Merge branch 'infraM/pod_status_restart_counts' into infraM/goroutines_for_concurrent_queries

docs/api/openapi.yml

@@ -4251,6 +4251,8 @@ components:
           $ref: '#/components/schemas/InframonitoringtypesNodeCountsByReadiness'
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
       required:
       - clusterName
       - clusterCPU
@@ -4259,6 +4261,7 @@ components:
       - clusterMemoryAllocatable
       - nodeCountsByReadiness
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesClusters:
@@ -4314,6 +4317,8 @@ components:
           type: object
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
       required:
       - daemonSetName
       - daemonSetCPU
@@ -4325,6 +4330,7 @@ components:
       - desiredNodes
       - currentNodes
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesDaemonSets:
@@ -4380,6 +4386,8 @@ components:
           type: object
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
       required:
       - deploymentName
       - deploymentCPU
@@ -4391,6 +4399,7 @@ components:
       - desiredPods
       - availablePods
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesDeployments:
@@ -4523,6 +4532,8 @@ components:
           type: object
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
         successfulPods:
           type: integer
       required:
@@ -4538,6 +4549,7 @@ components:
       - failedPods
       - successfulPods
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesJobs:
@@ -4628,11 +4640,14 @@ components:
           type: string
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
       required:
       - namespaceName
       - namespaceCPU
       - namespaceMemory
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesNamespaces:
@@ -4698,11 +4713,14 @@ components:
           type: string
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
       required:
       - nodeName
       - condition
       - nodeCountsByReadiness
       - podCountsByPhase
+      - podCountsByStatus
       - nodeCPU
       - nodeCPUAllocatable
       - nodeMemory
@@ -4748,6 +4766,64 @@ components:
       - failed
       - unknown
       type: object
+    InframonitoringtypesPodCountsByStatus:
+      properties:
+        completed:
+          type: integer
+        containerCannotRun:
+          type: integer
+        containerCreating:
+          type: integer
+        crashLoopBackOff:
+          type: integer
+        createContainerConfigError:
+          type: integer
+        errImagePull:
+          type: integer
+        error:
+          type: integer
+        evicted:
+          type: integer
+        failed:
+          type: integer
+        imagePullBackOff:
+          type: integer
+        nodeAffinity:
+          type: integer
+        nodeLost:
+          type: integer
+        oomKilled:
+          type: integer
+        pending:
+          type: integer
+        running:
+          type: integer
+        shutdown:
+          type: integer
+        unexpectedAdmissionError:
+          type: integer
+        unknown:
+          type: integer
+      required:
+      - pending
+      - running
+      - failed
+      - unknown
+      - crashLoopBackOff
+      - imagePullBackOff
+      - errImagePull
+      - createContainerConfigError
+      - containerCreating
+      - oomKilled
+      - completed
+      - error
+      - containerCannotRun
+      - evicted
+      - nodeAffinity
+      - nodeLost
+      - shutdown
+      - unexpectedAdmissionError
+      type: object
     InframonitoringtypesPodPhase:
       enum:
       - pending
@@ -4778,6 +4854,8 @@ components:
           type: number
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
         podMemory:
           format: double
           type: number
@@ -4789,6 +4867,11 @@ components:
           type: number
         podPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodPhase'
+        podRestarts:
+          format: int64
+          type: integer
+        podStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodStatus'
         podUID:
           type: string
       required:
@@ -4801,9 +4884,34 @@ components:
       - podMemoryLimit
       - podPhase
       - podCountsByPhase
+      - podStatus
+      - podCountsByStatus
+      - podRestarts
       - podAge
       - meta
       type: object
+    InframonitoringtypesPodStatus:
+      enum:
+      - pending
+      - running
+      - failed
+      - unknown
+      - crashloopbackoff
+      - imagepullbackoff
+      - errimagepull
+      - createcontainerconfigerror
+      - containercreating
+      - oomkilled
+      - completed
+      - error
+      - containercannotrun
+      - evicted
+      - nodeaffinity
+      - nodelost
+      - shutdown
+      - unexpectedadmissionerror
+      - no_data
+      type: string
     InframonitoringtypesPods:
       properties:
         endTimeBeforeRetention:
@@ -5102,6 +5210,8 @@ components:
           type: object
         podCountsByPhase:
           $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
+        podCountsByStatus:
+          $ref: '#/components/schemas/InframonitoringtypesPodCountsByStatus'
         statefulSetCPU:
           format: double
           type: number
@@ -5133,6 +5243,7 @@ components:
       - desiredPods
       - currentPods
       - podCountsByPhase
+      - podCountsByStatus
       - meta
       type: object
     InframonitoringtypesStatefulSets:

frontend/src/api/generated/services/sigNoz.schemas.ts

@@ -5693,6 +5693,81 @@ export interface InframonitoringtypesPodCountsByPhaseDTO {
 	unknown: number;
 }
 
+export interface InframonitoringtypesPodCountsByStatusDTO {
+	/**
+	 * @type integer
+	 */
+	completed: number;
+	/**
+	 * @type integer
+	 */
+	containerCannotRun: number;
+	/**
+	 * @type integer
+	 */
+	containerCreating: number;
+	/**
+	 * @type integer
+	 */
+	crashLoopBackOff: number;
+	/**
+	 * @type integer
+	 */
+	createContainerConfigError: number;
+	/**
+	 * @type integer
+	 */
+	errImagePull: number;
+	/**
+	 * @type integer
+	 */
+	error: number;
+	/**
+	 * @type integer
+	 */
+	evicted: number;
+	/**
+	 * @type integer
+	 */
+	failed: number;
+	/**
+	 * @type integer
+	 */
+	imagePullBackOff: number;
+	/**
+	 * @type integer
+	 */
+	nodeAffinity: number;
+	/**
+	 * @type integer
+	 */
+	nodeLost: number;
+	/**
+	 * @type integer
+	 */
+	oomKilled: number;
+	/**
+	 * @type integer
+	 */
+	pending: number;
+	/**
+	 * @type integer
+	 */
+	running: number;
+	/**
+	 * @type integer
+	 */
+	shutdown: number;
+	/**
+	 * @type integer
+	 */
+	unexpectedAdmissionError: number;
+	/**
+	 * @type integer
+	 */
+	unknown: number;
+}
+
 export interface InframonitoringtypesClusterRecordDTO {
 	/**
 	 * @type number
@@ -5724,6 +5799,7 @@ export interface InframonitoringtypesClusterRecordDTO {
 	meta: InframonitoringtypesClusterRecordDTOMeta;
 	nodeCountsByReadiness: InframonitoringtypesNodeCountsByReadinessDTO;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 }
 
 export enum InframonitoringtypesResponseTypeDTO {
@@ -5827,6 +5903,7 @@ export interface InframonitoringtypesDaemonSetRecordDTO {
 	 */
 	meta: InframonitoringtypesDaemonSetRecordDTOMeta;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 }
 
 export interface InframonitoringtypesDaemonSetsDTO {
@@ -5904,6 +5981,7 @@ export interface InframonitoringtypesDeploymentRecordDTO {
 	 */
 	meta: InframonitoringtypesDeploymentRecordDTOMeta;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 }
 
 export interface InframonitoringtypesDeploymentsDTO {
@@ -6070,6 +6148,7 @@ export interface InframonitoringtypesJobRecordDTO {
 	 */
 	meta: InframonitoringtypesJobRecordDTOMeta;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 	/**
 	 * @type integer
 	 */
@@ -6123,6 +6202,7 @@ export interface InframonitoringtypesNamespaceRecordDTO {
 	 */
 	namespaceName: string;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 }
 
 export interface InframonitoringtypesNamespacesDTO {
@@ -6189,6 +6269,7 @@ export interface InframonitoringtypesNodeRecordDTO {
 	 */
 	nodeName: string;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 }
 
 export interface InframonitoringtypesNodesDTO {
@@ -6226,6 +6307,27 @@ export type InframonitoringtypesPodRecordDTOMetaAnyOf = {
 export type InframonitoringtypesPodRecordDTOMeta =
 	InframonitoringtypesPodRecordDTOMetaAnyOf | null;
 
