AI in Norfolk
AI in Norfolk: Server Configuration
This article details the server configuration supporting the "AI in Norfolk" initiative. This initiative leverages artificial intelligence to analyze and improve various city services, including traffic flow, public safety, and resource allocation. This document is intended for new system administrators and engineers joining the team. It outlines the hardware, software, and networking components essential for maintaining this critical infrastructure. Please refer to the System Security Protocols for information on security best practices.
Overview
The "AI in Norfolk" project utilizes a distributed server architecture to handle the high volume of data generated by various sensors and systems across the city. The core infrastructure is housed within the Norfolk Data Center, with redundant backup systems located at the Disaster Recovery Site. The system is designed for high availability and scalability, utilizing virtualization and containerization technologies. Understanding the Network Topology is crucial for troubleshooting.
Hardware Specifications
The primary servers are built upon a hyperconverged infrastructure (HCI) model. Below is a breakdown of the hardware components used for the primary AI processing nodes.
| Component | Specification | Quantity |
|---|---|---|
| CPU | Dual Intel Xeon Gold 6338 (32 cores/64 threads per CPU) | 12 |
| RAM | 512GB DDR4 ECC Registered 3200MHz | 12 |
| Storage (Primary) | 4 x 4TB NVMe PCIe Gen4 SSD (RAID 10) | 12 |
| Storage (Secondary) | 8 x 16TB SAS 7.2k RPM HDD (RAID 6) | 4 |
| Network Interface | Dual 100GbE QSFP28 | 12 |
| Power Supply | 2 x 1600W Redundant Power Supplies | 12 |
The secondary servers, used for data ingestion and pre-processing, have slightly lower specifications.
| Component | Specification | Quantity |
|---|---|---|
| CPU | Dual Intel Xeon Silver 4310 (12 cores/24 threads per CPU) | 8 |
| RAM | 256GB DDR4 ECC Registered 3200MHz | 8 |
| Storage (Primary) | 2 x 2TB NVMe PCIe Gen3 SSD (RAID 1) | 8 |
| Storage (Secondary) | 4 x 8TB SAS 7.2k RPM HDD (RAID 5) | 4 |
| Network Interface | Dual 25GbE SFP28 | 8 |
| Power Supply | 2 x 800W Redundant Power Supplies | 8 |
Finally, the database servers require substantial resources.
| Component | Specification | Quantity |
|---|---|---|
| CPU | Dual Intel Xeon Platinum 8380 (40 cores/80 threads per CPU) | 4 |
| RAM | 1TB DDR4 ECC Registered 3200MHz | 4 |
| Storage (Primary) | 8 x 8TB NVMe PCIe Gen4 SSD (RAID 0) | 4 |
| Network Interface | Quad 100GbE QSFP28 | 4 |
| Power Supply | 3 x 1600W Redundant Power Supplies | 4 |
Refer to the Hardware Inventory for a complete list of all server assets.
Software Stack
The software stack is built around a core of open-source technologies.
- Operating System: Ubuntu Server 22.04 LTS. See Operating System Standards for detailed configuration.
- Virtualization: VMware vSphere 7.0. All AI processing nodes run as virtual machines. Consult the VMware Documentation for specific VM configurations.
- Containerization: Docker and Kubernetes. AI models are deployed as containerized applications. Kubernetes Cluster Configuration details the cluster setup.
- Programming Languages: Python 3.9, R, and C++.
- AI Frameworks: TensorFlow, PyTorch, and scikit-learn.
- Database: PostgreSQL 14 with the TimescaleDB extension for time-series data. See Database Administration Guide for details.
- Message Queue: RabbitMQ for asynchronous communication between services.
- Monitoring: Prometheus and Grafana for system monitoring and alerting. Refer to the Monitoring Dashboard Guide for pre-configured dashboards.
- Logging: ELK Stack (Elasticsearch, Logstash, Kibana) for centralized logging.
- Firewall: Palo Alto Networks Next-Generation Firewall.
- Load Balancing: HAProxy for distributing traffic across multiple servers.
- DNS: BIND9 for internal DNS resolution. External DNS is managed by a third-party provider.
- VLANs: * VLAN 10: Management Network * VLAN 20: AI Processing Network * VLAN 30: Data Ingestion Network * VLAN 40: Database Network
- Telegram: @powervps Servers at a discounted price
Networking Configuration
The servers are connected via a dedicated 100Gbps spine-leaf network architecture. Each server has dual network interfaces for redundancy. The network is segmented into multiple VLANs to isolate different services and ensure security. See the Network Segmentation Policy for details.
Understanding the IP Addressing Scheme is vital for efficient network management.
Security Considerations
Security is paramount. All servers are hardened according to the Security Hardening Checklist. Regular vulnerability scans are performed using Nessus. Multi-factor authentication is enforced for all administrative access. All data is encrypted at rest and in transit. Refer to the Incident Response Plan in case of a security breach.
Internal Wiki Home Data Center Documentation System Security Protocols Network Topology Hardware Inventory Operating System Standards VMware Documentation Kubernetes Cluster Configuration Database Administration Guide Monitoring Dashboard Guide Network Segmentation Policy IP Addressing Scheme Security Hardening Checklist Incident Response Plan Disaster Recovery Site AI Model Deployment Guide
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 configurationNeed Assistance?
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️