I'm trying to understand which scheduling algorithm is used by M series routers.
Quoting the JUNOS manual (6-swconfig90-cos.pdf, page 137, downloaded from Juniper website)
The software traverses the sets in descending order of priority. If at least one of the
queues in the set has a packet to transmit, the software selects that set. A queue
from the set is selected based on the weighted round robin (WRR) algorithm, which
operates within the set.
Reading the recent book (published March 27, 2008) "Junos Enterprise Routing" by D. Marschke and H. Reynolds, I found the following (Chapter 9, section 9.3):
Both the M7i and J-series platforms implement a modified deficit round-robin (MDRR) scheduler. Because different transmit weights can be assigned to each queue, the algorithm is technically a modified weighted deficit round-robin (MWDRR) approach.
The Juniper implementation of MDRR scheduling on the M-series supports a basic deficit weighted round-robin (DWRR) scheduling discipline, or a combination of strict-priority queuing (SPQ) and DWRR scheduling when a high-priority queue is configured.
So, I'm wondering who is right, or both are right ?
I thank you very much in advance who will be able to clarify me this issue.