3com S7906E 설치 설명서

 

5-2 

Each queuing algorithm addresses a particular network traffic problem and which algorithm is used 

affects bandwidth resource assignment, delay, and jitter significantly.  

Queue scheduling processes packets by their priorities, preferentially forwarding high-priority packets. 

In the following section, Strict Priority (SP) queuing, Weighted Fair Queuing (WFQ), and Weighted 

Round Robin (WRR) queuing are introduced.  

SP queuing is specially designed for mission-critical applications, which require preferential service to 

reduce the response delay when congestion occurs. 

Figure 5-2 Schematic diagram for SP queuing 

 

 

As shown in 

, SP queuing classifies eight queues on a port into eight classes, numbered 7 to 

0 in descending priority order.  

SP queuing schedules the eight queues strictly according to the descending order of priority. It sends 

packets in the queue with the highest priority first. When the queue with the highest priority is empty, it 

sends packets in the queue with the second highest priority, and so on. Thus, you can assign 

mission-critical packets to the high priority queue to ensure that they are always served first and 

common service packets to the low priority queues and transmitted when the high priority queues are 

empty.  

The disadvantage of SP queuing is that packets in the lower priority queues cannot be transmitted if 

there are packets in the higher priority queues. This may cause lower priority traffic to starve to death.  

WRR queuing schedules all the queues in turn to ensure that every queue can be served for a certain 

time, as shown in 

.