Two-Stage Cluster Scheduling for Equal Resource Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud management methods in large-scale container environments struggle with flexible resource expansion and efficient service migration due to sequential resource distribution rather than equal distribution, leading to inflexible application development and slow development processes.
Innovation Solution
A cloud management method and apparatus that performs first-stage filtering to select clusters close to requested resources and second-stage scoring to determine the most suitable cluster for resource allocation based on factors like idle resources, network use rate, and quality of service, ensuring optimal resource distribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If sequential distribution of Round Robbin scheduling is used, then resource allocation is simple to implement, but resource distribution is not equal and service migration is difficult
Solution Approach 1:
The patent changes the scheduling parameters from simple sequential distribution to a multi-parameter scoring system that evaluates cluster suitability based on resource status, service affinity, and regional conditions. This enables flexible service migration by dynamically adjusting scheduling decisions based on current system state rather than fixed sequential allocation.
2Productivity
If sequential distribution of Round Robbin scheduling is used, then scheduling process is fast, but resource distribution equality is poor
Solution Approach 1:
The patent segments the scheduling process into two distinct stages: first-stage filtering that quickly narrows down candidate clusters based on basic compatibility, and second-stage scoring that precisely evaluates resource distribution equality. This segmentation maintains overall scheduling speed while achieving precise and equal resource distribution through the detailed scoring mechanism.
3Manufacturing precision
If two-stage scheduling with first-stage filtering and second-stage scoring is implemented, then resource distribution equality is improved, but scheduling complexity increases
Solution Approach 1:
By dividing the scheduling process into two stages with distinct functions, the patent manages complexity through modular design. The first stage handles quick filtering based on essential criteria, while the second stage focuses on precise scoring. This segmentation allows each stage to be optimized independently, making the overall complex system more manageable and maintainable.
4Measurement precision
If comprehensive scoring based on multiple factors is used, then cluster selection accuracy is improved, but analysis time increases
Solution Approach 1:
The two-stage approach segments the analysis process to first quickly eliminate unsuitable clusters through basic filtering criteria, then apply comprehensive scoring only to the reduced set of candidate clusters. This segmentation maintains high selection accuracy through thorough scoring while reducing overall analysis time by avoiding comprehensive evaluation of all clusters.
Solution Approach 2:
The first-stage filtering performs preliminary action by pre-screening clusters based on essential compatibility criteria before the second-stage scoring begins. This preliminary filtering reduces the number of clusters that require detailed analysis, thereby maintaining accuracy while reducing the time consumed by comprehensive scoring.
Data Source
AI summary
There are provided a cloud management method and a cloud management apparatus for rapidly scheduling arrangements of service resources by considering equal distribution of resources in a large-scale container environment of a distributed collaboration type. The cloud management method according to an embodiment includes: receiving, by a cloud management apparatus, a resource allocation request for a specific service; monitoring, by the cloud management apparatus, available resource current statuses of a plurality of clusters, and selecting a cluster that is able to be allocated a requested resource; calculating, by the cloud management apparatus, a suitable score with respect to each of the selected clusters; and selecting, by the cloud management apparatus, a cluster that is most suitable to the requested resource for executing a requested service from among the selected clusters, based on the respective suitable scores. Accordingly, for the method for determining equal resource arrangements between associative clusters according to characteristics of a required resource, a model for selecting a candidate group and finally selecting a cluster that is suitable to a required resource can be supported.