Server rental store

AI in Eastbourne

AI in Eastbourne: Server Configuration Documentation

This document details the server configuration for the "AI in Eastbourne" project, providing a technical overview for new administrators and contributors. This project focuses on running several machine learning models for local environmental monitoring and predictive analysis. The system is designed for scalability and resilience. This article assumes a basic understanding of Linux server administration and networking.

Overview

The "AI in Eastbourne" project utilizes a distributed server architecture, consisting of three primary server roles: Data Ingestion, Model Training, and Model Serving. These roles are physically separated for security and performance reasons, and are connected via a dedicated internal network. The system runs on Ubuntu Server 22.04 LTS. Access to these servers is strictly controlled via SSH with key-based authentication. The central configuration management system is Ansible, ensuring consistency across all machines. The project also leverages a version control system – Git – for all code and configuration files.

Hardware Specifications

The following tables detail the hardware specifications for each server role.

Server Role Processor Memory (RAM) Storage Network Interface
Data Ingestion Server Intel Xeon Silver 4310 (12 cores) 64 GB DDR4 ECC 4TB NVMe SSD (RAID 1) 10 Gbps Ethernet
Model Training Server 2 x AMD EPYC 7763 (64 cores total) 256 GB DDR4 ECC 8TB NVMe SSD (RAID 0) + 20TB HDD (for backups) 10 Gbps Ethernet + InfiniBand
Model Serving Server Intel Core i7-12700K (12 cores) 32 GB DDR5 2TB NVMe SSD 1 Gbps Ethernet

These specifications are subject to change as the project evolves. All hardware is monitored using Nagios for proactive issue detection.

Software Stack

Each server utilizes a specific software stack tailored to its role. The base operating system is Ubuntu Server 22.04 LTS.

Server Role Operating System Programming Language Machine Learning Framework Database Web Server
Data Ingestion Server Ubuntu Server 22.04 LTS Python 3.10 N/A - Data Processing Only PostgreSQL 14 N/A
Model Training Server Ubuntu Server 22.04 LTS Python 3.10 TensorFlow 2.12, PyTorch 2.0 N/A N/A
Model Serving Server Ubuntu Server 22.04 LTS Python 3.10 TensorFlow 2.12, PyTorch 2.0 Redis 7 Flask

All Python dependencies are managed using pip and virtual environments. The training server utilizes CUDA and cuDNN for GPU acceleration. Database backups are automated using pg_dump.

Network Configuration

The servers are connected via a dedicated VLAN with a /24 subnet. Static IP addresses are assigned to each server. DNS is handled by an internal BIND9 server. Firewall rules are configured using iptables to restrict access to necessary ports only. The network topology is illustrated below.

Server IP Address Role Gateway
ingestion.eastbourne.ai 192.168.1.10 Data Ingestion 192.168.1.1
training.eastbourne.ai 192.168.1.20 Model Training 192.168.1.1
serving.eastbourne.ai 192.168.1.30 Model Serving 192.168.1.1
dns.eastbourne.ai 192.168.1.1 DNS Server N/A

The gateway (192.168.1.1) provides access to the external network, subject to strict firewall rules. VPN access is available for authorized personnel.

Security Considerations

Security is paramount. The following measures are in place:

⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️

View full article | Back to Server rental store