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:
- Regular security audits are conducted.
- All servers are kept up-to-date with the latest security patches.
- SSH access is limited to key-based authentication.
- Firewall rules are strictly enforced.
- Data is encrypted both in transit and at rest. We utilize TLS/SSL for all network communication.
- Intrusion detection and prevention systems are deployed using Fail2Ban.
Future Enhancements
Planned enhancements include:
- Implementing a containerization strategy using Docker and Kubernetes.
- Scaling the Model Serving infrastructure using a load balancer.
- Automating the deployment process using a CI/CD pipeline.
- Integrating with a more robust monitoring solution, such as Prometheus and Grafana.
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️