5G CU-UP and CU-CP Standby Pods for Instant Microservice Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
5G wireless networks face challenges in maintaining high availability and avoiding network outages and dropped calls due to failures in CU-UP and CU-CP microservices, which are critical for seamless user experiences.
Innovation Solution
Implementing CU-UP and CU-CP standby pods with anti-affinity configurations on spare cloud compute instances within a cluster, enabling automatic failover to ensure continuous operation and minimize service disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If standby pods with anti-affinity configurations are implemented on spare cloud compute instances, then service availability and reliability are improved through automatic failover, but device complexity and infrastructure requirements increase
Solution Approach 1:
Standby pods are pre-configured with anti-affinity rules and pre-warmed before failures occur. When a primary pod fails, the standby pod can immediately take over without needing to be instantiated from scratch, enabling near-instantaneous failover and improving service availability.
Solution Approach 2:
The standby pods are created as copies of the primary pod configuration but deployed on different cloud compute instances. This copying approach allows the standby to have the same service capabilities while being isolated on different infrastructure, enabling automatic failover when the primary instance fails.
2Adaptability or versatility
If microservices are deployed on cloud compute instances within a cluster, then deployment flexibility and scalability are improved, but network outages and service disruptions can occur due to instance failures
Solution Approach 1:
The system segments the microservice deployment by creating separate primary and standby pods that can be independently managed and deployed. This segmentation allows the service to be divided into failure-isolated units, where the standby segment can take over if the primary segment fails, maintaining service continuity while preserving deployment flexibility.
Solution Approach 2:
The system changes the deployment parameter by introducing anti-affinity configurations that constrain pod scheduling to different cloud compute instances. This parameter change ensures that standby pods are placed on different infrastructure than primary pods, preventing simultaneous failures and maintaining service continuity while preserving cloud-native deployment flexibility.
3Loss of time
If automatic failover mechanisms are implemented, then service interruption time is reduced and reliability is improved, but system complexity and resource requirements increase
Solution Approach 1:
The failover mechanism operates autonomously through Kubernetes' native pod scheduling and health check capabilities. When a primary pod fails, the system automatically detects the failure and activates the standby pod without requiring external intervention or complex custom failover logic, reducing service interruption time while keeping the system relatively simple by leveraging existing orchestration capabilities.
Data Source
AI summary
Example embodiments are directed towards detecting a failure of one or more microservices of a CU-UP pod or a CU-CP pod running on a first cloud compute instance within a node group of a cluster. In response to the detection of a failure of one or more microservices of a CU-UP pod or a CU-CP pod of a node group within a cluster being hosted on a first cloud compute instance, the system automatically switches to run the one or more microservices for which failure was detected on a standby pod running on a second cloud compute instance with user equipment (UE) context corresponding to the one or more microservices for which failure was detected. The standby pods running on the other cloud compute instance are generated with anti-affinity between the CU-CP microservices of the primary CNF instance and CU-CP microservices of the standby pod.