Smart-vLB Contextual Packet Routing for Network Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern communication networks face challenges in real-time monitoring and troubleshooting to maintain performance and quality of service due to their complexity and increasing reliance on virtualized and software-defined infrastructure.
Innovation Solution
A hierarchical load balancing system, referred to as Smart-vLB, comprising non-stateful and stateful virtual load balancers that distribute packets to virtual probes, distinguishing between contextual and non-contextual packets to efficiently process and route data within the network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a traditional load balancing system is used to distribute network packets, then the system structure is simple, but the system cannot efficiently handle contextual packets that require reference to other packets for processing
Solution Approach 1:
The load balancer is divided into multiple specialized components: a packet classification module that identifies contextual vs. non-contextual packets, a session management module that tracks packet associations, and multiple processing modules that handle different packet types. This segmentation allows efficient handling of contextual packets while maintaining clear system boundaries.
Solution Approach 2:
A session management module acts as an intermediary between packet reception and processing. It maintains session state information and coordinates the distribution of contextual packets to appropriate processing modules, enabling efficient contextual packet handling without requiring complex direct connections between all components.
2Productivity
If packets are distributed to different probes without contextual awareness, then the system is easier to operate, but the system loses the ability to process contextual packets that require reference to associated packets
Solution Approach 1:
The load balancer performs preliminary classification of packets as contextual or non-contextual upon receipt. Session state information is pre-established and maintained, allowing contextual packets to be quickly routed to appropriate processing modules without requiring complex real-time decisions during packet processing.
Solution Approach 2:
The session management module maintains feedback loops that track packet associations and processing states. This feedback mechanism enables the system to automatically route contextual packets to the correct processing modules based on previously established session information, simplifying the routing logic while maintaining contextual awareness.
3Productivity
If all packets are processed by the same probe, then contextual packet processing is simplified, but the system cannot achieve effective load balancing across multiple probes
Solution Approach 1:
Different processing modules are assigned specialized functions: some modules handle non-contextual packets with simple routing logic, while others handle contextual packets with access to session state. This local specialization allows each module to be optimized for its specific task, achieving efficient load balancing while maintaining simple individual module designs.
Solution Approach 2:
The system introduces a new dimension of packet classification by distinguishing between contextual and non-contextual packets. This dimensional separation allows the system to apply different routing strategies to different packet types, enabling efficient load balancing across multiple probes while maintaining simple processing logic within each probe.
Data Source
AI summary
A load balancing system that operates to categorize communication packets as to whether they are contextual or not and determines a decision relevant to data in a first contextual packet with respect to a predetermined task based on data comprised in a second contextual packet.