Native Application Service Maps Without Manual Instrumentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to generate service maps for bare metal workloads (native applications) running directly on physical computing devices without virtual machines or containers, making it difficult to identify performance issues and dependencies, particularly in complex network applications.
Innovation Solution
A system and method to generate service maps by associating applications with connections using process and connection information collected from compute nodes, determining server and client applications, and generating a service map with edges and nodes to represent these relationships, without requiring manual user input or instrumentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If service maps are generated for bare metal workloads without virtualization, then visibility into native application relationships is improved, but system complexity increases due to lack of automated instrumentation
Solution Approach 1:
The system automatically generates service maps by collecting process and connection information from compute nodes without requiring manual user input or instrumentation. The processing circuitry autonomously associates applications with connections, determines server/client roles, and generates service maps, enabling the system to self-monitor and self-document application relationships.
Solution Approach 2:
The patent introduces an intermediary processing system that collects data from compute nodes and generates service maps. This intermediary layer (processing circuitry and storage device) mediates between the compute nodes and the user, automatically translating raw process and connection information into visual service map representations without requiring direct user interaction with complex system data.
2Measurement precision
If manual instrumentation is required for service map generation, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The system performs self-service by automatically collecting process information and connection information from compute nodes, processing this data to identify applications and their relationships, and generating service maps without requiring any manual user input. This eliminates the need for users to manually instrument or configure monitoring while maintaining accurate service map generation.
Solution Approach 2:
The system performs preliminary data collection and processing actions automatically. Process and connection information is collected from compute nodes in advance, and the processing circuitry pre-processes this information to associate applications with connections and determine server/client roles before service map generation is requested, eliminating the need for manual preparation.
3Reliability
If comprehensive application monitoring is implemented, then reliability of performance troubleshooting is improved, but device complexity increases
Solution Approach 1:
The monitoring system is segmented into distinct functional components: compute nodes that collect process and connection information, processing circuitry that associates applications with connections and determines relationships, and a storage device that stores the collected data. This segmentation allows each component to perform its specific function independently, improving reliability while managing complexity through modular design.
Solution Approach 2:
The processing circuitry performs multiple functions: collecting process information, collecting connection information, associating applications with connections, determining server/client roles, and generating service maps. This multi-functionality consolidates what would otherwise require separate systems into a single unified processing unit, improving troubleshooting reliability without proportionally increasing overall system complexity.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
A system includes a storage device including process information and connection information collected by one or more host modules at a plurality of compute nodes and processing circuitry in communication with the storage device. The processing circuitry is configured to associate, with each connection of one or more connections identified in the connection information, one or more applications, wherein each of the one or more applications is an application of a plurality of applications identified in the process information, determine whether each of the one or more applications is a server application or a client application based on the one or more connections, generate a service map comprising an edge representing each connection of the one or more connections and a node representing each server application and each client application of the one or more applications, and output an indication of the service map.