Object Staging Data Structure for Storage Tier Transfers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current networked storage environments face inefficiencies in managing data across different storage tiers, particularly in identifying and transferring data chunks between performance and capacity tiers, which affects storage performance and resource utilization.
Innovation Solution
A method and system that utilize an object staging data structure to identify and transfer data chunks from one object to another, updating transfer logs with location information, and implementing a reference count data structure to manage data chunk usage, enabling efficient data movement and storage optimization across storage tiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is stored across multiple storage tiers without efficient management, then storage capacity is increased, but storage performance and resource utilization deteriorate
Solution Approach 1:
The patent segments data into data chunks and organizes them using data structure 521 that tracks reference counts for each chunk. This segmentation allows efficient identification and management of individual data chunks across storage tiers, enabling selective transfer and optimization without managing entire files or objects at once.
Solution Approach 2:
The patent introduces an intermediary data structure (521) that acts as a mediator between the storage operating system and the physical storage tiers. This data structure maintains reference count information and enables coordinated data movement between performance and capacity tiers, resolving the contradiction between capacity expansion and performance maintenance.
2Productivity
If data chunks are transferred between storage tiers, then storage optimization is improved, but system complexity increases
Solution Approach 1:
The storage system performs self-service through automatic identification and transfer of data chunks based on reference count information stored in data structure 521. The system autonomously determines which data chunks should be transferred between tiers without requiring complex external management, reducing operational complexity while maintaining optimization capabilities.
3Measurement precision
If reference counting is implemented for all data chunks, then data management accuracy is improved, but processing overhead increases
Solution Approach 1:
The patent implements reference counting selectively rather than universally - data structure 521 maintains reference count information for data chunks that benefit from tracking, particularly those being transferred between storage tiers. This partial application of reference counting provides sufficient management accuracy for critical operations while avoiding the processing overhead of tracking every single data chunk in the system.
Data Source
AI summary
Methods and systems for a networked storage environment are provided. One method includes scanning a first data structure by a processor executing instructions out of a memory for a storage operating system to determine whether any data chunk of a first object stored at a first storage tier is referenced by the storage operating; when the storage operating system references a certain number of data chunks, the processor using an object staging data structure to identify a second object that is in the process of being built with space for transferring the certain number of data chunks from the first object to the second object; and updating information regarding the second object at a transfer log with location information of the certain number of data chunks at the first storage tier.