Virtual Server Cluster Message Broadcast Protocol Handling Configuration Changes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional message broadcast protocols in non-virtualized server clusters fail to handle dynamic configuration changes in virtualized environments, leading to temporary unresponsiveness and potential misinterpretation of node failure, causing slowdowns and incorrect assumptions about node membership.

Innovation Solution

A message broadcast protocol for virtual server clusters that allows nodes to register for notifications of configuration changes, transmit temporary inactive states, adjust heartbeat timeouts, and initiate multi-phase commit protocols to ensure seamless operation during dynamic changes, such as virtual machine migration or resource reconfiguration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional message broadcast protocols are used in virtualized server clusters, then the cluster can operate with standard communication mechanisms, but the system fails to handle dynamic configuration changes, causing nodes to become temporarily unresponsive and other nodes to mistakenly assume node failure

Engineering Contradiction:

Improveability to handle dynamic configuration changesVSAvoidcorrect interpretation of node status

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by having nodes register for configuration change notifications in advance. When a configuration change is detected, the affected node proactively sends a notification message to the cluster before becoming unresponsive, allowing other nodes to adjust their behavior and avoid mistakenly interpreting the temporary unresponsiveness as node failure.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where nodes continuously monitor for configuration change notifications and adjust their message broadcasting and response handling accordingly. This feedback loop enables the cluster to adapt to dynamic changes while maintaining reliable operation and correct node status interpretation.

Inventive Principle:

Principle #23Feedback

2Productivity

If virtualization technology is used to enable dynamic configuration changes and resource consolidation, then hardware utilization improves and cost savings are achieved, but nodes become temporarily unable to receive and respond to broadcast messages during configuration changes

Engineering Contradiction:

Improvehardware utilization efficiencyVSAvoidmessage response delay

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system sends notification messages proactively before the node becomes unresponsive during configuration changes. This preliminary action allows other nodes to adjust their timeout thresholds and message handling behavior in advance, minimizing the effective impact time of the unresponsiveness and reducing overall message response delays in the cluster.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts message timeout thresholds and response expectations based on the detected configuration change state. When a node notifies the cluster of an upcoming configuration change, other nodes dynamically modify their timing parameters to accommodate the temporary unresponsiveness, thereby reducing unnecessary delays while maintaining reliable communication.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If nodes wait for unresponsive nodes to respond to broadcast messages during configuration changes, then message accuracy is maintained, but operation slowdown occurs in the cluster

Engineering Contradiction:

Improvemessage response accuracyVSAvoidcluster operation speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

By receiving advance notification of configuration changes, nodes can preliminarily adjust their message handling behavior. Instead of waiting for potentially unresponsive nodes, the system can proceed with operations using adjusted timing thresholds, maintaining sufficient message accuracy while avoiding unnecessary operation slowdowns.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes operational parameters such as message timeout thresholds and response expectations based on the configuration change state. This parameter adjustment allows the cluster to maintain adequate message accuracy while improving operation speed during dynamic reconfiguration periods.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8635318B1Message broadcast protocol which handles configuration changes in a cluster of virtual servers

Publication Date: 2014.01.21 ARCTERA US LLC

AI summary

A cluster of virtual servers includes a plurality of physical nodes, where each physical node executes virtualization software which implements a virtualization environment in which one or more virtual server machines execute. The virtualization software executed by each physical node may enable the virtualization environment implemented by the physical node to be dynamically changed. Some types of configuration changes to the virtualization environment may take a significant amount of time to perform, e.g., several seconds or longer. While the configuration change is taking place, the physical node may be unable to respond to messages sent by other physical nodes in the cluster of virtual servers. The nodes may execute message broadcast software which implements a message broadcast protocol which takes into account the dynamic configuration changes to the virtualization environments of the nodes in the cluster of virtual servers so that these periods of unresponsiveness can be handled gracefully.