Storage Controller Apparent Load Biasing for Data Type Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems lack the ability to effectively weight commands based on storage media device limitations and do not utilize biases to optimize command execution, leading to inefficient load distribution across storage media devices.
Innovation Solution
A system that computes apparent loads for storage media devices, applies biases to influence load distribution, and directs commands to the most suitable device based on data type, optimizing execution by adjusting biases to balance loads between devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If commands are distributed across storage media devices based on simple queue fullness, then load distribution is achieved, but storage media device limitations and data type requirements are not optimized
Solution Approach 1:
The patent applies local quality by introducing data-type-specific weighting factors that treat different data types (e.g., sequential vs. random access) differently when calculating apparent load. This allows the system to optimize command distribution based on the specific characteristics of each data type and storage media device combination, rather than applying a uniform load distribution approach.
Solution Approach 2:
The system dynamically changes parameters by adjusting weighting factors based on storage media device limitations and data type characteristics. The apparent load calculation incorporates multiple parameters including queue fullness, device limitations, and data type weights, allowing flexible adaptation to different operational conditions.
2Use of energy by stationary object
If apparent load is computed without biases, then neutral command distribution occurs, but intentional load balancing and power optimization are not achieved
Solution Approach 1:
The system performs preliminary action by pre-computing apparent loads with biases before actual command execution. This allows the controller to proactively balance loads and optimize power consumption by selecting target devices based on biased apparent load calculations, rather than reactively managing loads after commands are issued.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors storage media device status, command queue states, and power consumption patterns, then adjusts bias values accordingly. This closed-loop control enables dynamic optimization of power usage while managing device complexity through adaptive rather than static bias management.
3Productivity
If load distribution is optimized for current commands, then immediate execution efficiency improves, but sustainable data rates and long-term performance are compromised
Solution Approach 1:
The system applies dynamics by making apparent load calculations dynamic rather than static. The bias values are adjusted in real-time based on changing system conditions, including current command patterns, device temperature, power state, and queue depth. This dynamic approach allows the system to balance immediate execution efficiency with long-term sustainability by adapting to evolving operational conditions.
Data Source
AI summary
An apparent load is determined based on assigning weightings to commands based on various factors including, but not limited to, the limitations of the underlying storage media device(s), where the command queue fullness is viewed from that perspective rather than simply the number of commands outstanding in a storage media device. Also disclosed is the use of a positive bias and a negative bias to artificially influence the apparent load to influence where a particular data type gets stored.