Processor Core Allocation for Virtual Network Functions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The allocation of physical CPU cores to support virtual network functions (VNFs) is challenging due to unpredictable performance when data-planes from different VNFs are pinned to the same physical CPU core, leading to degraded performance and maintenance issues.
Innovation Solution
A system and method for allocating processor cores based on specific requirements, where available processor capacity is determined and processor cores are reserved for VNFs to ensure dedicated resources, preventing data-plane vCPUs from different VNFs from being allocated to the same core, thereby ensuring low latency throughput and preventing resource competition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data-plane vCPUs from different VNFs are pinned to the same physical CPU core, then resource utilization increases, but performance becomes unpredictable and degrades
Solution Approach 1:
The patent segments physical CPU cores into dedicated groups for control-plane vCPUs and data-plane vCPUs. Control-plane vCPUs are pinned to specific physical cores while data-plane vCPUs are allocated from separate physical cores, preventing them from sharing the same core and eliminating performance unpredictability while maintaining efficient resource utilization.
Solution Approach 2:
The patent applies different allocation strategies to different types of vCPUs based on their specific requirements. Control-plane vCPUs receive dedicated physical cores with guaranteed performance, while data-plane vCPUs are allocated from a separate pool of physical cores, allowing each to operate under optimal conditions without interfering with the other.
2Reliability
If physical CPU cores are dedicated to specific VNFs, then performance reliability improves, but resource utilization and efficiency decrease
Solution Approach 1:
The patent segments the physical CPU core pool into distinct segments: one segment dedicated to control-plane vCPUs and another segment for data-plane vCPUs. This segmentation ensures that control-plane functions have guaranteed performance while data-plane functions can efficiently utilize available cores without competition, achieving both reliability and productivity.
Solution Approach 2:
The patent creates a universal pool of physical CPU cores that can serve multiple VNFs for data-plane operations, while maintaining dedicated assignments for control-plane operations. This multi-functional approach allows the same physical infrastructure to support both guaranteed performance requirements and efficient resource sharing.
3Productivity
If more physical CPU cores are allocated to VNFs, then performance and throughput improve, but maintenance cost increases
Solution Approach 1:
The patent segments CPU core allocation into controlled segments, allowing throughput to scale by adding more data-plane physical cores without proportionally increasing control-plane complexity. This segmented approach enables linear scalability of throughput while maintaining manageable system complexity and reduced maintenance costs.
Data Source
AI summary
A virtual machine management service obtains a request to instantiate a virtual machine image (VMI) to implement a virtual network function (VNF). The request specifies a set of processor requirements corresponding to instantiation of the VMI. In response to the request, the service identifies, from a server comprising a set of processor cores, available processor capacity. The service determines, based on the available processor capacity and the set of processor requirements, whether to instantiate the VMI on to a subset of processor cores of the server. Based on this determination, the service instantiates the VMI on to the subset of processor cores to implement the VNF.