Stateful Services on Stateless Edge Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network edge services struggle with dynamic scaling, as they require additional resources to handle increasing traffic, and existing solutions fail to seamlessly integrate node additions or removals without disrupting stateful services.
Innovation Solution
A dynamically scalable cluster of network nodes is created using a consistent hash function to distribute flows, allowing for active-active operation, flow delegation, and indirection tables to maintain statefulness and service continuity during membership changes, ensuring all nodes participate in stateful services and handle traffic efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If additional nodes are added to handle increasing traffic, then network service capacity increases, but system complexity and disruption risk increase
Solution Approach 1:
The system implements dynamic cluster membership where nodes can be added or removed while the system adapts automatically. The consistent hash function dynamically recalculates flow assignments when membership changes, enabling the cluster to scale without manual reconfiguration or service interruption.
Solution Approach 2:
All nodes in the cluster operate in active-active mode, providing universal functionality for handling stateful service flows. Each node can process any flow assigned to it, and the system maintains redundancy where multiple nodes can handle the same flow, improving both capacity and fault tolerance.
2Adaptability or versatility
If nodes are dynamically added or removed, then cluster scalability improves, but stateful service continuity may be disrupted
Solution Approach 1:
The system pre-calculates flow assignments using the consistent hash function based on current cluster membership. When membership changes, the hash function immediately recalculates assignments, ensuring flows are continuously directed to valid nodes without interruption or loss of state information.
Solution Approach 2:
The consistent hash function acts as an intermediary between cluster membership changes and flow routing decisions. It translates membership changes into updated flow assignments, ensuring that stateful services maintain continuity while adapting to dynamic cluster configurations.
3Productivity
If all nodes operate in active-active mode, then processing power utilization maximizes, but coordination complexity increases
Solution Approach 1:
Each node independently determines which flows to process by evaluating the consistent hash function against its own identifier and the flow identifiers. This self-service approach eliminates the need for centralized flow assignment management, reducing coordination complexity while maintaining active-active operation across all nodes.
Solution Approach 2:
The system uses parameter-based flow identification (flow IDs) combined with the consistent hash function to automatically distribute flows across nodes. By changing the hash parameters to include dynamic cluster membership, the system achieves both high utilization and simplified coordination through deterministic flow assignment.
Data Source
AI summary
In order to enable dynamic scaling of network services at the edge, novel systems and methods are provided to enable addition of add new nodes or removal of existing nodes while retaining the affinity of the flows through the stateful services. The methods provide a cluster of network nodes that can be dynamically resized to handle and process network traffic that utilizes stateful network services. The existing traffic flows through the edge continue to function during and after the changes to membership of the cluster. All nodes in the cluster operate in active-active mode, i.e., they are receiving and processing traffic flows, thereby maximizing the utilization of the available processing power.