Update: devspaces, gpu, nfd operators

.wordlist-md

@@ -19,12 +19,14 @@ ClusterTask
 CodeReady
 DNS
 Dev
+DevSpaces
 DevWorkspace
 DevWorkspaces
 Devfile
 DotNET
 Eventing
 FullAccess
+GPUs
 Gi
 GitOps
 HTPasswd
@@ -101,6 +103,7 @@ arn
 aws
 canada
 ceph
+che
 checluster
 cicd
 cli
@@ -112,10 +115,12 @@ configmap
 datasource
 deployable
 dev
+devfile
 devspaces
 devworkspace
 devworkspaces
 disableNameSuffixHash
+dn
 dns
 dotnet
 ec
@@ -180,6 +185,7 @@ prometheus
 redhat
 redistributions
 repo
+rhel
 rhpds
 runtime
 sagemaker
@@ -194,8 +200,10 @@ sublicense
 tekton
 templating
 thanos
+traefik
 truly
 vSphere
+vscode
 vsphere
 wordlist
 workspaces

devspaces/NOTES.md

@@ -0,0 +1,34 @@
+# General Notes
+
+## Key images
+
+Init containers
+
+```
+# che / vscode image
+registry.redhat.io/devspaces/code-rhel8
+# init container copies bins to `/checode`
+
+# project clone
+registry.redhat.io/devworkspace/devworkspace-project-clone-rhel8
+```
+
+Other containers
+
+```
+# che gateway
+registry.redhat.io/devspaces/traefik-rhel8
+
+# developer tools
+https://github.com/devfile/developer-images
+
+# che docs
+https://eclipse.dev/che/docs/stable/overview/introduction-to-eclipse-che/
+https://github.com/eclipse/che
+```
+
+Dashboard / devfile registry
+
+```
+https://github.com/eclipse-che/che-devfile-registry
+```

devspaces/aggregate/overlays/default/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+commonAnnotations:
+  argocd.argoproj.io/sync-options: SkipDryRunOnMissingResource=true
+
+resources:
+  - ../../../instance/overlays/default
+  - ../../../operator/overlays/stable

devspaces/aggregate/overlays/fix-autoscale/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+commonAnnotations:
+  argocd.argoproj.io/sync-options: SkipDryRunOnMissingResource=true
+
+resources:
+  - ../../../instance/overlays/timeout-12m
+  - ../../../operator/overlays/stable

devspaces/instance/base/checluster.yaml

@@ -0,0 +1,63 @@
+apiVersion: org.eclipse.che/v2
+kind: CheCluster
+metadata:
+  annotations:
+    argocd.argoproj.io/sync-wave: "5"
+  name: devspaces
+spec:
+  components:
+    cheServer:
+      debug: false
+      logLevel: INFO
+      extraProperties:
+        CHE_SYSTEM_ADMIN__NAME: 'opentlc-mgr'
+    dashboard:
+      headerMessage:
+        show: false
+        text: >-
+          It's time to get your Dev on!
+    # database:
+    #   credentialsSecretName: postgres-credentials
+    #   externalDb: false
+    #   postgresDb: devspaces
+    #   # BUG: can not change postgresHostNamae
+    #   postgresHostName: postgres
+    #   postgresPort: '5432'
+    #   pvc:
+    #     claimSize: 1Gi
+    devfileRegistry:
+      # deployment:
+      #   containers:
+      #     - name: devfile-registry
+      #       # image: quay.io/eclipse/che-devfile-registry:next
+      #       image: registry.redhat.io/devspaces/devfileregistry-rhel8:latest
+      externalDevfileRegistries:
+      - url: https://eclipse-che.github.io/che-devfile-registry/main
+    metrics:
+      enable: true
+    # pluginRegistry:
+    #   openVSXURL: "https://open-vsx.org"
+    #   openVSXURL: "https://marketplace.visualstudio.com"
+  containerRegistry: {}
+  devEnvironments:
+    startTimeoutSeconds: 180
+    secondsOfRunBeforeIdling: -1
+    maxNumberOfRunningWorkspacesPerUser: 2
+    maxNumberOfWorkspacesPerUser: -1
+    containerBuildConfiguration:
+      openShiftSecurityContextConstraint: container-build
+    disableContainerBuildCapabilities: true
+    defaultEditor: che-incubator/che-code/latest
+    # defaultComponents:
+    #   - container:
+    #       sourceMapping: /projects
+    #       image: registry.redhat.io/devspaces/udi-rhel8:latest
+    #     name: universal-developer-image
+    defaultNamespace:
+      autoProvision: true
+      template: workspace-<username>
+    secondsOfInactivityBeforeIdling: 1800
+    storage:
+      pvcStrategy: per-user
+  gitServices: {}
+  networking: {}

devspaces/instance/base/devworkspace-config.yaml

@@ -0,0 +1,9 @@
+apiVersion: controller.devfile.io/v1alpha1
+kind: DevWorkspaceOperatorConfig
+metadata:
+  name: devworkspace-config
+config:
+  workspace:
+    # kludge: allow cluster autoscaling
+    ignoredUnrecoverableEvents:
+      - FailedScheduling

