[LITMUS^RT] Query on Resource Reservation

[Björn Brandenburg]

> On 2. Aug 2017, at 18:37, Antonio Vaz <antonio.k.vaz at gmail.com> wrote:
> 
> I would like to know more about the implementation of Resource Reservation in Litmus RT.
> 
> 1. How is the polling sporadic server implemented?

Have you looked at the source code?

> 
> 2. What is the difference between a polling sporadic server and a sporadic server?

A sporadic server retains budget. A polling sporadic server does not. 

> Where can I read more about polling sporadic server?

It’s so simple, I don’t think there’s a primary publication on it. It’s just a polling server that’s activated sporadically (rather than periodically like a classic polling server).

	sporadic polling server : sporadic task  ::
	periodic polling server : periodic task

> 3. When a task becomes ready, if there is budget and highest priority, 
> will the polling sporadic server schedule the task immediately?

Not sure what you mean. If the sporadic polling server was previously inactive, and if no higher-priority reservation exists, then, yes, the sporadic polling server will become active and schedule its newly arrived client. 

> In Linux, there are already a lot of processes running. 
> (normal Linux applications that are not linked against liblitmus) 
> How are these processes scheduled?

This is all described in the LITMUS^RT papers. Regular Linux tasks are scheduled by Linux’s default CFS scheduler, as a background workload from LITMUS^RT’s PoV. 

> Are they scheduled by the selected RT scheduler plugin?

No.

Regards,
Björn