doca-bare-metal-deployment — Claude Code skill: run DOCA on hardware
doca-bare-metal-deployment is a Claude Code skill for running DOCA applications on an x86 host with a BlueField NIC or on BlueField Arm without containers, and diagnosing launch failures.
Apache-2.0 158 installs ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a claude-codeWhat doca-bare-metal-deployment does
When a DOCA application exits with code 1 immediately after starting, cannot find the device on BlueField, or systemd loops restarting it—this skill covers that ground. It encompasses binding to PCI functions, NUMA nodes, and CPU sets; configuring process isolation via cgroup-v2 and network namespaces; a seven-layer error taxonomy for hardware failures; and the full BlueField lifecycle from BFB installation through post-failure recovery.
The skill handles two deployment paths: x86 host with DOCA installed, communicating with BlueField NIC over PCIe, or BlueField Arm with DOCA on the processor itself. Direct foreground runs, tmux sessions, systemd units, and supervised restarts all start here. Destructive operations like firmware burns or mlxconfig set require explicit confirmation through a separate doca-hardware-safety skill; build, environment setup, and library APIs are handled by other skills.
New to DOCA without hardware. Look at doca-setup instead. Need the container path under kubelet. That is a separate skill. Fleet-scale deployment across many servers lies outside this scope.
What it helps with
- Launch a DOCA application on an x86 host connected to BlueField NIC via PCIe
- Bind a process to the correct PCI function, NUMA node, and CPU set without errors
- Debug an application that crashes immediately on startup or restarts continuously
- Isolate multiple DOCA processes on a single BlueField using cgroup and netns
- Recover a BlueField after BFB installation failure or RShim issues
Example prompts for the agent
- Run a DOCA application in foreground on the host, bound to the first BlueField PCI function
- Set up a systemd unit for a DOCA service with auto-restart and NUMA node 1 affinity
- Diagnose why an application fails with 'no matching device on the BF' on BlueField Arm cores
How to install doca-bare-metal-deployment
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a claude-code2Manually: put the files in place
~/.claude/skills/doca-bare-metal-deployment/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/doca-bare-metal-deployment/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a codex2Manually: put the files in place
.agents/skills/doca-bare-metal-deployment/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a cursor2Manually: put the files in place
.cursor/skills/doca-bare-metal-deployment/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/doca-bare-metal-deployment2Manually: put the files in place
.github/skills/doca-bare-metal-deployment/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/doca-bare-metal-deploymentManually: put the files in place
.devin/skills/doca-bare-metal-deployment/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about doca-bare-metal-deployment
How do I install doca-bare-metal-deployment in Claude Code?
Run npx skills add NVIDIA/skills --skill doca-bare-metal-deployment -a claude-code, then open ~/.claude/skills/doca-bare-metal-deployment/SKILL.md.
What does doca-bare-metal-deployment do?
It teaches how to run DOCA applications directly on hardware without containers: correctly bind processes to devices, diagnose startup failures, configure isolation between processes, and recover BlueField after failures.
What is the difference between running DOCA in a container and on bare-metal?
Bare-metal runs directly on BlueField Arm cores or an x86 host without kubelet or static pods. It requires manual binding to devices, NUMA nodes, and CPUs, but gives you more control over resource allocation and process isolation.