devspaces/instance/base/kustomization.yaml

@@ -0,0 +1,12 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+commonLabels:
+  component: devspaces
+
+namespace: devspaces
+
+resources:
+  - checluster.yaml
+  - devworkspace-config.yaml
+  - namespace.yaml

devspaces/instance/base/namespace.yaml

@@ -0,0 +1,7 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: devspaces
+  annotations:
+    openshift.io/display-name: "DevSpaces Infra"
+    argocd.argoproj.io/sync-wave: "0"

devspaces/instance/base/network-policy.yaml

@@ -0,0 +1,13 @@
+apiVersion: networking.k8s.io/v1
+kind: NetworkPolicy
+metadata:
+  name: allow-from-openshift-devspaces
+spec:
+  ingress:
+    - from:
+      - namespaceSelector:
+          matchLabels:
+            kubernetes.io/metadata.name: openshift-devspaces
+  podSelector: {}
+  policyTypes:
+  - Ingress

devspaces/instance/overlays/default/README.md

@@ -0,0 +1,3 @@
+# Dev Spaces
+
+[OpenShift Dev Spaces Docs](https://access.redhat.com/documentation/en-us/red_hat_openshift_dev_spaces)

nvidia-gpu-operator/operator/base/kustomization.yaml → devspaces/instance/overlays/default/kustomization.yaml

@@ -2,6 +2,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 
 resources:
-  - namespace.yaml
-  - operator-group.yaml
-  - subscription.yaml
+  - ../../base

devspaces/instance/overlays/low-idle/kustomization.yaml

@@ -0,0 +1,17 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+namespace: devspaces
+
+resources:
+  - ../../base
+
+patches:
+  - target:
+      group: org.eclipse.che
+      kind: CheCluster
+      name: devspaces
+    patch: |-
+      - op: replace
+        path: /spec/devEnvironments/secondsOfRunBeforeIdling
+        value: 300

devspaces/instance/overlays/timeout-12m/kustomization.yaml

@@ -0,0 +1,24 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+namespace: devspaces
+
+resources:
+  - ../../base
+
+patches:
+  - target:
+      group: org.eclipse.che
+      kind: CheCluster
+      name: devspaces
+    patch: |-
+      - op: replace
+        path: /spec/components/dashboard/headerMessage/show
+        value: true
+      - op: replace
+        path: /spec/components/dashboard/headerMessage/text
+        value: |
+          Please be patient... GPUs may take up to 12 min to be available!
+      - op: replace
+        path: /spec/devEnvironments/startTimeoutSeconds
+        value: 720

gpu-operator-certified/instance/README.md

@@ -0,0 +1,51 @@
+# GPU Notes
+
+For more info please review the following:
+
+- [Demo GPUs on OpenShift](https://github.com/redhat-na-ssa/demo-ocp-gpu)
+
+## Instance Types
+
+AWS GPU Types:
+
+Multi-instance GPU (MIG) can be:
+
+- `p5.48xlarge`  - 8 x H100 Tensor Core
+- `p4d.24xlarge` - 8 x A100 Tensor Core  
+
+Time-slicing GPU can be any Nvidia type (as documented by Nvidia):
+
+- P3 - V100
+  - `p3.2xlarge`  - 1 x V100
+  - `p3.8xlarge`  - 4 x V100
+  - `p3.16xlarge` - 8 x V100
+- P2 - K80
+  - `P2.xlarge`   - 1  x K80
+  - `P2.8xlarge`  - 8  x K80
+  - `P2.16xlarge` - 16 x K80
+- G5g - T4G
+  - `g5g.{,2,4,8}xlarge`         - 1 x T4G
+  - `g5g.16xlarge`, `g5g.metal`  - 2 x T4G
+- G5 - A10G
+  - `g5.{,2,4,8,16}xlarge`  - 1 x A10G
+  - `g5.{12,24}xlarge`      - 4 x A10G
+  - `g5.48xlarge`           - 8 x A10G
+- G4dn - T4
+  - `g4dn.{,2,4,8,16}xlarge` - 1 x T4
+  - `g4dn.48xlarge`          - 4 x T4
+  - `g4dn.metal`             - 8 x T4
+- G3 - M60
+  - `g3s.xlarge`  - 1 x M60
+  - `g3.4xlarge`  - 1 x M60
+  - `g3.8xlarge`  - 2 x M60
+  - `g3.16xlarge` - 4 x M60
+
+## Links
+
+- [Docs - AWS GPU Instances](https://aws.amazon.com/ec2/instance-types/#Accelerated_Computing)
+- [Docs - Nvidia GPU Operator on Openshift](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/openshift/contents.html)
+- [Docs - Nvidia GPU admin dashboard](https://docs.openshift.com/container-platform/4.11/monitoring/nvidia-gpu-admin-dashboard.html)
+- [Docs - MIG support in OCP](https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/openshift/mig-ocp.html)
+- [Blog - RH Nvidia GPUs on OpenShift](https://cloud.redhat.com/blog/autoscaling-nvidia-gpus-on-red-hat-openshift)
+- [Demo - GPU DevSpaces](https://github.com/bkoz/devspaces)
+- [GPU Operator default config map](https://gitlab.com/nvidia/kubernetes/gpu-operator/-/blob/v23.6.1/assets/state-mig-manager/0400_configmap.yaml?ref_type=tags)