Synchronized Aggregation of Performance and Operating Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for managing web application load in multi-tier architectures are inadequate, as they either focus on local solutions that increase energy consumption and lead to premature hardware obsolescence, or require instrumentation that impacts performance and is rarely implemented in production, failing to provide fine-grained analysis of web application usage.

Innovation Solution

A method for synchronized aggregation of performance and operating data across servers, using synchronized clocks and identifier calculation functions to produce collection files that correlate system resource usage, allowing for insights into incident causes and enabling intervention strategies beyond local scale-out.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If local reinforcement strategies are used to manage server saturation, then the immediate incident is resolved, but energy consumption increases and hardware obsolescence occurs prematurely

Engineering Contradiction:
Improveincident resolutionVSAvoidenergy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent introduces a centralized analysis server as an intermediary that collects, aggregates, and analyzes performance data from multiple servers. This mediator enables global optimization decisions that reduce overall energy consumption while maintaining system reliability, preventing the need for energy-intensive local reinforcement strategies

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements continuous feedback loops where performance data is collected, analyzed, and used to generate actionable insights that prevent future saturation incidents. This proactive feedback mechanism resolves incidents before they occur, eliminating the need for reactive reinforcement that increases energy consumption

Inventive Principle:
Principle #23Feedback

2Measurement precision

If instrumentation is added to analyze web application load, then fine-grained analysis is possible, but application performance is impacted and implementation complexity increases

Engineering Contradiction:
Improveanalysis granularityVSAvoidinstrumentation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the analysis functionality from the application itself and places it on a separate dedicated analysis server. This extraction allows fine-grained measurement of application load without adding instrumentation complexity to the application code, as all analysis is performed externally on collected data

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

A dedicated analysis server acts as an intermediary that handles all complex analysis operations. This mediator receives raw performance data, performs sophisticated analysis to achieve fine-grained measurement precision, and returns simplified insights, thereby isolating measurement complexity from the application

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If multiple servers are deployed to handle load, then system capacity increases, but synchronization and coordination complexity increases

Engineering Contradiction:
Improvesystem capacityVSAvoidsynchronization complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent merges the analysis function into a single centralized server that processes data from all servers in the architecture. This consolidation eliminates the need for complex distributed synchronization protocols, as all analysis occurs at a single point, thereby maintaining high system capacity while reducing synchronization complexity

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The centralized analysis server performs multiple functions including data collection, aggregation, analysis, and insight generation for the entire multi-server system. This universal server handles all analytical tasks across the architecture, simplifying the overall system by replacing complex inter-server coordination with a single multi-functional component

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2950216B1Method and device for synchronised aggregation of performance data and operating data
Publication Date: 2018.10.24 BULL SA
  • EP2950216B1 patent drawingFigure 1
  • EP2950216B1 patent drawingFigure 2

AI summary

A method for the synchronized aggregation of performance and operational data from a production environment, in which trace files are synchronized to ensure consistent trace line dates. Aggregated data is extracted from these synchronized files using two functions: a period calculation function and an aggregation identifier calculation function. Threshold detection and temporal correlations can then be performed, enabling the generation of alarms and associated diagnostic information.