Synchronous Discovery Logs in Fabric Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Centralized discovery controllers in distributed storage systems are difficult to maintain and prone to interruption, leading to burdens on host systems to identify and query multiple controllers for storage system configuration changes.
Innovation Solution
Implementing a distributed synchronous discovery log system across storage subsystems, where each fabric node communicates with peer nodes using a network fabric protocol to update and share discovery logs, enabling host systems to easily identify fabric storage resources without relying on a single centralized controller.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a centralized discovery controller is used to manage storage subsystem identification, then host systems can query a single controller for configuration changes, but the system becomes difficult to maintain and prone to interruption
Solution Approach 1:
The patent divides the centralized discovery controller functionality into multiple distributed fabric nodes, each maintaining its own discovery log. This segmentation eliminates the single point of failure while preserving the ease of querying through local availability of discovery information at each node.
Solution Approach 2:
The patent creates copies of the discovery log across multiple fabric nodes through synchronous updates. Each node maintains an identical copy of the discovery log, ensuring that host systems can query any node for current configuration information without relying on a single centralized controller.
2Reliability
If multiple discovery controllers are distributed across the storage system, then reliability improves, but host systems must identify and query multiple controllers increasing complexity
Solution Approach 1:
The patent makes all fabric nodes universal by enabling each node to function as both a storage resource and a discovery information source. Any fabric node can respond to host discovery requests, eliminating the need for hosts to identify specific controller roles and simplifying the query process while maintaining distributed reliability.
3Stability of the object's composition
If discovery logs are updated synchronously across all fabric nodes, then consistency is maintained, but communication overhead increases
Solution Approach 1:
The patent implements a feedback mechanism where fabric nodes acknowledge receipt of discovery log updates. The managing fabric node receives acknowledgments from all nodes to confirm successful propagation, ensuring consistency while providing a controlled communication pattern that minimizes unnecessary traffic compared to continuous broadcasting.
Data Source
AI summary
Systems and methods for distributed storage systems using synchronous discovery logs for fabric subsystem discovery. Storage nodes may be configured with fabric services and a management service may provide synchronization of discovery logs across fabric subsystems and between peer fabric nodes. The peer fabric nodes may communicate with one another using a fabric network protocol and corresponding fabric subsystems may communicate with each peer fabric node. When a target subsystem fabric node updates its discovery log, the updated discovery log is sent to the corresponding peer fabric node. The corresponding peer fabric node sends the updated discovery log to each subsystem fabric node and to each peer fabric node for synchronization across all subsystem fabric nodes. A host may contact any subsystem fabric node for the updated discovery log.