Tunnel Endpoint Selection for Bridge Cluster Load Balancing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In data centers, managing multiple tunnel endpoint addresses for forwarding elements is complex, especially when implementing MAC over IP tunnels, as existing solutions lack efficient mechanisms for load balancing and endpoint selection across multiple interfaces or links.
Innovation Solution
A method for encapsulating packets at a source managed forwarding element (MFE) that involves selecting source and destination tunnel endpoints using techniques like hashing of MAC and IP addresses, or assessing current load, and storing mappings to ensure efficient traffic distribution across multiple tunnel endpoints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple tunnel endpoint addresses are assigned to forwarding elements to leverage multiple physical interfaces or links, then network redundancy and load balancing capability are improved, but endpoint selection complexity and mapping management overhead increase
Solution Approach 1:
The patent segments the tunnel endpoint selection process into distinct components: a controller that maintains the mapping table and a forwarding element that performs lookups. This segmentation allows the complex mapping management to be centralized while keeping the forwarding element simple, resolving the contradiction between reliability through multiple endpoints and selection complexity.
Solution Approach 2:
The patent introduces a controller as an intermediary between the network control plane and the forwarding elements. The controller maintains the mapping table and provides endpoint selection information to forwarding elements, acting as a mediator that handles the complexity of managing multiple tunnel endpoints while keeping the forwarding elements simple and reliable.
2Productivity
If multiple tunnel endpoint addresses are assigned to forwarding elements, then traffic distribution capability is improved, but mapping table size and storage requirements increase
Solution Approach 1:
The mapping table is designed to be universal and reusable across multiple forwarding elements. The same mapping table can serve multiple forwarding elements, allowing them to share the burden of storing endpoint mappings. This reduces the total quantity of mapping data required while maintaining traffic distribution capability across the network.
3Productivity
If tunnel endpoints are selected using hashing techniques, then load balancing performance is improved, but packet processing overhead increases
Solution Approach 1:
The patent applies preliminary action by pre-computing hash values and determining endpoint mappings before packets arrive. The controller pre-establishes the mapping between source addresses and tunnel endpoints, and forwarding elements pre-load this information. When packets arrive, the forwarding elements simply perform a quick lookup rather than computing hashes in real-time, significantly reducing packet processing overhead while maintaining load balancing performance.
Data Source
AI summary
Some embodiments provide a method for a first managed forwarding element (MFE). The method receives a packet from a data compute node that connects to the MFE. The packet has a destination address that corresponds to a data compute node in a remote network. The method determines (i) a group of MFEs that form a bridge cluster for sending packets to the remote network and (ii) multiple tunnel endpoints for the group of MFEs, wherein each MFE in the group has at least one of the plurality of tunnel endpoints. The method selects one of the plurality of tunnel endpoints as a destination tunnel endpoint for the packet. The method encapsulates the packet with a source tunnel endpoint associated with the first MFE and the selected destination tunnel endpoint.