Node Information Exchange Management in All Flash Array Servers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The management of accessing Flash memory in all flash array (AFA) servers is complex, leading to performance degradation due to differences between Flash SSDs and HDDs, necessitating a novel method for node information exchange management to ensure high availability and data protection.
Innovation Solution
A method utilizing a hardware manager module to establish Board Management Controller (BMC) and Non-Transparent Bridge (NTB) paths between nodes for continuous service provision, ensuring high availability by using multiple communications paths and switching to a remaining path in case of malfunction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple communication paths (BMC path and NTB path) are established for node information exchange, then system reliability and high availability are improved, but device complexity increases
Solution Approach 1:
The system dynamically switches between NTB path and BMC path based on real-time communication status. The NTB path is used for normal operations, while the BMC path serves as a dynamic backup that activates automatically when NTB fails, providing adaptive reliability without permanent complexity
Solution Approach 2:
The BMC (Board Management Controller) acts as an intermediary communication path that mediates between the primary NTB path and the nodes. It provides an alternative communication channel that can take over when the primary path fails, resolving the contradiction by adding a mediating component rather than complicating the existing path
2Ease of operation
If hardware manager module is used to control hardware components and establish BMC path, then system control capability is improved, but management complexity increases
Solution Approach 1:
The hardware manager module implements self-service by automatically detecting communication path failures and triggering path switching without manual intervention. The system monitors its own status and autonomously manages the complexity of hardware control, improving ease of operation while containing management complexity through automation
3Speed
If Flash SSDs are used instead of HDDs in AFA server, then performance and speed are improved, but compatibility and control method validity deteriorate
Solution Approach 1:
The system changes the communication parameters and protocols used when switching between NTB path and BMC path. Different communication parameters are applied depending on the path being used, allowing the system to adapt to the specific characteristics of each communication channel while maintaining Flash SSD performance benefits
Data Source
AI summary
A method and apparatus for performing node information exchange management of an all flash array (AFA) server are provided. The method may include: utilizing a hardware manager module among multiple program modules running on any node of multiple nodes of the AFA server to control multiple hardware components in a hardware layer of the any node, for establishing a Board Management Controller (BMC) path between the any node and a remote node among the multiple nodes; utilizing at least two communications paths to exchange respective node information of the any node and the remote node, to control a high availability (HA) architecture of the AFA server according to the respective node information of the any node and the remote node, for continuously providing a service to a user of the AFA server; and in response to malfunction of any communications path, utilizing remaining communications path(s) to exchange the node information.