Virtualization Underlay Network Probing for Latency Troubleshooting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies lack effective methods for monitoring and improving the performance of virtualization infrastructure underlay networks in cloud data centers, particularly in terms of connectivity and latency issues, which hinders efficient troubleshooting and resource management.
Innovation Solution
The generation of graphical user interfaces that provide real-time or near real-time visual representations of connectivity and communication latencies between workloads in virtualization infrastructure underlay networks, using probes to measure metrics and generate detailed graphical displays that allow for full mesh monitoring and rapid troubleshooting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If distributed probe-based monitoring is implemented across the virtualization infrastructure underlay network, then measurement precision and troubleshooting speed are improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent introduces probe packets as intermediary elements that travel through the network to collect performance data. These probes act as mediators between the monitoring system and the network infrastructure, enabling precise measurement of connectivity and latency without requiring complex modifications to the underlying network devices. The probes carry timing and identification information that allows accurate measurement while keeping the monitoring architecture relatively simple.
Solution Approach 2:
The system implements feedback mechanisms where probe results are collected and analyzed to generate performance metrics. The monitoring system sends probes, receives responses, processes the timing and connectivity data, and feeds back performance information to administrators through visual displays. This closed-loop feedback enables continuous monitoring while maintaining manageable system complexity through automated data collection and analysis.
2Loss of time
If real-time visual representation of network connectivity and latency is provided, then troubleshooting speed is improved, but information processing requirements and system resource consumption increase
Solution Approach 1:
The patent applies partial action by monitoring only the specific network paths and parameters that are relevant to troubleshooting. Rather than continuously monitoring all possible network metrics at full detail, the system selectively probes specific aggregates and connections based on monitoring needs. This approach provides sufficient information for rapid troubleshooting while avoiding the excessive resource consumption of comprehensive real-time monitoring of all network elements.
Solution Approach 2:
The network is segmented into aggregates of virtual machines and physical hosts, with monitoring focused on inter-aggregate connectivity. By dividing the complex network into manageable segments and monitoring connections between these segments rather than every individual connection, the system achieves effective troubleshooting capability while reducing the overall information processing burden and resource consumption.
3Reliability
If comprehensive network performance metrics are collected and displayed, then monitoring capability is improved, but ease of operation and user interface complexity increase
Solution Approach 1:
The patent merges multiple network performance metrics (connectivity status, latency values, packet loss rates) into a unified visual display that shows the health and performance of network aggregates. By combining these separate metrics into an integrated view with standardized visual indicators, the system maintains comprehensive monitoring capability while improving ease of operation through a consistent, easy-to-interpret interface that doesn't require users to separately analyze multiple complex data streams.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A variety of different graphical user interfaces are generated that when displayed provide a visual and interactive representation of one or more performance metrics associated with the operation of a computer network. The graphical user interfaces may be used to monitor the underlay computer network for a virtualization infrastructure, as one example. Aspects include grouping the servers of a computer network into a plurality of aggregates, each aggregate comprising one or more servers. A set of probes are configured that are issued by an agent of a server in one aggregate and sent through the computer network to one or more agents in the server(s) of a different aggregate. Responses and other measurements taken based on the issuance of the probes is gathered and analyzed to generate metrics that are then used to generate, at least in part, the information provided in the graphical user interfaces.