Quarantine List for Storage Metadata Consistency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data storage systems face limitations in persisting metadata consistency, leading to failures due to inconsistencies caused by faulty connections, data corruption, or locking mechanisms, which can result in excessive costs for triple-mirrored persistent storage to maintain validity lists for all storage objects.
Innovation Solution
Implementing a method where only invalid storage objects are stored in triple-mirrored persistent storage, with a quarantine list to manage metadata validity, allowing for efficient and cost-effective tracking of metadata validity by limiting expensive storage to a small number of invalid objects, and using a health level to address catastrophic failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a validity list for every storage object is stored in triple-mirrored persistent storage to ensure metadata consistency, then reliability is improved, but device complexity and storage cost increase excessively
Solution Approach 1:
The patent segments the validity list into two parts: a small quarantine list stored in triple-mirrored persistent storage for rapid access and a larger validity list stored in standard persistent storage. This segmentation allows the system to maintain reliability for critical operations while avoiding the excessive cost and complexity of triple-mirroring the entire validity list.
Solution Approach 2:
The patent extracts the critical quarantine functionality from the overall validity tracking system. By isolating only the quarantine list (containing identifiers of invalid storage objects) in triple-mirrored storage, the system maintains reliability for safety-critical metadata consistency checks without requiring triple-mirroring of all validity information.
2Reliability
If triple-mirrored persistent storage is used for the validity list, then reliability is improved, but storage cost increases excessively as system size grows
Solution Approach 1:
The patent divides the storage requirements into two segments: a small quarantine list in triple-mirrored persistent storage (expensive but highly reliable) and a larger validity list in standard persistent storage (cheaper but less redundant). This allows the system to maintain reliability where critical while reducing overall storage costs.
Solution Approach 2:
The patent applies different storage quality levels to different parts of the validity tracking system. The quarantine list receives the highest quality (triple-mirrored) storage for critical reliability, while the full validity list uses standard quality storage, optimizing the balance between reliability and cost.
3Stability of the object's composition
If the storage processor attempts to persist metadata updates, then data consistency is improved, but system productivity decreases due to locking mechanisms and potential failures
Solution Approach 1:
The patent implements preliminary action by maintaining a quarantine list in fast triple-mirrored persistent storage that can be quickly checked before I/O operations. This allows the system to pre-identify and quarantine invalid storage objects without blocking subsequent operations, improving productivity while maintaining consistency.
Solution Approach 2:
The patent uses copying by maintaining a lightweight quarantine list (a copy of critical validity information) in fast accessible storage. This copy allows rapid validation checks without requiring access to the full metadata or imposing locking constraints on the main storage system.
Data Source
AI summary
Techniques are presented for implementing a scalable approach to keeping track of the metadata validity of persistently-stored metadata for storage objects. In contrast with prior approaches, improved techniques only store a list of the invalid (or quarantined) objects rather than all objects regardless of validity of their metadata. Under normal circumstances, only a small number of storage objects are invalid at any given time, as the system generally takes steps to repair the invalid objects in the normal course of operation. Thus, the number of invalid objects tends to be small, barring some catastrophic system failure. Only a small amount of expensive privileged persistent storage is therefore needed. A health level may also be used to indicate many failures, indicative of catastrophic system failure.