Read Disturb Storage Temperature Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional read temperature identification systems in information handling systems are costly, complex, and inaccurate, requiring dedicated host memory and power-fail safety measures, and often introduce performance issues due to host processor involvement, while also lacking granularity and resilience to changing workloads.
Innovation Solution
A read-disturb-based physical storage read temperature identification system that uses storage devices to determine read disturb information and generate local logical storage element read temperature maps, which are then provided to a global subsystem for accurate temperature mapping without relying on host processors, allowing for efficient data placement and load balancing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional read temperature identification systems use host memory and host processor to track read temperatures, then read temperature information can be identified, but system costs increase and complexity increases due to dedicated host memory requirements and power-fail safety measures
Solution Approach 1:
The storage device autonomously tracks read temperatures using its own internal memory and processing resources, eliminating the need for dedicated host memory and processor involvement. The storage device serves itself by maintaining read temperature maps locally and providing this information to the host only when needed, thereby reducing system complexity while preserving measurement accuracy.
Solution Approach 2:
The patent introduces an intermediary read temperature map data structure that acts as a buffer between the storage device's internal tracking mechanism and the host system. This intermediary structure allows the storage device to maintain detailed read temperature information locally while presenting a simplified interface to the host, reducing the computational burden on the host processor and memory requirements.
2Measurement precision
If conventional systems involve host processor in read temperature tracking, then read temperature maps can be generated, but system performance deteriorates due to increased host processor workload and I/O latency
Solution Approach 1:
The storage device independently maintains read temperature maps using its own processing capabilities, eliminating the need for host processor involvement in tracking read temperatures. This self-service approach allows the storage device to update and maintain temperature information in the background without impacting host I/O performance, while still providing accurate temperature data when requested.
Solution Approach 2:
The storage device pre-calculates and maintains read temperature maps in advance, so that when the host needs temperature information for data placement decisions, the data is already available without requiring real-time computation. This preliminary action eliminates I/O latency associated with temperature tracking while maintaining accurate temperature mapping.
3Measurement precision
If conventional read temperature systems use dedicated host memory, then read temperature information can be stored, but costs increase due to additional memory requirements and power-fail safety infrastructure
Solution Approach 1:
The storage device utilizes its own internal memory resources to store read temperature maps, eliminating the need for dedicated host memory allocations. The storage device manages its temperature tracking data autonomously, providing this information to the host on demand without requiring the host to allocate additional memory resources or implement power-fail safety measures for temperature data.
4Adaptability or versatility
If conventional systems track read temperatures at host level, then read temperature information is available, but granularity is insufficient and resilience to changing workloads is limited
Solution Approach 1:
The patent segments the storage device's address space into logical units (such as logical unit numbers or LUNs) and maintains separate read temperature maps for each segment. This segmentation allows the system to track read temperatures with fine granularity at the logical unit level, enabling adaptive data placement decisions that can respond to changing workload patterns across different segments of the storage device.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution reduces costs and complexity by leveraging the read disturb effect to generate accurate read temperature maps within storage devices, improving data placement and system performance without the need for extensive host processor involvement, and enhances resilience to changing workloads.
Implementation Method 1
read-disturb-based physical storage read temperature information identification
Data Source
AI summary
A read-disturb-based physical storage read temperature information identification system includes a global read temperature identification subsystem coupled to at least one storage device. Each at least one storage device reads valid data and obsolete data from at least one physical block in that storage device and, based on the reading of the valid data and the obsolete data, generates read disturb information associated with each row provided by the at least one physical block in that storage device. Each at least one storage devices then uses the read disturb information associated with each row provided by the at least one physical block in that storage device to generate a local logical storage element read temperature map for that storage device that it provides to the global read temperature identification subsystem.