Five-level queue scheduling device and method for implementing hierarchical QoS (quality of service)

Abstract

The invention discloses a five-level queue scheduling device and method for implementing hierarchical QoS (quality of service). The device comprises a flow classification module, an enqueue level scheduling module, a shared cache module, a business flow level scheduling module, a user level scheduling module, a sub-network level scheduling module, an output port level scheduling module, a scheduling algorithm configuration module, a flow control module and a CPU (central processing unit) interface module. The method includes the steps: performing flow classification on data packets and judgingwhether the data packets can enqueue or not by calculating the enqueue threshold of a queue; configuring all level scheduling algorithms by the scheduling algorithm configuration module according tothe weight attribute of the queue to be scheduled, and jointly finishing the dequeuing scheduling process of the data packets by a flow control algorithm. The proper scheduling algorithms and the flowcontrol algorithm are selected, and bandwidths can be more flexibly distributed by the aid of the five-level queue scheduling device.

Description

technical field [0001] The invention belongs to the technical field of communication, and further relates to a five-level queue scheduling device and method for realizing hierarchical Quality of Service (QoS) in the technical field of data transmission. The present invention can realize the management of the bandwidth of the switch or the router through the setting of the queue weights and the control of the flow in the dispatching algorithms at all levels. Background technique [0002] Queue scheduling and QoS technologies are widely used in routers and switches. It performs flow classification, scheduling and flow control on the input packets of switching nodes according to certain service rules, so that all data packets can share the traffic of switching nodes in a predetermined way. Output link bandwidth. [0003] The queue-based scheduling method is the most commonly used in congestion management. The traditional queue-based scheduling method uses a single-level queue,...

AI Technical Summary

Problems solved by technology

The disadvantages of this device are: the encapsulation of the queue information in the uplink direction is only carried out on the receiving module, and its subnet number and user number attributes are not transmitted, and the queue has only one level, which cannot realize the Bandwidth configuration for

The shortcomings of this method are: this method can only guarantee the quality of service of users, and cannot further serve different business flows of users; only port-level scheduling can not guarantee the bandwidth allocation of different subnets

The shortcomings of this method are: the bandwidth management algorithm based on traffic shaping is too complicated, the cost of hardware implementation is high, and this solution can only be applied on the switch chip that supports the MEF Traffic Shaping algorithm, and the application area is not wide enough

Images