[processor/k8sattributes] Add container.image.repo_digests (open-te…

…lemetry#34031) **Description:** Adds support for extracting canonical repo digest image references for a container from k8s attributes **Link to tracking Issue:** open-telemetry#34029 **Testing:** 1. Adds unit tests for extracting the k8s `.imageID` field from container status API if it is of the `reference.Canonical` form, and storing it in a `ImageRepoDigest` string field. (Note: k8s will only ever return one value here, although the semantic conventions for `container.image.repo_digests` define it to be a `Slice`. We convert into a Slice lazily when we populate the pcommon data structure. 2. Adds unit tests for including `container.image.repo_digests` in rules for extraction. 3. Includes `container.image.repo_digests` in the e2e tests for k8sattributes processor. **Documentation:** Added `container.image.repo_digests` as an example of attributes that can be extracted from a container --------- Co-authored-by: Christos Markou <[email protected]>
asreehari-splunk · Aug 6, 2024 · 528678e · 528678e
1 parent e982922
commit 528678e
Show file tree

Hide file tree

Showing 21 changed files with 708 additions and 503 deletions.
diff --git a/.chloggen/container-repo-digests.yaml b/.chloggen/container-repo-digests.yaml
@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: processor/k8sattributes
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Add support for `container.image.repo_digests` metadata
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [34029]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]
diff --git a/processor/k8sattributesprocessor/README.md b/processor/k8sattributesprocessor/README.md
@@ -75,9 +75,11 @@ Additional container level attributes can be extracted provided that certain res
    - k8s.container.name
    - container.image.name
    - container.image.tag
+   - container.image.repo_digests (if k8s CRI populates [repository digest field](https://github.com/open-telemetry/semantic-conventions/blob/v1.26.0/model/registry/container.yaml#L60-L71))
 2. If the `k8s.container.name` resource attribute is provided, the following additional attributes will be available:
    - container.image.name
    - container.image.tag
+   - container.image.repo_digests (if k8s CRI populates [repository digest field](https://github.com/open-telemetry/semantic-conventions/blob/v1.26.0/model/registry/container.yaml#L60-L71))
 3. If the `k8s.container.restart_count` resource attribute is provided, it can be used to associate with a particular container
    instance. If it's not set, the latest container instance will be used:
    - container.id (not added by default, has to be specified in `metadata`)

diff --git a/processor/k8sattributesprocessor/config.go b/processor/k8sattributesprocessor/config.go
@@ -105,7 +105,7 @@ func (cfg *Config) Validate() error {
 			conventions.AttributeK8SNodeName, conventions.AttributeK8SNodeUID,
 			conventions.AttributeK8SContainerName, conventions.AttributeContainerID,
 			conventions.AttributeContainerImageName, conventions.AttributeContainerImageTag,
-			clusterUID:
+			containerImageRepoDigests, clusterUID:
 		default:
 			return fmt.Errorf("\"%s\" is not a supported metadata field", field)
 		}
@@ -143,8 +143,8 @@ type ExtractConfig struct {
 	//   k8s.daemonset.name, k8s.daemonset.uid,
 	//   k8s.job.name, k8s.job.uid, k8s.cronjob.name,
 	//   k8s.statefulset.name, k8s.statefulset.uid,
-	//   k8s.container.name, container.image.name,
-	//   container.image.tag, container.id
+	//   k8s.container.name, container.id, container.image.name,
+	//   container.image.tag, container.image.repo_digests
 	//   k8s.cluster.uid
 	//
 	// Specifying anything other than these values will result in an error.

