Virtual Machine Abstraction via Hypervisor and Sub-hypervisors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional virtualization approaches using hypervisors are limited in providing advanced networking features like RDMA and iSCSI to guest operating systems, and result in inefficient resource utilization and increased risk due to consolidation of server operations.
Innovation Solution
A system and method for abstracting virtual machines across a network, utilizing a hypervisor and sub-hypervisors to distribute and configure virtual machines across multiple devices, enabling load balancing, dynamic scaling, and advanced networking features such as L2, VLAN, L3, and L4 switching, while ensuring efficient resource allocation and protection through independent queues and address validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If server operations are consolidated into a single physical machine, then server efficiency is improved, but reliability deteriorates because a crash in one service causes loss of all services
Solution Approach 1:
The patent segments server operations into separate virtual machines, each running on its own isolated operating system instance. This allows multiple services to share physical hardware while maintaining operational independence, so a crash in one VM does not affect others, thus improving reliability while maintaining consolidation benefits
2Reliability
If multiple guest operating systems are utilized to maintain protection and optimization, then reliability is improved, but device complexity increases due to the need for hypervisor and resource arbitration
Solution Approach 1:
The patent implements a universal hypervisor architecture that can simultaneously support multiple guest operating systems with different requirements (L2 switching, L3 routing, L4 load balancing, RDMA, iSCSI). This single multi-functional platform reduces overall system complexity compared to maintaining separate specialized systems for each function
3Ease of operation
If virtual NIC is utilized for GOS access, then ease of operation is improved, but adaptability deteriorates because advanced features like RDMA and iSCSI cannot be directly supported
Solution Approach 1:
The patent introduces a physical NIC with integrated virtualization capabilities that acts as an intermediary between the hypervisor and guest operating systems. The physical NIC includes dedicated hardware queues and processing units that can directly handle advanced features like RDMA and iSCSI, bypassing the limitations of software-based virtual NICs while maintaining simplified GOS access
4Ease of operation
If data is copied among buffers for network transmission, then ease of operation is improved, but loss of energy increases due to host processor overhead
Solution Approach 1:
The patent implements self-service data transmission by enabling guest operating systems to directly access and manage network buffers through the physical NIC's hardware queues. The NIC autonomously handles data movement, buffering, and transmission without requiring host processor intervention for each data copy operation, significantly reducing CPU overhead and energy consumption
Data Source
AI summary
One or more processors and/or one or more circuits may be operable to configure one or more virtual machines and a hypervisor for controlling the one or more virtual machines. The virtual machines and the hypervisor may be distributed across a plurality of network devices. A sub-hypervisor may be configured within each of the virtual machines utilizing the hypervisor. Load information of the network devices may be communicated to the hypervisor utilizing the sub-hypervisors. The virtual machines may include threads, may be load balanced utilizing the hypervisor, dynamically configured utilizing the hypervisor based on changes in the network devices, and scaled by the distribution of the virtual machines across the network devices. Information from the processing of data may be received in the virtual machines. The network devices may include a plurality of: servers, switches, routers, racks, blades, mainframes, personal data assistants, smart phones, desktop computers, and/or laptop devices.