Memory-Based Cross-Domain Solution Fabric for Edge Computing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data center architectures face challenges in efficiently managing and processing high-volume computing and networking workloads, particularly in edge computing environments where latency and bandwidth requirements are stringent.
Innovation Solution
The implementation of a memory-based cross-domain solution (M-CDS) that facilitates secure and efficient communication between different computing domains by using shared memory buffers and customizable communication protocols, enabling direct memory-to-memory transfers and bypassing traditional network stacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional network stacks are used for communication between hosts, then protocol compatibility and security are maintained, but latency increases and performance decreases
Solution Approach 1:
The patent introduces a network processing device as an intermediary that sits between hosts and the traditional network stack. This device provides alternative communication paths that bypass the full network stack processing, reducing latency while maintaining security through controlled access points. The intermediary enables direct memory transfers and alternative protocols without compromising the security model.
Solution Approach 2:
The communication path is segmented into traditional network stack communication and alternative direct communication paths. The system divides network communication into multiple channels: standard TCP/IP paths for compatibility and alternative paths through the network processing device for low-latency performance. This segmentation allows simultaneous use of both approaches for different workloads.
2Productivity
If high-volume computing workloads are processed, then productivity increases, but system complexity and resource management difficulty increase
Solution Approach 1:
The network processing device acts as an intermediary that offloads complex networking functions from host systems. It handles protocol processing, packet routing, and memory management independently, allowing hosts to focus on computing workloads. This mediation reduces the complexity burden on the overall system while enabling high-volume processing.
Solution Approach 2:
The network processing device provides self-service capabilities by autonomously managing its own memory resources, processing workloads, and coordinating with hosts. It independently handles buffer management, protocol processing, and data routing without requiring complex coordination with external systems, thereby reducing overall system complexity.
3Loss of time
If edge computing is implemented to reduce latency, then response time improves, but infrastructure cost and deployment complexity increase
Solution Approach 1:
The network processing device is designed with universal functionality that can be deployed in multiple locations (edge, aggregation, core) and serve multiple purposes (routing, switching, processing). This multi-functionality allows the same hardware platform to be used across different deployment scenarios, reducing infrastructure cost and simplifying deployment while achieving low-latency edge computing performance.
Data Source
AI summary
A network processing device implements a cross-domain solution (CDS) and includes a shared memory, an I/O interface, a network interface, and a CDS manager to create a buffer in the shared memory to allow writes by a first software module in a first domain and reads by a second software module in a second domain, where the reads are received from the second software module over a network connection facilitated by the network interface. The buffer is used to implement a memory-based communication channel between the first software module and the second software module, where the first domain is independent of the second domain.