feat(operator): add Snapshot and SnapshotContent v1alpha1 CRDs

deploy/helm/charts/platform/components/operator/crds/nvidia.com_snapshotcontents.yaml

@@ -0,0 +1,180 @@
+# SPDX-FileCopyrightText: Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  annotations:
+    controller-gen.kubebuilder.io/version: v0.16.4
+    helm.sh/resource-policy: keep
+  name: snapshotcontents.nvidia.com
+spec:
+  group: nvidia.com
+  names:
+    kind: SnapshotContent
+    listKind: SnapshotContentList
+    plural: snapshotcontents
+    shortNames:
+      - snapcontent
+    singular: snapshotcontent
+  scope: Cluster
+  versions:
+    - additionalPrinterColumns:
+        - description: Bound Snapshot
+          jsonPath: .spec.snapshotRef.name
+          name: Snapshot
+          type: string
+        - description: Snapshot namespace
+          jsonPath: .spec.snapshotRef.namespace
+          name: Namespace
+          type: string
+        - description: Ready condition
+          jsonPath: .status.conditions[?(@.type=='Ready')].status
+          name: Ready
+          type: string
+        - jsonPath: .metadata.creationTimestamp
+          name: Age
+          type: date
+      name: v1alpha1
+      schema:
+        openAPIV3Schema:
+          description: |-
+            SnapshotContent is the Schema for the snapshotcontents API. It is the
+            cluster-scoped artifact-of-record for a captured container checkpoint.
+          properties:
+            apiVersion:
+              description: |-
+                APIVersion defines the versioned schema of this representation of an object.
+                Servers should convert recognized schemas to the latest internal value, and
+                may reject unrecognized values.
+                More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
+              type: string
+            kind:
+              description: |-
+                Kind is a string value representing the REST resource this object represents.
+                Servers may infer this from the endpoint the client submits requests to.
+                Cannot be updated.
+                In CamelCase.
+                More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
+              type: string
+            metadata:
+              type: object
+            spec:
+              description: |-
+                SnapshotContentSpec defines the desired state of SnapshotContent. It is
+                populated by the node agent at creation time and is immutable thereafter.
+              properties:
+                snapshotRef:
+                  description: |-
+                    SnapshotRef is the back-pointer to the bound Snapshot. It may span
+                    namespaces because SnapshotContent is cluster-scoped.
+                  properties:
+                    name:
+                      description: Name of the referenced Snapshot.
+                      type: string
+                    namespace:
+                      description: Namespace of the referenced Snapshot.
+                      type: string
+                    uid:
+                      description: |-
+                        UID of the referenced Snapshot, recorded at binding time to detect a
+                        stale reference after a delete and recreate.
+                      type: string
+                  required:
+                    - name
+                    - namespace
+                  type: object
+                source:
+                  description: Source locates the physical artifact via a self-contained, opaque handle.
+                  properties:
+                    snapshotHandle:
+                      description: |-
+                        SnapshotHandle is a self-contained, opaque artifact locator. The v1alpha1
+                        PVC format is:
+                          pvc://<namespace>/<claimName>/<basePath>/<checkpointID>/versions/<version>
+                        It fully locates the artifact without correlating any other field.
+                      minLength: 1
+                      type: string
+                  required:
+                    - snapshotHandle
+                  type: object
+              required:
+                - snapshotRef
+                - source
+              type: object
+            status:
+              description: SnapshotContentStatus defines the observed state of SnapshotContent.
+              properties:
+                conditions:
+                  description: |-
+                    Conditions reflect the latest observations of the SnapshotContent's state.
+                    Standard types are Ready and Failed.
+                  items:
+                    description: Condition contains details for one aspect of the current state of this API Resource.
+                    properties:
+                      lastTransitionTime:
+                        description: |-
+                          lastTransitionTime is the last time the condition transitioned from one status to another.
+                          This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                        format: date-time
+                        type: string
+                      message:
+                        description: |-
+                          message is a human readable message indicating details about the transition.
+                          This may be an empty string.
+                        maxLength: 32768
+                        type: string
+                      observedGeneration:
+                        description: |-
+                          observedGeneration represents the .metadata.generation that the condition was set based upon.
+                          For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                          with respect to the current state of the instance.
+                        format: int64
+                        minimum: 0
+                        type: integer
+                      reason:
+                        description: |-
+                          reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                          Producers of specific condition types may define expected values and meanings for this field,
+                          and whether the values are considered a guaranteed API.
+                          The value should be a CamelCase string.
+                          This field may not be empty.
+                        maxLength: 1024
+                        minLength: 1
+                        pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                        type: string
+                      status:
+                        description: status of the condition, one of True, False, Unknown.
+                        enum:
+                          - "True"
+                          - "False"
+                          - Unknown
+                        type: string
+                      type:
+                        description: type of condition in CamelCase or in foo.example.com/CamelCase.
+                        maxLength: 316
+                        pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                        type: string
+                    required:
+                      - lastTransitionTime
+                      - message
+                      - reason
+                      - status
+                      - type
+                    type: object
+                  type: array
+                snapshotHandle:
+                  description: |-
+                    SnapshotHandle mirrors spec.source.snapshotHandle once the node agent has
+                    verified the artifact.
+                  type: string
+              type: object
+          type: object
+          x-kubernetes-validations:
+            - message: spec is immutable
+              rule: '!has(oldSelf.spec) || self.spec == oldSelf.spec'
+      served: true
+      storage: true
+      subresources:
+        status: {}

