Renovate: Automate operand version bumps in GPU Operator

Author: shivakunv

.github/renovate.json

@@ -0,0 +1,97 @@
+{
+  "$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"
+    }
+  ],
+  "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/vgpu-cc-manager",
+        "nvcr.io/nvidia/kubevirt-gpu-device-plugin",
+        "nvcr.io/nvidia/k8s-device-plugin"
+      ],
+      "versioning": "regex:^v?(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)$",
+      "separateMajorMinor": false
+    },
+    {
+      "matchPaths": ["deployments/gpu-operator/values.yaml"],
+      "matchPackageNames": [
+       "nvcr.io/nvidia/k8s/container-toolkit",
+       "nvcr.io/nvidia/cloud-native/k8s-mig-manager"
+      ],
+      "versioning": "regex:^v?(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)-ubuntu(?<ubuntu>\\d+\\.\\d+)$",
+      "separateMajorMinor": false
+    },
+    {
+      "matchPaths": ["deployments/gpu-operator/values.yaml"],
+      "matchPackageNames": [
+       "nvcr.io/nvidia/cuda"
+      ],
+      "versioning": "regex:^(?<major>\\d+)\\.(?<minor>\\d+)\\.(?<patch>\\d+)-base-ubi9$",
+      "separateMajorMinor": false
+    },
+    {
+      "groupName": "bump all nvcr packages for deploymens and clusterservice, skip driver",
+      "matchPackageNames": ["/.*/"]
+    },
+    {
+      "matchPackageNames": ["nvcr.io/nvidia/driver"],
+      "enabled": false
+    }
+  ]
+}

.github/workflows/renovate.yaml

@@ -0,0 +1,22 @@
+name: Renovate
+
+on:
+  workflow_dispatch:
+  schedule:
+     - cron: "0 9 * * *"
+
+jobs:
+  renovate:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Run Renovate
+        uses: renovatebot/[email protected]
+        with:
+          configurationFile: .github/renovate.json
+        env:
+          RENOVATE_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          RENOVATE_REPOSITORIES: '["shivakunv/gpu-operator"]'
+          RENOVATE_ONBOARDING: false

bundle/manifests/gpu-operator-certified.clusterserviceversion.yaml

@@ -161,7 +161,7 @@ metadata:
             "driverType": "gpu",
             "repository": "nvcr.io/nvidia",
             "image": "driver",
-            "version": "sha256:b74c06db9fda39e93d65649e1f447cb7bb82edfdc729936b4e67d11bbf9a4715",
+            "version": "sha256:6729c252a8877f29a1e5e336b945efa5126ea555db3c83b06e2e3d9843e647c7",
             "nodeSelector": {},
             "manager": {},
             "repoConfig": {
@@ -203,13 +203,13 @@ spec:
     - name: gpu-operator-image
       image: ghcr.io/nvidia/gpu-operator:main-latest
     - name: dcgm-exporter-image
-      image: nvcr.io/nvidia/k8s/dcgm-exporter@sha256:6c78381d83e2ccd84e9645d35d8768d98a52b73c75d1bb9395b5f030ce9bd3a4
+      image: nvcr.io/nvidia/k8s/dcgm-exporter@sha256:b848747435dfecb216484d16363a9897f64232b3c3ae7f171dde06525d8606b4
     - name: dcgm-image
-      image: nvcr.io/nvidia/cloud-native/dcgm@sha256:ec473ac9f8e4f638e97ec5ffd6f6d3dbbfc3a53bdd07514745c8868676979bba
+      image: nvcr.io/nvidia/cloud-native/dcgm@sha256:954cb65ae82d3663903299b2c9dab006df8b2bb6d59115ac5f63262f3b10aa30
     - name: container-toolkit-image
       image: nvcr.io/nvidia/k8s/container-toolkit@sha256:51c8f71d3b3c08ae4eb4853697e3f8e6f11e435e666e08210178e6a1faf8028f
     - name: driver-image
-      image: nvcr.io/nvidia/driver@sha256:b74c06db9fda39e93d65649e1f447cb7bb82edfdc729936b4e67d11bbf9a4715
+      image: nvcr.io/nvidia/driver@sha256:6729c252a8877f29a1e5e336b945efa5126ea555db3c83b06e2e3d9843e647c7
     - name: driver-image-550
       image: nvcr.io/nvidia/driver@sha256:8b89435d54a2e6a33c480dd0659e9a4a73f872a6187f9f9eadd934ecb45ac273
     - name: driver-image-535
@@ -901,13 +901,13 @@ spec:
                   - name: "CONTAINER_TOOLKIT_IMAGE"
                     value: "nvcr.io/nvidia/k8s/container-toolkit@sha256:51c8f71d3b3c08ae4eb4853697e3f8e6f11e435e666e08210178e6a1faf8028f"
                   - name: "DCGM_IMAGE"
-                    value: "nvcr.io/nvidia/cloud-native/dcgm@sha256:ec473ac9f8e4f638e97ec5ffd6f6d3dbbfc3a53bdd07514745c8868676979bba"
+                    value: "nvcr.io/nvidia/cloud-native/dcgm@sha256:954cb65ae82d3663903299b2c9dab006df8b2bb6d59115ac5f63262f3b10aa30"
                   - name: "DCGM_EXPORTER_IMAGE"
-                    value: "nvcr.io/nvidia/k8s/dcgm-exporter@sha256:6c78381d83e2ccd84e9645d35d8768d98a52b73c75d1bb9395b5f030ce9bd3a4"
+                    value: "nvcr.io/nvidia/k8s/dcgm-exporter@sha256:b848747435dfecb216484d16363a9897f64232b3c3ae7f171dde06525d8606b4"
                   - name: "DEVICE_PLUGIN_IMAGE"
                     value: "nvcr.io/nvidia/k8s-device-plugin@sha256:037160a36de0f060fc21cc0cb2f795d980282ff1471b55530433ca4350b24c4f"
                   - name: "DRIVER_IMAGE"
-                    value: "nvcr.io/nvidia/driver@sha256:b74c06db9fda39e93d65649e1f447cb7bb82edfdc729936b4e67d11bbf9a4715"
+                    value: "nvcr.io/nvidia/driver@sha256:6729c252a8877f29a1e5e336b945efa5126ea555db3c83b06e2e3d9843e647c7"
                   - name: "DRIVER_IMAGE-550"
                     value: "nvcr.io/nvidia/driver@sha256:8b89435d54a2e6a33c480dd0659e9a4a73f872a6187f9f9eadd934ecb45ac273"
                   - name: "DRIVER_IMAGE-535"

