direction would be appreciated...

link|improve this question
Great, thanks for the quick response guys. – sankara May 19 '09 at 9:14
Thanks for the response guys. Monitoring iostat response over a period of time helped us realize that one of the two drives in our system is already being maxed out every now and then. Planning to the distribute the load by moving some files across. – sankara May 20 '09 at 5:20
feedback

2 Answers

up vote 1 down vote accepted

The iostat command ( I think provided by the apt package sysstat) will show you a percentage of disk utilization with the -x switch. If this is consistently high (over 85%) you might be disk bound over a long period. The first line of iostat is pretty useless, so you want to provide iostat with an interval, something like iostat -x 5. You can just watch this for a while if you are not prepared to set up monitoring software. Don't worry about spikes of utilization, only if stays high over time.

link|improve this answer
feedback
up vote 3 down vote

First you need something like munin or collectd to measure. Then you need experience to get sensible values for your setup/workload. Then you can define thresholds for "normal" and "excessive" loads.

link|improve this answer
feedback

Your Answer

 
or
required, but never shown
discard

Not the answer you're looking for? Browse other questions tagged or ask your own question.