Dynamic NVRAM Conversion for Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face limitations in dynamically utilizing non-volatile random access memory (NVRAM) for both temporary memory and persistent storage, leading to inefficiencies in memory allocation and storage capacity utilization, as well as increased costs due to static memory capacity and the need for additional physical components.
Innovation Solution
Implementing a method that dynamically converts NVRAM between temporary memory and persistent storage by using a portion of NVRAM as memory and another portion as storage, allowing for direct access and allocation of NVRAM portions based on I/O requests, and utilizing an internal switching fabric for communication, bypassing external networks and directors to reduce latency and enhance performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If NVRAM is statically allocated for memory or storage, then reliability is improved, but adaptability deteriorates
Solution Approach 1:
The system dynamically converts NVRAM between memory and storage modes based on workload requirements. A conversion module enables NVRAM regions to be transformed from storage mode to memory mode and vice versa, allowing the system to adapt to changing performance and capacity needs while maintaining data persistence when required.
Solution Approach 2:
The NVRAM system serves multiple functions by operating in different modes. The same physical NVRAM resource can function as temporary memory for high-speed operations or as persistent storage for data retention, eliminating the need for separate dedicated memory and storage components.
2Productivity
If NVRAM is used for both memory and storage, then productivity is improved, but device complexity increases
Solution Approach 1:
The NVRAM is divided into multiple regions or sub-portions that can be independently managed. The conversion module operates on specific sub-portions of NVRAM, converting them between modes as needed, while other regions maintain their current function. This segmentation allows granular control and reduces the complexity of managing the entire NVRAM space.
Solution Approach 2:
A conversion module acts as an intermediary between the NVRAM and the host system, managing the dynamic conversion process. This module handles the complexity of mode transitions, region allocation, and data migration, shielding the host from the underlying complexity while enabling high productivity through optimized I/O operations.
3Quantity of substance
If additional physical components are added for storage, then storage capacity is improved, but cost increases
Solution Approach 1:
The NVRAM resource performs dual roles as both memory and storage, eliminating the need for additional dedicated storage components in certain scenarios. This multi-functionality increases storage capacity utilization while reducing system cost by leveraging existing NVRAM infrastructure rather than adding separate storage hardware.
Data Source
AI summary
Non-volatile Random Access Memory (NVR) on a storage system may be dynamically converted between use as temporary memory in a memory context and use as persistent memory in a storage context. NVR (e.g., embodied as DIMM) may be utilized in a hybrid capacity, where some of the NVR is used as memory and some of the NVR is used as storage, and where NVR memory is converted to memory as needed, dynamically as I/O is being processed using the NVR. A host system may be directly connected to an internal switching fabric of the data storage system without an intervening component of the storage system (e.g., a director) controlling access of the host system to the internal fabric or to the memory. The host system may provision and use the NVR as storage by directly communicating with the NVR over the internal fabric, for example, using RDMA.