BFD Protocol for Hypervisor Control Information Delivery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Centralized exchange of control information in software-defined networking (SDN) data centers via a central server can lead to delays, causing issues such as dropped packets during VM migration, as hypervisors rely on reliable protocols like TCP which may introduce unnecessary overhead.

Innovation Solution

The method employs the Bidirectional Forwarding Detection (BFD) protocol to transmit control information directly between hypervisors, utilizing BFD packets with an ECHO flag for acknowledgment and incorporating control messages within the payload, reducing network bandwidth and compute cycles.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If centralized exchange of control information via a central server is used, then control information can be relayed between hypervisors, but delays occur in receiving control information particularly when the central server is busy

Engineering Contradiction:
Improvecontrol information deliveryVSAvoidcontrol information receipt delay
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts the control information exchange function from the centralized server model and implements it directly between hypervisors using BFD packets. This removes the central server as an intermediate bottleneck, allowing hypervisors to exchange control information peer-to-peer, thereby eliminating the delays caused by server busy states while maintaining reliable delivery through BFD's built-in acknowledgment mechanisms.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces BFD packets as a new intermediary mechanism for control information exchange. Instead of using traditional TCP-based protocols that rely on centralized servers, the BFD protocol serves as a lightweight intermediary that enables direct, efficient communication between hypervisors with built-in flow control and acknowledgment features, resolving the delay issue while preserving reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If TCP protocol is used for reliable data transmission, then control information can be delivered reliably, but network bandwidth and compute cycles are consumed due to protocol overhead

Engineering Contradiction:
Improvedata transmission reliabilityVSAvoidnetwork bandwidth and compute cycles
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The patent employs BFD packets as lightweight, disposable communication units that carry control information. These packets are simpler and less resource-intensive than traditional TCP packets, providing sufficient reliability for control information without the heavy overhead of full TCP protocol processing. The BFD protocol's streamlined design consumes fewer network bandwidth and compute cycles while maintaining adequate delivery reliability for hypervisor control messages.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Data Source

PatentUS10637781B2Method for reliable data delivery between tunnel endpoints using BFD protocol
Publication Date: 2020.04.28 VMWARE INC
  • US10637781B2 patent drawing
  • US10637781B2 patent drawing
  • US10637781B2 patent drawing

AI summary

The disclosure provides an approach for reliable and secure data delivery on a data plane of a network between virtual tunnel endpoints of hypervisors. The approach involves using the Bidirectional Forwarding Detection protocol to transport additional information without adding to network congestion. Data is added to periodic health-check packets and processed by the receiving side. The packets are further modified to set an echo bit and receive an acknowledgement of the packets' successful transmission to the destination side.