Parity Relocation for SSD Thermal Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Solid state drives (SSDs) face issues with overheated non-volatile memory dies, which can lead to reliability degradation due to increased temperatures, and current solutions like throttling reduce workload capacity and performance.
Innovation Solution
A method and apparatus that detect overheated memory dies, redirect parity data to these dies, and throttle performance only when necessary to maintain workload capacity and reduce temperature without degrading performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Temperature
If the entire system is throttled to reduce heat generation, then the temperature of memory dies is reduced, but the workload capacity and performance of the SSD are degraded
Solution Approach 1:
The invention segments the SSD into multiple memory dies with differentiated roles. Specifically, it separates parity data storage from user data storage across different dies. When one die becomes overheated, only the parity data on that specific die is relocated to another die, rather than throttling the entire system. This allows the overheated die to be cooled while other dies continue operating at full capacity, thus maintaining overall workload capacity while addressing the temperature issue locally.
Solution Approach 2:
The invention applies local quality by treating each memory die independently with respect to temperature management. Instead of applying a uniform throttling policy across all dies, the system monitors temperature individually for each die and only relocates parity data from specifically overheated dies. This localized approach ensures that only the necessary portion of the system is affected, preserving the performance of non-overheated dies while addressing thermal issues where they occur.
2Temperature
If parity data is redirected from overheated dies to other dies, then the temperature of the overheated dies is reduced, but the device complexity increases
Solution Approach 1:
The invention implements preliminary action by pre-establishing a pool of candidate dies that can receive parity data when needed. The controller maintains knowledge of which dies are suitable for parity storage in advance, so when overheating occurs, it can quickly relocate parity data without complex real-time decision-making. This pre-prepared architecture simplifies the relocation process and reduces the computational complexity during temperature emergencies.
Solution Approach 2:
The system employs feedback mechanisms by continuously monitoring the temperature of each memory die and dynamically adjusting parity data placement based on real-time thermal conditions. The controller receives temperature feedback from each die and automatically triggers parity relocation only when necessary, creating a closed-loop control system that adapts to thermal conditions without requiring complex manual intervention or predetermined scenarios.
Data Source
AI summary
Aspects of the disclosure provide for reducing a temperature of one or more non-volatile memory (NVM) dies of a solid state drive (SSD). The methods and apparatus detect a temperature of one or more NVM dies of a plurality of NVM dies of the SSD, the plurality of NVM dies including at least one parity NVM die, and determine that the one or more NVM dies is overheated when the detected temperature is at or above a threshold temperature. If the detected temperature is at or above the threshold temperature, the methods and apparatus redirect parity data designated for the at least one parity NVM die to the one or more overheated NVM dies. By repurposing the one more overheated NVM dies to store the parity data, the repurposed dies will experience less activity, and therefore, generate less heat without throttling or reducing the workload capability of the dies.