Skip to content

chore(docs): provide clear guidance on DPU configuration for site-controller nodes#3048

Open
spydaNVIDIA wants to merge 1 commit into
NVIDIA:mainfrom
spydaNVIDIA:pyda_docs
Open

chore(docs): provide clear guidance on DPU configuration for site-controller nodes#3048
spydaNVIDIA wants to merge 1 commit into
NVIDIA:mainfrom
spydaNVIDIA:pyda_docs

Conversation

@spydaNVIDIA

Copy link
Copy Markdown
Contributor

chore(docs): provide clear guidance on DPU configuration for site-controller nodes

Related issues

#2992

Type of Change

  • Add - New feature or capability
  • Change - Changes in existing functionality
  • Fix - Bug fixes
  • Remove - Removed features or deprecated functionality
  • Internal - Internal changes (refactoring, tests, docs, etc.)

Breaking Changes

  • This PR contains breaking changes

Testing

  • Unit tests added/updated
  • Integration tests added/updated
  • Manual testing performed
  • No testing required (docs, internal refactor, etc.)

Additional Notes

@spydaNVIDIA spydaNVIDIA requested a review from polarweasel as a code owner July 1, 2026 00:18
@coderabbitai

coderabbitai Bot commented Jul 1, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Summary by CodeRabbit

  • Documentation
    • Updated the quick-start guide with stricter BlueField-3 DPU requirements for site controller nodes, including full provisioning before Kubernetes setup.
    • Clarified that configuring site controller nodes without provisioned DPUs is not supported.
    • Refined firmware flashing guidance to the latest supported versions (DOCA 2.9.3 / HBN 2.4.3) and updated the firmware bundle download reference.
    • Updated hardware prerequisites with a detailed checklist, including DPU-mode-only operation and matching 200 Gb requirements with appropriate optics/cabling.

Walkthrough

This change updates the site controller DPU requirements across the quick-start and hardware prerequisite documentation. It now requires fully provisioned BlueField-3 DPUs, DPU mode only, and the listed firmware, optics, connectivity, and download details.

Changes

Site controller DPU requirements docs

Layer / File(s) Summary
Site controller DPU prerequisite updates
docs/getting-started/quick-start.md, docs/getting-started/prerequisites/hardware.md
Requires fully provisioned BlueField-3 DPUs before Kubernetes setup, restricts operating mode to DPU mode only, and updates the firmware, optics, connectivity, and bundle download requirements.

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title accurately summarizes the docs update for site-controller DPU configuration guidance.
Description check ✅ Passed The description is directly related to the documentation changes and matches the PR objective.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands.

@github-actions

github-actions Bot commented Jul 1, 2026

Copy link
Copy Markdown

🔍 Container Scan Summary

No Grype artifacts were found to aggregate.

@github-actions

github-actions Bot commented Jul 1, 2026

Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@docs/getting-started/prerequisites/hardware.md`:
- Line 31: The connectivity example in the hardware prerequisites doc uses curl
with -k, which bypasses TLS verification; update the example in the connectivity
check to use plain curl so it actually validates the trust path. Keep the
guidance aligned with the surrounding prerequisites content and adjust the
example text in the relevant markdown section so it remains realistic and safe
for operators.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 3db2954a-cf23-41db-8c23-3f7f286a687e

📥 Commits

Reviewing files that changed from the base of the PR and between 7eceb31 and c12da10.

