Dynamic TLP Payload Size for Storage Latency Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices face challenges in reducing latency during data access due to fixed maximum data packet sizes, which can impact memory request completion and performance.
Innovation Solution
A storage device with a dynamic host read request size mechanism, where a controller assesses latency criticality and adjusts the read request size based on latency requirements, using a latency monitor and TLP payload size selector to optimize data transfer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If a fixed maximum data packet size is used, then device complexity is reduced, but latency increases and memory request completion is adversely impacted
Solution Approach 1:
The patent implements dynamic adjustment of TLP payload size based on latency requirements. The controller monitors latency conditions and adapts the read request size dynamically, transitioning from a static fixed size to a variable size that responds to real-time performance needs, thereby reducing latency without requiring complex manual intervention
Solution Approach 2:
The patent changes the parameter of TLP payload size from a fixed maximum value to a variable value that can be adjusted based on latency criticality. By modifying this key parameter dynamically, the system optimizes memory request completion time while maintaining manageable controller complexity through structured decision logic
2Productivity
If a larger read request size is used, then productivity is improved, but latency increases for critical operations
Solution Approach 1:
The system dynamically adjusts read request size based on whether latency is critical. When latency is not critical, larger read request sizes are used to improve productivity through bulk data access. When latency is critical, the size is reduced to minimize wait time, thus adapting productivity strategies to real-time conditions
Solution Approach 2:
The TLP payload size parameter is changed from a constant maximum value to a variable that responds to latency conditions. This parameter change enables the system to switch between productivity-optimized sizes and latency-optimized sizes, balancing data access efficiency with response time requirements
3Loss of time
If a dynamic read request size mechanism is implemented, then latency is reduced for critical operations, but device complexity increases
Solution Approach 1:
The patent applies local quality by implementing latency monitoring and dynamic size adjustment specifically for latency-critical operations, rather than uniformly across all operations. This targeted approach reduces latency where it matters most while keeping the controller structure relatively simple for non-critical paths
Solution Approach 2:
The system implements feedback through latency monitoring that informs dynamic read request size selection. The controller measures latency, compares it against thresholds, and uses this feedback to adjust subsequent read request sizes, creating a self-regulating mechanism that reduces latency without requiring complex external control
Data Source
AI summary
Embodiments of the present disclosure generally relate to a storage device with reduced latency and a method of accessing data by a storage device with reduced latency. In one embodiment, a method of accessing data by a storage device with reduced latency include triggering a controller of the storage device for issuing a host read request. The controller determines if latency is critical for completion of the host read request. The controller issues the host read request in dynamic host read request size if latency is critical.