Distributed Instance Liveness Detection Without Cluster Roles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud native applications, instances of services fail without being detected, leading to service failures due to unnotified service data entries, and existing solutions either require third-party components or increase complexity by defining roles within the cluster.
Innovation Solution
Each instance in a cluster selects one or more monitored instances based on a selection criterion, detecting operational status and reporting failures to a centralized controller, ensuring full coverage without requiring third-party logic or special roles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If third-party components are used for instance liveness detection, then detection reliability is improved, but device complexity increases
Solution Approach 1:
Each instance in the cluster performs liveness detection on other instances autonomously without requiring external third-party components. The instance selects monitored instances based on predefined criteria and reports failures to the centralized controller, enabling self-managed detection that eliminates additional complexity while maintaining reliability
2Reliability
If roles are defined within the cluster for liveness detection, then detection coverage is improved, but device complexity increases
Solution Approach 1:
The liveness detection function is segmented and distributed across all instances rather than centralized in specific roles. Each instance independently selects and monitors other instances based on selection criteria, ensuring comprehensive coverage without requiring special role assignments or complex role management mechanisms
3Reliability
If all instances are monitored by at least one other instance, then detection completeness is improved, but device complexity increases
Solution Approach 1:
Instead of having a centralized controller or specific role assign monitoring relationships, each instance passively receives monitoring assignments from others based on selection criteria. This inverted approach ensures every instance is monitored while avoiding complex centralized management, as the monitoring relationships are established bottom-up through simple selection rules
Data Source
AI summary
According to a method, at a given instance of a cluster of instances of at least one service, at least one monitored instance is selected from the cluster of instances according to a selection criterion such that each instance of the cluster of instances is selected as a monitored instance by at least one other instance of the cluster of instances. The given instance is caused to detect an operational status of the at least one monitored instance. If the operational status indicates that one of the at least one monitored instance is failed, the operational status of the failed monitored instance is provided to a centralized controller for the cluster of instances. Through the solution, the detection of instance liveness can be executed by individual instances symmetrically in a distributed and self-management manner.