Shared Memory Data Plane Service Plane Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current edge computing systems experience inefficient use of computing resources due to the copying of data packets during transmission, leading to poor per-packet latency.
Innovation Solution
Implementing shared memory accessible between the data plane and the service plane to store identifying information about data packets, and using machine learning logic to evaluate and authenticate data packets, thereby reducing the need for packet duplication and optimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data packets are copied during transmission in edge computing systems, then data can be transmitted and processed, but computing resources are used inefficiently and per-packet latency increases
Solution Approach 1:
The patent applies selective copying by creating copies of data packets only when necessary for specific processing operations, rather than copying all packets universally. The system determines which packets require copying based on processing requirements, thereby reducing unnecessary duplication overhead and improving overall transmission efficiency while maintaining required functionality
Solution Approach 2:
The patent merges the data plane and service plane operations by allowing direct access to packet data without requiring separate copy operations. The service plane can directly process packets from the data plane through shared memory or direct references, eliminating the need for intermediate copying steps and reducing per-packet latency
2Ease of operation
If every data packet is copied before and after reaching an application, then packet processing can be performed, but computing resources are wasted and per-packet latency deteriorates
Solution Approach 1:
The patent implements partial action by applying packet copying only to the extent necessary for processing. Instead of copying every packet unconditionally, the system selectively copies only those packets that require processing by the service plane, leaving other packets to be handled directly without duplication. This partial application of copying reduces computing resource consumption while maintaining adequate processing capability
Solution Approach 2:
The system enables self-service by allowing the data plane to directly serve the service plane through shared memory access or direct packet references. The service plane can directly access and process packet data without requiring the data plane to create and manage copies, thereby eliminating unnecessary computing overhead associated with packet duplication while maintaining processing capability
Data Source
AI summary
The disclosed technology relates to a process for optimizing data flow within a computer network. The technology utilizes shared memory and machine learning logic to improve the efficiency of how computing resources are used during a transmission of data packets in the computer network. The shared memory is implemented during the transmission of data packets between the data plane and the service plane so that the copying of data packets after the data packets have been received and processed by an application is not necessary. The machine learning logic is implemented during the processing of the data packets in order to adjust a frequency or extent that the data packets (and corresponding source of the data packets) need to be evaluated to ensure that malicious content is not being transmitted across the computer network.