[Creator] [design-spec] vast-k8s-csi-health

codebundles/vast-k8s-csi-health/.runwhen/generation-rules/vast-k8s-csi-health.yaml

@@ -0,0 +1,54 @@
+apiVersion: runwhen.com/v1
+kind: GenerationRules
+spec:
+  generationRules:
+    # One SLX per namespace that has at least one VAST-backed PVC.
+    - resourceTypes:
+        - persistentvolumeclaim
+      matchRules:
+        - type: pattern
+          pattern: ".+"
+          properties: [name]
+          mode: substring
+        - type: or
+          matches:
+            - type: pattern
+              pattern: "vast"
+              properties: [spec/storageClassName]
+              mode: substring
+            - type: pattern
+              pattern: "vast"
+              properties: [metadata/annotations]
+              mode: substring
+      slxs:
+        - baseName: vast-k8s-csi-health
+          shortenedBaseName: vast-csi-hlth
+          qualifiers: ["namespace", "cluster"]
+          baseTemplateName: vast-k8s-csi-health
+          levelOfDetail: basic
+          outputItems:
+            - type: slx
+            - type: sli
+            - type: runbook
+              templateName: vast-k8s-csi-health-taskset.yaml
+
+    # Optional cluster-level SLX for the CSI driver install namespace when
+    # operators want driver health monitoring before workload namespaces exist.
+    - resourceTypes:
+        - namespace
+      matchRules:
+        - type: pattern
+          pattern: "vast-csi"
+          properties: [name]
+          mode: substring
+      slxs:
+        - baseName: vast-csi-driver
+          shortenedBaseName: vast-csi-drv
+          qualifiers: ["namespace", "cluster"]
+          baseTemplateName: vast-k8s-csi-health
+          levelOfDetail: basic
+          outputItems:
+            - type: slx
+            - type: sli
+            - type: runbook
+              templateName: vast-k8s-csi-health-taskset.yaml

codebundles/vast-k8s-csi-health/.runwhen/templates/vast-k8s-csi-health-sli.yaml

@@ -0,0 +1,52 @@
+apiVersion: runwhen.com/v1
+kind: ServiceLevelIndicator
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  displayUnitsLong: OK
+  displayUnitsShort: ok
+  locations:
+    - {{default_location}}
+  description: Measures VAST CSI health using CSI pod readiness, PVC binding, mount success, and NFS xprt congestion.
+  codeBundle:
+    {% if repo_url %}
+    repoUrl: {{repo_url}}
+    {% else %}
+    repoUrl: https://github.com/runwhen-contrib/rw-cli-codecollection.git
+    {% endif %}
+    {% if ref %}
+    ref: {{ref}}
+    {% else %}
+    ref: main
+    {% endif %}
+    pathToRobot: codebundles/vast-k8s-csi-health/sli.robot
+  intervalStrategy: intermezzo
+  intervalSeconds: 300
+  configProvided:
+    - name: CONTEXT
+      value: "{{context}}"
+    - name: NAMESPACE
+      value: "{{match_resource.resource.metadata.namespace | default(namespace.name)}}"
+    - name: CSI_NAMESPACE
+      value: "{{ custom.vast_csi_namespace | default('vast-csi') }}"
+    - name: KUBERNETES_DISTRIBUTION_BINARY
+      value: "{{ custom.kubernetes_distribution_binary | default('kubectl') }}"
+    - name: XPRT_PENDING_THRESHOLD
+      value: "{{ custom.xprt_pending_threshold | default('100') }}"
+    - name: RPC_ERROR_RATE_THRESHOLD
+      value: "{{ custom.rpc_error_rate_threshold | default('5') }}"
+  secretsProvided:
+  {% if wb_version %}
+    {% include "kubernetes-auth.yaml" ignore missing %}
+  {% else %}
+    - name: kubeconfig
+      workspaceKey: {{ custom.kubeconfig_secret_name | default("kubeconfig") }}
+  {% endif %}
+  alertConfig:
+    tasks:
+      persona: eager-edgar
+      sessionTTL: 10m

codebundles/vast-k8s-csi-health/.runwhen/templates/vast-k8s-csi-health-slx.yaml

@@ -0,0 +1,27 @@
+apiVersion: runwhen.com/v1
+kind: ServiceLevelX
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  imageURL: https://storage.googleapis.com/runwhen-nonprod-shared-images/icons/kubernetes/resources/labeled/pvc.svg
+  alias: {{namespace.name}} VAST CSI Health
+  asMeasuredBy: Aggregate score from CSI pod readiness, PVC binding, mount health, and NFS xprt metrics.
+  configProvided:
+  - name: OBJECT_NAME
+    value: {{match_resource.resource.metadata.name}}
+  owners:
+  - {{workspace.owner_email}}
+  statement: VAST CSI-backed storage in this namespace should have healthy driver pods, bound PVCs, and successful workload mounts.
+  additionalContext:
+    {% include "kubernetes-hierarchy.yaml" ignore missing %}
+    qualified_name: "{{ match_resource.qualified_name }}"
+  tags:
+    {% include "kubernetes-tags.yaml" ignore missing %}
+    - name: access
+      value: read-only
+    - name: storage
+      value: vast-csi

codebundles/vast-k8s-csi-health/.runwhen/templates/vast-k8s-csi-health-taskset.yaml

