Transport Node Data Consistency in Physical Sharding

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In software defined networking, sharding changes can lead to temporary inconsistencies in network configuration data processing, resulting in traffic flapping due to incomplete data sets during master node reassignments, affecting the scalability and availability of network configurations.

Innovation Solution

A method for consistent processing of transport node network configuration data involves determining a sharding table by a central control plane node, establishing connections with transport nodes, and transmitting network configuration data updates to a shared data store, ensuring all nodes have access to complete and accurate data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If logical sharding is used to distribute processing load across multiple CCP nodes, then scalability and availability of the control plane are improved, but temporary inconsistencies in network configuration data can occur during sharding changes

Engineering Contradiction:

Improveprocessing load distributionVSAvoiddata consistency

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements a preliminary action by having the new logical master node proactively request and receive network configuration data from the old logical master node before fully taking over the master role. This ensures that the new master has complete data before beginning to serve requests, preventing the temporary inconsistencies that would otherwise occur during sharding changes.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent employs feedback mechanisms where the new logical master node continuously monitors and requests updates from the old logical master node during the transition period. This feedback loop ensures that the new master receives all necessary network configuration data, including updates from logical entities, maintaining data consistency throughout the sharding change process.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If sharding changes are implemented to add or remove nodes from the CCP cluster, then system adaptability and scalability are improved, but traffic flapping can occur due to incomplete data sets

Engineering Contradiction:

Improvenode addition/removal capabilityVSAvoidtraffic flapping

Core Design Contradiction:

Adaptability or versatilityVSObject-generated harmful factors

Solution Approach 1:

Before the sharding change is fully completed, the new logical master node performs preliminary actions by requesting and caching all existing network configuration data from the old master. This preliminary data acquisition ensures that when the sharding change occurs, the new master immediately has a complete data set, preventing traffic flapping that would result from incomplete data.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent maintains continuity of useful action by establishing continuous data synchronization between the old and new logical master nodes during the transition. The new master continues to receive updates from the old master until the transition is complete, ensuring uninterrupted and consistent network configuration data availability, thereby eliminating traffic flapping.

Inventive Principle:

Principle #20Continuity of useful action

3Speed

If a new logical entity connects to the new logical master during the transition interval, then system responsiveness is improved, but the new master cannot provide complete network configuration data

Engineering Contradiction:

Improveconnection establishment speedVSAvoidnetwork configuration data

Core Design Contradiction:

SpeedVSLoss of information

Solution Approach 1:

The new logical master node performs preliminary actions by proactively requesting and receiving all network configuration data from the old master before the sharding change is finalized. This ensures that when new logical entities connect during the transition, the new master already has complete data to provide, preventing information loss while maintaining fast connection establishment.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements beforehand cushioning by having the new logical master node pre-load and cache all necessary network configuration data before the sharding transition completes. This cushioning of data ensures that even if new logical entities connect during the transition interval, they immediately receive complete and accurate configuration data, preventing any information loss.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS11212176B2Consistent processing of transport node network data in a physical sharding architecture

Publication Date: 2021.12.28 VMWARE INC

AI summary

Certain embodiments described herein are generally directed to consistent processing of transport node network configuration data in a physical sharding architecture. For example, in some embodiments a first central control plane (CCP) node of a plurality of CCP nodes determines a sharding table, which is shared by the plurality of CCP nodes. In certain embodiments, the first CCP node determines a connection establishment between a first transport node and the first CCP node. In some embodiments, if the first CCP node determines, based on the sharding table, that it is a physical master of the first transport node, the first CCP node receives network configuration data from the first transport node, stores at least a portion of the network configuration data, and transmits a data update comprising at least a portion of the network configuration data to a shared data store accessible by the plurality of CCP nodes.