NVM Storage Controller Architecture for Latency and Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprise storage systems face challenges with massive storage capacity, low latency, high bandwidth, low power consumption, and reliability, particularly due to the inherent errors and failures of hard disk drives (HDDs) with moving parts, which limit access time and increase costs.
Innovation Solution
Implementing a storage device using non-volatile memory (NVM) with an active/active or active/standby fault-tolerant configuration, featuring multiple controllers and processors for distributed I/O processing, enhanced heat dissipation, and reduced power consumption, along with the use of PCIe protocol for communication among components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If hard disk drives (HDD) with moving parts are used for storage, then massive storage capacity can be achieved, but access time increases and reliability deteriorates due to inherent errors and failures
Solution Approach 1:
The patent replaces the mechanical hard disk drive system with a non-volatile memory (NVM) based storage device. NVM eliminates moving parts such as spinning disks and magnetic heads, substituting mechanical storage with solid-state memory cells that provide faster access times and improved reliability without mechanical failure modes.
Solution Approach 2:
The patent changes the fundamental storage medium parameter from magnetic disk to non-volatile memory cells. This parameter change enables byte-addressable storage, parallel access patterns, and eliminates the physical constraints of rotational latency and seek time that characterize HDD access performance.
2Productivity
If multiple controllers and processors are implemented for distributed I/O processing, then latency is reduced and reliability is enhanced, but device complexity increases
Solution Approach 1:
The patent divides the storage device into multiple independent controller units, each with its own processors and I/O processing capabilities. This segmentation allows parallel processing of I/O operations across multiple controllers, improving throughput while distributing the complexity across modular units rather than concentrating it in a single complex controller.
Solution Approach 2:
The patent introduces a distributed architecture dimension where multiple controllers operate in parallel rather than a single centralized controller. This dimensional change from centralized to distributed processing enables scalability and improved throughput by adding processing resources across multiple spatial and functional dimensions.
Data Source
AI summary
Various systems, methods, apparatuses, and computer-readable media for accessing a storage device are described. In certain example embodiments, an active/active fault-tolerant storage device comprising two or more controllers may be implemented. In one aspect, each controller may have two or more processing entities for distributing the processing of the I/O requests. In one embodiment, the configuration of the components, modules and the controller board may be arranged in a manner to enhance heat dissipation, reduce power consumption, spread the power and work load, and reduce latency. In one embodiment, each controller may be coupled to the non-volatile memory (NVM) blades comprising the non-volatile memory (NVM) storage medium. In one example implementation, a standardized protocol, such as the Peripheral Component Interconnect Express protocol may be used for communicating amongst the various components of the controller and also the NVM storage medium.