diff --git a/processor/k8sattributesprocessor/documentation.md b/processor/k8sattributesprocessor/documentation.md
@@ -8,6 +8,7 @@
 | ---- | ----------- | ------ | ------- |
 | container.id | Container ID. Usually a UUID, as for example used to identify Docker containers. The UUID might be abbreviated. Requires k8s.container.restart_count. | Any Str | false |
 | container.image.name | Name of the image the container was built on. Requires container.id or k8s.container.name. | Any Str | true |
+| container.image.repo_digests | Repo digests of the container image as provided by the container runtime. | Any Slice | false |
 | container.image.tag | Container image tag. Requires container.id or k8s.container.name. | Any Str | true |
 | k8s.cluster.uid | Gives cluster uid identified with kube-system namespace | Any Str | false |
 | k8s.container.name | The name of the Container in a Pod template. Requires container.id. | Any Str | false |

diff --git a/processor/k8sattributesprocessor/e2e_test.go b/processor/k8sattributesprocessor/e2e_test.go
diff --git a/processor/k8sattributesprocessor/go.mod b/processor/k8sattributesprocessor/go.mod
@@ -3,6 +3,7 @@ module github.com/open-telemetry/opentelemetry-collector-contrib/processor/k8sat
 go 1.21.0
 
 require (
+	github.com/distribution/reference v0.5.0
 	github.com/google/go-cmp v0.6.0
 	github.com/google/uuid v1.6.0
 	github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal v0.106.1
@@ -38,7 +39,6 @@ require (
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
-	github.com/distribution/reference v0.5.0 // indirect
 	github.com/docker/docker v26.1.5+incompatible // indirect
 	github.com/docker/go-connections v0.5.0 // indirect
 	github.com/docker/go-units v0.5.0 // indirect

diff --git a/processor/k8sattributesprocessor/internal/kube/client.go b/processor/k8sattributesprocessor/internal/kube/client.go
@@ -11,6 +11,7 @@ import (
 	"sync"
 	"time"
 
+	"github.com/distribution/reference"
 	"go.opentelemetry.io/collector/component"
 	"go.opentelemetry.io/collector/featuregate"
 	conventions "go.opentelemetry.io/collector/semconv/v1.6.1"
@@ -572,24 +573,26 @@ func removeUnnecessaryPodData(pod *api_v1.Pod, rules ExtractionRules) *api_v1.Po
 	}
 
 	if needContainerAttributes(rules) {
+		removeUnnecessaryContainerStatus := func(c api_v1.ContainerStatus) api_v1.ContainerStatus {
+			transformedContainerStatus := api_v1.ContainerStatus{
+				Name:         c.Name,
+				ContainerID:  c.ContainerID,
+				RestartCount: c.RestartCount,
+			}
+			if rules.ContainerImageRepoDigests {
+				transformedContainerStatus.ImageID = c.ImageID
+			}
+			return transformedContainerStatus
+		}
+
 		for _, containerStatus := range pod.Status.ContainerStatuses {
 			transformedPod.Status.ContainerStatuses = append(
-				transformedPod.Status.ContainerStatuses,
-				api_v1.ContainerStatus{
-					Name:         containerStatus.Name,
-					ContainerID:  containerStatus.ContainerID,
-					RestartCount: containerStatus.RestartCount,
-				},
+				transformedPod.Status.ContainerStatuses, removeUnnecessaryContainerStatus(containerStatus),
 			)
 		}
 		for _, containerStatus := range pod.Status.InitContainerStatuses {
 			transformedPod.Status.InitContainerStatuses = append(
-				transformedPod.Status.InitContainerStatuses,
-				api_v1.ContainerStatus{
-					Name:         containerStatus.Name,
-					ContainerID:  containerStatus.ContainerID,
-					RestartCount: containerStatus.RestartCount,
-				},
+				transformedPod.Status.InitContainerStatuses, removeUnnecessaryContainerStatus(containerStatus),
 			)
 		}
 
