Skip to main content

nvca-self-managed-install

Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.

Quellinformationen

Repository
NVIDIA/nvcf
Letzte Quellaktivität
16. Oktober 2026 um 13:46
Erkannte Sprache von SKILL.md
Englisch
Sterne
238
Forks
94

Installationsoptionen

Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.

Quelldateien prüfen

Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.

SKILL.md wird angezeigt

SKILL.md
Quellanweisungen · Schreibgeschützte Vorschau
name
nvca-self-managed-install
description
Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.
license
Apache-2.0
compatibility
Requires a local checkout of the NVCF monorepo with deploy/helm/nvca-operator/ and deploy/stacks/self-managed/ present, plus helm.
author
nvcf-core-eng <nvcf-core-eng@exchange.nvidia.com>
version
1.0.0
tags
["nvcf","nvca","helm","install","self-managed"]
tools
["Read","Shell"]
metadata
{"internal":false,"author":"nvcf-core-eng <nvcf-core-eng@exchange.nvidia.com>","version":"1.0","tags":["nvcf","nvca","helm","install"],"languages":["bash"],"frameworks":["helm"],"domain":"cloud-infrastructure"}
# NVCA Self-Managed Install Use `deploy/helm/nvca-operator` as the install surface for NVCA Operator chart validation. Do not add NVCA back into the stack Helmfile just to test this chart. ## Source of Truth - Control-plane deployment: `deploy/stacks/self-managed` - NVCA chart and install workflow: `deploy/helm/nvca-operator` - NVCA source images and source chart: `src/compute-plane-services/nvca` - Cluster prerequisites: use the public `nvcf-self-managed-prerequisite` skill - Full stack install and teardown: use the public `nvcf-self-managed-installation` skill ## Instructions Run from `deploy/helm/nvca-operator`: ```bash make render-values-from-stack \ stack_env=local \ stack_repo=../../../deploy/stacks/self-managed ``` Inspect the generated file under `bin/`, then install or upgrade. The render also sets the values the control-plane validator role needs from the stack: `clusterValidator.gatewayNames` from the wired `ingress.gatewayApi.gateways`, `clusterValidator.storageClass` from `global.storageClass`, and `clusterValidator.externalComponents` from the quorum components the stack disables. It rewrites them on every render, empty included, so an upgrade does not keep a stale value from the release. On a registry other than NGC (`nvcr.io` or a subdomain) it also sets `clusterValidator.nodeToNodeProbeImage` to `busybox:1.36` under the stack's repository, so mirror that image there. It keeps a probe image the release already sets, and sets none when `networkChecks.enforcement.testImage` is set: ```bash make install-from-stack \ stack_env=local \ stack_repo=../../../deploy/stacks/self-managed ``` ## Optional Inputs - `additional_values=override.yml` for one-off overrides - `NCA_ID=<value>` to set the primary account ID explicitly - `CLUSTER_NAME=<value>` and `CLUSTER_ID=<value>` to preserve or pin cluster identity - `IMAGE_PULL_SECRET_NAME=<secret>` to attach a pre-created image pull secret - `NODE_TO_NODE_PROBE_IMAGE=<image>` to pick the node-to-node probe image; it must be pullable without an image pull secret ## Existing Release Reuse If `nvca-operator` is already installed in the `nvca-operator` namespace, the render helper reuses current release values first, then overlays repository paths derived from the stack environment file. Use this to preserve cluster IDs and operator settings during upgrades. ## Safety Before creating, deleting, or reusing local k3d clusters, read the local-dev safety guidance in `docs/dev/local-development.md` from the repo root. Do not delete clusters or Helm releases without explicit user approval.
Auf GitHub ansehen