deploy/helm/charts/platform/components/operator/crds/nvidia.com_snapshots.yaml

@@ -0,0 +1,182 @@
+# SPDX-FileCopyrightText: Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  annotations:
+    controller-gen.kubebuilder.io/version: v0.16.4
+    helm.sh/resource-policy: keep
+  name: snapshots.nvidia.com
+spec:
+  group: nvidia.com
+  names:
+    kind: Snapshot
+    listKind: SnapshotList
+    plural: snapshots
+    shortNames:
+      - snap
+    singular: snapshot
+  scope: Namespaced
+  versions:
+    - additionalPrinterColumns:
+        - description: Artifact identity
+          jsonPath: .spec.checkpointID
+          name: CheckpointID
+          type: string
+        - description: Bound SnapshotContent
+          jsonPath: .status.boundSnapshotContentName
+          name: Content
+          type: string
+        - description: Ready condition
+          jsonPath: .status.conditions[?(@.type=='Ready')].status
+          name: Ready
+          type: string
+        - jsonPath: .metadata.creationTimestamp
+          name: Age
+          type: date
+      name: v1alpha1
+      schema:
+        openAPIV3Schema:
+          description: |-
+            Snapshot is the Schema for the snapshots API. It is the namespaced binding
+            for a captured container checkpoint and is consumed by restore paths.
+          properties:
+            apiVersion:
+              description: |-
+                APIVersion defines the versioned schema of this representation of an object.
+                Servers should convert recognized schemas to the latest internal value, and
+                may reject unrecognized values.
+                More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
+              type: string
+            kind:
+              description: |-
+                Kind is a string value representing the REST resource this object represents.
+                Servers may infer this from the endpoint the client submits requests to.
+                Cannot be updated.
+                In CamelCase.
+                More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
+              type: string
+            metadata:
+              type: object
+            spec:
+              description: |-
+                SnapshotSpec defines the desired state of Snapshot.
+
+                Minimal "trigger" shape: it names what to capture (an existing pod) and the
+                artifact identity (CheckpointID). Capture parameters the node agent needs at
+                dump time (target container, storage base path) are read from the referenced
+                pod's existing annotations and mounts, not duplicated here. The spec is
+                immutable after creation.
+              properties:
+                checkpointID:
+                  description: |-
+                    CheckpointID is the stable artifact identity and the on-PVC artifact
+                    subdirectory name (<basePath>/<checkpointID>/versions/<version>/). It is
+                    the primary key of the storage contract shared with the restore path and
+                    is immutable after creation.
+                  maxLength: 253
+                  minLength: 1
+                  type: string
+                source:
+                  description: |-
+                    Source identifies the captured workload. It is a struct (rather than an
+                    inlined reference) so future source variants can be added additively.
+                  properties:
+                    podRef:
+                      description: |-
+                        PodRef references the pod, in the Snapshot's namespace, that is captured.
+                        The operator prepares the pod (control volume, target-container annotation,
+                        checkpoint storage mount) before creating the Snapshot.
+                      properties:
+                        name:
+                          description: Name of the source pod.
+                          minLength: 1
+                          type: string
+                      required:
+                        - name
+                      type: object
+                  required:
+                    - podRef
+                  type: object
+              required:
+                - checkpointID
+                - source
+              type: object
+            status:
+              description: SnapshotStatus defines the observed state of Snapshot.
+              properties:
+                boundSnapshotContentName:
+                  description: |-
+                    BoundSnapshotContentName is the name of the cluster-scoped SnapshotContent
+                    this Snapshot is bound to. It is nil until the agent has created the
+                    content and recorded the binding.
+                  type: string
+                conditions:
+                  description: |-
+                    Conditions reflect the latest observations of the Snapshot's state.
+                    Standard types are Ready and Failed.
+                  items:
+                    description: Condition contains details for one aspect of the current state of this API Resource.
+                    properties:
+                      lastTransitionTime:
+                        description: |-
+                          lastTransitionTime is the last time the condition transitioned from one status to another.
+                          This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                        format: date-time
+                        type: string
+                      message:
+                        description: |-
+                          message is a human readable message indicating details about the transition.
+                          This may be an empty string.
+                        maxLength: 32768
+                        type: string
+                      observedGeneration:
+                        description: |-
+                          observedGeneration represents the .metadata.generation that the condition was set based upon.
+                          For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                          with respect to the current state of the instance.
+                        format: int64
+                        minimum: 0
+                        type: integer
+                      reason:
+                        description: |-
+                          reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                          Producers of specific condition types may define expected values and meanings for this field,
+                          and whether the values are considered a guaranteed API.
+                          The value should be a CamelCase string.
+                          This field may not be empty.
+                        maxLength: 1024
+                        minLength: 1
+                        pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                        type: string
+                      status:
+                        description: status of the condition, one of True, False, Unknown.
+                        enum:
+                          - "True"
+                          - "False"
+                          - Unknown
+                        type: string
+                      type:
+                        description: type of condition in CamelCase or in foo.example.com/CamelCase.
+                        maxLength: 316
+                        pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                        type: string
+                    required:
+                      - lastTransitionTime
+                      - message
+                      - reason
+                      - status
+                      - type
+                    type: object
+                  type: array
+              type: object
+          type: object
+          x-kubernetes-validations:
+            - message: spec is immutable
+              rule: '!has(oldSelf.spec) || self.spec == oldSelf.spec'
+      served: true
+      storage: true
+      subresources:
+        status: {}