Peripheral Virtualization Management Device for Client-Selected Servers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current virtualized computing services restrict clients to using only hardware servers selected by the operator, limiting the use of specialized or customized hardware for compute instances, as clients cannot easily transfer software licenses or utilize custom components.
Innovation Solution
The implementation of peripheral virtualization management devices (PVMDs) that allow clients to configure compute instances on client-selected hardware servers, using industry-standard connectivity and encapsulation protocols to provide access to storage and network virtualization, enabling isolated virtual networks and flexible network configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If clients use only operator-selected hardware servers, then the provider network can maintain standardized hardware infrastructure, but clients cannot utilize specialized or customized hardware for their compute instances
Solution Approach 1:
The system separates hardware selection authority from infrastructure management. Clients can select and configure their own hardware servers (segmenting the selection function), while the provider network maintains centralized management of the hardware fleet and virtualization infrastructure (segmenting the management function). This allows both customized hardware usage and standardized infrastructure management to coexist.
Solution Approach 2:
The patent introduces intermediary components including hardware abstraction layers and virtualization management systems that mediate between client hardware selections and the provider network infrastructure. These intermediaries translate client-specific hardware configurations into standardized management interfaces, enabling hardware diversity without compromising infrastructure manageability.
2Speed
If clients deploy compute instances in non-traditional locations, then data transfer distances are reduced and latency improves, but connectivity to provider network services must be maintained
Solution Approach 1:
The system performs preliminary configuration of network connectivity and service access pathways before compute instances are deployed to non-traditional locations. Network routes, security credentials, and service endpoints are pre-established, ensuring that when instances are deployed closer to data sources, connectivity to provider network services is automatically maintained without requiring post-deployment configuration.
3Adaptability or versatility
If clients bring their own hardware servers, then specialized equipment can be utilized, but the provider network loses direct control over hardware configuration
Solution Approach 1:
The patent implements universal management interfaces and standardized communication protocols that work across diverse hardware configurations. The virtualization management system provides multi-functional capabilities to handle both operator-managed and client-brought hardware through common interfaces, enabling hardware customization while maintaining ease of operation through standardized procedures.
Data Source
AI summary
A peripheral device includes one or more processors and a memory storing program instructions that when executed implement virtualization offloading components of a virtualized computing service, including a storage manager. The offloading components establish network connectivity with a control plane of the service. Based on detecting that a hardware server, in a separate enclosure, has been linked to the peripheral device, the hardware server is presented as a virtualization host of the service. The offloading components initiate compute instance configuration operations at the server in response to commands issued to the control plane, including at least one configuration operation initiated by the storage manager to enable access to a logical storage device from a compute instance.