+export enum InframonitoringtypesPodStatusDTO {
+	pending = 'pending',
+	running = 'running',
+	failed = 'failed',
+	unknown = 'unknown',
+	crashloopbackoff = 'crashloopbackoff',
+	imagepullbackoff = 'imagepullbackoff',
+	errimagepull = 'errimagepull',
+	createcontainerconfigerror = 'createcontainerconfigerror',
+	containercreating = 'containercreating',
+	oomkilled = 'oomkilled',
+	completed = 'completed',
+	error = 'error',
+	containercannotrun = 'containercannotrun',
+	evicted = 'evicted',
+	nodeaffinity = 'nodeaffinity',
+	nodelost = 'nodelost',
+	shutdown = 'shutdown',
+	unexpectedadmissionerror = 'unexpectedadmissionerror',
+	no_data = 'no_data',
+}
 export interface InframonitoringtypesPodRecordDTO {
 	/**
 	 * @type object,null
@@ -6252,6 +6354,7 @@ export interface InframonitoringtypesPodRecordDTO {
 	 */
 	podCPURequest: number;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 	/**
 	 * @type number
 	 * @format double
@@ -6268,6 +6371,12 @@ export interface InframonitoringtypesPodRecordDTO {
 	 */
 	podMemoryRequest: number;
 	podPhase: InframonitoringtypesPodPhaseDTO;
+	/**
+	 * @type integer
+	 * @format int64
+	 */
+	podRestarts: number;
+	podStatus: InframonitoringtypesPodStatusDTO;
 	/**
 	 * @type string
 	 */
@@ -6585,6 +6694,7 @@ export interface InframonitoringtypesStatefulSetRecordDTO {
 	 */
 	meta: InframonitoringtypesStatefulSetRecordDTOMeta;
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
+	podCountsByStatus: InframonitoringtypesPodCountsByStatusDTO;
 	/**
 	 * @type number
 	 * @format double

pkg/modules/inframonitoring/implinframonitoring/checks_constants.go

@@ -117,8 +117,16 @@ var podsSpec = checkSpec{
 			DocumentationLink: docLinkKubeletStatsReceiver,
 		},
 		{
-			Component:         componentK8sClusterReceiver,
-			DefaultMetrics:    []string{"k8s.pod.phase"},
+			Component: componentK8sClusterReceiver,
+			DefaultMetrics: []string{
+				"k8s.pod.phase",
+				"k8s.container.restarts", // pod restart count (default-on)
+			},
+			OptionalMetrics: []string{
+				// kubectl-style pod display status (default-off in the receiver).
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -149,6 +157,10 @@ var nodesSpec = checkSpec{
 				//  By default, only k8s.node.condition_ready is enabled. (Check https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/4f9a578b210a6dcb9f9bf47942f27208b5765298/receiver/k8sclusterreceiver/metadata.yaml#L802)
 				"k8s.pod.phase", // pod counts per node by phase
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -182,6 +194,10 @@ var deploymentsSpec = checkSpec{
 				"k8s.deployment.desired",
 				"k8s.deployment.available",
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -220,6 +236,10 @@ var daemonsetsSpec = checkSpec{
 				"k8s.daemonset.desired_scheduled_nodes",
 				"k8s.daemonset.current_scheduled_nodes",
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -258,6 +278,10 @@ var statefulsetsSpec = checkSpec{
 				"k8s.statefulset.desired_pods",
 				"k8s.statefulset.current_pods",
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -298,6 +322,10 @@ var jobsSpec = checkSpec{
 				"k8s.job.failed_pods",
 				"k8s.job.successful_pods",
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -324,8 +352,12 @@ var namespacesSpec = checkSpec{
 			DocumentationLink: docLinkKubeletStatsReceiver,
 		},
 		{
-			Component:         componentK8sClusterReceiver,
-			DefaultMetrics:    []string{"k8s.pod.phase"},
+			Component:      componentK8sClusterReceiver,
+			DefaultMetrics: []string{"k8s.pod.phase"},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{
@@ -360,6 +392,10 @@ var clustersSpec = checkSpec{
 				"k8s.node.condition_ready", // node counts by readiness
 				"k8s.pod.phase",            // pod counts per cluster by phase
 			},
+			OptionalMetrics: []string{
+				"k8s.pod.status_reason",
+				"k8s.container.status.reason",
+			},
 			DocumentationLink: docLinkK8sClusterReceiver,
 		},
 		{

pkg/modules/inframonitoring/implinframonitoring/clusters.go

@@ -20,6 +20,7 @@ func buildClusterRecords(
 	metadataMap map[string]map[string]string,
 	nodeConditionCountsMap map[string]nodeConditionCounts,
 	podPhaseCountsMap map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.ClusterRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -69,6 +70,10 @@ func buildClusterRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/clusters_constants.go

@@ -27,6 +27,8 @@ var clustersTableMetricNamesList = []string{
 	"k8s.node.allocatable_memory",
 	"k8s.node.condition_ready", //TODO(nikhilmantri0902): should these metrics be used to count groups k8s.node.condition_ready and k8s.pod.phase
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 }
 
 var clusterAttrKeysForMetadata = []string{

pkg/modules/inframonitoring/implinframonitoring/daemonsets.go

@@ -19,6 +19,7 @@ func buildDaemonSetRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.DaemonSetRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -77,6 +78,10 @@ func buildDaemonSetRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/daemonsets_constants.go

@@ -23,6 +23,8 @@ var daemonSetNameGroupByKey = qbtypes.GroupByKey{
 // response to short-circuit cleanly when the phase metric is absent.
 var daemonSetsTableMetricNamesList = []string{
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 	"k8s.pod.cpu.usage",
 	"k8s.pod.cpu_request_utilization",
 	"k8s.pod.cpu_limit_utilization",

pkg/modules/inframonitoring/implinframonitoring/deployments.go

@@ -19,6 +19,7 @@ func buildDeploymentRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.DeploymentRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -77,6 +78,10 @@ func buildDeploymentRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/deployments_constants.go

@@ -23,6 +23,8 @@ var deploymentNameGroupByKey = qbtypes.GroupByKey{
 // response to short-circuit cleanly when the phase metric is absent.
 var deploymentsTableMetricNamesList = []string{
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 	"k8s.pod.cpu.usage",
 	"k8s.pod.cpu_request_utilization",
 	"k8s.pod.cpu_limit_utilization",

pkg/modules/inframonitoring/implinframonitoring/helpers.go

@@ -440,6 +440,30 @@ func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter,
 	return whereClause.WhereClause, nil
 }
 
+// mergeQueryWarnings combines any number of query warnings. It is nil-safe and
+// skips nil entries. The first non-nil warning becomes the primary; each
+// subsequent one contributes its message (as an additional warning) and its
+// own additional warnings. Returns nil when all inputs are nil.
+func mergeQueryWarnings(warnings ...*qbtypes.QueryWarnData) *qbtypes.QueryWarnData {
+	var merged *qbtypes.QueryWarnData
+	for _, w := range warnings {
+		if w == nil {
+			continue
+		}
+		if merged == nil {
+			// Copy so we don't mutate the caller's warning.
+			primary := *w
+			merged = &primary
+			continue
+		}
+		if w.Message != "" {
+			merged.Warnings = append(merged.Warnings, qbtypes.QueryWarnDataAdditional{Message: w.Message})
+		}
+		merged.Warnings = append(merged.Warnings, w.Warnings...)
+	}
+	return merged
+}
+
 // NOTE: this method is not specific to infra monitoring — it queries attributes_metadata generically.
 // Consider moving to telemetryMetaStore when a second use case emerges.
 //

pkg/modules/inframonitoring/implinframonitoring/internaltypes.go

@@ -26,6 +26,60 @@ type podPhaseCounts struct {
 	Unknown   int
 }
 
+// podStatusCounts holds per-group pod counts bucketed by latest kubectl-style
+// display status in window. Mirrors inframonitoringtypes.PodCountsByStatus.
+type podStatusCounts struct {
+	// Phase fallback.
+	Pending int
+	Running int
+	Failed  int
+	Unknown int
+
+	// Container-level reasons.
+	CrashLoopBackOff           int
+	ImagePullBackOff           int
+	ErrImagePull               int
+	CreateContainerConfigError int
+	ContainerCreating          int
+	OOMKilled                  int
+	Completed                  int
+	Error                      int
+	ContainerCannotRun         int
+
+	// Pod-level reasons.
+	Evicted                  int
+	NodeAffinity             int
+	NodeLost                 int
+	Shutdown                 int
+	UnexpectedAdmissionError int
+}
+
+// podStatusCountsToResponse copies the internal per-group status counts into the
+// public response struct. Shared by every entity that surfaces pod status
+// counts (pods, nodes, namespaces, clusters, workloads).
+func podStatusCountsToResponse(podStatuses podStatusCounts) inframonitoringtypes.PodCountsByStatus {
+	return inframonitoringtypes.PodCountsByStatus{
+		Pending:                    podStatuses.Pending,
+		Running:                    podStatuses.Running,
+		Failed:                     podStatuses.Failed,
+		Unknown:                    podStatuses.Unknown,
+		CrashLoopBackOff:           podStatuses.CrashLoopBackOff,
+		ImagePullBackOff:           podStatuses.ImagePullBackOff,
+		ErrImagePull:               podStatuses.ErrImagePull,
+		CreateContainerConfigError: podStatuses.CreateContainerConfigError,
+		ContainerCreating:          podStatuses.ContainerCreating,
+		OOMKilled:                  podStatuses.OOMKilled,
+		Completed:                  podStatuses.Completed,
+		Error:                      podStatuses.Error,
+		ContainerCannotRun:         podStatuses.ContainerCannotRun,
+		Evicted:                    podStatuses.Evicted,
+		NodeAffinity:               podStatuses.NodeAffinity,
+		NodeLost:                   podStatuses.NodeLost,
+		Shutdown:                   podStatuses.Shutdown,
+		UnexpectedAdmissionError:   podStatuses.UnexpectedAdmissionError,
+	}
+}
+
 // nodeConditionCounts holds per-group node counts bucketed by latest condition_ready in window.
 type nodeConditionCounts struct {
 	Ready    int

pkg/modules/inframonitoring/implinframonitoring/jobs.go

@@ -19,6 +19,7 @@ func buildJobRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.JobRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -85,6 +86,10 @@ func buildJobRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/jobs_constants.go

