External Fault Isolation for Faster Virtualized Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional virtualization systems require manual intervention for failure recovery, which is slow and cannot recover from failures earlier than the default cycle of container virtualization software failure recovery functions.
Innovation Solution
A virtualization system failure separation device that includes a calculation resource cluster, a cluster management unit, an abnormality detection unit, and an abnormality handling unit, which detects and stops abnormal containers outside the cluster management unit to facilitate early failure recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the failure recovery function of container virtualization software is used, then the system can automatically recover from failures, but the recovery time is limited by the predetermined slow monitoring cycle (e.g., one second)
Solution Approach 1:
The system is divided into two independent parts: the container virtualization software (Kubernetes) that manages container orchestration, and the abnormality detection unit that operates externally to detect and report failures. This segmentation allows the external detection unit to operate with a faster, independent monitoring cycle without being constrained by the internal failure recovery function's predetermined slow cycle, thereby reducing overall recovery time while maintaining automatic recovery capability.
2Ease of operation
If manual intervention is used for failure recovery, then human control over recovery processes is maintained, but the recovery process becomes slow and cannot be accelerated
Solution Approach 1:
The abnormality detection unit operates autonomously outside the container virtualization software, independently detecting failures and transmitting control commands to stop abnormal containers. This self-service mechanism eliminates the need for manual intervention while maintaining system control, enabling automatic failure detection and response at a faster pace than conventional manual processes.
3Loss of time
If the abnormality detection unit operates outside the container virtualization software, then faster failure detection is achieved, but the system architecture becomes more complex
Solution Approach 1:
The abnormality detection unit acts as an intermediary component that operates externally to the container virtualization software. It receives container status information, detects abnormalities, and transmits control commands to the cluster management unit. This intermediary role enables faster failure detection independent of the internal software cycle while maintaining a relatively simple architecture through clear functional separation and standardized communication interfaces.
Data Source
AI summary
A calculation resource cluster that is virtually created on a physical machine by container virtualization software and in which containers virtually created on the physical machine by the container virtualization software are clustered and arranged; and a cluster management unit that is virtually created and manages control related to arrangement and operation of the containers clustered. Further, included are: an abnormality detection unit that is created at an outside of the calculation resource cluster and the cluster management unit that are virtually created and detects an abnormality in the containers; and an abnormality handling unit that is created at the outside and transmits, to the cluster management unit, a command for giving an instruction to stop an abnormal container detected by the abnormality detection unit. The cluster management unit stops the abnormal container in response to the command.