Source text
SKILL.md · Apache-2.0
--- license: Apache-2.0 name: doca-bare-metal-deployment description: > Running a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills. metadata: author: NVIDIA <[email protected]> kind: library doca_version: "3.5" tags: - doca - deployment - bare-metal compatibility: > No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within this skill require a live DOCA install at /opt/mellanox/doca on a host or BlueField with a built DOCA-linked binary. --- # DOCA bare-metal deployment ## Examples - **"The binary exits 1 right after launch."** — this is in scope. Treat it as a launch / device-bind / isolation failure before rewriting application code. - **"systemd keeps restarting my DOCA app."** — a restart loop on hardware is high-stakes. Debug the first exit before enabling Restart=always. ## Instructions Follow Loading order below. Open the tasks companion for launch / supervise / recover, and the capabilities companion for the runtime contract. Do not open every companion file. **Where to start:** This skill is the bundle's home for *operating* a DOCA-linked application binary **directly on hardware** — no container, no kubelet, no static-pod manifest. It is the parallel of `doca-container-deployment/SKILL.md` for the non-container path. If the user has a DOCA-linked binary they built (per the canonical workflow in `doca-programming-guide/SKILL.md`) and they want to know *how to actually run it on the host or on the BlueField Arm cores correctly*, open the tasks companion and start at `## configure`. If the question is *what shape does the bare-metal runtime even have and what is the deployment contract*, start at the capabilities companion. If the user is not yet sure whether their target system shape is the container path or the bare-metal path, route the recognition step to `doca-setup/SKILL.md` first; only return here once *bare-metal* is the confirmed shape. ## Audience This skill serves **external DOCA developers and operators who have a DOCA-linked application binary they built and want to run it directly on hardware** — i.e., people who already have: - a DOCA-linked application binary they built per `doca-programming-guide ## build`, - a real BlueField NIC and a host that talks to it (the **host x86** path — DOCA host install on the host talks to the BlueField NIC over PCIe), OR a BlueField with a console or SSH to the Arm side (the **BlueField Arm bare-metal** path — DOCA installed on the DPU Arm cores; the binary runs there directly), and - a desire to RUN that binary directly on the hardware, not inside a kubelet-standalone-managed container. It is **not** for: - kernel-driver developers contributing to `mlx5_*` or the BlueField OS, - DOCA library contributors (library changes are outside the scope of a bare-metal deployment), - full-Kubernetes-cluster operators managing a fleet of BlueFields (the bundle covers `doca-container-deployment/SKILL.md` for the single-host kubelet-standalone shape; **fleet/production-scale deployment is fleet-orchestration scope** — route to the orchestration entry-point in `doca-public-knowledge-map ## Deploying DOCA services at scale` (DPF / Network Operator / Launch Kit), not hand-rolled static-pod loops), - fresh-laptop-no-hardware users with no DOCA install yet — those belong on `doca-setup ## no-install`. The skill teaches the agent the bare-metal-deployment *procedure* and the rules for quoting documented commands from the public DOCA Programming Guide and the public BlueField / DPU User Manual via `doca-public-knowledge-map/SKILL.md`; it does not invent flag names, PCI BDFs, NUMA numbers, devlink paths, representor strings, or systemd `Restart=` mode names from memory. ## When to load this skill Load this skill when the user is doing **hands-on bare-metal deployment of a DOCA-linked application binary** on either of the two supported host modes (host x86 or BlueField Arm), or asking a cross-cutting bare-metal question that is not specific to one library's API. Concretely: - Launching a DOCA-linked binary for the first time on a host with a BlueField NIC in a PCIe slot, with DOCA installed on the host. - Launching a DOCA-linked binary on the BlueField Arm cores directly (BlueField Arm bare-metal mode), with DOCA installed on the Arm side per the BlueField OS image. - Deciding which launch mode to use (direct foreground for interactive debug; tmux/screen for long-running with manual reattach; systemd-supervised for restart-after-reboot, journald-integrated logs, and Restart= policy). - Binding the DOCA process to the right PCIe function, the right representor, the right NUMA node, and the right CPU set — and pinning IRQs to match — without inventing the addresses or the flag names. - Setting up per-tenant isolation (cgroup-v2 cpu / memory / io controllers, network namespaces for multi-tenant deployments, `numactl` / `taskset` for CPU + NUMA binding) so multiple DOCA processes co-tenant on the same BlueField without crushing each other. - Diagnosing