@@ -23,6 +23,8 @@ var jobNameGroupByKey = qbtypes.GroupByKey{
 // response to short-circuit cleanly when the phase metric is absent.
 var jobsTableMetricNamesList = []string{
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 	"k8s.pod.cpu.usage",
 	"k8s.pod.cpu_request_utilization",
 	"k8s.pod.cpu_limit_utilization",

pkg/modules/inframonitoring/implinframonitoring/module.go

@@ -17,6 +17,7 @@ import (
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
+	"golang.org/x/sync/errgroup"
 )
 
 type module struct {
@@ -213,23 +214,37 @@ func (m *module) ListHosts(ctx context.Context, orgID valuer.UUID, req *inframon
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, hostsFilterExpr, req.GroupBy, pageGroups, m.newListHostsQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
 	// Compute per-group active/inactive host counts.
 	// When host.name is in groupBy, each row = one host, so counts are derived
 	// directly from activeHostsMap in buildHostRecords (no extra query needed).
 	// When host.name is not in groupBy, we need to run an additional query to get the counts per group for the current page,
 	// using the same filter expression as the main query (including user filters + page groups IN clause).
-	hostCounts := make(map[string]groupHostStatusCounts)
 	isHostNameInGroupBy := isKeyInGroupByAttrs(req.GroupBy, inframonitoringtypes.HostNameAttrKey)
+
+	var (
+		queryResp  *qbtypes.QueryRangeResponse
+		hostCounts = make(map[string]groupHostStatusCounts)
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+
 	if !isHostNameInGroupBy {
-		hostCounts, err = m.getPerGroupHostStatusCounts(ctx, orgID, req, hostsTableMetricNamesList, pageGroups, sinceUnixMilli)
-		if err != nil {
-			return nil, err
-		}
+		g.Go(func() error {
+			var err error
+			hostCounts, err = m.getPerGroupHostStatusCounts(gCtx, orgID, req, hostsTableMetricNamesList, pageGroups, sinceUnixMilli)
+			return err
+		})
+	}
+
+	if err := g.Wait(); err != nil {
+		return nil, err
 	}
 
 	resp.Records = buildHostRecords(isHostNameInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, activeHostsMap, hostCounts)
@@ -299,19 +314,45 @@ func (m *module) ListPods(ctx context.Context, orgID valuer.UUID, req *inframoni
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newPodsTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	var (
+		queryResp     *qbtypes.QueryRangeResponse
+		phaseCounts   map[string]podPhaseCounts
+		statusCounts  map[string]podStatusCounts
+		statusWarning *qbtypes.QueryWarnData
+		restartCounts map[string]int64
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		statusCounts, statusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		restartCounts, err = m.getPerGroupPodRestartCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
 	isPodUIDInGroupBy := isKeyInGroupByAttrs(req.GroupBy, podUIDAttrKey)
-	resp.Records = buildPodRecords(isPodUIDInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, req.End)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildPodRecords(isPodUIDInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, statusCounts, restartCounts, req.End)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, statusWarning)
 
 	return resp, nil
 }
@@ -377,24 +418,45 @@ func (m *module) ListNodes(ctx context.Context, orgID valuer.UUID, req *inframon
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newNodesTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
-	nodeConditionCounts, err := m.getPerGroupNodeConditionCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
-		return nil, err
-	}
+	var (
+		queryResp           *qbtypes.QueryRangeResponse
+		nodeConditionCounts map[string]nodeConditionCounts
+		podPhaseCounts      map[string]podPhaseCounts
+		podStatusCounts     map[string]podStatusCounts
+		podStatusWarning    *qbtypes.QueryWarnData
+	)
 
-	podPhaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		nodeConditionCounts, err = m.getPerGroupNodeConditionCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podPhaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
 	isNodeNameInGroupBy := isKeyInGroupByAttrs(req.GroupBy, inframonitoringtypes.NodeNameAttrKey)
-	resp.Records = buildNodeRecords(isNodeNameInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCounts, podPhaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildNodeRecords(isNodeNameInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCounts, podPhaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -460,18 +522,38 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newNamespacesTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
+
+	var (
+		queryResp        *qbtypes.QueryRangeResponse
+		phaseCounts      map[string]podPhaseCounts
+		podStatusCounts  map[string]podStatusCounts
+		podStatusWarning *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	resp.Records = buildNamespaceRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildNamespaceRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -537,25 +619,46 @@ func (m *module) ListClusters(ctx context.Context, orgID valuer.UUID, req *infra
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newClustersTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
 	// With default groupBy [k8s.cluster.name], counts are bucketed per cluster;
 	// with a custom groupBy, they aggregate across clusters in that group.
-	nodeConditionCountsMap, err := m.getPerGroupNodeConditionCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	var (
+		queryResp              *qbtypes.QueryRangeResponse
+		nodeConditionCountsMap map[string]nodeConditionCounts
+		podPhaseCountsMap      map[string]podPhaseCounts
+		podStatusCounts        map[string]podStatusCounts
+		podStatusWarning       *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		nodeConditionCountsMap, err = m.getPerGroupNodeConditionCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podPhaseCountsMap, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	podPhaseCountsMap, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	resp.Records = buildClusterRecords(queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCountsMap, podPhaseCountsMap)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildClusterRecords(queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCountsMap, podPhaseCountsMap, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -705,18 +808,38 @@ func (m *module) ListDeployments(ctx context.Context, orgID valuer.UUID, req *in
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newDeploymentsTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
+
+	var (
+		queryResp        *qbtypes.QueryRangeResponse
+		phaseCounts      map[string]podPhaseCounts
+		podStatusCounts  map[string]podStatusCounts
+		podStatusWarning *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	resp.Records = buildDeploymentRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildDeploymentRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -788,20 +911,40 @@ func (m *module) ListStatefulSets(ctx context.Context, orgID valuer.UUID, req *i
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newStatefulSetsTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
 	// Pods owned by a StatefulSet carry k8s.statefulset.name as a resource attribute,
 	// so default-groupBy gives per-statefulset phase counts automatically.
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	var (
+		queryResp        *qbtypes.QueryRangeResponse
+		phaseCounts      map[string]podPhaseCounts
+		podStatusCounts  map[string]podStatusCounts
+		podStatusWarning *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	resp.Records = buildStatefulSetRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildStatefulSetRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -873,20 +1016,40 @@ func (m *module) ListJobs(ctx context.Context, orgID valuer.UUID, req *inframoni
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newJobsTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
 	// Pods owned by a Job carry k8s.job.name as a resource attribute, so default-groupBy
 	// gives per-job phase counts automatically.
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	var (
+		queryResp        *qbtypes.QueryRangeResponse
+		phaseCounts      map[string]podPhaseCounts
+		podStatusCounts  map[string]podStatusCounts
+		podStatusWarning *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	resp.Records = buildJobRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildJobRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }
@@ -958,20 +1121,40 @@ func (m *module) ListDaemonSets(ctx context.Context, orgID valuer.UUID, req *inf
 	}
 
 	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newDaemonSetsTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
 
 	// Pods owned by a DaemonSet carry k8s.daemonset.name as a resource attribute,
 	// so default-groupBy gives per-daemonset phase counts automatically.
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
-	if err != nil {
+	var (
+		queryResp        *qbtypes.QueryRangeResponse
+		phaseCounts      map[string]podPhaseCounts
+		podStatusCounts  map[string]podStatusCounts
+		podStatusWarning *qbtypes.QueryWarnData
+	)
+
+	g, gCtx := errgroup.WithContext(ctx)
+
+	g.Go(func() error {
+		var err error
+		queryResp, err = m.querier.QueryRange(gCtx, orgID, fullQueryReq)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+	g.Go(func() error {
+		var err error
+		podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
+		return err
+	})
+
+	if err := g.Wait(); err != nil {
 		return nil, err
 	}
 
-	resp.Records = buildDaemonSetRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
+	resp.Records = buildDaemonSetRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts, podStatusCounts)
+	resp.Warning = mergeQueryWarnings(queryResp.Warning, podStatusWarning)
 
 	return resp, nil
 }

pkg/modules/inframonitoring/implinframonitoring/namespaces.go

@@ -18,6 +18,7 @@ func buildNamespaceRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.NamespaceRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -52,6 +53,10 @@ func buildNamespaceRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/namespaces_constants.go

@@ -23,6 +23,8 @@ var namespacesTableMetricNamesList = []string{
 	"k8s.pod.cpu.usage",
 	"k8s.pod.memory.working_set",
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 }
 
 var namespaceAttrKeysForMetadata = []string{

pkg/modules/inframonitoring/implinframonitoring/nodes.go

@@ -26,6 +26,7 @@ func buildNodeRecords(
 	metadataMap map[string]map[string]string,
 	nodeConditionCounts map[string]nodeConditionCounts,
 	podPhaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.NodeRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -86,6 +87,10 @@ func buildNodeRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/nodes_constants.go

@@ -26,6 +26,8 @@ var nodesTableMetricNamesList = []string{
 	"k8s.node.allocatable_memory",
 	"k8s.node.condition_ready",
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 }
 
 var nodeAttrKeysForMetadata = []string{

pkg/modules/inframonitoring/implinframonitoring/pods.go

@@ -26,6 +26,8 @@ func buildPodRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	statusCounts map[string]podStatusCounts,
+	restartCounts map[string]int64,
 	reqEnd int64,
 ) []inframonitoringtypes.PodRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
@@ -38,6 +40,8 @@ func buildPodRecords(
 		record := inframonitoringtypes.PodRecord{ // initialize with default values
 			PodUID:           podUID,
 			PodPhase:         inframonitoringtypes.PodPhaseNoData,
+			PodStatus:        inframonitoringtypes.PodStatusNoData,
+			PodRestarts:      -1,
 			PodCPU:           -1,
 			PodCPURequest:    -1,
 			PodCPULimit:      -1,
@@ -95,6 +99,57 @@ func buildPodRecords(
 			}
 		}
 
