ADDM Graphs for Data Center Application Provisioning Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods struggle to determine if data center infrastructure is over-provisioned or under-provisioned based on current load for applications and workloads, making it challenging to track components and their inter-dependencies effectively.
Innovation Solution
Implement Application Discovery and Dependency Mapping (ADDM) to identify components as nodes and edges, calculate component resource utilization, determine carbon footprint, and use workload managers to assess over-provisioning or under-provisioning ratios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Application Discovery and Dependency Mapping (ADDM) is implemented to track components and inter-dependencies, then measurement precision of resource utilization is improved, but device complexity increases
Solution Approach 1:
The patent segments the data center infrastructure into discrete components (compute resources, storage resources, networking resources) and maps their dependencies through a graph structure. This segmentation enables precise measurement of resource utilization for each component while maintaining manageable complexity through modular tracking.
Solution Approach 2:
The patent introduces an intermediary measurement system that collects metrics from components and calculates utilization ratios without requiring direct complex interactions between all components. This intermediary layer simplifies the measurement process while maintaining precision.
2Reliability
If infrastructure is provisioned based on specific compute, storage, networking, memory and performance requirements, then reliability is improved, but loss of energy increases
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors component resource utilization and compares it against provisioned infrastructure capacity. This feedback enables dynamic adjustment of infrastructure provisioning to match actual demand, reducing energy consumption while maintaining reliability.
Solution Approach 2:
The patent changes the parameter of infrastructure provisioning from static to dynamic based on measured utilization ratios. By adjusting provisioning levels according to actual workload demands, the system maintains reliability while reducing energy waste from over-provisioning.
3Adaptability or versatility
If multiple users create many applications for various projects over time, then adaptability is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
The patent segments the complex environment into standardized component types (compute, storage, networking) and uses a unified measurement approach for each type. This segmentation makes it easier to detect and measure resources across diverse applications while maintaining adaptability to different workloads.
Solution Approach 2:
The patent creates a universal measurement framework that can track various component types and application configurations through a common graph-based approach. This universal system handles diversity in applications while maintaining consistent measurement capabilities.
Data Source
AI summary
A computerized method for determining a ratio to identify when an application is over-provisioned or under-provisioned in a data center in a data center comprising: performing Application Discovery and Dependency Mapping (ADDM) of one or more individual applications of the data center; with an ADDM output from the ADDM, generating an ADDM graph; determining each component of each individual application of one or more individual applications of the data center, wherein a component comprises a hardware component or a software component of each individual application; implementing a components mapping of each component of each individual application into the ADDM graph, wherein, with the ADDM graph, a plurality of components are represented as nodes and the connectivity between the nodes represented as edges, wherein based on a knowledge of the data-center environment, wherein each component is identified to correspond to each hardware component or each software component; implementing a workload in the data center, wherein the workload comprises a set of one or more tasks which are performed over a time period towards a specific goal; implementing a workload manager, wherein the workload manager executes the set of tasks in the workload, wherein a path of execution of the set of tasks is defined as the workflow; with the ADDM, ADDM graph and Component Resource Utilization, for the application: calculating a cost of each workload of the application; calculating a cost of running the application in the data center based on the cost of each workload of the application; and determining a ratio to identify when the application is over-provisioned or under-provisioned in the data center.