Hierarchical Clustering of Hardware Resources in NFV Deployments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current hardware offload solutions in commercial deployments for network function virtualization (NFV) lack adequate support for compute-intensive and latency-sensitive applications, due to limited resource availability and complexity of firmware modification, which hinders efficient deployment in high-performance computing environments.
Innovation Solution
The implementation of a system for hierarchical clustering of hardware resources in NFV deployments, where a compute node identifies and allocates interconnected resources to form a cluster, defines hardware profiles based on network function profiles, and deploys network functions across these resources to optimize resource usage and meet workload requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If hardware offload solutions are used in commercial NFV deployments, then processing performance for network functions is improved, but resource availability and flexibility are limited
Solution Approach 1:
The hardware resource pool is designed to support multiple network function types (firewall, load balancer, NAT, DPI, etc.) on a single platform. The system can dynamically allocate hardware resources to different VNFs based on workload requirements, making the hardware infrastructure universal and adaptable to various NFV deployment scenarios without requiring specialized hardware for each function type.
Solution Approach 2:
The system segments hardware resources into discrete, manageable units that can be independently allocated and configured. Hardware resources are divided into functional components (packet processing, security, routing, etc.) that can be selectively combined to meet specific workload requirements, providing both performance optimization and resource flexibility.
2Speed
If hardware offload solutions are used, then processing speed is improved, but firmware modification complexity increases
Solution Approach 1:
The system introduces a hardware resource pool management layer that acts as an intermediary between the hardware resources and the VNFs. This management layer handles firmware configuration and resource allocation, shielding users from firmware modification complexity while maintaining high processing speeds through hardware acceleration.
Solution Approach 2:
The system uses virtualization to create virtual copies of hardware resources that can be allocated to multiple VNFs simultaneously. Instead of modifying firmware for each individual deployment, the system creates virtual instances that replicate hardware functionality, simplifying deployment and reducing firmware modification requirements.
3Productivity
If hardware resources are allocated to specific network functions, then performance is optimized, but resource utilization efficiency decreases
Solution Approach 1:
The hardware resource pool implements dynamic allocation where resources are not statically assigned but continuously adjusted based on real-time workload demands. The system can migrate hardware resource allocations between different VNFs as needs change, ensuring both performance optimization for active workloads and efficient utilization by preventing resource idle time.
Solution Approach 2:
The system enables workloads to self-manage their hardware resource requirements through automated resource discovery and allocation mechanisms. VNFs can request and receive appropriate hardware resources from the pool based on their performance needs, eliminating the need for manual configuration and improving both performance optimization and resource utilization efficiency.
Data Source
AI summary
Technologies for the hierarchical clustering of hardware resources in network function virtualization (NFV) deployments include a compute node that is configured to create a network function profile that includes a plurality of network functions to be deployed on the compute node. Additionally, the compute node is configured to translate the network function profile usable to identify which of the plurality of network functions are to be managed by each of the plurality of interconnected hardware resources into a hardware profile for each of a plurality of interconnected hardware resources. The compute node is further configured to deploy each of the plurality of network functions to one or more of the plurality of interconnected hardware resources based on the hardware profile. Other embodiments are described herein.