Incorrect statement in the FAQ

[igarny]

http://docs.perfsonar.net/FAQ.html#q-can-i-run-both-throughput-and-latency-loss-tests-on-the-same-interface-without-interference-due-to-the-way-pscheduler-scheduling-works

A: Currently you cannot guarantee no interference. pScheduler rtt test that execute the ping tool and OWAMP latency and latencybg tests that execute owping and powstream respectively, are considered background tasks and can be scheduled in parallel to each other as well as throughput tests. Given the frequency with which users prefer to run tools such as ping and owping (and powstream runs constantly), there would be very few tests slots available if this were not the case. This does not mean you cannot run these tests on the same interface, it just means some correlation of results may be necessary when debugging. It is recommended, though not required, you run these tests on separate interfaces from throughput.

[igarny]

A: First of all one should review the documentation with regards the type of tasks and the associated tests http://docs.perfsonar.net/pscheduler_client_schedule.html#visualizing-the-schedule-with-pscheduler-plot-schedule (listed below the image)
In order to accommodate both Throughput and Latency tests on a system, the specifics of the Throughput tasks should be considered. These require exclusive access to the system resources.
Latency tests, on the other hand, can be performed as either Normal or Background tasks.
Having done these considerations there are 2 approaches, each of them having their advantages and deficiencies.
a. Run Latency tests as Background tasks along with Throughput tasks.
This approach is the easiest in getting results, but it is also very likely to observe periodically the negative influence of the throughput tests on the latency measurement results.
This does not mean you cannot run these tests on the same interface, it just means some correlation of results may be necessary when debugging. It is recommended, though not required, you run these tests on separate interfaces from throughput.
b. Run Latency tests as Normal task along with Throughput tasks.
This would guarantee you “clean” latency measurements without the impact from throughput tests running in parallel, but it would be very difficult for you to accommodate both type of tests on the system, because of the demanding nature for time of both type of tasks.