+		if statusCountsForGroup, ok := statusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(statusCountsForGroup)
+
+			// In list mode each group is one pod; the count==1 bucket identifies the status.
+			if isPodUIDInGroupBy {
+				switch {
+				case statusCountsForGroup.Pending == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusPending
+				case statusCountsForGroup.Running == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusRunning
+				case statusCountsForGroup.Failed == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusFailed
+				case statusCountsForGroup.Unknown == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusUnknown
+				case statusCountsForGroup.CrashLoopBackOff == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusCrashLoopBackOff
+				case statusCountsForGroup.ImagePullBackOff == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusImagePullBackOff
+				case statusCountsForGroup.ErrImagePull == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusErrImagePull
+				case statusCountsForGroup.CreateContainerConfigError == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusCreateContainerConfigError
+				case statusCountsForGroup.ContainerCreating == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusContainerCreating
+				case statusCountsForGroup.OOMKilled == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusOOMKilled
+				case statusCountsForGroup.Completed == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusCompleted
+				case statusCountsForGroup.Error == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusError
+				case statusCountsForGroup.ContainerCannotRun == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusContainerCannotRun
+				case statusCountsForGroup.Evicted == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusEvicted
+				case statusCountsForGroup.NodeAffinity == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusNodeAffinity
+				case statusCountsForGroup.NodeLost == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusNodeLost
+				case statusCountsForGroup.Shutdown == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusShutdown
+				case statusCountsForGroup.UnexpectedAdmissionError == 1:
+					record.PodStatus = inframonitoringtypes.PodStatusUnexpectedAdmissionError
+				}
+			}
+		}
+
+		// Restart count: pod's own sum (list mode) or group total (grouped mode).
+		if restartCountForGroup, ok := restartCounts[compositeKey]; ok {
+			record.PodRestarts = restartCountForGroup
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			// podAge only makes sense when pod uid is in groupBy. Otherwise the
 			// group can contain multiple pods with different start times.
@@ -334,3 +389,519 @@ func (m *module) getPerGroupPodPhaseCounts(
 	}
 	return result, nil
 }
+
+// getPerGroupPodStatusCountsWithReqMetricChecks gates getPerGroupPodStatusCounts
+// on the required metrics being present. If any of podStatusMetricNamesList has
+// never been reported, it skips the query and returns a warning instead (the
+// status query would otherwise silently degrade to bare phase). Otherwise it
+// runs the query. The returned counts map is empty (never nil) when gated off.
+func (m *module) getPerGroupPodStatusCountsWithReqMetricChecks(
+	ctx context.Context,
+	start, end int64,
+	filter *qbtypes.Filter,
+	groupBy []qbtypes.GroupByKey,
+	pageGroups []map[string]string,
+) (map[string]podStatusCounts, *qbtypes.QueryWarnData, error) {
+	present, err := m.getMetricsExistence(ctx, podStatusMetricNamesList)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	var missing []string
+	for _, name := range podStatusMetricNamesList {
+		if !present[name] {
+			missing = append(missing, name)
+		}
+	}
+	if len(missing) > 0 {
+		warning := &qbtypes.QueryWarnData{
+			Message: fmt.Sprintf(
+				"Pod status could not be computed: required metric(s) not found: %s. "+
+					"Enable the optional k8s.pod.status_reason and k8s.container.status.reason "+
+					"metrics in the k8s_cluster receiver to see pod statuses.",
+				strings.Join(missing, ", "),
+			),
+			Url: docLinkK8sClusterReceiver,
+		}
+		return map[string]podStatusCounts{}, warning, nil
+	}
+
+	counts, err := m.getPerGroupPodStatusCounts(ctx, start, end, filter, groupBy, pageGroups)
+	if err != nil {
+		return nil, nil, err
+	}
+	return counts, nil, nil
+}
+
+// getPerGroupPodStatusCounts computes per-group pod counts bucketed by each
+// pod's latest kubectl-style display status in the requested window. Caller
+// must ensure the required metrics exist (getPerGroupPodStatusCountsWithReqMetricChecks).
+// Pipeline (mirrors getPerGroupPodPhaseCounts, more CTEs):
+//
+//	phase_fps / phase_per_pod:           latest k8s.pod.phase per pod (+ groupBy cols).
+//	pod_reason_fps / pod_reason_per_pod: latest k8s.pod.status_reason per pod.
+//	container_reason_fps / container_reason_per_pod:
+//	                                     highest-priority active k8s.container.status.reason per pod.
+//	pod_status:                          display status per pod (container > pod reason > phase).
+//	countPodsPerStatus:                  per-group uniqExactIf into the fixed status buckets.
+//
+// Groups absent from the result map have implicit zero counts (caller default).
+func (m *module) getPerGroupPodStatusCounts(
+	ctx context.Context,
+	start, end int64,
+	filter *qbtypes.Filter,
+	groupBy []qbtypes.GroupByKey,
+	pageGroups []map[string]string,
+) (map[string]podStatusCounts, error) {
+	if len(pageGroups) == 0 || len(groupBy) == 0 {
+		return map[string]podStatusCounts{}, nil
+	}
+
+	// Merge user filter with page-groups IN clauses.
+	userFilterExpr := ""
+	if filter != nil {
+		userFilterExpr = filter.Expression
+	}
+	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
+
+	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
+	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+
+	// Build the merged filter clause once; it's identical across the three fps
+	// CTEs, and buildFilterClause hits the metadata store + parses the
+	// expression, so we don't want to repeat it per CTE. AddWhereClause only
+	// reads the clause, so the same instance is safe to attach to each builder.
+	var (
+		filterClause *sqlbuilder.WhereClause
+		err          error
+	)
+	if mergedFilterExpr != "" {
+		filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	// ----- phase_fps (carries groupBy cols) -----
+	phaseFps := sqlbuilder.NewSelectBuilder()
+	phaseFpsCols := []string{
+		"fingerprint",
+		fmt.Sprintf("JSONExtractString(labels, %s) AS pod_uid", phaseFps.Var(podUIDAttrKey)),
+	}
+	for _, key := range groupBy {
+		phaseFpsCols = append(phaseFpsCols,
+			fmt.Sprintf("JSONExtractString(labels, %s) AS %s", phaseFps.Var(key.Name), quoteIdentifier(key.Name)),
+		)
+	}
+	phaseFps.Select(phaseFpsCols...)
+	phaseFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	phaseFps.Where(
+		phaseFps.E("metric_name", podPhaseMetricName),
+		phaseFps.GE("unix_milli", tsAdjustedStart),
+		phaseFps.LE("unix_milli", flooredEndMs),
+	)
+	if filterClause != nil {
+		phaseFps.AddWhereClause(filterClause)
+	}
+	phaseFpsGroupBy := []string{"fingerprint", "pod_uid"}
+	for _, key := range groupBy {
+		phaseFpsGroupBy = append(phaseFpsGroupBy, quoteIdentifier(key.Name))
+	}
+	phaseFps.GroupBy(phaseFpsGroupBy...)
+	phaseFpsSQL, phaseFpsArgs := phaseFps.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- phase_per_pod -----
+	phasePerPod := sqlbuilder.NewSelectBuilder()
+	phasePerPodCols := []string{"fps.pod_uid AS pod_uid"}
+	for _, key := range groupBy {
+		col := quoteIdentifier(key.Name)
+		phasePerPodCols = append(phasePerPodCols, fmt.Sprintf("argMax(fps.%s, samples.unix_milli) AS %s", col, col))
+	}
+	phasePerPodCols = append(phasePerPodCols, fmt.Sprintf("argMax(samples.%s, samples.unix_milli) AS phase_value", valueCol))
+	phasePerPod.Select(phasePerPodCols...)
+	phasePerPod.From(fmt.Sprintf(
+		"%s.%s AS samples INNER JOIN phase_fps AS fps ON samples.fingerprint = fps.fingerprint",
+		telemetrymetrics.DBName, distributedSamplesTable,
