Distributed Network Service Platform Traffic Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers face complexity and cost issues due to the deployment and coordination of separate physical boxes for network services, which often result in a centralized architecture that is a single point of failure and a bottleneck for traffic.
Innovation Solution
A distributed network service platform is implemented, where instances of target network service applications execute within virtual machines on multiple physical devices, with multiple service engines cooperating to redirect traffic and share processing resources, eliminating the need for a centralized load balancer and simplifying resource configuration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a centralized load balancer is used to intercept and redistribute incoming traffic, then traffic distribution is achieved, but the system becomes a single point of failure and a bottleneck
Solution Approach 1:
The patent divides the centralized load balancing function into multiple distributed service engines deployed across different physical devices. Each service engine handles a portion of the traffic independently, eliminating the single point of failure. The segmentation transforms one centralized bottleneck into multiple parallel processing nodes that can operate independently.
Solution Approach 2:
The patent transitions from a single-dimensional centralized architecture to a multi-dimensional distributed architecture by deploying service engines across multiple physical devices and virtual machines. This dimensional expansion allows traffic to be routed through multiple paths and nodes, removing the bottleneck created by a single load balancer.
2Adaptability or versatility
If separate physical boxes are deployed for each network service, then service functionality is achieved, but device complexity and coordination difficulty increase
Solution Approach 1:
The patent merges multiple separate physical network service devices into a unified distributed system where service engines run as virtual machines on shared physical infrastructure. This consolidation reduces the number of physical boxes while maintaining service functionality through virtualization and distributed deployment.
Solution Approach 2:
The patent creates universal service engines that can perform multiple network service functions across different physical devices. Each service engine is designed to be multi-functional, capable of handling various network services and traffic types, thereby reducing the need for specialized physical boxes for each service type.
3Productivity
If multiple virtual machines are deployed on multi-CPU servers, then resource utilization is improved, but configuration and management complexity increases
Solution Approach 1:
The patent implements self-service mechanisms where service engines automatically discover available resources, configure themselves, and manage their own deployment across virtual machines. This automation reduces the manual configuration burden despite the complexity of multi-VM environments, allowing the system to self-organize and adapt to available resources.
Data Source
AI summary
Providing a distributed network service includes: receiving network traffic at a first physical device; and executing a service engine to participate in the distributed network service. The distributed network service is provided to at least the first target application instance executing in a first VM on the first physical device, and a second target application instance executing in a second VM on a second physical device; and a shared state of the distributed network service is maintained with respect to the first physical device and the second physical device.