Update Nvidia, LAMP-Contao, Readme

helm-values/LAMP-Contao-CSLSA/README.md

@@ -14,10 +14,10 @@ LAMP (Linux Apache Mysql PHP) System als Basis für die Installation von Contao,
     mkdir <path>/containerize/helm-values/LAMP
     cd <path>/containerize/helm-values/LAMP
     # Default Values ausgeben
-    helm inspect values lamp/lamp > values-default.yaml
+    helm inspect values containerize/ti-lamp > values-default.yaml
     ```
 
-2. `values.yaml` anlegen und anpassen, sieh mitgelieferte `values.yaml`
+2. `values.yaml` anlegen und anpassen, siehe mitgelieferte `values.yaml`
 
 3. Installation
 
@@ -26,10 +26,25 @@ LAMP (Linux Apache Mysql PHP) System als Basis für die Installation von Contao,
     ```bash
     helm upgrade --install --wait contao \
         -n contao --create-namespace \
-        lamp/lamp \
+        containerize/ti-lamp \
         --values values.yaml \
         --set mysql.rootPassword=<pass1> \
         --set mysql.database=contao \
         --set mysql.user=contao \
         --set mysql.password=<pass2>
+    ```
+
+4. Upgrade / Anpassungen
+
+    ```bash
+    helm upgrade --install --wait contao \
+        -n contao --create-namespace \
+        containerize/ti-lamp \
+        --values values.yaml \
+        --set mysql.rootPassword=<pass1> \
+        --set mysql.database=contao \
+        --set mysql.user=contao \
+        --set mysql.password=<pass2> \
+        --set webdav.user=contao \
+        --set webdav.password=<PASSWORD>
     ```
\ No newline at end of file

helm-values/LAMP-Contao-CSLSA/values.yaml

@@ -35,12 +35,18 @@ httpd:
       </VirtualHost>    
 
 php:
+  # official PHP images ----
+  #  repository: "php"
+  #  tag: "8.3-fpm-alpine"  # has no gd+intl
+  #  tag: "8.3-fpm"         # has no gd+intl
+  # local Repo -------------
   repository: "mcr.informatik.uni-halle.de/studio-r215/containerize/php-fpm"
   tag: "83"
-#  # official PHP images
-#  repository: "php"
-#  tag: "8.3-fpm-alpine"  # has no gd+intl
-#  tag: "8.3-fpm"         # has no gd+intl
+  # php.ini
+  ini: |
+      max_input_vars = 2000
+      upload_max_filesize = 50M
+      post_max_size = 55M
 #  resources:
 #    requests:
 #      memory: "128Mi"
@@ -55,6 +61,11 @@ phpmyadmin:
   tag: "apache"
   subdomain: pma
 
+webdav:
+  enabled: true
+  subdomain: webdv
+
+
 ingress:
   enabled: true
   domain: cslsa.tikube.informatik.uni-halle.de

helm-values/NVidia/README.md

@@ -5,6 +5,8 @@
 Für die Nutzung von CUDA in Kubernetes Knoten:
 Siehe https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/gpu-driver-configuration.html
 
+Für die Nutzung mit vorinstallierten Treibern und Toolkit:
+Siehe https://www.jimangel.io/posts/nvidia-rtx-gpu-kubernetes-setup/
 
 ### Installation
 
@@ -34,7 +36,7 @@ Siehe https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/gpu-dr
     helm status gpu-operator -n gpu-operator
     ```
 
-#### Variante Bare-metal/Passthrough with pre-installed NVIDIA drivers
+#### Variante Bare-metal/Passthrough mit pre-installed NVIDIA-Treiber
 
 ```yaml
 driver:
@@ -57,6 +59,44 @@ toolkit:
      value: "true"  
 ```
 
+#### Variante Bare-metal/Passthrough mit pre-installed NVIDIA-Treiber und -Toolkit
+
+- Toolkit instlallieren 
+
+```bash
+# add nvidia-container-toolkit repo to apt sources
+curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
+&& curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
+sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
+sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
+sudo apt update
+
+# install container toolkit
+sudo apt install -y nvidia-container-toolkit
+# options: --dry-run
+sudo nvidia-ctk runtime configure --runtime=containerd
+
+reboot
+```
+
+```yaml
+driver:
+  enabled: false
+  version: "550.127.05"  # hier muss die passende Version NVidia-Treiber der Basismaschine eingetragen werden 
+  
+toolkit:
+  enabled: false
+  env:
+   - name: CONTAINERD_CONFIG
+     value: /var/lib/rancher/rke2/agent/etc/containerd/config.toml.tmpl
+   - name: CONTAINERD_SOCKET
+     value: /run/k3s/containerd/containerd.sock
+   - name: CONTAINERD_RUNTIME_CLASS
+     value: nvidia
+   - name: CONTAINERD_SET_AS_DEFAULT
+     value: "true"  
+```
+
 ### Time-Slicing
 <https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/gpu-sharing.html>
 

helm-values/NVidia/gpu-operator-values-default.yaml

@@ -20,6 +20,18 @@ sandboxWorkloads:
   enabled: false
   defaultWorkload: "container"
 
