Mixed Job Scheduling for Service Dispersion in Resource Clusters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud computing platforms, the centralized deployment of service copies on the same resource leads to poor service availability due to aggravated resource usage, which is not effectively addressed by current scheduling methods.
Innovation Solution
A job scheduling method that implements mixed-deployment of multiple jobs' implementation units in combined resource allocations, optimizing resource usage to improve service dispersion and availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If service copies are centrally deployed on the same resource, then resource utilization is improved, but service availability deteriorates
Solution Approach 1:
The patent segments service copies into different deployment groups that are distributed across multiple resource nodes. Instead of concentrating all copies on a single resource, the system divides them into separate groups (e.g., first group on first resource node, second group on second resource node), ensuring that service availability is maintained even if one resource fails while still achieving good resource utilization through coordinated deployment.
2Productivity
If implementation units of multiple jobs are deployed on the same resource node, then resource efficiency is improved, but service dispersion deteriorates
Solution Approach 1:
The patent applies local quality by assigning different deployment characteristics to different job implementation units based on their specific requirements. High-priority jobs are deployed on dedicated resource nodes to ensure service dispersion and availability, while lower-priority jobs can share resources. This allows the system to optimize resource efficiency locally for each job type while maintaining overall service dispersion.
Data Source
Figure 1~2
Figure 3
Figure 4~7
AI summary
This application discloses a job scheduling method and apparatus, and pertains to the field of resource scheduling technologies. The method includes: obtaining a plurality of implementation combinations based on resource demands of implementation units that need to be deployed for a plurality of to-be-scheduled jobs, where at least a part of the plurality of implementation combinations include implementation units of at least two to-be-scheduled jobs, and a first proportion of a resource demand of the implementation combination to an idle resource specification of a resource node in a resource cluster is greater than a preset value; obtaining a target implementation set based on the plurality of implementation combinations, where the target implementation set includes at least one implementation combination, and includes all implementation units of the plurality of to-be-scheduled jobs; and scheduling, to the resource node based on the target implementation set, the implementation units that need to be deployed for the plurality of to-be-scheduled jobs. In this application, mixed-deployment of the implementation units of the plurality of to-be-scheduled jobs is implemented, so that an aggravation degree of implementation units of a same job can be effectively reduced, a service dispersion degree can be improved, and high service availability can be ensured.