Load balancing method and system based on accurate congestion feedback in cloud data center

Abstract

The invention discloses a load balancing method and system based on accurate congestion feedback in a cloud data center. The load balancing method comprises two main aspects: an accurate source end flow balancing method and an accurate flow rate control method. The source end flow balancing method is based on accurate end-to-end delay monitoring, the congestion degree of a plurality of equivalentpaths among nodes in a cloud data center can be obtained in time, and flow path distribution is carried out in a balanced manner, so that load balancing among the plurality of equivalent paths is ensured, and the link bandwidth utilization rate is improved. The accurate flow rate control method is based on congestion feedback marks, and congestion feedback which does not belong to the current state due to path switching is eliminated, so that the accuracy of congestion feedback information is improved, and the stability of a data flow sending rate is ensured. According to the method, the accuracy of load balancing under the asymmetric network of the data center is improved, a hardware switch does not need to be modified, and the method has the performance advantage of competing with a customized hardware load balancing method.

Description

technical field [0001] The invention belongs to the field of data center load balancing, and more specifically relates to a load balancing method and system based on accurate congestion feedback in a cloud data center. Background technique [0002] The rapid development of cloud computing technology in recent years has promoted the deployment of large-scale data centers. Data center networks generally adopt multi-root node topology to deploy networks, such as fat-tree (fat-tree) and leaf-spine (leaf-spine) topologies, etc., making There are multiple equal-cost paths between nodes and provide high link bandwidth. Balancing load across multiple paths to fully utilize network resources can improve throughput and reduce latency for data center applications. [0003] On the one hand, the load of different applications in the data center varies greatly, including applications with high latency sensitivity (such as Memcached) and applications with high bandwidth requirements (such...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a load balancing method and system based on accurate congestion feedback in a cloud data center, thereby solving the existing load balancing method that needs to customize hardware switches, which cannot be accurately Technical issues reflecting the congestion status of different paths

Images