[rabbitmq-discuss] Determining Cause of Flow-Control Invocation
richard at raseley.com
Fri Oct 4 19:52:52 BST 2013
Thank you for that explanation - it was helpful.
On Fri, Oct 4, 2013 at 11:23 AM, Michael Klishin <michael at rabbitmq.com>wrote:
> On oct 4, 2013, at 9:58 p.m., Richard Raseley <richard at raseley.com> wrote:
> > Will you expand more on your statement "[I]t's a little more complicated
> than '1 queue per core'."?
> You get one Erlang process per queue. Those are scheduled to run in one or
> run queues (VM queues, nothing to do with RabbitMQ queues). Recent Erlang
> versions detect how many cores are available on start and create a new run
> per core.
> How scheduling is performed (that is, how processes are given time to run
> and distributed between run queues) is not so trivial to explain and
> varies between
> SMP and non-SMP systems, see
> for a fairly concise and approachable overview.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the rabbitmq-discuss