Merge branch 'NVIDIA:main' into allow-overriding-lease-namespace

Author: ratschance

.common-ci.yml

@@ -25,7 +25,7 @@ stages:
   - e2e_tests
   - aws_kube_clean
   - release
-  - sign
+  - ngc-publish
 
 # Enable pipelines on merge requests, tags, and branches.
 # Avoid duplicate pipelines when pushing to a branch associated with an open MR.
@@ -81,26 +81,13 @@ trigger-pipeline:
 
     -  '[[ -n "${SKIP_QEMU_SETUP}" ]] || docker run --rm --privileged multiarch/qemu-user-static --reset -p yes'
 
-# Define targets for the gpu-operator and gpu-operator-validator images
-.dist-ubi9:
-  variables:
-    DIST: ubi9
-    CVE_UPDATES: "cyrus-sasl-lib"
-
+# Define targets for the gpu-operator image
 .target-gpu-operator:
   variables:
     IMAGE_NAME: "${CI_REGISTRY_IMAGE}"
     IN_IMAGE_NAME: "gpu-operator"
     IMAGE_ARCHIVE: "gpu-operator.tar"
 
-.target-gpu-operator-validator:
-  variables:
-    SUBCOMPONENT: "validator"
-    IMAGE_NAME: "${CI_REGISTRY_IMAGE}/gpu-operator-validator"
-    IN_IMAGE_NAME: "gpu-operator-validator"
-    IMAGE_ARCHIVE: "gpu-operator-validator.tar"
-    IN_REGISTRY: "${STAGING_REGISTRY}/gpu-operator"
-
 # .release forms the base of the deployment jobs which push images to the CI registry.
 # This is extended with the version to be deployed (e.g. the SHA or TAG) and the
 # target os.
@@ -130,7 +117,7 @@ trigger-pipeline:
 
     # Since OUT_IMAGE_NAME and OUT_IMAGE_VERSION are set, this will push the CI image to the
     # Target
-    - make push-${DIST}
+    - make push-image
 
 .release-bundle:
   stage: release
@@ -150,7 +137,7 @@ trigger-pipeline:
 # Download the regctl binary for use in the release steps
 .regctl-setup:
   before_script:
-    - export REGCTL_VERSION=v0.8.2
+    - export REGCTL_VERSION=v0.11.2
     - apk add --no-cache curl
     - mkdir -p bin
     - curl -sSLo bin/regctl https://github.com/regclient/regclient/releases/download/${REGCTL_VERSION}/regctl-linux-amd64
@@ -175,55 +162,15 @@ trigger-pipeline:
   extends:
     - .release
   variables:
-    OUT_REGISTRY_USER: "${CI_REGISTRY_USER}"
-    OUT_REGISTRY_TOKEN: "${CI_REGISTRY_PASSWORD}"
-    OUT_REGISTRY: "${CI_REGISTRY}"
+    OUT_REGISTRY_USER: "${NGC_REGISTRY_USER}"
+    OUT_REGISTRY_TOKEN: "${NGC_REGISTRY_TOKEN}"
+    OUT_REGISTRY: "${NGC_REGISTRY}"
 
 release:staging-gpu-operator:
   extends:
     - .release:staging
-    - .dist-ubi9
     - .target-gpu-operator
   variables:
-    OUT_IMAGE_NAME: "${CI_REGISTRY_IMAGE}/staging/gpu-operator"
-
-release:staging-gpu-operator-validator:
-  extends:
-    - .release:staging
-    - .dist-ubi9
-    - .target-gpu-operator-validator
-  variables:
-    OUT_IMAGE_NAME: "${CI_REGISTRY_IMAGE}/staging/gpu-operator-validator"
-
-release:staging-latest-gpu-operator:
-  extends:
-    - .release:staging
-    - .dist-ubi9
-    - .target-gpu-operator
-  variables:
-    OUT_IMAGE_NAME: "${CI_REGISTRY_IMAGE}/staging/gpu-operator"
-    OUT_IMAGE_VERSION: ${CI_COMMIT_BRANCH}-latest
-  rules:
-    - if: $CI_COMMIT_BRANCH
-
-release:staging-latest-gpu-operator-validator:
-  extends:
-    - .release:staging
-    - .dist-ubi9
-    - .target-gpu-operator-validator
-  variables:
-    OUT_IMAGE_NAME: "${CI_REGISTRY_IMAGE}/staging/gpu-operator-validator"
-    OUT_IMAGE_VERSION: ${CI_COMMIT_BRANCH}-latest
-  rules:
-    - if: $CI_COMMIT_BRANCH
-
-release:gpu-operator-bundle-image:
-  extends:
-    - .release-bundle
-  variables:
-    BUNDLE_IMAGE: "${CI_REGISTRY_IMAGE}/staging/gpu-operator-bundle:${CI_COMMIT_BRANCH}-latest"
-    VERSION: ""
-    DEFAULT_CHANNEL: "stable"
-    CHANNELS: "stable"
-  rules:
-    - if: $CI_COMMIT_BRANCH
+    OUT_IMAGE_NAME: "${NGC_STAGING_REGISTRY}/gpu-operator"
+  needs:
+    - image:gpu-operator