+	))
+	phasePerPod.Where(
+		phasePerPod.E("samples.metric_name", podPhaseMetricName),
+		phasePerPod.GE("samples.unix_milli", samplesStartMs),
+		phasePerPod.L("samples.unix_milli", flooredEndMs),
+		"fps.pod_uid != ''",
+	)
+	phasePerPod.GroupBy("pod_uid")
+	phasePerPodSQL, phasePerPodArgs := phasePerPod.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- pod_reason_fps -----
+	podReasonFps := sqlbuilder.NewSelectBuilder()
+	podReasonFps.Select(
+		"fingerprint",
+		fmt.Sprintf("JSONExtractString(labels, %s) AS pod_uid", podReasonFps.Var(podUIDAttrKey)),
+	)
+	podReasonFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	podReasonFps.Where(
+		podReasonFps.E("metric_name", podStatusReasonMetricName),
+		podReasonFps.GE("unix_milli", tsAdjustedStart),
+		podReasonFps.LE("unix_milli", flooredEndMs),
+	)
+	if filterClause != nil {
+		podReasonFps.AddWhereClause(filterClause)
+	}
+	podReasonFps.GroupBy("fingerprint", "pod_uid")
+	podReasonFpsSQL, podReasonFpsArgs := podReasonFps.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- pod_reason_per_pod -----
+	podReasonPerPod := sqlbuilder.NewSelectBuilder()
+	podReasonPerPod.Select(
+		"fps.pod_uid AS pod_uid",
+		fmt.Sprintf("argMax(samples.%s, samples.unix_milli) AS reason_value", valueCol),
+	)
+	podReasonPerPod.From(fmt.Sprintf(
+		"%s.%s AS samples INNER JOIN pod_reason_fps AS fps ON samples.fingerprint = fps.fingerprint",
+		telemetrymetrics.DBName, distributedSamplesTable,
+	))
+	podReasonPerPod.Where(
+		podReasonPerPod.E("samples.metric_name", podStatusReasonMetricName),
+		podReasonPerPod.GE("samples.unix_milli", samplesStartMs),
+		podReasonPerPod.L("samples.unix_milli", flooredEndMs),
+		"fps.pod_uid != ''",
+	)
+	podReasonPerPod.GroupBy("pod_uid")
+	podReasonPerPodSQL, podReasonPerPodArgs := podReasonPerPod.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- container_reason_fps -----
+	containerReasonFps := sqlbuilder.NewSelectBuilder()
+	containerReasonFps.Select(
+		"fingerprint",
+		fmt.Sprintf("JSONExtractString(labels, %s) AS pod_uid", containerReasonFps.Var(podUIDAttrKey)),
+		fmt.Sprintf("JSONExtractString(labels, %s) AS container_name", containerReasonFps.Var(containerNameAttrKey)),
+		fmt.Sprintf("JSONExtractString(labels, %s) AS reason", containerReasonFps.Var(containerStatusReasonAttrKey)),
+	)
+	containerReasonFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	containerReasonFps.Where(
+		containerReasonFps.E("metric_name", containerStatusReasonMetricName),
+		containerReasonFps.GE("unix_milli", tsAdjustedStart),
+		containerReasonFps.LE("unix_milli", flooredEndMs),
+	)
+	if filterClause != nil {
+		containerReasonFps.AddWhereClause(filterClause)
+	}
+	containerReasonFps.GroupBy("fingerprint", "pod_uid", "container_name", "reason")
+	containerReasonFpsSQL, containerReasonFpsArgs := containerReasonFps.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- container_reason_per_pod -----
+	// Inner: latest value per (pod, container, reason) -> kills stale
+	// fingerprints from old container incarnations; keep only active (=1).
+	// Outer: highest-priority active reason per pod (waiting > terminated).
+	priorityCase := "CASE fps.reason " +
+		"WHEN 'CrashLoopBackOff' THEN 8 " +
+		"WHEN 'ImagePullBackOff' THEN 7 " +
+		"WHEN 'ErrImagePull' THEN 6 " +
+		"WHEN 'CreateContainerConfigError' THEN 5 " +
+		"WHEN 'ContainerCreating' THEN 4 " +
+		"WHEN 'OOMKilled' THEN 3 " +
+		"WHEN 'Error' THEN 2 " +
+		"WHEN 'ContainerCannotRun' THEN 1 " +
+		"ELSE 0 END"
+	containerInner := sqlbuilder.NewSelectBuilder()
+	containerInner.Select(
+		"fps.pod_uid AS pod_uid",
+		"fps.container_name AS container_name",
+		"fps.reason AS reason",
+		fmt.Sprintf("argMax(samples.%s, samples.unix_milli) AS is_active", valueCol),
+		priorityCase+" AS priority",
+	)
+	containerInner.From(fmt.Sprintf(
+		"%s.%s AS samples INNER JOIN container_reason_fps AS fps ON samples.fingerprint = fps.fingerprint",
+		telemetrymetrics.DBName, distributedSamplesTable,
+	))
+	containerInner.Where(
+		containerInner.E("samples.metric_name", containerStatusReasonMetricName),
+		containerInner.GE("samples.unix_milli", samplesStartMs),
+		containerInner.L("samples.unix_milli", flooredEndMs),
+		"fps.pod_uid != ''",
+	)
+	containerInner.GroupBy("fps.pod_uid", "fps.container_name", "fps.reason")
+	containerInner.Having("is_active = 1")
+	containerInnerSQL, containerInnerArgs := containerInner.BuildWithFlavor(sqlbuilder.ClickHouse)
+	containerPerPodSQL := fmt.Sprintf(
+		"SELECT pod_uid, argMax(reason, priority) AS active_reason FROM (%s) GROUP BY pod_uid",
+		containerInnerSQL,
+	)
+
+	// ----- pod_status (display status per pod) -----
+	// container reason > pod-level reason > phase fallback. Numeric literals
+	// match the k8s.pod.status_reason and k8s.pod.phase metric encodings.
+	displayStatusExpr := "multiIf(" +
+		"cr.active_reason != '', cr.active_reason, " +
+		"pr.reason_value = 1, 'Evicted', " +
+		"pr.reason_value = 2, 'NodeAffinity', " +
+		"pr.reason_value = 3, 'NodeLost', " +
+		"pr.reason_value = 4, 'Shutdown', " +
+		"pr.reason_value = 5, 'UnexpectedAdmissionError', " +
+		"pp.phase_value = 1, 'Pending', " +
+		"pp.phase_value = 2, 'Running', " +
+		"pp.phase_value = 3, 'Completed', " +
+		"pp.phase_value = 4, 'Failed', " +
+		"pp.phase_value = 5, 'Unknown', " +
+		"'Unknown')"
+	podStatusSelectCols := []string{"pp.pod_uid AS pod_uid"}
+	for _, key := range groupBy {
+		col := quoteIdentifier(key.Name)
+		podStatusSelectCols = append(podStatusSelectCols, fmt.Sprintf("pp.%s AS %s", col, col))
+	}
+	podStatusSelectCols = append(podStatusSelectCols, displayStatusExpr+" AS display_status")
+	podStatusSQL := fmt.Sprintf(
+		"SELECT %s FROM phase_per_pod AS pp "+
+			"LEFT JOIN pod_reason_per_pod AS pr ON pp.pod_uid = pr.pod_uid "+
+			"LEFT JOIN container_reason_per_pod AS cr ON pp.pod_uid = cr.pod_uid",
+		strings.Join(podStatusSelectCols, ", "),
+	)
+
+	// ----- countPodsPerStatus (outer SELECT) -----
+	// Fixed status order; MUST match the podStatusCounts assignment in the
+	// scan loop below.
+	statusCountCols := []string{
+		"uniqExactIf(pod_uid, display_status = 'Pending') AS pending_count",
+		"uniqExactIf(pod_uid, display_status = 'Running') AS running_count",
+		"uniqExactIf(pod_uid, display_status = 'Failed') AS failed_count",
+		"uniqExactIf(pod_uid, display_status = 'Unknown') AS unknown_count",
+		"uniqExactIf(pod_uid, display_status = 'CrashLoopBackOff') AS crash_loop_back_off_count",
+		"uniqExactIf(pod_uid, display_status = 'ImagePullBackOff') AS image_pull_back_off_count",
+		"uniqExactIf(pod_uid, display_status = 'ErrImagePull') AS err_image_pull_count",
+		"uniqExactIf(pod_uid, display_status = 'CreateContainerConfigError') AS create_container_config_error_count",
+		"uniqExactIf(pod_uid, display_status = 'ContainerCreating') AS container_creating_count",
+		"uniqExactIf(pod_uid, display_status = 'OOMKilled') AS oom_killed_count",
+		"uniqExactIf(pod_uid, display_status = 'Completed') AS completed_count",
+		"uniqExactIf(pod_uid, display_status = 'Error') AS error_count",
+		"uniqExactIf(pod_uid, display_status = 'ContainerCannotRun') AS container_cannot_run_count",
+		"uniqExactIf(pod_uid, display_status = 'Evicted') AS evicted_count",
+		"uniqExactIf(pod_uid, display_status = 'NodeAffinity') AS node_affinity_count",
+		"uniqExactIf(pod_uid, display_status = 'NodeLost') AS node_lost_count",
+		"uniqExactIf(pod_uid, display_status = 'Shutdown') AS shutdown_count",
+		"uniqExactIf(pod_uid, display_status = 'UnexpectedAdmissionError') AS unexpected_admission_error_count",
+	}
+	countSelectCols := make([]string, 0, len(groupBy)+len(statusCountCols))
+	countGroupBy := make([]string, 0, len(groupBy))
+	for _, key := range groupBy {
+		col := quoteIdentifier(key.Name)
+		countSelectCols = append(countSelectCols, col)
+		countGroupBy = append(countGroupBy, col)
+	}
+	countSelectCols = append(countSelectCols, statusCountCols...)
+	countSQL := fmt.Sprintf(
+		"SELECT %s FROM pod_status GROUP BY %s",
