VM Migration Address Distribution to ToR Switches

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques for providing address information of migrated virtual machines to Top of Rack (ToR) switches are inefficient, leading to disruptions in network communications during live migration, as they often fail to update routing tables with complete context identifiers, especially for IPv6 addresses, resulting in lost communications.

Innovation Solution

The physical server detects virtual machine migration and sends address information to a first physical switch, which shares it with other switches, using protocols like Virtual Station Interface (VSI) Discovery Configuration Protocol or Neighbor Advertisement messages, ensuring all ToR switches receive context identifiers, including IPv6 addresses, to update their routing tables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If existing techniques are used to provide address information of migrated virtual machines to ToR switches, then the system maintains simplicity in address information distribution, but communication reliability deteriorates due to incomplete routing table updates and lost communications during live migration

Engineering Contradiction:
Improvecommunication reliabilityVSAvoidaddress information distribution complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by detecting virtual machine migration events before actual migration completes and proactively notifying ToR switches of upcoming address changes. This advance notification allows switches to prepare routing table updates in advance, preventing communication disruptions during the migration process.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where ToR switches confirm receipt and processing of address information notifications. The physical server receives acknowledgments from switches to verify that routing table updates were successfully applied, ensuring reliable delivery of address information and enabling retransmission if necessary.

Inventive Principle:
Principle #23Feedback

2Loss of information

If existing techniques are used for address information distribution, then the protocol overhead remains low, but information completeness deteriorates as IPv6 addresses and other context identifiers are not properly transmitted

Engineering Contradiction:
Improveaddress information completenessVSAvoidrouting table update time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system merges multiple address information elements (IPv4 addresses, IPv6 addresses, MAC addresses, and other context identifiers) into a single comprehensive notification message. This consolidation ensures that all necessary address information is transmitted together in one operation, preventing information loss and reducing the number of separate update operations required.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system gathers and validates complete address information from the virtualization management server before initiating the notification process. This preliminary information collection ensures that all context identifiers including IPv6 addresses are available and properly formatted before transmission to ToR switches, eliminating the need for multiple follow-up updates.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If existing techniques are used to handle virtual machine migration, then the system maintains simplicity in migration management, but productivity deteriorates due to communication disruptions and failed migrations

Engineering Contradiction:
Improvevirtual machine migration efficiencyVSAvoidmigration management complexity
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The system implements self-service mechanisms where the physical server automatically detects migration events and initiates address information distribution to ToR switches without requiring manual intervention. The virtualization management server automatically provides address information to the physical server, which then autonomously notifies affected switches, enabling seamless live migration operations.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The physical server acts as an intermediary between the virtualization management server and ToR switches during migration events. It receives address information from the virtualization management server, processes the migration detection, and forwards the necessary routing information to the appropriate ToR switches, simplifying the overall migration management process while ensuring reliable information distribution.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS9513970B2Optimizing handling of virtual machine mobility in data center environments
Publication Date: 2016.12.06 CISCO TECHNOLOGY INC
  • US9513970B2 patent drawing
  • US9513970B2 patent drawing
  • US9513970B2 patent drawing

AI summary

Techniques are provided for sending address information of virtual machines to a physical switch. A migration of a virtual machine to a physical server is detected. The physical server obtains address information of the virtual machine, and upon obtaining the address information of the virtual machine, the physical server sends the address information to a first physical switch that is connected to the physical server.