EMA Super Instance Provisioning for Flexible Cloud Resource Sizing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud computing systems face challenges in meeting tenant requirements for memory capacity and resource utilization due to predefined virtual machine specifications, leading to inefficiencies and increased costs.
Innovation Solution
A cloud service providing method that allows tenants to customize computing and memory resources through an elastic memory accelerator service (EMAS) management node, creating a target EMA super instance based on service requirements, without preset limitations, and integrating resources to optimize performance and reduce waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If preset virtual machine specifications are used, then device complexity is reduced and ease of operation is improved, but adaptability to tenant requirements deteriorates
Solution Approach 1:
The patent segments the virtual machine specification into separate configurable parameters (CPU cores, memory size, storage capacity) that can be independently adjusted. This allows tenants to customize each parameter according to their specific needs without changing the overall system architecture, thereby improving adaptability while maintaining manageable complexity.
Solution Approach 2:
The patent implements dynamic specification adjustment where virtual machine parameters can be modified during runtime based on tenant requirements. The system allows tenants to scale CPU cores, memory, and storage dynamically, transforming the static preset specification model into a dynamic, adaptable configuration model that responds to changing service demands.
2Productivity
If preset virtual machine specifications are used, then ease of operation is improved, but resource utilization deteriorates
Solution Approach 1:
The patent enables parameter changes in virtual machine specifications during operation. Tenants can adjust CPU cores, memory size, and storage capacity parameters based on actual service requirements, allowing the system to optimize resource utilization dynamically rather than being constrained by fixed preset specifications, thereby improving productivity.
Solution Approach 2:
The system transitions from static preset specifications to dynamic configurable specifications, where resource parameters can be adjusted in real-time. This dynamic approach allows the cloud platform to better match resource allocation with actual demand, improving resource utilization while providing tenants with operational flexibility.
3Loss of substance
If preset virtual machine specifications are used, then device complexity is reduced, but loss of substance increases
Solution Approach 1:
The patent allows parameter changes to virtual machine specifications, enabling tenants to precisely match resource allocation with actual service needs. By adjusting CPU cores, memory, and storage parameters dynamically, the system reduces resource waste from over-provisioning while avoiding the complexity of physical resource reconfiguration.
Solution Approach 2:
The patent implements a resource recovery mechanism where unused or excess virtual machine resources can be released and reallocated to other tenants. This allows the cloud platform to recover and reuse resources that would otherwise be wasted, improving overall resource utilization without requiring complex physical resource management.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application discloses a cloud service providing method, a cloud platform, and a related apparatus, and pertains to the field of cloud computing technologies. The method includes: providing a configuration interface; obtaining attribute information of a target cloud service from the configuration interface; creating, based on the attribute information, a target elastic memory accelerator EMA super instance in a target resource node included in a plurality of resource nodes; and setting a management interface of the target EMA super instance based on a providing manner of the target cloud service, and providing the management interface for a tenant. The tenant may customize a computing resource and a memory resource of the target cloud service based on a service requirement of the tenant, without being limited by a preset specification, to meet the requirement of the tenant and improve performance of the cloud service. In addition, resources of the at least one resource node can be integrated to provide a service for the tenant. In this way, while a user requirement is met, utilization of an idle resource in a data center can be effectively improved, and a resource waste and operation and maintenance costs of a cloud service provider can be reduced.