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,48 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: '[Bug]: '
+labels: ["bug", "needs-triage"]
+
+---
+
+_**Important Note:  NVIDIA AI Enterprise customers can get support from NVIDIA Enterprise support. Please open a case [here](https://enterprise-support.nvidia.com/s/create-case)**._
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Detailed steps to reproduce the issue.
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Environment (please provide the following information):**
+ - GPU Operator Version: [e.g. v25.3.0]
+ - OS: [e.g. Ubuntu24.04]
+ - Kernel Version: [e.g. 6.8.0-generic]
+ - Container Runtime Version: [e.g. containerd 2.0.0]
+ - Kubernetes Distro and Version: [e.g. K8s, OpenShift, Rancher, GKE, EKS]
+
+
+
+**Information to [attach](https://help.github.com/articles/file-attachments-on-issues-and-pull-requests/)** (optional if deemed irrelevant)
+
+ - [ ] kubernetes pods status: `kubectl get pods -n OPERATOR_NAMESPACE`
+ - [ ] kubernetes daemonset status: `kubectl get ds -n OPERATOR_NAMESPACE`
+ - [ ] If a pod/ds is in an error state or pending state `kubectl describe pod -n OPERATOR_NAMESPACE POD_NAME`
+ - [ ] If a pod/ds is in an error state or pending state `kubectl logs -n OPERATOR_NAMESPACE POD_NAME --all-containers`
+ - [ ] Output from running `nvidia-smi` from the driver container: `kubectl exec DRIVER_POD_NAME -n OPERATOR_NAMESPACE -c nvidia-driver-ctr -- nvidia-smi`
+ - [ ] containerd logs `journalctl -u containerd > containerd.log`
+
+
+Collecting full debug bundle (optional):
+
+```
+curl -o must-gather.sh -L https://raw.githubusercontent.com/NVIDIA/gpu-operator/main/hack/must-gather.sh
+chmod +x must-gather.sh
+./must-gather.sh
+```
+**NOTE**: please refer to the [must-gather](https://raw.githubusercontent.com/NVIDIA/gpu-operator/main/hack/must-gather.sh) script for debug data collected.
+
+This bundle can be submitted to us via email: **operator_feedback@nvidia.com**

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1 @@
+blank_issues_enabled: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,8 @@
+---
+name: Feature request
+about: Submit a feature request
+title: "[Feature]: "
+labels: ["feature", "needs-triage", "lifecycle/frozen"]
+---
+
+<!-- A clear and concise description of the feature request. Please outline the motivation for the proposal. Is your feature request related to a specific problem? e.g., *"I'm working on X and would like Y to be possible"*. If this is related to another GitHub issue, please link it here too. -->

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,8 @@
+---
+name: Question / General Discussion
+about: Ask a question or raise a discussion
+title: "[Question]: "
+labels: ["question"]
+---
+
+<!-- Ask question(s) or raise a discussion related to GPU Operator -->

.github/ISSUE_TEMPLATE/question.md

@@ -0,0 +1,16 @@
+## Description
+
+<!-- Brief description of the change, including context or motivation -->
+
+## Checklist
+
+- [ ] No secrets, sensitive information, or unrelated changes
+- [ ] Lint checks passing (`make lint`)
+- [ ] Generated assets in-sync (`make validate-generated-assets`)
+- [ ] Go mod artifacts in-sync (`make validate-modules`)
+- [ ] Test cases are added for new code paths
+
+## Testing
+
+<!-- How was this tested? e.g., unit tests, manual testing on cluster -->
+

