Adaptive Flow Control Mechanism for I/O Throughput Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face challenges in optimizing the flow of I/O requests between interconnected data storage systems, leading to suboptimal performance and resource utilization, particularly in networked environments with varying conditions and distances between storage systems.
Innovation Solution
A method and system that dynamically adjust the maximum number of outstanding I/O requests by assessing performance at different threshold values (R, R+delta1, and R-delta2) over trial periods, using a network optimizer when present, to determine the optimal R value for maximizing throughput and minimizing resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the maximum number of outstanding I/O requests is increased to improve throughput, then I/O throughput is improved, but system reliability and resource utilization deteriorate due to potential resource exhaustion and increased failure risk
Solution Approach 1:
The patent implements dynamic adjustment of the maximum number of outstanding I/O requests based on real-time system conditions. The system monitors performance metrics and automatically adjusts the threshold parameter, transitioning from static to dynamic control. This allows the system to optimize throughput by increasing the threshold when resources are abundant while maintaining reliability by reducing the threshold when resource constraints are detected.
Solution Approach 2:
The patent employs feedback mechanisms where the system continuously monitors I/O performance metrics and uses this information to adjust the maximum outstanding requests threshold. The feedback loop compares current system state against predefined criteria and modifies the threshold accordingly, enabling adaptive control that balances throughput optimization with reliability maintenance based on actual system conditions.
2Productivity
If the maximum number of outstanding I/O requests is increased to improve throughput, then I/O throughput is improved, but device complexity increases due to additional monitoring and adjustment mechanisms
Solution Approach 1:
The patent implements self-service functionality where the flow control mechanism automatically monitors its own performance and adjusts parameters without external intervention. The system performs self-diagnosis by monitoring I/O metrics and self-regulates by automatically modifying the maximum outstanding requests threshold, eliminating the need for complex external management systems while maintaining optimization capabilities.
Solution Approach 2:
The patent focuses on adjusting key parameters (the maximum number of outstanding I/O requests threshold) rather than implementing completely new systems. By modifying existing parameter values based on performance feedback, the system achieves throughput optimization without introducing excessive complexity, as the changes are made within the framework of existing flow control architecture.
3Productivity
If assessment processing is performed frequently to optimize R value, then I/O throughput is improved, but processing time and resource consumption increase
Solution Approach 1:
The patent implements periodic assessment processing rather than continuous monitoring and adjustment. The system performs assessment at defined intervals or when specific trigger conditions are met, allowing optimization of throughput while reducing processing overhead. This periodic approach balances the need for timely adjustments with the cost of frequent assessments, preventing excessive resource consumption.
Solution Approach 2:
The patent applies partial assessment action by evaluating only the most critical performance metrics and using incremental adjustments to the R value rather than comprehensive re-evaluation. The system makes partial adjustments (e.g., changing R by delta1 or delta2) rather than complete redesign, reducing the time and resources required for each assessment while still achieving meaningful throughput optimization.
Data Source
AI summary
Described are techniques for controlling a flow of I/O requests. R is received denoting a current maximum number of outstanding I/O requests allowed to be issued by a first data storage system to a second data storage system over a path. Assessment processing is performed to obtain a first performance value, a second performance value, and a third performance value, respectively, when the maximum number of outstanding I/O requests allowed to be issued by the first data storage system to the second data storage system over the path is R+delta1, R, and R−delta2 (delta1 and delta 2 are positive integer values). It is determined whether to update R in accordance with criteria including the first performance value, the second performance value and the third performance value.