Switch Fabric Application Density Metrics for SAN Bandwidth Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In datacenters, identifying an optimal switch configuration to effectively utilize storage area network (SAN) bandwidth is challenging, leading to inefficient application deployment and network maintenance, particularly due to higher network traffic, redundant I/O accesses, and sluggish processing.
Innovation Solution
Calculating and utilizing metrics such as switch application density, fabric application density, effective switch application density, and effective fabric application density to recommend efficient switch configurations, which involve categorizing switches by speed, assigning port weights, and determining the number of applications' storage access paths through each switch, ultimately suggesting optimal deployment configurations based on these metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If applications are deployed over multiple hosts handling one component each, then application functionality is achieved, but network traffic increases and processing efficiency decreases
Solution Approach 1:
The patent segments the fabric into multiple zones based on switch application density metrics, allowing applications to be deployed across distributed hosts while maintaining efficient communication paths. Each zone is optimized for specific workloads, reducing redundant traffic while preserving deployment flexibility.
Solution Approach 2:
The patent changes the parameter of switch configuration by dynamically adjusting zone memberships and path selections based on calculated density metrics. This optimization reduces network traffic and improves processing efficiency without sacrificing the ability to deploy applications across multiple hosts.
2Productivity
If switch configurations are optimized for SAN bandwidth utilization, then network efficiency improves, but configuration complexity increases
Solution Approach 1:
The patent implements self-service through automated calculation of switch application density metrics and generation of zone configuration recommendations. The system automatically analyzes the fabric topology and application deployment patterns to determine optimal switch configurations, eliminating the need for manual complex configuration while maximizing SAN bandwidth utilization.
3Productivity
If more metrics are calculated for fabric and switch configurations, then deployment optimization improves, but calculation and analysis time increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating switch application density metrics and fabric application density metrics before application deployment. These pre-computed metrics enable rapid determination of optimal zone configurations and switch settings, improving deployment efficiency without incurring significant calculation time delays during the actual deployment process.
Data Source
AI summary
A non-transitory machine-readable storage device includes executable instructions that, when executed, cause one or more processors to calculate an effective application density for switches in fabrics. The processors are further caused to calculate an effective application density for the fabrics using the switch application densities. The processors are further caused to recommend deployment of an application on a first switch in a first fabric if the effective application density of the first switch is below a first threshold and the effective application density of the first fabric is below a second threshold.