Virtual Machine Cluster Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In data centers, it is challenging to efficiently allocate virtual machines to physical devices due to resource contention and inefficiencies in resource allocation, leading to reduced performance and utilization.
Innovation Solution
A virtual machine manager that dynamically assigns virtual machines to real devices based on resource needs and activity patterns, predicts optimal allocation, transfers virtual machines between devices, and provides failover and resource buffering through external clusters or cloud services to optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If virtual machines are allocated to real devices to meet resource demands, then service capacity is improved, but resource contention occurs when demands exceed physical capacity
Solution Approach 1:
The patent implements dynamic resource allocation where the virtual machine manager continuously monitors resource usage and dynamically assigns virtual machines to real devices based on current workload conditions. This dynamic approach allows the system to adapt to changing demands and prevents resource contention by redistributing virtual machines when capacity thresholds are approached.
Solution Approach 2:
The system changes allocation parameters by considering multiple resource types (processor usage, disk I/O, network I/O, memory space) simultaneously when making allocation decisions. This multi-parameter optimization ensures that virtual machines are assigned to devices that can handle their specific resource profiles, preventing contention across different resource dimensions.
2Quantity of substance
If virtual machines are assigned to real devices to ensure requested memory usage, then memory allocation is improved, but other resources are allocated inefficiently
Solution Approach 1:
The virtual machine manager performs multiple allocation functions simultaneously - it evaluates and allocates not just memory but also processor usage, disk I/O, and network I/O resources. This multi-functional approach ensures that a single allocation decision optimizes across all resource types rather than just memory, improving overall resource allocation efficiency.
Solution Approach 2:
The system transitions from single-parameter (memory-only) allocation to multi-parameter allocation by incorporating processor usage, disk I/O, network I/O, and memory space into the allocation decision-making process. This parameter expansion allows for more comprehensive resource optimization.
3Productivity
If virtual machines are allocated to real devices, then computing operations are performed, but infrastructure expansion is required to meet growing demand
Solution Approach 1:
The patent merges multiple virtual machines onto shared real devices, allowing the system to handle growing computing demands without proportionally expanding physical infrastructure. By consolidating and virtualizing resources, the system achieves increased productivity while minimizing the need for additional hardware.
Solution Approach 2:
The dynamic allocation system allows existing infrastructure to be utilized more flexibly and efficiently. By continuously monitoring and reallocating virtual machines based on current workload, the system can accommodate growing demand through better resource utilization rather than requiring proportional infrastructure expansion.
Data Source
AI summary
Managing resources in a VM cluster; allocation of resources among competing VMs. Assigning VMs to real devices, responsive to needs for resources: processor usage, disk I/O, network I/O, memory space, disk space. Assigning VMs responsive to needs for cluster activity: network response latency, QoS. Using predictive models of resource usage by VMs. Transferring VMs, improving utilization. Failing-soft onto alternative VM resources. Providing a resource buffer for collective VM resource demand. Transferring VMs to a cloud service that charges for resources.