Active-Active Mapped Logical Volumes for Storage Processor Redundancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage arrays manage logical volumes in an active-passive manner, leading to degraded performance due to redirection of I/O requests between storage processors, which increases latency and reduces throughput.
Innovation Solution
Implementing active-active mapped logical volumes, where multiple storage processors can handle I/O requests simultaneously, allowing I/O requests to be sent to the owning storage processor based on the portion of the volume accessed, thereby eliminating redirection and optimizing performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If active-passive mapping is used, then storage processor redundancy is achieved, but I/O performance degrades due to request redirection
Solution Approach 1:
The logical volume is segmented into multiple portions, each mapped to a specific storage processor. This segmentation allows I/O requests to be distributed across multiple storage processors simultaneously, eliminating the need for request redirection and enabling parallel processing, thus improving both reliability and throughput
Solution Approach 2:
The mapping configuration is made dynamic by allowing the system to adaptively route I/O requests based on the segmented mapping information. This dynamic routing enables the system to maintain redundancy while optimizing performance by directing requests to the appropriate storage processor without redirection overhead
2Productivity
If active-active mapping is implemented, then I/O performance improves, but mapping complexity increases
Solution Approach 1:
A mapping configuration structure acts as an intermediary between the logical volume and physical storage resources. This intermediary maintains the segmentation mapping information and provides a standardized interface for routing I/O requests, simplifying the management of active-active mappings while enabling improved I/O performance through structured request distribution
3Reliability
If I/O requests are redirected between storage processors, then failover capability is maintained, but latency increases
Solution Approach 1:
The system performs preliminary action by pre-establishing the mapping between logical volume portions and specific storage processors. This pre-configuration eliminates the need for real-time redirection decisions during I/O operations, allowing requests to be directly routed to the appropriate storage processor from the outset, thus maintaining failover capability while minimizing latency
Data Source
AI summary
A method is used in managing accesses to active-active mapped logical volumes. A portion of a mapped logical volume associated with an I/O request is determined. Based on the determination, a set of storage processor paths for accessing the mapped logical volume is determined. The I/O request is sent using a storage processor path from the set of storage processor paths for accessing the mapped logical volume.


