Die Translation Table for Storage Parallelism Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage devices do not fully utilize their inherent parallelism architecture, leading to inefficiencies where some dies are overworked while others are idle, resulting in compromised read command execution and latency during storage operations.
Innovation Solution
A die translation table is used to estimate the appropriate die for storage device operations, allowing for more efficient scheduling of operations by using a formula and look-up table to determine the correct die for read and write operations, thereby optimizing die usage and reducing idle time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional translation methods are used to determine die location, then the system is simple to implement, but some dies are overworked while others are idle, compromising parallelism efficiency
Solution Approach 1:
The patent pre-calculates and stores die location information in a translation table during system initialization or previous operations. This preliminary action allows the system to quickly retrieve die locations without performing complex real-time calculations, thereby improving parallelism efficiency while avoiding the need for complex runtime translation mechanisms.
Solution Approach 2:
The patent creates a simplified copy of the die mapping relationship in the form of a translation table that maps logical addresses to physical die locations. This copy allows the controller to quickly determine which die to access without performing complex physical address translations, thus improving parallelism efficiency while maintaining implementation simplicity.
2Productivity
If the number of read commands is limited, then the host can issue fewer commands, but some dies will be idle while others are overworked, reducing overall efficiency
Solution Approach 1:
The patent implements dynamic command scheduling that adapts to the current state of each die. The controller uses the translation table to identify which dies are currently idle and actively assigns read commands to these idle dies, thereby balancing the workload across all dies and eliminating idle time, which improves overall efficiency without requiring the host to issue a large number of commands.
Solution Approach 2:
The system continuously monitors the status of each die and uses this feedback information to dynamically adjust command assignment. By tracking which dies are busy or idle and using the translation table to redirect commands appropriately, the system ensures optimal utilization of all dies, reducing idle time and improving overall efficiency even with limited read commands from the host.
3Productivity
If commands are executed in the order generated by the host, then the system is easy to control, but die parallelism is not optimized and latency increases
Solution Approach 1:
The patent pre-computes the die location for each logical address and stores this information in the translation table before command execution. This preliminary action allows the command scheduler to quickly determine the optimal die for each command without performing complex real-time analysis, thereby enabling optimized die parallelism while keeping the scheduling mechanism relatively simple.
Solution Approach 2:
The system creates a simplified mapping copy in the translation table that directly associates logical addresses with their target dies. This copy enables the controller to reorder commands for optimal die utilization without complex address translation calculations, thus improving die parallelism while maintaining control simplicity through the use of pre-computed mappings.
Data Source
AI summary
In one non-limiting embodiment, a method is disclosed for performing a storage device operation on a die is provide having steps of choosing a storage device operation to perform, estimating which die is related to the storage device operation chosen to be performed and performing the storage device operation at the die based on the estimating.