Tiered Storage Service Levels for Cost-Optimized Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face increasing costs and resource inefficiencies due to the need for emergency-based resource allocation, where the probability and cost of data storage issues are difficult to accurately calculate, leading to unjustified expenses for enterprises and service providers.
Innovation Solution
Implementing a data storage array with multiple service levels, allowing for the association of different sets of services with varying levels of performance, enabling on-demand service provision and billing based on usage, where resources are allocated and billed according to specific service levels characterized by performance metrics such as IOs per second, drive speed, and availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If emergency-based resource allocation is implemented to ensure data storage reliability, then data storage reliability is improved, but cost increases
Solution Approach 1:
The patent applies parameter changes by transitioning from binary emergency-based resource allocation to a multi-level service quality parameter system. Different service levels (e.g., premium, standard, economy) are defined with specific performance parameters such as response time, availability, and throughput. This allows resources to be allocated according to actual service level requirements rather than emergency triggers, reducing unnecessary resource provisioning while maintaining reliability where needed.
Solution Approach 2:
The patent implements dynamics by making resource allocation flexible and adaptive based on actual service level agreements and usage patterns. Instead of static emergency-based allocation, the system dynamically adjusts resource distribution across different service levels, allowing enterprises to optimize their resource consumption and costs while maintaining the reliability required for their specific workloads.
2Reliability
If resources are allocated for emergency scenarios, then data storage reliability is improved, but resource utilization efficiency deteriorates
Solution Approach 1:
The patent applies local quality by assigning different service level characteristics to different data storage workloads or enterprises. Instead of uniform resource allocation, each service level is optimized for its specific requirements - premium services receive higher reliability resources, while economy services use standard resources. This localized optimization improves overall resource utilization efficiency while maintaining necessary reliability for critical operations.
Solution Approach 2:
The patent changes the allocation parameters from binary emergency/non-emergency states to a continuous spectrum of service levels with defined performance parameters. This allows resources to be allocated proportionally to actual needs, improving utilization efficiency by eliminating over-provisioning for low-priority workloads while ensuring adequate resources for high-priority operations.
3Adaptability or versatility
If multiple service levels are implemented, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the storage system into distinct service level tiers, each with defined characteristics and resource allocations. This segmentation provides adaptability by allowing enterprises to select appropriate service levels for different workloads, while the modular structure manages complexity through clear boundaries and standardized interfaces between service levels.
Solution Approach 2:
The patent implements universality by creating a multi-service-level architecture that can accommodate diverse enterprise requirements within a single standardized framework. The service level abstraction layer provides universal interfaces and management mechanisms that handle complexity internally, allowing the system to serve multiple purposes and customer needs without proportionally increasing operational complexity.
Data Source
AI summary
A catalog of services defines which storage-related services are applied to each service level of storage where storage capacity is managed and allocated in terms of chunks of capacity at different service levels. Each service level is defined based on one or more of tiered storage policy settings, drive size, drive speed, drive count, RAID protection, engine fractions, bandwidth and availability and characterized by one or more performance capabilities. Examples of services in the catalog include but are not limited to mobility, availability, continuity, and recovery services. Any combination of services, or no services at all, can be associated with a given service level of storage. Services may be performed at different performance levels. Further, services may be provided on-demand and billed on a usage basis.