Thin Provisioning Storage Allocation with Garbage Collection Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage provisioning methods result in low utilization and wasted resources due to over-allocation of storage space, while existing solutions like thin provisioning and garbage collection either lead to inefficient performance or require additional memory.
Innovation Solution
A method and system for increased efficiency thin provisioning that allocates storage space by turning off the garbage collector when receiving a request from a client device, allowing for faster allocation without the need for additional memory resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional storage provisioning allocates storage space beyond current needs, then sufficient space is available at any given time, but unneeded allocation results in low utilization and wasted storage resources
Solution Approach 1:
The patent implements dynamic storage allocation where the system continuously monitors storage usage and adjusts allocation in real-time. When a storage device has available capacity (garbage collector turned off), space is allocated to client devices. When garbage collection is needed, allocation pauses. This dynamic approach replaces static over-provisioning with adaptive allocation that matches actual needs.
Solution Approach 2:
The system changes the operational state parameter of storage devices between 'garbage collection mode' and 'allocation mode'. By switching between these states based on monitored conditions, the system optimizes both storage reclamation and allocation efficiency, resolving the contradiction between maintaining availability and avoiding waste.
2Loss of substance
If garbage collection is performed to reduce wasted storage space, then data storage efficiency increases, but performance slows down or additional memory is required
Solution Approach 1:
The patent implements periodic garbage collection where the process is activated at specific intervals or under specific conditions rather than continuously. The system monitors when garbage collection is needed and temporarily suspends allocation operations during these periods, then resumes allocation when complete. This periodic approach minimizes performance impact while maintaining storage efficiency.
Solution Approach 2:
The system prioritizes and accelerates garbage collection operations when they are detected as needed, completing them quickly to minimize disruption to allocation operations. By rushing through the garbage collection process when necessary and then immediately returning to allocation mode, the system reduces overall performance impact while still achieving storage reclamation.
3Loss of substance
If thin provisioning allocates storage space flexibly based on minimum space needed, then storage efficiency increases, but storage performance may be compromised due to on-demand allocation
Solution Approach 1:
The patent performs preliminary checks on storage device status before allocation operations. By monitoring whether the garbage collector is turned off or on, the system determines in advance whether allocation can proceed without interruption. This preliminary assessment prevents wasted allocation attempts and ensures that when allocation does occur, it happens immediately without delays, thus maintaining high speed while preserving efficiency.
Data Source
AI summary
A system and method for increased efficiency thin provisioning of data storage. The method includes: receiving a request for storage allocation from a client device; and allocating, to the client device, at least a portion of a first storage of the plurality of storages when a garbage collector of the first storage is turned off.