Acceleration Management Node for NFV Hardware Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In virtualization scenarios, accurately scheduling network function virtualization (NFV) hardware to meet the service requirements of application programs is a challenge, as existing methods do not consider the specific acceleration types, algorithms, and bandwidth requirements of hardware acceleration devices.
Innovation Solution
An acceleration management node that receives and processes information from multiple acceleration devices, determines the most suitable device based on the service requirements, including acceleration type, algorithm type, and bandwidth, to ensure accurate invocation and allocation of resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If general-purpose NFV hardware is used after virtualization, then hardware adaptability is improved, but the ability to accurately schedule hardware according to specific service requirements deteriorates
Solution Approach 1:
The patent segments the hardware scheduling process into multiple dimensions: acceleration type segmentation (encryption, compression, etc.), algorithm type segmentation (AES, DES, etc.), and bandwidth segmentation. By dividing the hardware resources into distinct categories with specific attributes, the system can precisely match service requirements while maintaining hardware generalization through virtualization.
2Ease of operation
If hardware acceleration devices are allocated without considering specific acceleration types and algorithms, then resource allocation simplicity is improved, but service execution accuracy deteriorates
Solution Approach 1:
The patent introduces an acceleration management node as an intermediary between the client and acceleration devices. This mediator collects acceleration device information (acceleration type, algorithm type, bandwidth) from multiple acceleration nodes, matches it with service requirements, and allocates appropriate resources. This intermediary layer maintains allocation simplicity while ensuring execution accuracy through structured information management and matching logic.
3Device complexity
If acceleration device information is not collected and managed centrally, then system complexity is reduced, but the ability to make accurate allocation decisions deteriorates
Solution Approach 1:
The patent implements preliminary action by having the acceleration management node collect and store acceleration device information (acceleration type, algorithm type, bandwidth capabilities) in advance from all acceleration nodes. This pre-collected information is maintained in a structured format, enabling rapid and accurate matching when allocation requests arrive, thus achieving precise allocation decisions without increasing operational complexity during runtime.
Data Source
AI summary
Embodiments of the present application provide an acceleration management node. The acceleration management node separately receives acceleration device information of all acceleration devices. The acceleration device information includes an algorithm type, an acceleration bandwidth or non-uniform memory access architecture (NUMA). The acceleration management node obtains an invocation request from a client. The acceleration management node queries the acceleration device information to determine, from all the acceleration devices of the at least one acceleration node, a target acceleration device matching the invocation request. The acceleration management node further instructs a target acceleration node to respond to the invocation request.