+hostPaths:
+  # rootFS represents the path to the root filesystem of the host.
+  # This is used by components that need to interact with the host filesystem
+  # and as such this must be a chroot-able filesystem.
+  # Examples include the MIG Manager and Toolkit Container which may need to
+  # stop, start, or restart systemd services
+  rootFS: "/"
+
+  # driverInstallDir represents the root at which driver files including libraries,
+  # config files, and executables can be found.
+  driverInstallDir: "/run/nvidia/driver"
+
 daemonsets:
   labels: {}
   annotations: {}
@@ -67,11 +79,11 @@ operator:
   cleanupCRD: false
   # upgrade CRD on chart upgrade, requires --disable-openapi-validation flag
   # to be passed during helm upgrade.
-  upgradeCRD: false
+  upgradeCRD: true
   initContainer:
     image: cuda
     repository: nvcr.io/nvidia
-    version: 12.4.1-base-ubi8
+    version: 12.6.2-base-ubi9
     imagePullPolicy: IfNotPresent
   tolerations:
   - key: "node-role.kubernetes.io/master"
@@ -131,7 +143,7 @@ driver:
   usePrecompiled: false
   repository: nvcr.io/nvidia
   image: driver
-  version: "550.54.15"
+  version: "550.127.05"
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   startupProbe:
@@ -181,7 +193,7 @@ driver:
     repository: nvcr.io/nvidia/cloud-native
     # 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: v0.6.8
+    version: v0.7.0
     imagePullPolicy: IfNotPresent
     env:
       - name: ENABLE_GPU_POD_EVICTION
@@ -219,7 +231,7 @@ toolkit:
   enabled: true
   repository: nvcr.io/nvidia/k8s
   image: container-toolkit
-  version: v1.15.0-ubuntu20.04
+  version: v1.17.0-ubuntu20.04
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -230,7 +242,7 @@ devicePlugin:
   enabled: true
   repository: nvcr.io/nvidia
   image: k8s-device-plugin
-  version: v0.15.0-ubi8
+  version: v0.17.0-ubi9
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   args: []
@@ -271,7 +283,7 @@ devicePlugin:
   config:
     # Create a ConfigMap (default: false)
     create: false
-    # ConfigMap name (either exiting or to create a new one with create=true above)
+    # ConfigMap name (either existing or to create a new one with create=true above)
     name: ""
     # Default config name within the ConfigMap
     default: ""
@@ -288,9 +300,8 @@ dcgm:
   enabled: false
   repository: nvcr.io/nvidia/cloud-native
   image: dcgm
-  version: 3.3.5-1-ubuntu22.04
+  version: 3.3.8-1-ubuntu22.04
   imagePullPolicy: IfNotPresent
-  hostPort: 5555
   args: []
   env: []
   resources: {}
@@ -299,7 +310,7 @@ dcgmExporter:
   enabled: true
   repository: nvcr.io/nvidia/k8s
   image: dcgm-exporter
-  version: 3.3.5-3.4.1-ubuntu22.04
+  version: 3.3.8-3.6.0-ubuntu22.04
   imagePullPolicy: IfNotPresent
   env:
     - name: DCGM_EXPORTER_LISTEN
@@ -321,12 +332,31 @@ dcgmExporter:
     #   target_label: instance
     #   replacement: $1
     #   action: replace
+  # DCGM Exporter configuration
+  # This block is used to configure DCGM Exporter to emit a customized list of metrics.
+  # Use "name" to either point to an existing ConfigMap or to create a new one with a
+  # list of configurations (i.e with create=true).
+  # When pointing to an existing ConfigMap, the ConfigMap must exist in the same namespace as the release.
+  # The metrics are expected to be listed under a key called `dcgm-metrics.csv`.
+  # Use "data" to build an integrated ConfigMap from a set of custom metrics as
+  # part of the chart. An example of some custom metrics are shown below. Note that
+  # the contents of "data" must be in CSV format and be valid DCGM Exporter metric configurations.
+  # config:
+    # name: custom-dcgm-exporter-metrics
+    # create: true
+    # data: |-
+      # Format
+      # If line starts with a '#' it is considered a comment
+      # DCGM FIELD, Prometheus metric type, help message
 
