Custom Server Assembly Using Workload Trend-Based Configuration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers often face inefficiencies and bottlenecks due to mismatched server configurations and support infrastructure, as actual computing demands can differ significantly from anticipated levels, leading to underutilization or overload of resources.
Innovation Solution
A near-real-time custom server system that uses robots to assemble and install servers with tailored configurations based on current demand, selecting slots with matching infrastructure support requirements, allowing for efficient distribution of resources and minimizing waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If server configurations are selected based on anticipated demand, then infrastructure planning is simplified, but actual resource utilization becomes inefficient
Solution Approach 1:
The patent implements dynamic server configuration where servers can be reconfigured in real-time based on actual demand. The system monitors workload patterns and automatically adjusts server specifications (CPU, memory, storage) to match current needs, transforming the static infrastructure planning approach into a dynamic adaptation mechanism that resolves the contradiction between planning simplicity and resource efficiency.
Solution Approach 2:
The system changes physical parameters of server configurations (processing power, memory capacity, storage size) based on monitored demand patterns. By adjusting these parameters dynamically rather than fixing them during initial planning, the system maintains infrastructure simplicity while optimizing resource utilization according to actual workload requirements.
2Loss of time
If support infrastructure is designed based on anticipated demand, then initial deployment is faster, but actual performance may be suboptimal
Solution Approach 1:
The patent applies preliminary action by pre-establishing a flexible infrastructure framework that can quickly deploy servers, while simultaneously implementing continuous monitoring and automated reconfiguration capabilities. This allows rapid initial deployment followed by automatic performance optimization as demand patterns emerge, resolving the contradiction between deployment speed and performance optimization.
Solution Approach 2:
The system implements feedback loops that continuously monitor actual server performance and workload demands, then automatically adjust infrastructure configuration in response. This feedback mechanism ensures that while rapid deployment is achieved initially, the system continuously optimizes performance based on actual operating conditions, resolving the contradiction between deployment time and performance reliability.
3Manufacturing precision
If profiling techniques are used to determine applications, then server configuration accuracy improves, but customer privacy and security are compromised
Solution Approach 1:
The patent introduces an intermediary layer that analyzes workload characteristics and resource consumption patterns without directly accessing or exposing customer application data. This intermediary monitoring system captures performance metrics and usage patterns needed for accurate server configuration while maintaining a barrier that protects customer privacy and security, resolving the contradiction between configuration accuracy and privacy protection.
Solution Approach 2:
Instead of directly accessing customer applications for profiling, the system creates indirect copies or representations of workload patterns through anonymized performance metrics and resource usage data. This copying approach allows accurate configuration decisions to be made based on workload characteristics while the original sensitive customer data remains protected and never directly exposed to the configuration system.
Data Source
AI summary
A server assembly service determines configurations for custom assembled servers based on time-series utilization metadata for servers executing workloads similar to workloads that are to be executed on the custom assembled servers. The server assembly service determines trends in the time-series utilization metadata and compares the identified trends to associations between workload utilization trends and application classes to determine one or more application classes for applications executing the workloads. The service uses the determined application classes to select server configurations for custom servers that are to be assembled to execute workloads similar to the workloads related to the server utilization metadata. In some embodiments, the service selects custom server configurations without access to applications or application data for workloads of concern. For example, the service may select custom server configurations without using profiling techniques that may intrude on customer privacy by requiring access to underlying applications or application data.