<div><div>Hey there, mailing list.</div><div><br></div><div>I've got a quick question for you. We've been using erlang:statistics(run_queue) to have one of many ways to measure overload on a system. The documentation for the function says the following:</div>
<div><br></div><div style="margin-left:40px!important">run_queue</div><div style="margin-left:40px!important"> Returns the length of the run queue, that is, the number of processes that are ready to run.</div><div><br>
</div><div>I was wondering if this has any relationship to the run queues used by the schedulers ([rq:N] when starting the VM in pre R15 Erlang releases). And if so, is the value obtained by the function call representing the union of all run queues, or only the run queue(s) of the scheduler executing the call? How reliable can we consider this information to be?</div>
<div><br></div><div>Regards,</div><div>Fred.</div></div>