@@ -670,11 +673,26 @@ func (c *WatchClient) extractPodContainersAttributes(pod *api_v1.Pod) PodContain
 			containerID = parts[1]
 		}
 		containers.ByID[containerID] = container
-		if c.Rules.ContainerID {
+		if c.Rules.ContainerID || c.Rules.ContainerImageRepoDigests {
 			if container.Statuses == nil {
 				container.Statuses = map[int]ContainerStatus{}
 			}
-			container.Statuses[int(apiStatus.RestartCount)] = ContainerStatus{containerID}
+			containerStatus := ContainerStatus{}
+			if c.Rules.ContainerID {
+				containerStatus.ContainerID = containerID
+			}
+
+			if c.Rules.ContainerImageRepoDigests {
+				if parsed, err := reference.ParseAnyReference(apiStatus.ImageID); err == nil {
+					switch parsed.(type) {
+					case reference.Canonical:
+						containerStatus.ImageRepoDigest = parsed.String()
+					default:
+					}
+				}
+			}
+
+			container.Statuses[int(apiStatus.RestartCount)] = containerStatus
 		}
 	}
 	return containers
@@ -965,6 +983,7 @@ func needContainerAttributes(rules ExtractionRules) bool {
 	return rules.ContainerImageName ||
 		rules.ContainerName ||
 		rules.ContainerImageTag ||
+		rules.ContainerImageRepoDigests ||
 		rules.ContainerID
 }
 

diff --git a/processor/k8sattributesprocessor/internal/kube/client_test.go b/processor/k8sattributesprocessor/internal/kube/client_test.go
@@ -1488,18 +1488,21 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 				{
 					Name:         "container1",
 					ContainerID:  "docker://container1-id-123",
+					ImageID:      "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da",
 					RestartCount: 0,
 				},
 				{
 					Name:         "container2",
 					ContainerID:  "docker://container2-id-456",
+					ImageID:      "sha256:430ac608abaa332de4ce45d68534447c7a206edc5e98aaff9923ecc12f8a80d9",
 					RestartCount: 2,
 				},
 			},
 			InitContainerStatuses: []api_v1.ContainerStatus{
 				{
 					Name:         "init_container",
-					ContainerID:  "containerd://init-container-id-123",
+					ContainerID:  "containerd://init-container-id-789",
+					ImageID:      "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b",
 					RestartCount: 0,
 				},
 			},
@@ -1537,7 +1540,7 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 				ByID: map[string]*Container{
 					"container1-id-123":     {ImageName: "test/image1"},
 					"container2-id-456":     {ImageName: "example.com:port1/image2"},
-					"init-container-id-123": {ImageName: "test/init-image"},
+					"init-container-id-789": {ImageName: "test/init-image"},
 				},
 				ByName: map[string]*Container{
 					"container1":     {ImageName: "test/image1"},
@@ -1586,9 +1589,9 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
-					"init-container-id-123": {
+					"init-container-id-789": {
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "init-container-id-123"},
+							0: {ContainerID: "init-container-id-789"},
 						},
 					},
 				},
@@ -1605,7 +1608,50 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 					},
 					"init_container": {
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "init-container-id-123"},
+							0: {ContainerID: "init-container-id-789"},
+						},
+					},
+				},
+			},
+		},
+		{
+			name: "container-image-repo-digest-only",
+			rules: ExtractionRules{
+				ContainerImageRepoDigests: true,
+			},
+			pod: &pod,
+			want: PodContainers{
+				ByID: map[string]*Container{
+					"container1-id-123": {
+						Statuses: map[int]ContainerStatus{
+							0: {ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
+						},
+					},
+					"container2-id-456": {
+						Statuses: map[int]ContainerStatus{
+							2: {},
+						},
+					},
+					"init-container-id-789": {
+						Statuses: map[int]ContainerStatus{
+							0: {ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
+						},
+					},
+				},
+				ByName: map[string]*Container{
+					"container1": {
+						Statuses: map[int]ContainerStatus{
+							0: {ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
+						},
+					},
+					"container2": {
+						Statuses: map[int]ContainerStatus{
+							2: {},
+						},
+					},
+					"init_container": {
+						Statuses: map[int]ContainerStatus{
+							0: {ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
 						},
 					},
 				},
@@ -1614,9 +1660,10 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 		{
 			name: "all-container-attributes",
 			rules: ExtractionRules{
-				ContainerImageName: true,
-				ContainerImageTag:  true,
-				ContainerID:        true,
+				ContainerImageName:        true,
+				ContainerImageTag:         true,
+				ContainerID:               true,
+				ContainerImageRepoDigests: true,
 			},
 			pod: &pod,
 			want: PodContainers{
@@ -1625,7 +1672,7 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 						ImageName: "test/image1",
 						ImageTag:  "0.1.0",
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "container1-id-123"},
+							0: {ContainerID: "container1-id-123", ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
 						},
 					},
 					"container2-id-456": {
@@ -1635,11 +1682,11 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 							2: {ContainerID: "container2-id-456"},
 						},
 					},
-					"init-container-id-123": {
+					"init-container-id-789": {
 						ImageName: "test/init-image",
 						ImageTag:  "1.0.2",
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "init-container-id-123"},
+							0: {ContainerID: "init-container-id-789", ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
 						},
 					},
 				},
@@ -1648,7 +1695,7 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 						ImageName: "test/image1",
 						ImageTag:  "0.1.0",
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "container1-id-123"},
+							0: {ContainerID: "container1-id-123", ImageRepoDigest: "docker.io/otel/collector@sha256:55d008bc28344c3178645d40e7d07df30f9d90abe4b53c3fc4e5e9c0295533da"},
 						},
 					},
 					"container2": {
@@ -1662,7 +1709,7 @@ func Test_extractPodContainersAttributes(t *testing.T) {
 						ImageName: "test/init-image",
 						ImageTag:  "1.0.2",
 						Statuses: map[int]ContainerStatus{
-							0: {ContainerID: "init-container-id-123"},
+							0: {ContainerID: "init-container-id-789", ImageRepoDigest: "ghcr.io/initimage1@sha256:42e8ba40f9f70d604684c3a2a0ed321206b7e2e3509fdb2c8836d34f2edfb57b"},
 						},
 					},
 				},

