Selective Multipath Packet Spraying for Data Center Resilience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data center networks face significant challenges in detecting path failures and reducing packet loss due to link or node failures, as they rely on slow control plane updates of forwarding tables to adapt to network topology changes.
Innovation Solution
Implementing techniques where source and destination network devices maintain information about path health and connectivity, allowing them to spray packets over healthy paths and avoid failed ones, enabling fast recovery and reduced packet loss without waiting for control plane updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If control plane software updates forwarding tables to address detected failures, then network reliability is improved, but recovery time increases
Solution Approach 1:
The patent pre-establishes multiple forwarding paths and maintains path health information before failures occur. When a failure is detected, the system can immediately switch to pre-planned alternative paths without waiting for control plane updates, thus achieving fast recovery while maintaining reliability
Solution Approach 2:
The data plane devices autonomously detect path failures and make routing decisions based on local path health information without requiring control plane intervention. This self-service mechanism enables immediate local response to failures, reducing recovery time while maintaining network reliability
2Device complexity
If packets are forwarded along a single path through the switching fabric, then device complexity is reduced, but network reliability deteriorates due to significant failure rates
Solution Approach 1:
The patent segments the network into multiple independent forwarding paths between source and destination. By dividing the single path into multiple parallel paths, the system achieves both simplicity (each path uses standard forwarding) and reliability (multiple paths provide redundancy against failures)
3Adaptability or versatility
If forwarding tables are updated to reflect network topology changes, then adaptability is improved, but productivity decreases due to long update times
Solution Approach 1:
The system pre-computes and caches multiple alternative forwarding paths along with their health status before topology changes occur. When failures are detected, the system can immediately activate pre-planned alternative paths without waiting for control plane topology updates, thus maintaining both adaptability and productivity
Solution Approach 2:
Data plane devices autonomously track path health and make adaptive routing decisions without requiring control plane updates. This self-service approach enables immediate adaptation to topology changes while maintaining high data transmission efficiency by avoiding control plane update delays
Data Source
AI summary
Techniques for detecting path failures and reducing packet loss as a result of such failures are described for use within a data center or other environment. For example, a source and/or destination access node may create and/or maintain information about health and/or connectivity for a plurality of ports or paths between the source and destination device and core switches. The source access node may spray packets over a number of paths between the source access node and the destination access node. The source access node may use the information about connectivity for the paths between the source or destination access nodes and the core switches to limit the paths over which packets are sprayed. The source access node may spray packets over paths between the source access node and the destination access node that are identified as healthy, while avoiding paths that have been identified as failed.