Dynamic Storage Zone Prioritization for IOPS Density
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage devices (DSDs) face a decline in input/output operations per second (IOPS) density as storage capacity increases, due to mechanical limitations and the need for additional devices or costly design modifications, without effectively utilizing storage capacity or improving performance.
Innovation Solution
Implementing a prioritization and configuration process that differentiates between various storage areas on a disk or flash memory, using command queues and caching strategies to optimize performance by prioritizing operations in areas with faster data access methodologies, such as CMR over SMR, and adjusting the relative number of storage areas to achieve a target performance density.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If storage capacity of DSDs is increased, then storage capacity is improved, but IOPS density deteriorates
Solution Approach 1:
The patent divides the storage disk into different zone types (first zone type with faster data access methodology and second zone type with slower data access methodology) and applies different prioritization strategies to different zones. Commands are prioritized based on their target zone, allowing the system to optimize performance in high-speed zones while maintaining storage capacity across the entire disk surface.
2Productivity
If more DSDs with smaller storage capacities are added for parallel operation, then IOPS density is improved, but cost effectiveness deteriorates
Solution Approach 1:
The patent implements dynamic command prioritization where the system adaptively schedules commands based on real-time zone availability and performance characteristics. The controller dynamically adjusts command scheduling to maximize IOPS density within a single DSD, eliminating the need for multiple smaller DSDs and improving cost effectiveness.
3Productivity
If split actuator or multiple actuators are used to move heads independently, then IOPS density is improved, but device complexity and cost deteriorates
Solution Approach 1:
The patent introduces a command prioritization mechanism as an intermediary layer between the host and the storage zones. This software-based mediator manages access to different zone types and prioritizes commands without requiring physical hardware modifications like split actuators or multiple actuators, thereby maintaining mechanical simplicity while improving performance.
4Productivity
If stroke distance of the actuator is limited (de-stroking) to increase operations per time, then IOPS density is improved, but storage capacity utilization deteriorates
Solution Approach 1:
The patent performs preliminary classification of commands into different priority levels based on their target zones before execution. High-priority commands targeting first zone type areas are scheduled preferentially, allowing the system to maximize operations in high-performance zones without physically limiting the actuator stroke distance, thereby maintaining full storage capacity utilization.
Data Source
AI summary
A Data Storage Device (DSD) includes at least one disk for storing data in a plurality of storage areas including at least a first area type for using a first data access methodology and a second area type for using a second data access methodology. It is determined whether to perform a command in a storage area of the first or second area type. If the command is to be performed in the first area type, the command is prioritized over at least one other command for the second area type. In another aspect, a value is determined representing a number of data access operations within a predetermined time period for a data storage capacity of the DSD. Storage areas of the DSD are configured as one of at least the first area type and the second area type based at least in part on the determined value.