Generic Pruning in Trill Networks via Controller-Managed Identifiers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network communication distribution methods require spine devices to evaluate frame payloads to prune distribution trees efficiently, which is inefficient and not scalable with evolving network attributes, as they need hardware modifications to understand all possible attributes.
Innovation Solution
The method involves leaf devices determining their interested network attributes, sending attribute interest messages to a controller device, which generates and maps identifiers for these attributes, allowing spine devices to prune distribution trees based on these identifiers included in frame headers without evaluating payloads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If spine devices evaluate frame payloads to prune distribution trees, then pruning accuracy is improved, but device complexity and processing overhead increase
Solution Approach 1:
The patent extracts the payload evaluation function from spine devices and relocates it to controller devices. Spine devices only need to match identifiers in frame headers against their pruning tables, while the complex payload analysis is performed by controllers that maintain attribute-identifier mappings. This extraction resolves the contradiction by maintaining pruning accuracy through controller-based payload analysis while reducing spine device complexity.
Solution Approach 2:
The patent introduces identifier mappings as an intermediary mechanism between frame payloads and pruning decisions. Controllers create mappings between network attributes and identifiers, which are then used by spine devices to make pruning decisions based on header identifiers rather than evaluating entire payloads. This intermediary approach maintains accuracy while simplifying spine device operations.
2Adaptability or versatility
If hardware modifications are made to understand all possible network attributes, then adaptability is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a universal identifier system that can represent multiple network attributes through a common mapping mechanism. The controller device maintains a mapping table that associates various network attributes with standardized identifiers, allowing spine devices to handle diverse attributes without hardware modifications. This universal approach resolves the contradiction by providing adaptability through software-based mapping rather than hardware customization.
Solution Approach 2:
The patent uses identifier copies as simplified representations of complex network attributes. Instead of requiring spine devices to understand and process all possible attribute types directly, the system creates identifier copies that represent these attributes and can be matched efficiently in pruning tables. This copying mechanism provides adaptability while keeping spine device hardware simple.
3Manufacturing precision
If frame payloads are evaluated for pruning decisions, then pruning precision is improved, but processing time and energy consumption increase
Solution Approach 1:
The patent performs preliminary action by pre-computing identifier mappings for all network attributes at controller devices before frames arrive at spine devices. The controllers establish attribute-identifier mappings and distribute pruning tables containing these identifiers to spine devices in advance. This preliminary preparation resolves the contradiction by enabling fast header-based matching at spine devices while maintaining pruning precision through the pre-established mappings.
Solution Approach 2:
The patent segments the pruning decision process into two distinct phases: (1) controller devices perform complex payload analysis and create identifier mappings, (2) spine devices perform simple identifier matching in frame headers using pre-populated pruning tables. This segmentation resolves the contradiction by separating the precision-requiring payload analysis from the time-critical forwarding decision, allowing each to be optimized independently.
Data Source
AI summary
Techniques are provided for managing and distributing communications in a network. At a first switch device arranged in a first configuration in a network, a set of one or more network attributes are determined, which are associated with network communications that the first switch device is interested in receiving from other network devices. The first switch device sends to a controller device an attribute interest message that informs the controller device of the set of network attributes. The first switch device receives a mapping of the network attributes in to one or more identifiers. The identifiers are included in a header of subsequent frames sent in the network. An identifier interest message is then sent to a second switch device arranged in a second network configuration in the network to inform the second switch device of identifiers of the network attributes of which the first device has an interest.