Storage Management Rebuilding via Access Flag Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In storage systems, temporary disk failures lead to inefficient rebuilding processes, causing increased system overhead and potential data loss, as conventional methods rebuild all storage units associated with a failed disk, even if they are not necessary.
Innovation Solution
The method determines candidate storage units based on historical access information and rebuilds only those that were actively accessed during the disk's unavailable state, reducing unnecessary rebuilding and minimizing data loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If scanning is required to detect whether each PLB needs to be rebuilt, then data loss can be avoided, but the rebuilding process proceeds slowly and system performance is affected
Solution Approach 1:
The system performs preliminary actions by setting access flags during normal operation to mark storage units that are actively accessed. When a disk fails, these pre-marked flags immediately identify which storage units need rebuilding, eliminating the need for slow scanning detection during the rebuild process while ensuring no data loss is prevented.
Solution Approach 2:
The system uses access flags as feedback mechanisms that continuously track which storage units are actively accessed. This feedback information is used during disk failure to automatically determine which storage units require rebuilding, resolving the contradiction between reliable data loss prevention and fast rebuilding by using real-time access status information.
2Reliability
If all storage units associated with a failed disk are rebuilt, then data integrity is maintained, but rebuilding overhead is significantly increased
Solution Approach 1:
The system extracts only the necessary storage units that require rebuilding by checking access flags, rather than rebuilding all storage units associated with a failed disk. This selective approach maintains data integrity for accessed storage units while eliminating unnecessary rebuilding overhead for storage units that were not actively accessed during the disk failure period.
Solution Approach 2:
The system applies partial action by rebuilding only the subset of storage units that were actively accessed (marked with access flags) rather than performing excessive action on all storage units. This partial rebuilding approach sufficient to maintain data integrity while significantly reducing the energy overhead and time required for the rebuild process.
3Measurement precision
If scanning is required for each PLB to detect rebuild needs, then accurate rebuild detection is achieved, but rebuilding overhead is significantly increased
Solution Approach 1:
The system performs preliminary marking of storage units with access flags during normal operation, so when a disk fails, the rebuild detection is immediately accurate without requiring slow scanning of each PLB. This preliminary action maintains high measurement precision for rebuild detection while eliminating the excessive overhead associated with scanning during the failure recovery process.
Data Source
AI summary
Techniques for storage management involve determining, in response to a detection that a disk changes from an unavailable state to an available state, at least one candidate storage unit associated with the disk; acquiring historical access information about the at least one candidate storage unit, the historical information comprising information related to a write request directed to the at least one candidate storage unit when the disk is in the unavailable state; determining a target storage unit from the at least one candidate storage unit based on the historical access information; and rebuilding the target storage unit. Such techniques may, in a low-cost manner, improve rebuilding efficiency and reliability of a storage system.