Coordinated Container Scheduling for Dynamic VM Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In cloud computing systems, virtual machines often remain idle with unused resource capacity, leading to inefficient hardware utilization due to underutilization of resources such as vCPUs and memory.
Innovation Solution
A method and system for resource allocation that coordinates between a container scheduler and a hypervisor to dynamically reallocate unused resources among virtual machines, ensuring efficient utilization by monitoring and reallocating resources in real time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If resources are allocated to virtual machines for potential use, then resource availability for applications is improved, but hardware utilization efficiency deteriorates due to idle resources
Solution Approach 1:
The system dynamically adjusts resource allocation between virtual machines and containers based on real-time utilization monitoring. When VMs are idle, their resources are reallocated to containers; when VMs need resources, they can reclaim them. This dynamic approach resolves the contradiction by making resource allocation flexible rather than static.
Solution Approach 2:
The system changes the resource allocation parameters by introducing oversubscription ratios that allow containers to use a portion of VM resources when those resources are not fully utilized. This parameter change enables the system to maintain both resource availability and improved hardware utilization through controlled over-allocation.
2Reliability
If resources are statically allocated to virtual machines, then resource availability is improved, but resource efficiency deteriorates due to unused capacity
Solution Approach 1:
The patent transforms static resource allocation into a dynamic system where resources can be reallocated between VMs and containers based on actual usage patterns. The container scheduler monitors VM resource utilization and dynamically assigns unused resources to containers, while the VM can reclaim resources when needed, thus maintaining both availability and efficiency.
Solution Approach 2:
The system implements self-service mechanisms where containers automatically receive unused VM resources without manual intervention, and VMs can automatically reclaim resources when their utilization increases. This self-regulating approach improves resource efficiency while maintaining availability through automated resource management.
3Reliability
If virtual machines are provisioned with sufficient resources, then application performance is improved, but hardware utilization deteriorates due to idle vCPUs and memory
Solution Approach 1:
The patent merges the resource pools of multiple VMs by allowing containers to access unused resources from any VM in the cluster. The container scheduler consolidates idle resources across VM boundaries and allocates them to containers that need them, thus improving hardware utilization without compromising application performance.
Solution Approach 2:
The system introduces multi-functionality to VM resources by enabling them to serve both their original VM workloads and container workloads simultaneously through oversubscription. Resources are allocated universally to multiple potential users (VMs and containers), improving utilization while maintaining performance through on-demand allocation.
Data Source
AI summary
The technology provides for allocating an available resource in a computing system by bidirectional communication between a hypervisor and a container scheduler in the computing system. The computing system for allocating resources includes one or more processors configured to receive a first scheduling request to initiate a first container on a first virtual machine having a set of resources. A first amount of resources is allocated from the set of resources to the first container on the first virtual machine in response to the first scheduling request. A hypervisor is notified in a host of the first amount of resources allocated to the first container. A second amount of resources from the set of resources is allocated to a second virtual machine in the host. A reduced amount of resources available in the set of resources is determined. A container scheduler is notified by the hypervisor for the reduced amount of resources of the set of resources available on the first virtual machine.