Counter-Based Storage Node Locking Mechanism
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dual storage node systems face challenges in providing a safe and reliable locking mechanism to avoid operation conflicts, particularly when both nodes access the same storage area simultaneously, leading to inefficiencies and potential data loss due to the need for extensive communication and resource usage in acquiring stripe locks.
Innovation Solution
The system employs counters at each storage node to track historical access frequencies and allocates a lock flag to the node with higher access frequency, allowing it to lock the storage area, thereby reducing resource requirements and improving stripe lock efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a locking mechanism is implemented to avoid operation conflicts between two storage control nodes, then data reliability is improved, but device complexity and resource consumption increase due to extensive communication and queue management requirements
Solution Approach 1:
The patent extracts the complex queue management and communication overhead from the locking mechanism by using a counter-based approach. Instead of implementing full queue structures and extensive inter-node communication, the system uses simple counters at each storage node to track access frequencies, significantly reducing device complexity while maintaining data reliability through the lock flag mechanism
Solution Approach 2:
The patent changes the parameter representation from complex queue structures to simple numerical counters. By tracking access frequency as a numerical parameter rather than maintaining ordered queues, the system reduces computational complexity and resource consumption while still enabling effective lock allocation decisions between storage nodes
2Measurement precision
If traditional queue-based locking mechanisms are used to allocate locks between storage nodes, then lock allocation accuracy is improved, but storage resource consumption increases due to the need for maintaining queues and extensive communication
Solution Approach 1:
The patent replaces expensive, long-lived queue structures with cheap, simple counters that require minimal storage resources. The counters are easily incremented and compared, providing sufficient information for lock allocation without the overhead of maintaining complex queue data structures, thus reducing storage resource consumption while preserving allocation accuracy
Solution Approach 2:
Instead of using queues to track detailed access sequences and timestamps, the patent inverts the approach by using counters to track only the essential frequency information. This inversion simplifies the data structure from complex ordered sequences to simple numerical values, reducing storage requirements while maintaining the ability to make accurate lock allocation decisions
3Productivity
If stripe lock reduction efficiency is improved by using access frequency statistics, then processing speed is improved, but storage resource usage increases due to the need for maintaining access statistics
Solution Approach 1:
The patent changes the statistics representation from detailed access records to simplified counters. By using numerical counters that are easily incremented and compared, the system maintains accurate access frequency information for efficient lock allocation while minimizing storage resource usage, achieving high productivity without significant resource overhead
Data Source
AI summary
Techniques lock a storage area in a storage system including a first storage node and a second storage node. Such techniques involve adjusting a value of at least one of a first counter at the first node and a second counter at the second node in response to receiving a data access request for the storage area at at least one of the first node and the second node. Such techniques further involve allocating a lock flag to the first node in response to a ratio of the value of the first counter to the value of the second counter being greater than a first threshold, the lock flag indicating that the storage area is locked by the first node. Accordingly, storage resources required by nodes that are accessed more frequently in statistics are effectively reduced, and the efficiency of applying stripe lock reduction are improved.