Data Center Disk Array Configuration via Workload Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data center management systems face challenges in optimally configuring disk arrays, often leading to overprovisioning or underprovisioning of resources based on average usage, failing to map application workloads to appropriate physical drives, and not providing differentiated storage types with suitable infrastructure warranties.
Innovation Solution
A data-driven approach is employed for configuring data center disk arrays using a monitoring and management console, which includes a warranty optimization operation to generate a disk array configuration with the lowest-warranty drives that meet customer needs, utilizing solid-state drive (SSD) storage with varying warranty grades based on Drive Writes Per Day (DWPD) or Terabytes Written (TBW) metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If disk arrays are configured based on average usage, then resource allocation is simplified, but overprovisioning or underprovisioning occurs
Solution Approach 1:
The system performs preliminary analysis of application workload characteristics and historical usage patterns before configuring disk arrays. By pre-characterizing workloads and predicting future usage based on identified patterns, the system can provision resources accurately without relying on simple average usage metrics, thus avoiding overprovisioning or underprovisioning while maintaining operational simplicity.
2Manufacturing precision
If differentiated storage types with varying warranties are implemented, then resource allocation precision is improved, but system complexity increases
Solution Approach 1:
The system changes parameters by characterizing application workloads based on multiple dimensions including I/O patterns, data access frequencies, and performance requirements. These parameter changes enable precise matching of storage types and warranty levels to specific workload characteristics, achieving high allocation precision while the automated analysis framework manages the complexity of differentiated storage configurations.
3Loss of energy
If lowest-warranty drives are selected to meet customer needs, then operational costs are reduced, but storage reliability may be compromised
Solution Approach 1:
The system applies local quality by matching different warranty levels to specific storage locations and workload types. Critical workloads requiring high reliability are assigned to drives with higher warranty levels, while less critical workloads use lower-warranty drives. This localized quality differentiation optimizes operational costs by avoiding unnecessary high-warranty drives for non-critical applications while maintaining adequate reliability where needed.
Data Source
AI summary
A system, method, and computer-readable medium for performing a data center management and monitoring operation. The data center management and monitoring operation includes: receiving data center asset customer information from a data center customer; identifying a plurality of data center asset features from the data center asset customer information; applying a configuration model to the plurality of data center asset features, the configuration model generating a data center asset part distribution; and, generating a data center asset part configuration using the configuration model.