deployments/gpu-operator/values.yaml

@@ -80,8 +80,8 @@ operator:
   # to be passed during helm upgrade.
   upgradeCRD: true
   initContainer:
-    image: cuda
     repository: nvcr.io/nvidia
+    image: cuda
     version: 12.8.1-base-ubi9
     imagePullPolicy: IfNotPresent
   tolerations:
@@ -146,7 +146,7 @@ driver:
   usePrecompiled: false
   repository: nvcr.io/nvidia
   image: driver
-  version: "570.158.01"
+  version: "570.148.08"
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   startupProbe:
@@ -192,8 +192,8 @@ driver:
       timeoutSeconds: 300
       deleteEmptyDir: false
   manager:
-    image: k8s-driver-manager
     repository: nvcr.io/nvidia/cloud-native
+    image: k8s-driver-manager
     # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4
     # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0
     version: v0.8.0
@@ -234,7 +234,7 @@ toolkit:
   enabled: true
   repository: nvcr.io/nvidia/k8s
   image: container-toolkit
-  version: v1.17.8-ubuntu20.04
+  version: v1.17.7-ubuntu20.04
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -245,7 +245,7 @@ devicePlugin:
   enabled: true
   repository: nvcr.io/nvidia
   image: k8s-device-plugin
-  version: v0.17.2
+  version: v0.17.1
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   args: []
@@ -303,7 +303,7 @@ dcgm:
   enabled: false
   repository: nvcr.io/nvidia/cloud-native
   image: dcgm
-  version: 4.2.3-1-ubuntu22.04
+  version: 4.1.1-2-ubuntu22.04
   imagePullPolicy: IfNotPresent
   args: []
   env: []
@@ -313,7 +313,7 @@ dcgmExporter:
   enabled: true
   repository: nvcr.io/nvidia/k8s
   image: dcgm-exporter
-  version: 4.2.3-4.1.3-ubuntu22.04
+  version: 4.2.3-4.1.1-ubuntu22.04
   imagePullPolicy: IfNotPresent
   env:
     - name: DCGM_EXPORTER_LISTEN
@@ -464,8 +464,8 @@ vgpuManager:
   env: []
   resources: {}
   driverManager:
-    image: k8s-driver-manager
     repository: nvcr.io/nvidia/cloud-native
+    image: k8s-driver-manager
     # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4
     # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0
     version: v0.8.0
@@ -498,8 +498,8 @@ vfioManager:
   env: []
   resources: {}
   driverManager:
-    image: k8s-driver-manager
     repository: nvcr.io/nvidia/cloud-native
+    image: k8s-driver-manager
     # When choosing a different version of k8s-driver-manager, DO NOT downgrade to a version lower than v0.6.4
     # to ensure k8s-driver-manager stays compatible with gpu-operator starting from v24.3.0
     version: v0.8.0