+      # Clocks
+      # DCGM_FI_DEV_SM_CLOCK,  gauge, SM clock frequency (in MHz).
+      # DCGM_FI_DEV_MEM_CLOCK, gauge, Memory clock frequency (in MHz).
 gfd:
   enabled: true
   repository: nvcr.io/nvidia
   image: k8s-device-plugin
-  version: v0.15.0-ubi8
+  version: v0.17.0-ubi9
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env:
@@ -340,16 +370,52 @@ migManager:
   enabled: true
   repository: nvcr.io/nvidia/cloud-native
   image: k8s-mig-manager
-  version: v0.7.0-ubuntu20.04
+  version: v0.10.0-ubuntu20.04
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env:
     - name: WITH_REBOOT
       value: "false"
   resources: {}
+  # MIG configuration
+  # Use "name" to either point to an existing ConfigMap or to create a new one with a list of configurations(i.e with create=true).
+  # Use "data" to build an integrated ConfigMap from a set of configurations as
+  # part of this helm chart. An example of setting "data" might be:
+  # config:
+  #   name: custom-mig-parted-configs
+  #   create: true
+  #   data: |-
+  #     config.yaml: |-
+  #       version: v1
+  #       mig-configs:
+  #         all-disabled:
+  #           - devices: all
+  #             mig-enabled: false
+  #         custom-mig:
+  #           - devices: [0]
+  #             mig-enabled: false
+  #           - devices: [1]
+  #              mig-enabled: true
+  #              mig-devices:
+  #                "1g.10gb": 7
+  #           - devices: [2]
+  #             mig-enabled: true
+  #             mig-devices:
+  #               "2g.20gb": 2
+  #               "3g.40gb": 1
+  #           - devices: [3]
+  #             mig-enabled: true
+  #             mig-devices:
+  #               "3g.40gb": 1
+  #               "4g.40gb": 1
   config:
-    name: "default-mig-parted-config"
     default: "all-disabled"
+    # Create a ConfigMap (default: false)
+    create: false
+    # ConfigMap name (either existing or to create a new one with create=true above)
+    name: ""
+    # Data section for the ConfigMap to create (i.e only applies when create=true)
+    data: {}
   gpuClientsConfig:
     name: ""
 
@@ -367,7 +433,7 @@ gds:
   enabled: false
   repository: nvcr.io/nvidia/cloud-native
   image: nvidia-fs
-  version: "2.17.5"
+  version: "2.20.5"
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -377,7 +443,7 @@ gdrcopy:
   enabled: false
   repository: nvcr.io/nvidia/cloud-native
   image: gdrdrv
-  version: "v2.4.1"
+  version: "v2.4.1-2"
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -397,7 +463,7 @@ vgpuManager:
     repository: nvcr.io/nvidia/cloud-native
     # 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: v0.6.8
+    version: v0.7.0
     imagePullPolicy: IfNotPresent
     env:
       - name: ENABLE_GPU_POD_EVICTION
@@ -409,7 +475,7 @@ vgpuDeviceManager:
   enabled: true
   repository: nvcr.io/nvidia/cloud-native
   image: vgpu-device-manager
-  version: "v0.2.6"
+  version: v0.2.8
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -421,7 +487,7 @@ vfioManager:
   enabled: true
   repository: nvcr.io/nvidia
   image: cuda
-  version: 12.4.1-base-ubi8
+  version: 12.6.2-base-ubi9
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -431,7 +497,7 @@ vfioManager:
     repository: nvcr.io/nvidia/cloud-native
     # 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: v0.6.8
+    version: v0.7.0
     imagePullPolicy: IfNotPresent
     env:
       - name: ENABLE_GPU_POD_EVICTION
@@ -457,7 +523,7 @@ kataManager:
           pullSecret: ""
   repository: nvcr.io/nvidia/cloud-native
   image: k8s-kata-manager
-  version: v0.2.0
+  version: v0.2.2
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   env: []
@@ -467,7 +533,7 @@ sandboxDevicePlugin:
   enabled: true
   repository: nvcr.io/nvidia
   image: kubevirt-gpu-device-plugin
-  version: v1.2.7
+  version: v1.2.10
   imagePullPolicy: IfNotPresent
   imagePullSecrets: []
   args: []
@@ -489,6 +555,7 @@ ccManager:
 
 node-feature-discovery:
   enableNodeFeatureApi: true
+  priorityClassName: system-node-critical
   gc:
     enable: true
     replicaCount: 1

helm-values/NVidia/gpu-operator-values.yaml

-# values for gpu-operator.
-
+# values for gpu-operator
 
 driver:
   #enabled: true
   enabled: false
-  usePrecompiled: true
-  repository: nvcr.io/nvidia
-  image: driver
+  #usePrecompiled: true
+  #repository: nvcr.io/nvidia
+  #image: driver
   #version: "535.129.03"
   #version: "535.161.08"
-  version: "550.54.15"
+  #version: "550.54.15"
+  #version: "550.90.07"
+  version: "550.127.05"
 
 toolkit:
-  enabled: true
+  #enabled: true
+  enabled: false
   #env: []
   env:
    - name: CONTAINERD_CONFIG
@@ -24,3 +26,4 @@ toolkit:
    - name: CONTAINERD_SET_AS_DEFAULT
      value: "true"  
 
+