I know how to collect and make use of the data gathered by the sar tool, but I don't know how to interpret it correctly.

For example, PAGING: I can see that my pgpin is 300.000 but how can I tell if that is good or bad, and what is the maximum possible value of pgpin (not max(pgin))?

Same with other values, IO: BREAD 1 million ... but what is the upper limit?

If someone could hint me in the right direction that would be great. Thanks

1 Answer 1


sar(1) shows the records the system keeps on a large number of events that might be of interest for auditing and performance tuning. For none of them a "bad if more than..." value can be given, as they depend a lot on what the machine is doing (it's workload) and any levels that could be worrying depend on the resources available. You'd have to dig in and find out exactly what is being measured for each number, and perhaps set your own desirable values. It is probably much more profitable to look at how the numbers evolve (is any one growing much?), and what numbers you see when performance is good/bad.

Performance is multi-dimensional, trying to summarize it as a single number you can compare among machines (or for the same machine at different times) will work only for a fixed workload composition: You'll see much different numbers on a machine used as webserver, firewall, storage, desktop for office applications or gaming. Each would require different tuning/hardware emphasis. Workloads evolve, uses change, ...

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .