Virtual Network Interface Multiplexing for Dynamic Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual network interface (VNI) implementations in data centers lack flexibility in dynamically re-mapping network addresses to underlying physical resources, which limits their ability to meet the needs of applications and services in virtual computing environments, particularly in terms of load balancing and resource utilization.
Innovation Solution
A VNI multiplexing service is implemented at the provider network level, allowing virtual network interfaces to be logically aggregated and mapped to client-accessible service endpoint addresses (CSEAs) in various ways, enabling intelligent and stateful load balancing without dedicated load balancers, through the creation and management of interface groups comprising multiple VNIs, and the use of encapsulation protocols for packet distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If standard networking protocols and physical NIC level configuration are used, then network connectivity is established, but network configuration complexity increases and flexibility decreases
Solution Approach 1:
The patent segments the network interface functionality by introducing virtual network interfaces (VNIs) that separate the logical network configuration from the physical NIC. This allows independent management of virtual interfaces without affecting physical hardware configuration, thereby increasing flexibility while managing complexity through abstraction.
Solution Approach 2:
The patent introduces an intermediary layer (virtual network interface) between the physical NIC and the network protocols. This intermediary enables flexible network address mapping and load balancing without requiring changes to physical NIC configuration or standard networking protocols, resolving the contradiction between flexibility and complexity.
2Adaptability or versatility
If virtual network interfaces are introduced to ease network configuration, then configuration simplicity improves, but support for dynamic re-mapping of network addresses to physical resources is insufficient
Solution Approach 1:
The patent implements dynamic re-mapping capability by allowing virtual network interfaces to be programmatically detached from one virtual machine and attached to another, and by enabling dynamic association of multiple VNIs with interface groups. This dynamic behavior provides adaptability while maintaining ease of operation through automated management.
Solution Approach 2:
The patent changes the mapping parameters between network addresses and physical resources by introducing interface groups that can dynamically associate multiple VNIs with different physical NICs. This allows flexible re-mapping without requiring manual reconfiguration, maintaining ease of operation while enhancing adaptability.
3Productivity
If multiple virtual network interfaces are managed individually, then network isolation is maintained, but load balancing and resource utilization efficiency decrease
Solution Approach 1:
The patent merges multiple virtual network interfaces into interface groups that can be collectively managed and associated with physical NICs. This combining approach enables load balancing across multiple interfaces and improves resource utilization while reducing management complexity through unified interface group operations.
Solution Approach 2:
The patent gives interface groups universal functionality by enabling them to work with multiple VNIs, support load balancing, and provide flexible mapping to different physical NICs. This multi-functionality allows a single interface group construct to handle various networking scenarios, improving productivity without proportionally increasing complexity.
Data Source
AI summary
A control-plane component of a virtual network interface (VNI) multiplexing service assigns one or more VNIs as members of a first interface group. A first VNI of the interface group is attached to a first compute instance. Network traffic directed to a particular endpoint address associated with the first interface group is to be distributed among members of the first interface group by client-side components of the service. The control-plane component propagates membership metadata of the first interface group to the client-side components. In response to a detection of an unhealthy state of the first compute instance, the first VNI is attached to a different compute instance by the control-plane component.