Hypervisor Resource Negotiation for Virtual Partitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In virtualized computing environments, applications face challenges in negotiating for resources that meet specific performance parameters within a virtualized host system and among multiple remote host systems, as existing systems often rely on performance trade-offs that slow down memory access or fail to efficiently allocate resources.
Innovation Solution
A system and computer program product that enables applications to initiate negotiations for resources by a hypervisor, which manages local and remote resource allocations, migrating logical partitions to ensure performance parameters are met, using a broker agent to negotiate and migrate resources across host systems based on availability and cost estimates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the operating system satisfies the resource request using paging items to disk, then the resource request is satisfied, but memory access speed deteriorates
Solution Approach 1:
The hypervisor performs preliminary actions by proactively negotiating and reserving resources before the application actually needs them. The system anticipates future resource requirements and secures resources in advance through negotiation with other logical partitions and remote systems, preventing the need for performance-degrading paging operations.
Solution Approach 2:
The hypervisor acts as an intermediary between the application and the physical resources. It manages the negotiation process with other logical partitions and remote host systems, translating application resource requests into coordinated resource allocations across the virtualized environment, thereby avoiding direct paging to disk.
2Quantity of substance
If the logical partition cannot satisfy the resource request with free memory, then the resource request is rejected or satisfied with paging, but application performance deteriorates
Solution Approach 1:
The system performs preliminary resource negotiation and reservation before applications submit their actual resource requests. The hypervisor anticipates resource needs and secures allocations in advance through negotiation with other logical partitions and remote systems, ensuring resources are available when needed without degrading application performance.
Solution Approach 2:
The system extends resource allocation from a single host system to multiple remote host systems. When local resources are insufficient, the hypervisor negotiates resource allocation across the network with remote host systems, adding a spatial dimension to resource availability that prevents performance degradation from resource exhaustion.
3Productivity
If the hypervisor negotiates to reserve available local resources, then resource allocation efficiency improves, but system complexity increases
Solution Approach 1:
The hypervisor is designed as a universal platform that handles multiple functions: local resource management, negotiation with other logical partitions, and coordination with remote host systems. This multi-functionality consolidates what would otherwise require separate systems into a single versatile component, managing complexity while improving allocation efficiency.
Solution Approach 2:
The negotiation system incorporates feedback mechanisms where the hypervisor continuously monitors resource availability, allocation status, and performance metrics. This feedback enables dynamic adjustment of resource reservations and negotiations, optimizing allocation efficiency while the systematic feedback loops help manage complexity through automated control rather than manual intervention.
Data Source
AI summary
A hypervisor negotiates to reserve at least one available local resource in a host system that meets a performance parameter for at least one resource specified in a reservation request by a particular logical partition from among one or more logical partitions of virtualized pools of resources managed by the hypervisor in the host system, wherein the at least one performance parameter is specified by a particular application initiating the reservation request. The hypervisor, responsive to determining that the at least one available resource is not available in the host system, negotiates for offers to migrate the particular logical partition to at least one other host system comprising at least one available remote resource that meets the performance parameter, wherein the at least one other host system is managed by at least one other hypervisor that manages one or more other logical partitions of virtualized pools of resources.