📒 Files selected for processing (2)
  • docs/getting-started/prerequisites/hardware.md
  • docs/getting-started/quick-start.md
✅ Files skipped from review due to trivial changes (1)
  • docs/getting-started/quick-start.md

Comment thread docs/getting-started/prerequisites/hardware.md

@polarweasel polarweasel left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Minor stuff, including arguing with Coderabbit 😁

Comment on lines +27 to +29
Today, site-controller nodes must have Bluefield-3 DPUs. Ensure the following requirements are met:
- Verify the correct DPU power cable has been ordered from the server vendor.
- The Bluefield-3's operating mode is DPU mode (not NIC mode). Today, NIC mode is not supported.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Today, site-controller nodes must have Bluefield-3 DPUs. Ensure the following requirements are met:
- Verify the correct DPU power cable has been ordered from the server vendor.
- The Bluefield-3's operating mode is DPU mode (not NIC mode). Today, NIC mode is not supported.
Site-controller nodes must have Bluefield-3 DPUs. Ensure the following requirements are met:
- You have the correct DPU power cable from the server vendor.
- The Bluefield-3's operating mode is DPU mode. NIC mode is not supported.

- The Bluefield-3's operating mode is DPU mode (not NIC mode). Today, NIC mode is not supported.
- For BF3 DPUs, verify link speed and optics: BF3 runs at 200 Gb, so match ports to 200 Gb-capable optics, fiber, or DACs.
- A basic onboard NIC for management is sufficient--no extra ConnectX NICs are needed.
- Verify that the DPU can connect to the outside world (curl -k https://www.google.com)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Use curl -I to get a quick connection report (just the HTTP status code and some headers). Also... why not ping NVIDIA instead of Google?

Suggested change
- Verify that the DPU can connect to the outside world (curl -k https://www.google.com)
- Verify that the DPU can connect to the outside world (curl -I https://www.nvidia.com)

- For BF3 DPUs, verify link speed and optics: BF3 runs at 200 Gb, so match ports to 200 Gb-capable optics, fiber, or DACs.
- A basic onboard NIC for management is sufficient--no extra ConnectX NICs are needed.
- Verify that the DPU can connect to the outside world (curl -k https://www.google.com)
- The DPUs are at the latest supported firmware version: DOCA 2.9.3 and HBN 2.4.3

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you want to include these numbers here and have to maintain them, or include links to their release pages instead?

Comment on lines +40 to +44
- Flash the DPU firmware to the latest supported version using the BlueField Firmware Bundle. Latest supported firmware versions:

| DOCA | HBN |
| ----- | ----- |
| 2.9.3 | 2.4.3 |

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same question as previous file: if you include version numbers, you have to maintain them, vs linking to release pages and letting the reader figure out what they need to do. UNLESS...do we not support the very latest releases?

| ----- | ----- |
| 2.9.3 | 2.4.3 |

- Configure the Bluefield-3 device in DPU mode (operating mode). We do not support having DPUs in NIC mode today.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- Configure the Bluefield-3 device in DPU mode (operating mode). We do not support having DPUs in NIC mode today.
- Configure the Bluefield-3 device in DPU mode (operating mode). We do not currently support NIC mode.


- Configure the Bluefield-3 device in DPU mode (operating mode). We do not support having DPUs in NIC mode today.
- Ensure the DPU ARM OS is booted and reachable via its management interface.
- Verify that the DPU can connect to the outside world (curl -k https://www.google.com)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same as previous file...

Suggested change
- Verify that the DPU can connect to the outside world (curl -k https://www.google.com)
- Verify that the DPU can connect to the outside world (curl -I https://www.nvidia.com)

Comment on lines 50 to +52
Refer to the NVIDIA DOCA documentation and the BlueField Firmware Bundle download archive for firmware flashing instructions and supported firmware versions:

[https://developer.nvidia.com/doca-2-9-2-lts-ovs-doca-download-archive?deployment_platform=BlueField&deployment_package=BF-FW-Bundle](https://developer.nvidia.com/doca-2-9-2-lts-ovs-doca-download-archive?deployment_platform=BlueField&deployment_package=BF-FW-Bundle)
[https://developer.nvidia.com/doca-2-9-3-download-archive?deployment_platform=BlueField&deployment_package=BF-FW-Bundle](https://developer.nvidia.com/doca-2-9-3-download-archive?deployment_platform=BlueField&deployment_package=BF-FW-Bundle)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same question, really. :) Can we just link to the docs and the release page(s) directly, instead of having to increment here every time these get updated?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants