Service Slicing for Cloud Node Incarnation Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
When moving applications to a remote services environment, such as cloud computing, it is challenging to accurately determine the correct number of nodes and their performance capabilities needed to meet service level agreements while minimizing costs, as resource usage varies over time and conventional methods only assess this after migration, leading to unnecessary expenses.
Innovation Solution
A system that receives an application, obtains a resource profile of each service's resource usage over time, splits services into slices based on consistent demand intervals, identifies suitable node incarnations based on resource capacity, and assigns these slices to nodes, optimizing node usage and cost before migration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional methods are used to determine node requirements after migration, then service level agreements can be met, but unnecessary expenses are incurred due to over-provisioning
Solution Approach 1:
The patent performs resource profiling and incarnation selection before migration to the remote services environment. By analyzing resource usage patterns and selecting appropriate node incarnations in advance, the system determines accurate node requirements prior to deployment, preventing over-provisioning and reducing costs while ensuring service level agreements are met.
2Productivity
If resource usage is not analyzed over time, then migration can proceed quickly, but accurate determination of node requirements cannot be achieved
Solution Approach 1:
The system performs resource profiling during a preliminary period before migration, collecting and analyzing resource usage data over time. This advance preparation enables accurate determination of node requirements without delaying the actual migration process, as all analysis is completed beforehand.
Solution Approach 2:
The patent divides the service into multiple service slices based on resource profiles and time periods. By segmenting the service and analyzing resource usage for each slice separately, the system achieves precise node requirement determination while maintaining efficient migration through structured, modular analysis.
3Device complexity
If services are not split into slices, then the process is simpler, but accurate matching of service demand to node capacity cannot be achieved
Solution Approach 1:
The patent segments services into multiple service slices based on resource profiles and demand patterns. Each slice represents a consistent demand interval that can be accurately matched to specific node incarnations. This segmentation enables precise matching of service demand to node capacity while maintaining manageable process complexity through structured analysis.
Solution Approach 2:
The system changes the parameter of service representation from monolithic to sliced, allowing different service slices to be matched to different node incarnations based on their specific resource requirements. This parameter change enables accurate demand-capacity matching while the systematic approach keeps process complexity controlled.
Data Source
AI summary
One embodiment provides a computer implemented method, including: receiving an application including a plurality of services to be hosted on a remote services environment; obtaining, a resource profile identifying a usage of a resource by a given service of the plurality of services over a period of time; splitting, based upon the resource profile corresponding to a given service, the given service into a plurality of service slices; selecting, for each of the plurality of service slices an incarnation fulfilling a resource demand requirement and a service-performance-offering, wherein an incarnation has a total demand value based upon a resource capacity of a node at the remote services environment; and assigning, for each of the plurality of service slices the incarnation selected to at least one node within the remote services environment based upon the resource capacity of the at least one node.