a bare-metal launch that is misbehaving — won't start, starts and exits immediately, runs but can't find the device, attaches to the device but the workload errors, OOMs or is signal-killed, is in a restart loop under a supervisor, or is being interfered with by a co-tenant. - Cross-cutting questions: *"should I run this in tmux or as a systemd unit"*, *"what is the smoke-before-bulk loop for a binary on bare metal"*, *"my binary works in a container on the BlueField but not when I run it directly on the Arm — what changed"*. Do **not** load this skill for the container-path equivalent (those questions go to `doca-container-deployment/SKILL.md`); for full-Kubernetes-cluster operations (out of scope per the bundle's non-goals); for library-API questions (route to the matching `libs/<library>` skill); for env-preparation questions including hugepages, IOMMU, pkg-config, and devlink mode flips (use `doca-setup/SKILL.md`); for any hardware-state-changing operation including `mlxconfig` writes and BFB reflashes (route to `doca-hardware-safety/SKILL.md` for the cross-cutting meta-policy); or for cross-library programming questions (use `doca-programming-guide/SKILL.md`). ## What this skill provides This is a **thin loader**. Substantive material lives in two companion files: - the capabilities companion — the bare-metal deployment runtime contract for a DOCA-linked binary: the two host modes (host x86 vs BlueField Arm bare-metal), the three launch modes (direct, tmux/screen, systemd-supervised), the hardware-resource-binding surface (PF / VF / representor enumeration; NUMA topology discovery; CPU pinning rationale; IRQ affinity rules), the per-tenant isolation surface (cgroup-v2 cpu / memory / io, network namespaces, `numactl` / `taskset`), the restart and recovery semantics (documented `systemd` `Restart=` modes vs crash-and-investigate vs supervisor-driven restart), the bare-metal-specific version overlay on the four-way version match owned by `doca-version/SKILL.md`, the cross-cutting error taxonomy (seven layers, walked in order), the observability surface (stdout/stderr discipline by launch mode; device-state introspection via `devlink` / `sysfs` / `mlxconfig` *query*; per-tenant resource visibility), and the safety policy (overlay on `doca-hardware-safety/SKILL.md`: smoke-before-bulk for binaries; failed bare-metal process is HIGH-STAKES; do not invent PCI addresses, NUMA numbers, representor names, devlink paths, or systemd `Restart=` mode names; confirm tenant-isolation primitives BEFORE the workload starts). - the tasks companion — step-by-step workflows for the in-scope bare-metal verbs: `configure`, `build`, `modify`, `run` (with an explicit `### isolation` sub-anchor covering cgroup-v2 / namespaces / numactl per-tenant primitives), `test`, `debug`, `bluefield-lifecycle` (the BFB-install → RShim/TMFIFO → post-BFB-recovery operational sequencing ladder, with the six-state `bluefield-state-classifier` sub-anchor), the `Command appendix` (documented commands the agent may quote, each cross-linked to its public-doc source — no invented commands), and the `Deferred task verbs` block routing container-path / cluster / library-API / env-prep / hardware-state-change / cross-library questions out to their owning skills. (The change-application discipline for any mutating burn invoked from `## bluefield-lifecycle` is still meta-policy owned by `doca-hardware-safety/SKILL.md`, loaded alongside.) The skill assumes a host or BlueField target where: - DOCA is already installed and healthy (per `doca-setup ## test`), - the user has a DOCA-linked application binary they built (per `doca-programming-guide ## build`), - the user has the host-OS permissions to enumerate devices, reserve hugepages, write systemd units (if they choose that launch mode), and bind processes to NUMA nodes. It does not cover installing DOCA — that path goes through `doca-setup/SKILL.md` — and it does not cover building the binary — that path goes through `doca-programming-guide/SKILL.md`. ## Loading order 1. Read this skill first to confirm the user's question is in scope (bare-metal launch of a DOCA-linked binary on host x86 or BlueField Arm; NOT the container path, NOT a full cluster, NOT a library-API question). 2. **For the runtime contract (two host modes, three launch modes, hardware-binding surface, per-tenant isolation, version overlay, seven-layer error taxonomy, observability surface, bare-metal safety overlay), see the capabilities companion.** 3. **For step-by-step workflows — `configure`, `build` (routing stub), `modify` (routing stub), `run` (with `### isolation` sub-anchor), `test`, `debug`, `bluefield-lifecycle` (BFB install + RShim/TMFIFO + post-BFB recovery + the six-state `bluefield-state-classifier`), plus the `Command appendix` and the `Deferred task verbs` block — see the tasks companion.** ## Example questions this skill answers well ## What this skill deliberately does not ship ## Related skills
© NVIDIA · Apache-2.0 · NVIDIA/skills