Simulate networks with NVIDIA Air: Worked Example — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)

Simulating Networks with NVIDIA Air: A Worked Example

NVIDIA Air is a powerful network simulation tool integral to the NVIDIA Spectrum Networking domain, accounting for 30% of the NVIDIA-Certified Professional: AI Networking exam. It enables professionals to model, test, and validate complex network topologies and configurations before deployment, reducing risk and optimizing performance.

Scenario Overview

Imagine you are tasked with simulating a multi-tenant data center network that leverages BGP-EVPN for tenant isolation and RoCE for high-speed, low-latency communication. The goal is to validate Quality of Service (QoS) policies and priority flow control settings under realistic traffic conditions.

Step 1: Define Network Topology

Using NVIDIA Air's graphical interface or configuration files, start by defining the physical and logical topology:

• Create multiple leaf and spine switches representing the Spectrum switches.
• Define tenant segments using BGP-EVPN overlays.
• Assign RoCE-enabled endpoints to simulate RDMA traffic.

Step 2: Configure Network Protocols

Next, configure the protocols to be simulated:

• Enable BGP sessions between spine and leaf switches to establish EVPN routes.
• Configure RoCE parameters on endpoints to simulate RDMA traffic flows.
• Set up QoS policies, including bandwidth allocation and priority queues.
• Enable Explicit Congestion Notification (ECN) and Priority Flow Control (PFC) to manage congestion and lossless Ethernet behavior.

Step 3: Define Traffic Profiles

Specify traffic characteristics to emulate realistic workloads:

• Generate RDMA traffic with varying packet sizes and rates to test RoCE performance.
• Include background traffic to simulate multi-tenant environment load.
• Apply traffic classes aligned with QoS policies to observe prioritization effects.

Step 4: Run Simulation and Monitor Metrics

Start the simulation and use NVIDIA Air’s monitoring tools to observe:

• Latency and throughput metrics on RoCE flows.
• Queue occupancy and drop rates to verify QoS and PFC effectiveness.
• ECN marking behavior during congestion events.

Step 5: Analyze Results and Adjust Configuration

Interpret the simulation data to identify bottlenecks or misconfigurations:

• If latency spikes occur, verify RoCE and PFC settings.
• Adjust QoS bandwidth allocations if priority traffic is starved.
• Modify BGP-EVPN configurations if tenant isolation is compromised.

Step 6: Iterate and Validate

Repeat the simulation with adjusted parameters until the network meets performance and isolation requirements. Document configurations and simulation outcomes for deployment reference.

Worked Example Summary

Problem: Validate a multi-tenant AI data center network using NVIDIA Air to simulate RoCE traffic with QoS and BGP-EVPN overlays.

Solution:

1. Defined leaf-spine topology with BGP-EVPN tenant overlays.
2. Configured RoCE endpoints and enabled ECN, PFC, and QoS policies.
3. Generated mixed traffic profiles representing tenant workloads.
4. Monitored latency, throughput, and congestion indicators.
5. Analyzed results and tuned configurations to optimize performance.

This step-by-step simulation approach ensures robust network design aligned with NVIDIA Spectrum Networking best practices, preparing candidates for the NVIDIA-Certified Professional: AI Networking exam.

More in this topic

NVIDIA Spectrum Networking — NVIDIA-Certified Professional: AI NetworkingEnable and verify QoS, ECN, and priority flow control: Practice Questions — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Simulate networks with NVIDIA Air: Common Mistakes — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Simulate networks with NVIDIA Air: Practice Questions — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Enable and verify QoS, ECN, and priority flow control — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Simulate networks with NVIDIA Air — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Configure RoCE for high-speed, low-latency communication — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Diagnose with in-band telemetry and WJH: Worked Example — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Simulate networks with NVIDIA Air: Quick Reference — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Monitor in real time with NetQ — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Diagnose with in-band telemetry and WJH: Common Mistakes — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Enable and verify QoS, ECN, and priority flow control: Common Mistakes — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Diagnose with in-band telemetry and WJH — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Diagnose with in-band telemetry and WJH: Practice Questions — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Set up multi-tenancy with BGP-EVPN — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Enable and verify QoS, ECN, and priority flow control: Worked Example — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Install NVIDIA DOCA and configure SuperNIC functionality — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Enable and verify QoS, ECN, and priority flow control: Quick Reference — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)Diagnose with in-band telemetry and WJH: Quick Reference — NVIDIA Spectrum Networking (NVIDIA-Certified Professional: AI Networking)