@@ -0,0 +1,51 @@
+apiVersion: runwhen.com/v1
+kind: Runbook
+metadata:
+  name: {{slx_name}}
+  labels:
+    {% include "common-labels.yaml" %}
+  annotations:
+    {% include "common-annotations.yaml" %}
+spec:
+  location: {{default_location}}
+  description: Monitors VAST CSI driver health and traces workload storage for the namespace.
+  codeBundle:
+    {% if repo_url %}
+    repoUrl: {{repo_url}}
+    {% else %}
+    repoUrl: https://github.com/runwhen-contrib/rw-cli-codecollection.git
+    {% endif %}
+    {% if ref %}
+    ref: {{ref}}
+    {% else %}
+    ref: main
+    {% endif %}
+    pathToRobot: codebundles/vast-k8s-csi-health/runbook.robot
+  configProvided:
+    - name: CONTEXT
+      value: "{{context}}"
+    - name: NAMESPACE
+      value: "{{match_resource.resource.metadata.namespace | default(namespace.name)}}"
+    - name: CSI_NAMESPACE
+      value: "{{ custom.vast_csi_namespace | default('vast-csi') }}"
+    - name: KUBERNETES_DISTRIBUTION_BINARY
+      value: "{{ custom.kubernetes_distribution_binary | default('kubectl') }}"
+    - name: VAST_VMS_ENDPOINT
+      value: "{{ custom.vast_vms_endpoint | default('') }}"
+    - name: VAST_CLUSTER_NAME
+      value: "{{ custom.vast_cluster_name | default('') }}"
+    - name: XPRT_PENDING_THRESHOLD
+      value: "{{ custom.xprt_pending_threshold | default('100') }}"
+    - name: RPC_ERROR_RATE_THRESHOLD
+      value: "{{ custom.rpc_error_rate_threshold | default('5') }}"
+  secretsProvided:
+  {% if wb_version %}
+    {% include "kubernetes-auth.yaml" ignore missing %}
+  {% else %}
+    - name: kubeconfig
+      workspaceKey: {{ custom.kubeconfig_secret_name | default("kubeconfig") }}
+  {% endif %}
+  {% if custom.vast_vms_credentials_secret_name %}
+    - name: vast_vms_credentials
+      workspaceKey: {{ custom.vast_vms_credentials_secret_name }}
+  {% endif %}

codebundles/vast-k8s-csi-health/.test/README.md

@@ -0,0 +1,18 @@
+# Test infrastructure for vast-k8s-csi-health
+
+Static Kubernetes manifests under `kubernetes/manifest.yaml` create:
+
+- Namespace `test-vast-csi-health`
+- StorageClass `vast-test-sc` with provisioner `csi.vastdata.com`
+- PVC and Deployment referencing VAST storage
+
+## Usage
+
+```bash
+task build-infra          # kubectl apply manifests
+task validate-generation-rules
+task default              # requires pushed commits + RunWhen Local
+task clean
+```
+
+The PVC will remain Pending without a real VAST CSI driver; generation rules still match the StorageClass name and annotations for SLX discovery testing.