+		strings.Join(countSelectCols, ", "),
+		strings.Join(countGroupBy, ", "),
+	)
+
+	// Combine CTEs + outer. Arg order mirrors CTE declaration order.
+	cteFragments := []string{
+		fmt.Sprintf("phase_fps AS (%s)", phaseFpsSQL),
+		fmt.Sprintf("phase_per_pod AS (%s)", phasePerPodSQL),
+		fmt.Sprintf("pod_reason_fps AS (%s)", podReasonFpsSQL),
+		fmt.Sprintf("pod_reason_per_pod AS (%s)", podReasonPerPodSQL),
+		fmt.Sprintf("container_reason_fps AS (%s)", containerReasonFpsSQL),
+		fmt.Sprintf("container_reason_per_pod AS (%s)", containerPerPodSQL),
+		fmt.Sprintf("pod_status AS (%s)", podStatusSQL),
+	}
+	finalSQL := querybuilder.CombineCTEs(cteFragments) + countSQL
+	finalArgs := querybuilder.PrependArgs([][]any{
+		phaseFpsArgs, phasePerPodArgs,
+		podReasonFpsArgs, podReasonPerPodArgs,
+		containerReasonFpsArgs, containerInnerArgs,
+	}, nil)
+
+	rows, err := m.telemetryStore.ClickhouseDB().Query(ctx, finalSQL, finalArgs...)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	result := make(map[string]podStatusCounts)
+	for rows.Next() {
+		groupVals := make([]string, len(groupBy))
+		counts := make([]uint64, len(statusCountCols))
+		scanPtrs := make([]any, 0, len(groupBy)+len(statusCountCols))
+		for i := range groupVals {
+			scanPtrs = append(scanPtrs, &groupVals[i])
+		}
+		for i := range counts {
+			scanPtrs = append(scanPtrs, &counts[i])
+		}
+		if err := rows.Scan(scanPtrs...); err != nil {
+			return nil, err
+		}
+		result[compositeKeyFromList(groupVals)] = podStatusCounts{
+			Pending:                    int(counts[0]),
+			Running:                    int(counts[1]),
+			Failed:                     int(counts[2]),
+			Unknown:                    int(counts[3]),
+			CrashLoopBackOff:           int(counts[4]),
+			ImagePullBackOff:           int(counts[5]),
+			ErrImagePull:               int(counts[6]),
+			CreateContainerConfigError: int(counts[7]),
+			ContainerCreating:          int(counts[8]),
+			OOMKilled:                  int(counts[9]),
+			Completed:                  int(counts[10]),
+			Error:                      int(counts[11]),
+			ContainerCannotRun:         int(counts[12]),
+			Evicted:                    int(counts[13]),
+			NodeAffinity:               int(counts[14]),
+			NodeLost:                   int(counts[15]),
+			Shutdown:                   int(counts[16]),
+			UnexpectedAdmissionError:   int(counts[17]),
+		}
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return result, nil
+}
+
+// getPerGroupPodRestartCounts computes the absolute pod restart count per group
+// from k8s.container.restarts (default-enabled, so no existence gate). In list
+// mode (groupBy=pod_uid) each group is one pod -> its restart count; in grouped
+// mode it's the summed restarts across all pods in the group. Mirrors DD:
+// argMax(value, unix_milli) per (pod, container) takes the current cumulative
+// count from the latest incarnation (handling fingerprint staleness/pruning),
+// then sum.
+//
+//	restart_fps:        fp ↔ (pod_uid, container_name, groupBy cols) from time_series.
+//	container_restarts: INNER JOIN samples, latest restartCount per (pod, container).
+//	(outer):            per-group sum(restart_count).
+//
+// Groups absent from the result map have no data (caller default).
+func (m *module) getPerGroupPodRestartCounts(
+	ctx context.Context,
+	start, end int64,
+	filter *qbtypes.Filter,
+	groupBy []qbtypes.GroupByKey,
+	pageGroups []map[string]string,
+) (map[string]int64, error) {
+	if len(pageGroups) == 0 || len(groupBy) == 0 {
+		return map[string]int64{}, nil
+	}
+
+	// Merge user filter with page-groups IN clauses.
+	userFilterExpr := ""
+	if filter != nil {
+		userFilterExpr = filter.Expression
+	}
+	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
+
+	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
+	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+
+	var (
+		filterClause *sqlbuilder.WhereClause
+		err          error
+	)
+	if mergedFilterExpr != "" {
+		filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	// ----- restart_fps (carries groupBy cols) -----
+	restartFps := sqlbuilder.NewSelectBuilder()
+	restartFpsCols := []string{
+		"fingerprint",
+		fmt.Sprintf("JSONExtractString(labels, %s) AS pod_uid", restartFps.Var(podUIDAttrKey)),
+		fmt.Sprintf("JSONExtractString(labels, %s) AS container_name", restartFps.Var(containerNameAttrKey)),
+	}
+	for _, key := range groupBy {
+		restartFpsCols = append(restartFpsCols,
+			fmt.Sprintf("JSONExtractString(labels, %s) AS %s", restartFps.Var(key.Name), quoteIdentifier(key.Name)),
+		)
+	}
+	restartFps.Select(restartFpsCols...)
+	restartFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	restartFps.Where(
+		restartFps.E("metric_name", containerRestartsMetricName),
+		restartFps.GE("unix_milli", tsAdjustedStart),
+		restartFps.LE("unix_milli", flooredEndMs),
+	)
+	if filterClause != nil {
+		restartFps.AddWhereClause(filterClause)
+	}
+	restartFpsGroupBy := []string{"fingerprint", "pod_uid", "container_name"}
+	for _, key := range groupBy {
+		restartFpsGroupBy = append(restartFpsGroupBy, quoteIdentifier(key.Name))
+	}
+	restartFps.GroupBy(restartFpsGroupBy...)
+	restartFpsSQL, restartFpsArgs := restartFps.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- container_restarts (latest cumulative count per container) -----
+	containerRestarts := sqlbuilder.NewSelectBuilder()
+	containerRestartsCols := []string{
+		"fps.pod_uid AS pod_uid",
+		"fps.container_name AS container_name",
+	}
+	for _, key := range groupBy {
+		col := quoteIdentifier(key.Name)
+		containerRestartsCols = append(containerRestartsCols, fmt.Sprintf("argMax(fps.%s, samples.unix_milli) AS %s", col, col))
+	}
+	containerRestartsCols = append(containerRestartsCols, fmt.Sprintf("argMax(samples.%s, samples.unix_milli) AS restart_count", valueCol))
+	containerRestarts.Select(containerRestartsCols...)
+	containerRestarts.From(fmt.Sprintf(
+		"%s.%s AS samples INNER JOIN restart_fps AS fps ON samples.fingerprint = fps.fingerprint",
+		telemetrymetrics.DBName, distributedSamplesTable,
+	))
+	containerRestarts.Where(
+		containerRestarts.E("samples.metric_name", containerRestartsMetricName),
+		containerRestarts.GE("samples.unix_milli", samplesStartMs),
+		containerRestarts.L("samples.unix_milli", flooredEndMs),
+		"fps.pod_uid != ''",
+	)
+	containerRestarts.GroupBy("fps.pod_uid", "fps.container_name")
+	containerRestartsSQL, containerRestartsArgs := containerRestarts.BuildWithFlavor(sqlbuilder.ClickHouse)
+
+	// ----- outer: per-group sum across containers (hence across pods) -----
+	sumSelectCols := make([]string, 0, len(groupBy)+1)
+	sumGroupBy := make([]string, 0, len(groupBy))
+	for _, key := range groupBy {
+		col := quoteIdentifier(key.Name)
+		sumSelectCols = append(sumSelectCols, col)
+		sumGroupBy = append(sumGroupBy, col)
+	}
+	sumSelectCols = append(sumSelectCols, "sum(restart_count) AS total_restarts")
+	sumSQL := fmt.Sprintf(
+		"SELECT %s FROM container_restarts GROUP BY %s",
+		strings.Join(sumSelectCols, ", "),
+		strings.Join(sumGroupBy, ", "),
+	)
+
+	cteFragments := []string{
+		fmt.Sprintf("restart_fps AS (%s)", restartFpsSQL),
+		fmt.Sprintf("container_restarts AS (%s)", containerRestartsSQL),
+	}
+	finalSQL := querybuilder.CombineCTEs(cteFragments) + sumSQL
+	finalArgs := querybuilder.PrependArgs([][]any{restartFpsArgs, containerRestartsArgs}, nil)
+
+	rows, err := m.telemetryStore.ClickhouseDB().Query(ctx, finalSQL, finalArgs...)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	result := make(map[string]int64)
+	for rows.Next() {
+		groupVals := make([]string, len(groupBy))
+		var totalRestarts float64
+		scanPtrs := make([]any, 0, len(groupBy)+1)
+		for i := range groupVals {
+			scanPtrs = append(scanPtrs, &groupVals[i])
+		}
+		scanPtrs = append(scanPtrs, &totalRestarts)
+		if err := rows.Scan(scanPtrs...); err != nil {
+			return nil, err
+		}
+		result[compositeKeyFromList(groupVals)] = int64(totalRestarts)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return result, nil
+}

