Heterogeneous Server Cluster Capacity Planning for Streaming Media
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Streaming media service providers face challenges in evaluating the capacity of media server configurations to support expected workloads, particularly in determining the optimal mix of heterogeneous servers that can maintain service quality during peak demands and handle node failures, while also considering cost-effectiveness.
Innovation Solution
A capacity planning tool that evaluates the capacity of heterogeneous server clusters by receiving workload information and service parameters, determining the number of servers needed for each configuration type, and optimizing server configurations to ensure compliance with performance and cost constraints using interval analysis and load balancing strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If heterogeneous server clusters are used to support expected workload, then service quality and capacity utilization are improved, but system complexity and evaluation difficulty increase
Solution Approach 1:
The patent transforms the complex heterogeneous server evaluation problem into a standardized parameter-based assessment system. It defines specific performance parameters (CPU utilization, memory usage, I/O operations, network bandwidth) and converts diverse server configurations into comparable metric sets, enabling systematic evaluation while maintaining productivity benefits
Solution Approach 2:
The patent introduces an intermediary evaluation system that acts as a mediator between heterogeneous server configurations and workload requirements. This system standardizes the interface between diverse server types and uniform performance metrics, simplifying the evaluation process while preserving the advantages of heterogeneous clustering
2Reliability
If more servers are added to handle peak demands, then service reliability is improved, but cost and resource utilization efficiency deteriorate
Solution Approach 1:
The patent applies partial action by evaluating and provisioning servers based on actual workload requirements rather than worst-case scenarios. It determines the minimum necessary server capacity needed to meet service level agreements during peak periods, avoiding over-provisioning while maintaining reliability
Solution Approach 2:
The patent introduces dynamic evaluation that adapts server capacity planning to varying workload conditions. It uses performance parameters measured under different load conditions to determine optimal server configurations, enabling the system to maintain reliability during peaks while avoiding unnecessary resource allocation during low-demand periods
3Manufacturing precision
If comprehensive performance evaluation is conducted, then manufacturing precision of capacity planning is improved, but measurement precision requirements and evaluation time increase
Solution Approach 1:
The patent segments the comprehensive performance evaluation into distinct, manageable parameter categories (compute, memory, storage, network). Each parameter is evaluated independently using standardized measurement approaches, which improves overall evaluation precision while reducing the complexity and time required for comprehensive assessment
4Loss of substance
If existing servers are utilized before adding new ones, then loss of substance is reduced, but productivity and service quality may deteriorate
Solution Approach 1:
The patent implements feedback mechanisms that continuously monitor existing server performance parameters and compare them against capacity requirements. This feedback loop identifies when current servers are sufficiently utilized versus when additional capacity is needed, enabling optimized resource allocation that reduces waste while maintaining productivity
Data Source
AI summary
According to at least one embodiment, a method comprises receiving, into a capacity planning system, workload information representing an expected workload of client accesses of streaming media files from a site. The method further comprises receiving, into the capacity planning system, at least one service parameter that defines a desired service characteristic to be provided by a heterogeneous cluster of servers under the expected workload. The capacity planning system evaluates whether the heterogeneous cluster, having a plurality of different server configurations included therein, is capable of supporting the expecting workload in compliance with the at least one service parameter.