Container Migration With Queued Write I/O for Service Continuity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Container migration in existing systems often results in service interruption due to the time required for the new container to startup on the target host node.
Innovation Solution
The method involves queuing write input/output operations for the migrating container, generating new read-only layers based on the read/write layer content, and comparing these layers to identify and transfer data changes, ensuring seamless service continuity by merging these changes into the target container's read/write layer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the new container is started up on the target host node during migration, then the service can be continued on the target node, but service interruption occurs due to the startup time required
Solution Approach 1:
The patent applies preliminary action by queuing write I/O operations before the container migration is complete. The system captures and queues write operations that occur during the migration process, then applies them to the new container after it starts up on the target host node. This ensures that no data changes are lost during the transition, maintaining service continuity without requiring the new container to be fully ready before the migration begins.
2Reliability
If all write input/output operations are transferred to the new container, then data consistency is maintained, but migration time increases due to the need to process and transfer all operations
Solution Approach 1:
The patent applies partial action by selectively processing only the necessary write I/O operations during migration. Instead of transferring all possible operations, the system identifies and queues only those write operations that occurred during the migration window (between the first and second timestamps). This partial processing approach maintains data consistency for the critical period while minimizing the overhead and time required for the migration process.
3Reliability
If the read/write layer is continuously updated during migration, then the latest data is captured, but the complexity of managing queued and new operations increases
Solution Approach 1:
The patent applies segmentation by dividing the write I/O operations into distinct segments: operations queued before migration (first set), operations occurring during migration (second set), and operations after migration completes. Each segment is handled at the appropriate time - the first set is queued, the second set is captured and re-applied to the new container, and the third set continues normal processing. This segmentation simplifies the management complexity by providing clear boundaries and handling procedures for each operation group.
Data Source
AI summary
Container migration is provided. A comparison of a second image and a third image is performed to detect data changes made by write input/output operations occurring between a second timestamp and a third timestamp. It is determined whether a set of data changes exists in the third image that occurred between the second timestamp and the third timestamp. In response to determining that the set of data changes does exist in the third image that occurred between the second timestamp and the third timestamp, a copy of the set of data changes is sent to a second host node. The set of data changes are merged into the second host node. The write input/output operations are resumed to the second host node using previously queued write input/output operations and new incoming write input/output operations so that the second host node is processing read input/output operations and the write input/output operations.