Splitting Management Network for Clustered Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing clustered and federated storage systems face challenges in automatic and non-disruptive reconfiguration of management networks due to changes in IP addresses or virtual local area networks, leading to disrupted internal cluster connectivity and manual, error-prone processes, especially in heterogeneous and hyperconverged infrastructure environments.
Innovation Solution
The solution involves splitting the management network into a public management network and an internal intra-cluster management network, using IPv6 unique local addresses to automatically configure the internal network without user input, allowing for cluster-wide network reconfiguration even with failing nodes, and eliminating the need for storage stack component editing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If IP addresses on cluster nodes are changed or moved to a different VLAN, then network flexibility and adaptability are improved, but internal cluster connectivity is disrupted and reconfiguration becomes problematic
Solution Approach 1:
The patent segments the management network into two distinct networks: a public management network for external access and an internal intra-cluster management network for cluster node communication. This segmentation allows the public network to be reconfigured (IP changes, VLAN moves) without affecting the internal cluster connectivity, as the internal network uses stable IPv6 unique local addresses that remain constant during reconfiguration events.
Solution Approach 2:
The internal intra-cluster management network acts as an intermediary layer between cluster nodes, providing a stable communication channel that is independent of the public management network. This intermediary network uses IPv6 ULAs as a stable addressing mechanism, allowing public network changes without disrupting internal cluster operations.
2Adaptability or versatility
If the management network is reconfigured manually with service scripts on each node, then network changes can be implemented, but the process becomes manual and error-prone
Solution Approach 1:
The internal intra-cluster management network is configured to automatically assign IPv6 unique local addresses to cluster nodes without requiring manual intervention or service scripts. This self-service addressing mechanism eliminates the need for administrators to manually reconfigure each node during network changes, reducing errors and simplifying the reconfiguration process.
Solution Approach 2:
The internal intra-cluster management network provides a universal stable addressing foundation that works across all cluster nodes regardless of public network changes. This universal IPv6 ULA-based addressing system serves all cluster communication needs internally, making the system independent of external network configuration variations.
3Device complexity
If a single management network is used for both external access and internal cluster management, then network infrastructure is simplified, but reconfiguration becomes disruptive and complex
Solution Approach 1:
The patent divides the management network infrastructure into two separate networks: public management network for external access and internal intra-cluster management network for cluster operations. This segmentation resolves the contradiction by allowing each network to serve its specific purpose independently, maintaining simplicity in each while ensuring stability in cluster operations during reconfiguration.
4Adaptability or versatility
If the entire cluster is brought down for network reconfiguration, then reconfiguration can be performed, but productivity is reduced and downtime increases
Solution Approach 1:
The patent extracts the internal cluster management traffic from the public management network into a separate internal intra-cluster management network. This extraction allows public network reconfiguration to proceed without affecting internal cluster operations, enabling reconfiguration activities while maintaining cluster availability and productivity.
Solution Approach 2:
The internal intra-cluster management network ensures continuous cluster node communication and coordination during public network reconfiguration events. By maintaining this separate stable communication channel, the cluster can continue its useful actions (data operations, node coordination) without interruption while the public network is being reconfigured.
Data Source
AI summary
A method, computer program product, and computing system for use in a clustered storage system are provided. Embodiments may include providing, using a management network, one or more of external access to the clustered storage system, management of intra-cluster traffic, management of hypervisor traffic, and access to infrastructure services. Embodiments may further include allowing, using a storage network, access to the clustered storage system from within the clustered storage system and one or more external hosts. Embodiments may also include providing a migration network to allow for mobility of one or more virtual machines within clustered storage system. Embodiments may further include splitting the management network into a public management network and an internal intra-cluster management network.