Tiered Cloud Storage Allocation for Performance Cost Trade-offs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud infrastructure environments face challenges in providing flexible and cost-effective data storage solutions that balance performance and scalability, as on-premise storage area networks are constrained to rack-level capacity and availability, while cloud providers offer specific storage options with disjoint capabilities and high friction when moving data between them.
Innovation Solution
A data storage service that automatically adjusts data storage for cloud instances across performance tiers by allocating storage between different types of storage devices, such as SSD/NVMe, HDD, and object storage, using caching processes to determine which data is 'hot' or 'cold' based on usage, allowing for dynamic configuration of performance and cost optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud providers offer multiple specific storage options with different performance characteristics, then data performance and availability can be optimized for different workloads, but device complexity and operational friction increase when moving data between storage options
Solution Approach 1:
The patent combines multiple storage types (block storage and object storage) into a unified tiered storage system. The block storage layer provides high-performance access for active data while the object storage layer provides cost-effective archival for inactive data, merging their capabilities into a single managed storage service that automatically handles data placement and movement between tiers.
Solution Approach 2:
The storage system provides multi-functional capabilities by offering both block storage and object storage through a single unified interface. The system can dynamically serve different performance requirements and data access patterns through the same storage service, eliminating the need for separate storage systems and reducing operational complexity.
2Speed
If high-performance storage devices like SSD/NVMe are used for all data, then data access speed and performance are improved, but storage cost increases significantly
Solution Approach 1:
The patent applies local quality by providing different storage performance characteristics to different data based on its access patterns. Frequently accessed ('hot') data is stored on high-performance block storage devices, while infrequently accessed ('cold') data is stored on lower-cost object storage, ensuring that high-performance storage is applied only where needed rather than uniformly across all data.
Solution Approach 2:
The system dynamically changes storage parameters by automatically adjusting the performance tier of storage devices based on data access patterns. The storage system monitors usage patterns and transitions data between high-performance and cost-effective storage tiers, changing the performance and cost parameters adaptively rather than statically.
3Adaptability or versatility
If data is moved between different storage options in cloud providers, then specific performance requirements can be met, but operational friction and complexity increase
Solution Approach 1:
The tiered storage system provides self-service by automatically monitoring data access patterns and autonomously moving data between storage tiers without requiring manual intervention. The system itself manages the complexity of data placement and migration, performing required actions in advance and handling all operational details internally while presenting a simplified interface to users.
4Adaptability or versatility
If on-premise storage area networks are used, then flexible configurations are available, but capacity and scalability are constrained to rack level
Solution Approach 1:
The patent transitions from the rack-level physical dimension of on-premise storage to the cloud-regional dimension, enabling storage capacity to scale beyond physical rack constraints. The tiered storage architecture allows capacity to expand across multiple data centers and regions while maintaining configuration flexibility through software-defined storage policies and automated tiering mechanisms.
Data Source
AI summary
In accordance with an embodiment, described herein are systems and methods for providing tiered data storage in cloud infrastructure environments. A data storage service (block store) is adapted to automatically adjust the manner by which the data for a data volume or block volume (data/block volume), associated with a cloud instance, can be stored to meet the requirements of a performance tier. For example, responsive to selection of a particular performance tier, the storage of the data/block volume can be allocated between a first type of data storage associated with a first performance characteristics; and a second type of data storage associated with a second performance characteristics. A graphical user interface enables configuring data/block volumes to use particular performance tiers, and/or to support automatic tuning.