Virtual Checkpoint Frame for Cloud Resource Reclamation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud service technologies face complexity and performance degradation when managing resources for deferential services, as they require pre-planning and human intervention to reclaim resources, especially in continual services that need to persist state and scale independently of workload.
Innovation Solution
Implementing a virtual checkpoint frame interval that allows for the synchronized release of resources by collecting and copying packets and transactions during this interval, writing their state to a shared database, and transferring them to another server upon instance loss, enabling graceful resource reduction and reuse.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If time-based resource allocation is used with predefined time-windows, then resources can be reclaimed by cloud operators, but service design complexity increases and human intervention is required
Solution Approach 1:
The system performs preliminary actions by pre-defining release intervals and checkpoint frames before resources are actually released. The service operator configures release intervals and checkpoint frames in advance, allowing the system to automatically manage resource reclamation without human intervention during the actual release process.
Solution Approach 2:
The patent introduces an intermediary mechanism (the release interval management system with checkpoint frames) that mediates between the service operator's resource allocation and the cloud operator's resource reclamation. This intermediary automatically handles the coordination, eliminating the need for direct human intervention and complex service design.
2Productivity
If resources are released with advance notice, then cloud operators can reclaim excess servers, but continual services may experience performance degradation or loss of state
Solution Approach 1:
The system performs preliminary state capture by writing packet states to a shared state database before resources are released. This preliminary action ensures that service state is preserved and can be restored if needed, maintaining reliability during resource reclamation.
Solution Approach 2:
The patent uses copying to create a backup of the service state by writing packet information to a shared state database before resource release. This copy serves as a safety mechanism that allows service continuity even when original resources are reclaimed.
3Ease of operation
If service operators design services to complete before resource release, then resource reclamation is simplified, but service flexibility and adaptability are reduced
Solution Approach 1:
The system introduces dynamic checkpoint frames within release intervals that can be configured based on service requirements. This dynamic structure allows services to maintain flexibility in their design while still enabling automated resource reclamation, as the checkpoint frames can be adjusted to match different service lifecycles.
Solution Approach 2:
The patent allows service operators to change parameters such as release interval duration and checkpoint frame timing to optimize for different service types. This parameter flexibility enables both simple resource reclamation and service adaptability to be achieved simultaneously.
4Loss of energy
If excess servers are monetized by running services, then additional revenue is generated, but resource availability for paying customers may be reduced
Solution Approach 1:
The system implements periodic release intervals that allow services to run on excess servers for defined periods, generating revenue, while automatically reclaiming resources when needed. This periodic structure ensures that excess servers are monetized during intervals but remain available for paying customers when resources are released.
Solution Approach 2:
By pre-defining release intervals and checkpoint frames, the system prepares excess servers for future reclamation while allowing them to be used for revenue-generating services in the meantime. This preliminary planning ensures both revenue opportunity and resource availability are managed proactively.
Data Source
AI summary
A method is provided of using a set of servers to provide deferential services that have a pre-negotiated time for notice to release the servers. The method includes defining a virtual checkpoint frame interval that is constrained to a duration of up to half of the pre-negotiated time for notice to release the servers. The method includes collecting packets and transactions occurring during the interval that are processed by a current server. The method includes, responsive to an end of the interval, (i) writing, to a shared state database, a state of processing of the packets and transactions occurring during the interval, and (ii) releasing the packets and transactions occurring during the interval. The method includes copying the packets and transactions occurring during the interval, and the state, from the current server to another server for subsequent processing, responsive to an indication of an instance loss on the current server.