Unlock instant, AI-driven research and patent intelligence for your innovation.

Load balancing method based on CPU kernel sharing and device thereof

A CPU core and load balancing technology, applied in multi-programming devices, resource allocation, electrical components, etc., can solve problems such as server load balancing difficulties, and achieve high availability and high performance

Active Publication Date: 2010-03-03
ZTE CORP
View PDF0 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a load balancing method and device based on CPU core sharing, which overcomes the defect that it is difficult to achieve server load balancing in a network environment based on sending Location commands in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Load balancing method based on CPU kernel sharing and device thereof
  • Load balancing method based on CPU kernel sharing and device thereof
  • Load balancing method based on CPU kernel sharing and device thereof

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0030] In the first embodiment of the present invention, a load balancing method based on CPU core sharing, such as figure 2 shown, including the following steps:

[0031] Step 101 , setting and maintaining CPU core load tables of itself and other servers in the server cluster on each server in the server cluster. Assuming that in this embodiment, each server has 4 CPU cores working at the same time, the CPU core load table of each server is as follows image 3 shown.

[0032] Specifically, the way each server obtains its own CPU core load is as follows: in the Windows environment, the CPU core load can be obtained through the operating system, or many application software based on the operating system that can read the CPU core occupancy rate can be used. Load profiles can also be obtained. In the LINUX or UNIX environment, you can directly call the top program to get the CPU core load. In addition, those skilled in the art can also use C language to write a small progra...

no. 2 example

[0041] The second embodiment of the present invention is a load balancing method based on CPU core sharing, which is roughly the same as the load balancing method in the first embodiment, the difference is that the server set and maintained on each server in the server cluster The CPU core load table of all servers in the cluster further includes the weight value of the server, such as Figure 4 As shown, the weight value is set according to the criticality of the server processing business.

[0042] Just because the weight value of the server is included in the CPU core load table, this embodiment has the following advantages compared with the first embodiment: when an idle server receives load migration requests from at least two servers at the same time, if it can Provide idle CPU cores to participate in the service of migrating load, and select and process the client request of the server with the higher weight value according to the weight values ​​of the two servers.

no. 3 example

[0043] In the third embodiment of the present invention, a load balancing device based on CPU core sharing, such as Figure 5 As shown, it includes the following components:

[0044] The CPU core load table configuration maintenance module is used to record and update the CPU core load tables of itself and other servers in the server cluster on the server in real time.

[0045] The migration load judging module is used to judge the processing capability of client requests according to its own CPU core load table, find out idle servers according to the CPU core load tables of other servers in the server cluster, and send load migration requests to idle servers.

[0046] The migration load negotiation module, when the server does not have the ability to process client requests, the migration load negotiation with the idle server is carried out through this module.

[0047] The client request processing module is configured to schedule a local idle CPU core to process the client...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a load balancing method based on CPU kernel sharing and a device thereof; when the self CPU kernel of a local server has no capability to process the client request, the local server searches a disengaged server in a server cluster and sends load transfer request to the disengaged server; and the disengaged server processes the client request and returns the processing result into the local server. According to the different load conditions of CPU kernels of the servers, when having no capability of processing the client request, the server has load transfer negotiation with the disengaged server to dispatch an idle kernel to take part in operation, so that the loads of all the servers in the network server cluster can be ensured to be balanced. Compared with the load balancing method in the prior art, the method has the advantages of high availability and performance.

Description

technical field [0001] The invention relates to the technical field of network server load balancing, in particular to a load balancing method and device based on CPU core sharing. Background technique [0002] Due to the rapid growth of business volume, access volume and data flow of each core part of the existing network, its processing capacity and calculation intensity also increase correspondingly, making it impossible for a single server device to bear it. In this case, if the existing equipment is abandoned and a large number of hardware upgrades are made, existing resources will be wasted. And even after adding hardware, due to the uneven distribution of calculations in the network, it will still cause serious load imbalance. [0003] Load balancing technology is the key technology in multi-machine server system. Its main function is to balance the load so that the entire system can achieve the best performance. The current mainstream load balancing methods mainly...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L29/08G06F9/50
Inventor 黄剑刘钊
Owner ZTE CORP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com