pkg/modules/inframonitoring/implinframonitoring/pods_constants.go

@@ -8,11 +8,26 @@ import (
 )
 
 const (
-	podUIDAttrKey       = "k8s.pod.uid"
-	podStartTimeAttrKey = "k8s.pod.start_time"
-	podPhaseMetricName  = "k8s.pod.phase"
+	podUIDAttrKey                = "k8s.pod.uid"
+	podStartTimeAttrKey          = "k8s.pod.start_time"
+	containerNameAttrKey         = "k8s.container.name"
+	containerStatusReasonAttrKey = "k8s.container.status.reason"
+
+	podPhaseMetricName              = "k8s.pod.phase"
+	podStatusReasonMetricName       = "k8s.pod.status_reason"
+	containerStatusReasonMetricName = "k8s.container.status.reason"
+	containerRestartsMetricName     = "k8s.container.restarts"
 )
 
+// podStatusMetricNamesList are the metrics required to derive the kubectl-style
+// pod display status. All three must be present (getMetricsExistence gate)
+// before getPerGroupPodStatusCounts runs.
+var podStatusMetricNamesList = []string{
+	podPhaseMetricName,
+	podStatusReasonMetricName,
+	containerStatusReasonMetricName,
+}
+
 var podUIDGroupByKey = qbtypes.GroupByKey{
 	TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
 		Name:          podUIDAttrKey,
@@ -29,6 +44,9 @@ var podsTableMetricNamesList = []string{
 	"k8s.pod.memory_request_utilization",
 	"k8s.pod.memory_limit_utilization",
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
+	"k8s.container.restarts",
 }
 
 var podAttrKeysForMetadata = []string{

pkg/modules/inframonitoring/implinframonitoring/statefulsets.go

@@ -19,6 +19,7 @@ func buildStatefulSetRecords(
 	groupBy []qbtypes.GroupByKey,
 	metadataMap map[string]map[string]string,
 	phaseCounts map[string]podPhaseCounts,
+	podStatusCounts map[string]podStatusCounts,
 ) []inframonitoringtypes.StatefulSetRecord {
 	metricsMap := parseFullQueryResponse(resp, groupBy)
 
@@ -77,6 +78,10 @@ func buildStatefulSetRecords(
 			}
 		}
 
+		if podStatusCountsForGroup, ok := podStatusCounts[compositeKey]; ok {
+			record.PodCountsByStatus = podStatusCountsToResponse(podStatusCountsForGroup)
+		}
+
 		if attrs, ok := metadataMap[compositeKey]; ok {
 			for k, v := range attrs {
 				record.Meta[k] = v

pkg/modules/inframonitoring/implinframonitoring/statefulsets_constants.go

@@ -23,6 +23,8 @@ var statefulSetNameGroupByKey = qbtypes.GroupByKey{
 // response to short-circuit cleanly when the phase metric is absent.
 var statefulSetsTableMetricNamesList = []string{
 	"k8s.pod.phase",
+	"k8s.pod.status_reason",
+	"k8s.container.status.reason",
 	"k8s.pod.cpu.usage",
 	"k8s.pod.cpu_request_utilization",
 	"k8s.pod.cpu_limit_utilization",

pkg/types/inframonitoringtypes/clusters.go

@@ -27,6 +27,7 @@ type ClusterRecord struct {
 	ClusterMemoryAllocatable float64               `json:"clusterMemoryAllocatable" required:"true"`
 	NodeCountsByReadiness    NodeCountsByReadiness `json:"nodeCountsByReadiness" required:"true"`
 	PodCountsByPhase         PodCountsByPhase      `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus        PodCountsByStatus     `json:"podCountsByStatus" required:"true"`
 	Meta                     map[string]string     `json:"meta" required:"true"`
 }
 

pkg/types/inframonitoringtypes/daemonsets.go

@@ -17,16 +17,17 @@ type DaemonSets struct {
 }
 
 type DaemonSetRecord struct {
-	DaemonSetName          string           `json:"daemonSetName" required:"true"`
-	DaemonSetCPU           float64          `json:"daemonSetCPU" required:"true"`
-	DaemonSetCPURequest    float64          `json:"daemonSetCPURequest" required:"true"`
-	DaemonSetCPULimit      float64          `json:"daemonSetCPULimit" required:"true"`
-	DaemonSetMemory        float64          `json:"daemonSetMemory" required:"true"`
-	DaemonSetMemoryRequest float64          `json:"daemonSetMemoryRequest" required:"true"`
-	DaemonSetMemoryLimit   float64          `json:"daemonSetMemoryLimit" required:"true"`
+	DaemonSetName          string            `json:"daemonSetName" required:"true"`
+	DaemonSetCPU           float64           `json:"daemonSetCPU" required:"true"`
+	DaemonSetCPURequest    float64           `json:"daemonSetCPURequest" required:"true"`
+	DaemonSetCPULimit      float64           `json:"daemonSetCPULimit" required:"true"`
+	DaemonSetMemory        float64           `json:"daemonSetMemory" required:"true"`
+	DaemonSetMemoryRequest float64           `json:"daemonSetMemoryRequest" required:"true"`
+	DaemonSetMemoryLimit   float64           `json:"daemonSetMemoryLimit" required:"true"`
 	DesiredNodes           int               `json:"desiredNodes" required:"true"`
 	CurrentNodes           int               `json:"currentNodes" required:"true"`
 	PodCountsByPhase       PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus      PodCountsByStatus `json:"podCountsByStatus" required:"true"`
 	Meta                   map[string]string `json:"meta" required:"true"`
 }
 

pkg/types/inframonitoringtypes/deployments.go

@@ -27,6 +27,7 @@ type DeploymentRecord struct {
 	DesiredPods             int               `json:"desiredPods" required:"true"`
 	AvailablePods           int               `json:"availablePods" required:"true"`
 	PodCountsByPhase        PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus       PodCountsByStatus `json:"podCountsByStatus" required:"true"`
 	Meta                    map[string]string `json:"meta" required:"true"`
 }
 

pkg/types/inframonitoringtypes/jobs.go

@@ -29,6 +29,7 @@ type JobRecord struct {
 	FailedPods            int               `json:"failedPods" required:"true"`
 	SuccessfulPods        int               `json:"successfulPods" required:"true"`
 	PodCountsByPhase      PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus     PodCountsByStatus `json:"podCountsByStatus" required:"true"`
 	Meta                  map[string]string `json:"meta" required:"true"`
 }
 

pkg/types/inframonitoringtypes/namespaces.go

@@ -17,11 +17,12 @@ type Namespaces struct {
 }
 
 type NamespaceRecord struct {
-	NamespaceName    string            `json:"namespaceName" required:"true"`
-	NamespaceCPU     float64           `json:"namespaceCPU" required:"true"`
-	NamespaceMemory  float64           `json:"namespaceMemory" required:"true"`
-	PodCountsByPhase PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
-	Meta             map[string]string `json:"meta" required:"true"`
+	NamespaceName     string            `json:"namespaceName" required:"true"`
+	NamespaceCPU      float64           `json:"namespaceCPU" required:"true"`
+	NamespaceMemory   float64           `json:"namespaceMemory" required:"true"`
+	PodCountsByPhase  PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus PodCountsByStatus `json:"podCountsByStatus" required:"true"`
+	Meta              map[string]string `json:"meta" required:"true"`
 }
 
 // PostableNamespaces is the request body for the v2 namespaces list API.

pkg/types/inframonitoringtypes/nodes.go

@@ -28,6 +28,7 @@ type NodeRecord struct {
 	Condition             NodeCondition         `json:"condition" required:"true"`
 	NodeCountsByReadiness NodeCountsByReadiness `json:"nodeCountsByReadiness" required:"true"`
 	PodCountsByPhase      PodCountsByPhase      `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus     PodCountsByStatus     `json:"podCountsByStatus" required:"true"`
 	NodeCPU               float64               `json:"nodeCPU" required:"true"`
 	NodeCPUAllocatable    float64               `json:"nodeCPUAllocatable" required:"true"`
 	NodeMemory            float64               `json:"nodeMemory" required:"true"`

pkg/types/inframonitoringtypes/pods.go

@@ -26,18 +26,49 @@ type PodCountsByPhase struct {
 	Unknown   int `json:"unknown" required:"true"`
 }
 
