Cloud computing load balancing evaluation system and evaluation method

Abstract

The invention discloses a cloud computing load balancing evaluation system. In the system, a signal output end of a cloud cluster load information collection module is connected with a signal input end of an image conversion module, and the signal output end of the image conversion module is connected with a signal input end of a cluster balance analysis module. The invention further discloses a loud computing load balancing evaluation method. The method comprises the steps of: conducting regional division and multipoint collection of cloud cluster load information on a cluster monitoring module; generating a load conversion picture by adopting a method for mapping a node comprehensive load value to a gray-scale map; and analyzing the load conversion picture by adopting a load image analysis method. According to the invention, regional division and multipoint collection strategies are adopted on the traditional cluster monitoring module, and the load conversion picture can be generated by adopting the method for mapping the node comprehensive load value to the gray-scale map and is analyzed according to the load image analysis method, thus achieving the purpose of accurately and wholly evaluating a load.

Description

technical field [0001] The present invention relates to a cloud computing load balance evaluation system and method, in particular to a cloud computing load balance evaluation system and evaluation method using area division and multi-point collection. Background technique [0002] In a resource sharing cloud environment based on untrusted nodes, traditional load balancing algorithms will face the following problems: [0003] 1. When obtaining node load information, due to the huge number of nodes in cloud computing, it may cause network storms and I / O bottlenecks and processing performance bottlenecks of the information collection server. [0004] 2. The node selection algorithm after information collection at the current stage is to sort or classify the best node according to the load information of a single node, without considering the overall or regional load status of the cluster. This is fine for traditional clusters, but not for zoned cloud clusters. For example, a...

AI Technical Summary

Problems solved by technology

[0003] 1. When obtaining node load information, due to the huge number of nodes in cloud computing, it may cause network storms and I / O bottlenecks and processing performance bottlenecks of the information collection server

[0004] 2. The node selection algorithm after information collection at this stage is to sort or classify the best node according to the load information of a single node, without considering the overall or regional load status of the cluster

This is fine for traditional clusters, but not for zoned cloud clusters

For example, a certain area is already in a saturated state, but there may be idle nodes that have released resources. When using traditional algorithms for task allocation, this node is likely to be selected, which will cause local load overload and affect the overall performance of the system.

Images