codebundles/vast-k8s-csi-health/.test/Taskfile.yaml

@@ -0,0 +1,132 @@
+version: "3"
+
+tasks:
+  default:
+    desc: "Run/refresh config"
+    cmds:
+      - task: check-unpushed-commits
+      - task: generate-rwl-config
+      - task: run-rwl-discovery
+
+  clean:
+    desc: "Run cleanup tasks"
+    cmds:
+      - task: remove-kubernetes-objects
+      - task: delete-slxs
+      - task: clean-rwl-discovery
+
+  build-infra:
+    desc: "Build test infrastructure"
+    cmds:
+      - task: create-kubernetes-objects
+
+  create-kubernetes-objects:
+    desc: "Apply manifests from kubernetes directory using kubectl"
+    cmds:
+      - kubectl apply -f kubernetes/*
+    silent: true
+
+  remove-kubernetes-objects:
+    desc: "Delete kubernetes objects"
+    cmds:
+      - kubectl delete -f kubernetes/* --ignore-not-found
+    silent: true
+
+  check-unpushed-commits:
+    desc: Check if outstanding commits or file updates need to be pushed before testing.
+    vars:
+      BASE_DIR: "../"
+    cmds:
+      - |
+        echo "Checking for uncommitted changes in $BASE_DIR and $BASE_DIR.runwhen, excluding '.test'..."
+        UNCOMMITTED_FILES=$(git diff --name-only HEAD | grep -E "^${BASE_DIR}(\.runwhen|[^/]+)" | grep -v "/\.test/" || true)
+        if [ -n "$UNCOMMITTED_FILES" ]; then
+          echo "Uncommitted changes found:"
+          echo "$UNCOMMITTED_FILES"
+          exit 1
+        fi
+      - |
+        echo "Checking for unpushed commits..."
+        git fetch origin
+        UNPUSHED_FILES=$(git diff --name-only origin/$(git rev-parse --abbrev-ref HEAD) HEAD | grep -E "^${BASE_DIR}(\.runwhen|[^/]+)" | grep -v "/\.test/" || true)
+        if [ -n "$UNPUSHED_FILES" ]; then
+          echo "Unpushed commits found:"
+          echo "$UNPUSHED_FILES"
+          exit 1
+        fi
+    silent: true
+
+  generate-rwl-config:
+    desc: "Generate RunWhen Local configuration (workspaceInfo.yaml)"
+    env:
+      RW_WORKSPACE: '{{.RW_WORKSPACE | default "my-workspace"}}'
+    cmds:
+      - |
+        repo_url=$(git config --get remote.origin.url)
+        branch_name=$(git rev-parse --abbrev-ref HEAD)
+        codebundle=$(basename "$(dirname "$PWD")")
+        namespace=$(yq e 'select(.kind == "Namespace") | .metadata.name' kubernetes/manifest.yaml -N)
+        cat <<EOF > workspaceInfo.yaml
+        workspaceName: "$RW_WORKSPACE"
+        workspaceOwnerEmail: authors@runwhen.com
+        defaultLocation: location-01
+        defaultLOD: none
+        cloudConfig:
+          kubernetes:
+            kubeconfigFile: /shared/kubeconfig
+            namespaceLODs:
+              $namespace: detailed
+            namespaces:
+              - $namespace
+        codeCollections:
+        - repoURL: "$repo_url"
+          branch: "$branch_name"
+          codeBundles: ["$codebundle"]
+        custom:
+          kubeconfig_secret_name: "kubeconfig"
+          kubernetes_distribution_binary: kubectl
+          vast_csi_namespace: vast-csi
+        EOF
+    silent: true
+
+  run-rwl-discovery:
+    desc: "Run RunWhen Local Discovery on test infrastructure"
+    cmds:
+      - |
+        CONTAINER_NAME="RunWhenLocal"
+        docker rm -f $CONTAINER_NAME 2>/dev/null || true
+        sudo rm -rf output || true
+        mkdir -p output && chmod 777 output
+        kubeconfig=$(echo "$RW_FROM_FILE" | jq -r .kubeconfig)
+        docker run --name $CONTAINER_NAME -p 8081:8081 \
+          -v "$(pwd)":/shared -v "$kubeconfig":/shared/kubeconfig \
+          -d ghcr.io/runwhen-contrib/runwhen-local:latest
+        docker exec -w /workspace-builder $CONTAINER_NAME ./run.sh --verbose
+    silent: true
+
+  validate-generation-rules:
+    desc: "Validate YAML files in .runwhen/generation-rules"
+    cmds:
+      - |
+        temp_dir=$(mktemp -d)
+        curl -s -o "$temp_dir/generation-rule-schema.json" \
+          https://raw.githubusercontent.com/runwhen-contrib/runwhen-local/refs/heads/main/src/generation-rule-schema.json
+        for yaml_file in ../.runwhen/generation-rules/*.yaml; do
+          json_file="$temp_dir/$(basename "${yaml_file%.*}.json")"
+          yq -o=json "$yaml_file" > "$json_file"
+          ajv validate -s "$temp_dir/generation-rule-schema.json" -d "$json_file" --spec=draft2020 --strict=false
+        done
+        rm -rf "$temp_dir"
+
+  clean-rwl-discovery:
+    desc: "Clean up RunWhen Local discovery output"
+    cmds:
+      - sudo rm -rf output
+      - rm -f workspaceInfo.yaml
+    silent: true
+
+  delete-slxs:
+    desc: "Placeholder for platform SLX deletion (requires RW API credentials)"
+    cmds:
+      - echo "Configure RW_WORKSPACE, RW_API, and RW_PAT to delete SLXs from the platform."
+    silent: true