diff --git a/processor/k8sattributesprocessor/internal/kube/kube.go b/processor/k8sattributesprocessor/internal/kube/kube.go
@@ -140,7 +140,8 @@ type Container struct {
 
 // ContainerStatus stores resource attributes for a particular container run defined by k8s pod status.
 type ContainerStatus struct {
-	ContainerID string
+	ContainerID     string
+	ImageRepoDigest string
 }
 
 // Namespace represents a kubernetes namespace.
@@ -194,30 +195,31 @@ type FieldFilter struct {
 // ExtractionRules is used to specify the information that needs to be extracted
 // from pods and added to the spans as tags.
 type ExtractionRules struct {
-	CronJobName        bool
-	DeploymentName     bool
-	DeploymentUID      bool
-	DaemonSetUID       bool
-	DaemonSetName      bool
-	JobUID             bool
-	JobName            bool
-	Namespace          bool
-	PodName            bool
-	PodUID             bool
-	PodHostName        bool
-	PodIP              bool
-	ReplicaSetID       bool
-	ReplicaSetName     bool
-	StatefulSetUID     bool
-	StatefulSetName    bool
-	Node               bool
-	NodeUID            bool
-	StartTime          bool
-	ContainerName      bool
-	ContainerID        bool
-	ContainerImageName bool
-	ContainerImageTag  bool
-	ClusterUID         bool
+	CronJobName               bool
+	DeploymentName            bool
+	DeploymentUID             bool
+	DaemonSetUID              bool
+	DaemonSetName             bool
+	JobUID                    bool
+	JobName                   bool
+	Namespace                 bool
+	PodName                   bool
+	PodUID                    bool
+	PodHostName               bool
+	PodIP                     bool
+	ReplicaSetID              bool
+	ReplicaSetName            bool
+	StatefulSetUID            bool
+	StatefulSetName           bool
+	Node                      bool
+	NodeUID                   bool
+	StartTime                 bool
+	ContainerName             bool
+	ContainerID               bool
+	ContainerImageName        bool
+	ContainerImageRepoDigests bool
+	ContainerImageTag         bool
+	ClusterUID                bool
 
 	Annotations []FieldExtractionRule
 	Labels      []FieldExtractionRule