Host Connectivity States for I/O Request Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage systems face inefficiencies in managing data storage and retrieval due to direct write operations to storage drives, leading to increased latency and unnecessary write operations, which can impact reliability and performance.
Innovation Solution
Implementing a system where host connectivity states are used to avoid queuing I/O requests by utilizing non-volatile random access memory (NVRAM) as a buffer for data destined to be written to storage drives, allowing for quicker access and reduced latency, and offloading device management responsibilities from storage drives to storage array controllers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If direct write operations are performed to storage drives, then data is stored reliably, but latency increases and write operations become unnecessary frequent
Solution Approach 1:
The patent implements a write buffer that temporarily holds data before it is written to storage drives. This preliminary buffering action allows multiple write requests to be accumulated and processed together, reducing the frequency of actual write operations to the drives while maintaining data reliability through proper buffering management and flush operations.
Solution Approach 2:
The patent introduces a write buffer as an intermediary component between the host system and storage drives. This buffer mediates write operations by absorbing write requests, managing data temporarily, and coordinating with storage drives at an optimized pace, thereby reducing latency without compromising data integrity.
2Productivity
If I/O requests are queued for processing, then storage drives can manage writes systematically, but latency increases due to queuing overhead
Solution Approach 1:
The patent extracts the queuing function from the storage drive and relocates it to a write buffer in memory. This separation allows the storage drive to process writes systematically while the buffer handles request accumulation and management, eliminating queuing overhead at the drive level and reducing overall latency.
3Adaptability or versatility
If storage drives manage their own device responsibilities, then drive autonomy is maintained, but system complexity increases and management becomes difficult
Solution Approach 1:
The patent implements a storage array controller that centralizes device management responsibilities. This controller serves multiple storage drives simultaneously, providing unified management for tasks such as write buffering, data placement, and drive coordination. This multi-functional approach maintains drive autonomy while reducing overall system complexity through centralized control.
Data Source
AI summary
Using host connectivity states to avoid queuing I/O requests: identifying a fault in data communications between a first storage system and a second storage system among a plurality of storage systems across which a dataset is synchronously replicated; updating, upon identifying the fault, an access state of a data communications path between first storage system and a host from an active state to a transitional state with respect to the dataset; and indicating, to the host, a first access state change.