Take the 2-minute tour ×
Server Fault is a question and answer site for system and network administrators. It's 100% free, no registration required.

The common way to determine load for Linux is via uptime, which processes /proc/loadavg.

$ cat /proc/loadavg 
0.64 0.68 0.69 1/558 3043

However, this information is the load average for the past 1,5, and 15 minutes.

However, this is a rolling/trailing indicator and I'd like to get more fine-grained information than one minute (say, I'd like the instantaneous load or perhaps the 5-second load average).

For context, I'm running load tests, and it'd be nice to have more data.

share|improve this question

1 Answer 1

For context, I'm running load tests, and it'd be nice to have more data.

Load average is going to be a rather crude measurement for load tests even if you get it every 5 seconds.

You should look at something like New Relic instead. It will give you reams of data.


share|improve this answer
Not going to deny that it's a bit crude. However, *aaS offerings are not going to work due to org policy. It's going to have to be 100% locally installed. –  Paul Nathan Jan 17 '13 at 0:43
Well then you can profile your application the old way, e.g. css.dzone.com/news/profiling-php-application and/or capture metrics using Munin or Cacti. –  HTTP500 Jan 17 '13 at 14:56

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

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