File System Queue Recovery via Extended Attribute Metadata
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Clustered file systems face challenges in efficiently recovering from queue failure events, particularly in cloud-based storage sites where unreliable inode numbers hinder effective replication and recovery of pending operations, leading to time-consuming and resource-intensive processes.
Innovation Solution
The method involves using a modified extended attribute of a file to store and manage information about operations performed on files across cluster sites, enabling efficient recovery by storing predetermined information on extended attributes and performing recovery processes to fulfill queue entries without relying on extensive dirty directory comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional recovery methods using inode number comparisons are used, then recovery can be performed, but processing time and resource consumption increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-storing operation information (such as object names, types, and metadata) in extended attributes of files before operations are completed or during normal operation. This advance preparation ensures that when a queue failure occurs, the recovery process can immediately access this pre-stored information without needing to perform time-consuming inode number comparisons or scan through operation logs, thereby significantly reducing recovery time while maintaining reliable recovery capability.
2Reliability
If extensive dirty directory comparisons are performed for recovery, then all pending operations can be identified, but processing resources and time increase
Solution Approach 1:
The patent extracts the essential operation information from the complex dirty directory comparison process by storing it directly in extended attributes of files. Instead of extracting information during the time-consuming process of comparing dirty directories and parsing operation logs, the critical operation details are already extracted and stored in a compact, easily accessible format in the file metadata, enabling fast and efficient recovery without requiring extensive comparisons.
Solution Approach 2:
The extended attribute serves as an intermediary structure that bridges the gap between file system operations and recovery processes. It stores operation information in a standardized format that can be quickly read and processed during recovery, eliminating the need for complex intermediary steps like dirty directory comparisons and operation log parsing, thereby significantly improving recovery efficiency while maintaining completeness.
3Adaptability or versatility
If unreliable inode numbers are used in cloud-based storage, then storage flexibility is improved, but replication and recovery effectiveness deteriorate
Solution Approach 1:
The patent uses copying by creating a copy of the operation information storage mechanism that is independent of inode numbers. Instead of relying on inode numbers for tracking operations (which are unreliable in cloud storage), the system copies operation details into extended attributes, providing a redundant and reliable record that works regardless of inode number stability or availability, thus maintaining replication reliability while preserving storage flexibility.
Data Source
AI summary
A computer-implemented method according to one embodiment includes, in response to a determination that a predetermined operation has been performed on an object of a first file stored on a first cluster site, storing predetermined information about the object of the first file stored on the first cluster site. The predetermined information is stored on an extended attribute of the first file stored on the first cluster site. In response to a determination that the predetermined operation is performed on an object of a first file stored on a second cluster site, the predetermined information is removed from the extended attribute of the first file stored on the first cluster site. In response to a determination that a failure event has occurred on a queue of the first cluster site, a predetermined recovery process is performed, thereby enabling fulfillment of entries of the queue of the first cluster site.