Load balancing method and device for cloud computing
A load balancing and cloud computing technology, applied in the field of cloud computing, can solve problems such as failure to achieve load balancing of server computing units, failure to fully utilize server resources, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] Such as figure 1 As shown, the load balancing method of cloud computing, the method performs the following steps:
[0032] Step 1: The scheduling server obtains load information reported by each cloud service unit, each cloud service unit includes a plurality of sub-computing units, and the load information is information reflecting the resource occupancy of the sub-computing units;
[0033] Step 2: The scheduling server determines the overloaded sub-computing unit in each cloud service unit, and the overloaded sub-computing unit is a sub-computing unit whose load state is overloaded;
[0034] Step 3: The scheduling server first performs load balancing within the unit, and determines the lightly loaded target sub-computing unit in the current cloud service unit according to the load information, and the target sub-computing unit is to share the load of the overloaded cloud service unit sub-computing unit; when the scheduling server cannot obtain a light-loaded target s...
Embodiment 2
[0038] On the basis of the previous embodiment, when the scheduling server performs intra-unit load balancing, it first obtains the number of sub-computing units in the current cloud service unit, numbers each sub-computing unit, and regards each sub-computing unit as a Nodes connect all sub-computing units to build a resource network; through the constructed resource network, the scheduling server is in the current cloud service unit, combined with the location of the overloaded sub-computing unit in the resource network, and other light-loaded sub-units The location of the computing unit, find the shortest shortest path between the overloaded sub-computing unit and the light-loaded sub-computing unit, connect the overloaded sub-computing unit and the light-loaded sub-computing unit, and instruct the two to perform load balancing.
[0039] Specifically, load balancing, also known as load balancing (Load balancing), is a computer technology used to distribute load among multipl...
Embodiment 3
[0043] On the basis of the previous embodiment, when the scheduling server performs load balancing among units, it first obtains the number of all cloud service units, numbers the cloud service units, and uses each cloud service unit as a node to connect all cloud service units The cloud service unit constructs a cloud service resource network; through the constructed cloud service resource network, the scheduling server combines the position of the overloaded cloud service unit in the cloud service resource network and the positions of other lightly loaded cloud service units to find the overloaded The shortest path between the cloud service unit and the light-loaded cloud service unit connects the overloaded cloud service unit and the light-loaded cloud service unit, and instructs the two to perform load balancing; In the cloud service unit, a lightly loaded sub-computing unit is found, and the lightly loaded sub-computing unit is instructed to perform load balancing with the...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com