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,103 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
+  "prHourlyLimit": 10,
+  "prConcurrentLimit": 10,
+  "dependencyDashboard": false,
+  "extends": [
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard",
+    "config:recommended",
+    ":disableDependencyDashboard"
+  ],
+  "forkProcessing": "enabled",
+  "ignorePaths": ["vendor/**"],
+  "enabledManagers": ["custom.regex"],
+  "recreateWhen": "always",
+  "separateMultipleMajor": false,
+  "separateMinorPatch": false,
+  "customManagers": [
+    {
+      "customType": "regex",
+      "managerFilePatterns": [
+        "bundle/manifests/gpu-operator-certified.clusterserviceversion.yaml"
+      ],
+      "matchStrings": [
+        "[-\\s]*value:\\s*\"?(?<depName>[^:\"]+)(?::(?<currentValue>[^@\"]+))?@(?<currentDigest>sha256:[a-f0-9]{64})\"?",
+        "[-\\s]*image: (?<depName>.*?)(?::(?<currentValue>.*?))?@(?<currentDigest>sha256:[a-f0-9]{64})",
+        "- name: (?<suffix>[\\w-]+)[-\\s]*image: (?<depName>.*?)(?::(?<currentValue>.*?))?@(?<currentDigest>sha256:[a-f0-9]{64})"
+      ],
+      "versioningTemplate": "{{depName}}{{#if newValue}}:{{newValue}}{{/if}}{{#if newDigest}}@{{newDigest}}{{/if}}",
+      "datasourceTemplate": "docker"
+    },
+    {
+      "customType": "regex",
+      "managerFilePatterns": [
+        "deployments/gpu-operator/values.yaml"
+      ],
+      "matchStrings": [
+       "[-\\s]*repository:\\s*(?<repo>\\S+)\\s*\\n(?:\\s*#.*\\n|\\s*\\n)*[-\\s]*image:\\s*(?<image>\\S+)\\s*\\n(?:\\s*#.*\\n|\\s*\\n)*[-\\s]*version:\\s*(?<currentValue>\\S+)"
+      ],
+      "depNameTemplate": "{{repo}}/{{image}}",
+      "datasourceTemplate": "docker",
+      "versioningTemplate": "loose"
+    }
+  ],
+  "labels": [
+    "dependencies",
+    "renovate"
+  ],
+  "packageRules": [
+    {
+      "matchPaths": ["deployments/gpu-operator/values.yaml"],
+      "matchPackageNames": [
+        "nvcr.io/nvidia/cloud-native/k8s-driver-manager",
+        "nvcr.io/nvidia/cloud-native/k8s-kata-manager",
+        "nvcr.io/nvidia/cloud-native/vgpu-device-manager",
+        "nvcr.io/nvidia/cloud-native/k8s-cc-manager",
+        "nvcr.io/nvidia/cloud-native/nvidia-sandbox-device-plugin",
+        "nvcr.io/nvidia/kubevirt-gpu-device-plugin",
+        "nvcr.io/nvidia/k8s-device-plugin",
+        "nvcr.io/nvidia/k8s/container-toolkit",
+        "nvcr.io/nvidia/cloud-native/k8s-mig-manager"
+      ],
+      "versioning": "regex:^v?(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)$",
+      "separateMajorMinor": false
+    },
+    {
+      "matchPaths": ["deployments/gpu-operator/values.yaml"],
+      "matchPackageNames": [
+        "nvcr.io/nvidia/k8s/dcgm-exporter"
+      ],
+      "versioning": "regex:^v?(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)-distroless$",
+      "separateMajorMinor": false
+    },
+    {
+      "matchPaths": ["deployments/gpu-operator/values.yaml"],
+      "matchPackageNames": [
+       "nvcr.io/nvidia/cuda"
+      ],
+      "versioning": "regex:^(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)-base-ubi9$",
+      "separateMajorMinor": false
+    },
+    {
+      "matchPackageNames": ["nvcr.io/nvidia/driver"],
+      "enabled": false
+    },
+    {
+      "matchDatasources": ["*"],
+      "groupName": "{{depName}}"
+    }
+  ]
+}