Storage Emulation via Virtual Device Layer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems face challenges in delivering specified performance levels to customers, especially when multiple independent workloads compete for shared resources, leading to difficulties in managing and allocating resources efficiently.
Innovation Solution
A system and method for emulating a data storage system that allows customers to specify the level of service in terms of known storage devices, allocating sufficient resources to meet performance characterizations by prioritizing requests and adjusting queue depths based on latency statistics, enabling performance isolation among workloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If dedicated storage devices are allocated to each customer, then service level and performance are improved, but device complexity and cost increase
Solution Approach 1:
The patent segments storage resources into virtual devices that can be independently allocated to different customers or workloads. Each virtual device appears as a separate storage device to the customer but is implemented using shared physical storage resources, thereby providing dedicated service levels without requiring dedicated physical devices for each customer.
Solution Approach 2:
The patent creates virtual copies of storage devices that emulate the behavior and performance characteristics of physical devices. These virtual device copies allow customers to specify service levels in terms of known device types while the actual implementation uses shared physical resources, reducing the need for proliferating physical device types.
2Productivity
If multiple independent workloads are served on shared storage resources, then resource utilization is improved, but performance isolation and service level delivery become difficult
Solution Approach 1:
The patent introduces virtual devices as an intermediary layer between customers and physical storage resources. This virtualization layer provides performance isolation by managing resource allocation and scheduling, ensuring that each workload receives its specified service level while multiple workloads share the underlying physical storage resources efficiently.
Solution Approach 2:
The patent implements dynamic resource allocation where the virtual device layer can adjust resource distribution in real-time based on workload demands and service level requirements. This dynamic management allows the system to maintain performance isolation and meet service level agreements while maximizing overall resource utilization across multiple workloads.
3Ease of operation
If physical reconfiguration is performed to meet customer requirements, then service customization is improved, but flexibility and adaptability decrease
Solution Approach 1:
The patent enables dynamic reconfiguration of storage resources through the virtual device layer without requiring physical hardware changes. Service levels and device characteristics can be modified by reconfiguring virtual devices, allowing the system to adapt to changing customer requirements while maintaining flexibility and avoiding costly physical reconfiguration.
Solution Approach 2:
The patent creates a universal virtual device layer that can emulate different device types and service characteristics using the same physical storage resources. This multi-functional approach allows the system to provide customized service levels for different customers without requiring dedicated physical devices for each service type, thereby improving adaptability while maintaining ease of customization.
Data Source
AI summary
A technique for emulation of a data storage system. The invention allows the level of services to be provided by a data storage system to be specified in terms of the level of services provided by another storage system. In one aspect, a performance characterization of a data storage device to be emulated is obtained (e.g., by experimental techniques). A specification of a workload is also obtained that includes a specification of a plurality of data stores for the workload. The data stores are assigned to an emulation data storage device according to the performance characterization and according to the specification of the workload such that sufficient resources of the emulation data storage device are allocated to the workload to meet the performance characterization of the data storage device to be emulated. The emulation data storage device is then operated under the workload. Quality-of-service (QoS) control may be performed so as to provide a degree of performance isolation among the workloads.