+// PodCountsByStatus buckets pod counts by their latest kubectl-style display
+// status in the time window (see PodStatus). One field per derivable status.
+type PodCountsByStatus struct {
+	// Phase fallback.
+	Pending int `json:"pending" required:"true"`
+	Running int `json:"running" required:"true"`
+	Failed  int `json:"failed" required:"true"`
+	Unknown int `json:"unknown" required:"true"`
+
+	// Container-level reasons.
+	CrashLoopBackOff           int `json:"crashLoopBackOff" required:"true"`
+	ImagePullBackOff           int `json:"imagePullBackOff" required:"true"`
+	ErrImagePull               int `json:"errImagePull" required:"true"`
+	CreateContainerConfigError int `json:"createContainerConfigError" required:"true"`
+	ContainerCreating          int `json:"containerCreating" required:"true"`
+	OOMKilled                  int `json:"oomKilled" required:"true"`
+	Completed                  int `json:"completed" required:"true"`
+	Error                      int `json:"error" required:"true"`
+	ContainerCannotRun         int `json:"containerCannotRun" required:"true"`
+
+	// Pod-level reasons.
+	Evicted                  int `json:"evicted" required:"true"`
+	NodeAffinity             int `json:"nodeAffinity" required:"true"`
+	NodeLost                 int `json:"nodeLost" required:"true"`
+	Shutdown                 int `json:"shutdown" required:"true"`
+	UnexpectedAdmissionError int `json:"unexpectedAdmissionError" required:"true"`
+}
+
 type PodRecord struct {
-	PodUID           string            `json:"podUID" required:"true"`
-	PodCPU           float64           `json:"podCPU" required:"true"`
-	PodCPURequest    float64           `json:"podCPURequest" required:"true"`
-	PodCPULimit      float64           `json:"podCPULimit" required:"true"`
-	PodMemory        float64           `json:"podMemory" required:"true"`
-	PodMemoryRequest float64           `json:"podMemoryRequest" required:"true"`
-	PodMemoryLimit   float64           `json:"podMemoryLimit" required:"true"`
-	PodPhase         PodPhase          `json:"podPhase" required:"true"`
-	PodCountsByPhase PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
-	PodAge           int64             `json:"podAge" required:"true"`
-	Meta             map[string]string `json:"meta" required:"true"`
+	PodUID            string            `json:"podUID" required:"true"`
+	PodCPU            float64           `json:"podCPU" required:"true"`
+	PodCPURequest     float64           `json:"podCPURequest" required:"true"`
+	PodCPULimit       float64           `json:"podCPULimit" required:"true"`
+	PodMemory         float64           `json:"podMemory" required:"true"`
+	PodMemoryRequest  float64           `json:"podMemoryRequest" required:"true"`
+	PodMemoryLimit    float64           `json:"podMemoryLimit" required:"true"`
+	PodPhase          PodPhase          `json:"podPhase" required:"true"`
+	PodCountsByPhase  PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodStatus         PodStatus         `json:"podStatus" required:"true"`
+	PodCountsByStatus PodCountsByStatus `json:"podCountsByStatus" required:"true"`
+	PodRestarts       int64             `json:"podRestarts" required:"true"`
+	PodAge            int64             `json:"podAge" required:"true"`
+	Meta              map[string]string `json:"meta" required:"true"`
 }
 
 // PostablePods is the request body for the v2 pods list API.

pkg/types/inframonitoringtypes/pods_constants.go

@@ -26,6 +26,70 @@ func (PodPhase) Enum() []any {
 	}
 }
 
+// PodStatus is the kubectl-style pod display status, derived from
+// k8s.pod.phase + k8s.pod.status_reason + k8s.container.status.reason
+// (priority cascade: container reason > pod-level reason > phase).
+// Wire values are lowercased by valuer.NewString (e.g. "crashloopbackoff");
+// the comment strings below are the kubectl spelling for readability. The
+// query emits kubectl-style strings, so SQL output maps to these constants
+// explicitly (not by raw string-wrapping).
+type PodStatus struct {
+	valuer.String
+}
+
+var (
+	// Phase fallback.
+	PodStatusPending = PodStatus{valuer.NewString("Pending")}
+	PodStatusRunning = PodStatus{valuer.NewString("Running")}
+	PodStatusFailed  = PodStatus{valuer.NewString("Failed")}
+	PodStatusUnknown = PodStatus{valuer.NewString("Unknown")}
+
+	// Container-level reasons (k8s.container.status.reason allowlist).
+	PodStatusCrashLoopBackOff           = PodStatus{valuer.NewString("CrashLoopBackOff")}
+	PodStatusImagePullBackOff           = PodStatus{valuer.NewString("ImagePullBackOff")}
+	PodStatusErrImagePull               = PodStatus{valuer.NewString("ErrImagePull")}
+	PodStatusCreateContainerConfigError = PodStatus{valuer.NewString("CreateContainerConfigError")}
+	PodStatusContainerCreating          = PodStatus{valuer.NewString("ContainerCreating")}
+	PodStatusOOMKilled                  = PodStatus{valuer.NewString("OOMKilled")}
+	PodStatusCompleted                  = PodStatus{valuer.NewString("Completed")}
+	PodStatusError                      = PodStatus{valuer.NewString("Error")}
+	PodStatusContainerCannotRun         = PodStatus{valuer.NewString("ContainerCannotRun")}
+
+	// Pod-level reasons (k8s.pod.status_reason).
+	PodStatusEvicted                  = PodStatus{valuer.NewString("Evicted")}
+	PodStatusNodeAffinity             = PodStatus{valuer.NewString("NodeAffinity")}
+	PodStatusNodeLost                 = PodStatus{valuer.NewString("NodeLost")}
+	PodStatusShutdown                 = PodStatus{valuer.NewString("Shutdown")}
+	PodStatusUnexpectedAdmissionError = PodStatus{valuer.NewString("UnexpectedAdmissionError")}
+
+	// Sentinel when status cannot be derived (metrics absent / not in list view).
+	PodStatusNoData = PodStatus{valuer.NewString("no_data")}
+)
+
+func (PodStatus) Enum() []any {
+	return []any{
+		PodStatusPending,
+		PodStatusRunning,
+		PodStatusFailed,
+		PodStatusUnknown,
+		PodStatusCrashLoopBackOff,
+		PodStatusImagePullBackOff,
+		PodStatusErrImagePull,
+		PodStatusCreateContainerConfigError,
+		PodStatusContainerCreating,
+		PodStatusOOMKilled,
+		PodStatusCompleted,
+		PodStatusError,
+		PodStatusContainerCannotRun,
+		PodStatusEvicted,
+		PodStatusNodeAffinity,
+		PodStatusNodeLost,
+		PodStatusShutdown,
+		PodStatusUnexpectedAdmissionError,
+		PodStatusNoData,
+	}
+}
+
 // Numeric pod phase values emitted by the k8s.pod.phase metric
 // (source: OTel kubeletstats receiver).
 const (

pkg/types/inframonitoringtypes/statefulsets.go

@@ -27,6 +27,7 @@ type StatefulSetRecord struct {
 	DesiredPods              int               `json:"desiredPods" required:"true"`
 	CurrentPods              int               `json:"currentPods" required:"true"`
 	PodCountsByPhase         PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
+	PodCountsByStatus        PodCountsByStatus `json:"podCountsByStatus" required:"true"`
 	Meta                     map[string]string `json:"meta" required:"true"`
 }
 

tests/fixtures/inframonitoring.py

@@ -0,0 +1,52 @@
+"""Shared constants/helpers for v2 infra-monitoring pod-status tests."""
+
+# All 18 PodCountsByStatus buckets (camelCase, matches inframonitoringtypes.PodCountsByStatus / the API response).
+STATUS_BUCKETS = (
+    "pending",
+    "running",
+    "failed",
+    "unknown",
+    "crashLoopBackOff",
+    "imagePullBackOff",
+    "errImagePull",
+    "createContainerConfigError",
+    "containerCreating",
+    "oomKilled",
+    "completed",
+    "error",
+    "containerCannotRun",
+    "evicted",
+    "nodeAffinity",
+    "nodeLost",
+    "shutdown",
+    "unexpectedAdmissionError",
+)
+
+# Maps a PodStatus wire value (lowercase) to its PodCountsByStatus bucket key (camelCase).
+STATUS_TO_BUCKET = {
+    "pending": "pending",
+    "running": "running",
+    "failed": "failed",
+    "unknown": "unknown",
+    "crashloopbackoff": "crashLoopBackOff",
+    "imagepullbackoff": "imagePullBackOff",
+    "errimagepull": "errImagePull",
+    "createcontainerconfigerror": "createContainerConfigError",
+    "containercreating": "containerCreating",
+    "oomkilled": "oomKilled",
+    "completed": "completed",
+    "error": "error",
+    "containercannotrun": "containerCannotRun",
+    "evicted": "evicted",
+    "nodeaffinity": "nodeAffinity",
+    "nodelost": "nodeLost",
+    "shutdown": "shutdown",
+    "unexpectedadmissionerror": "unexpectedAdmissionError",
+}
+
+
+def expected_status_counts(**nonzero: int) -> dict:
+    """Full 19-bucket PodCountsByStatus with the given buckets set, rest 0."""
+    counts = {bucket: 0 for bucket in STATUS_BUCKETS}
+    counts.update(nonzero)
+    return counts

tests/integration/testdata/inframonitoring/clusters_pod_phases.jsonl

@@ -34,3 +34,30 @@
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"pp-fail-2-uid","k8s.pod.name":"pp-fail-2","k8s.namespace.name":"ns-x","k8s.node.name":"pp-node","k8s.cluster.name":"pp-cluster"},"timestamp":"2025-01-10T10:00:00+00:00","value":4,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"pp-fail-2-uid","k8s.pod.name":"pp-fail-2","k8s.namespace.name":"ns-x","k8s.node.name":"pp-node","k8s.cluster.name":"pp-cluster"},"timestamp":"2025-01-10T10:02:00+00:00","value":4,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"pp-fail-2-uid","k8s.pod.name":"pp-fail-2","k8s.namespace.name":"ns-x","k8s.node.name":"pp-node","k8s.cluster.name":"pp-cluster"},"timestamp":"2025-01-10T10:04:00+00:00","value":4,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pend-1-uid", "k8s.pod.name": "pp-pend-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pend-1-uid", "k8s.pod.name": "pp-pend-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pend-1-uid", "k8s.pod.name": "pp-pend-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.namespace.name": "ns-x", "k8s.node.name": "pp-node", "k8s.cluster.name": "pp-cluster"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/deployments_pod_phases.jsonl

@@ -151,3 +151,30 @@
 {"metric_name":"k8s.deployment.available","labels":{"k8s.deployment.name":"pp-dep","k8s.namespace.name":"ns-pp","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:02:00+00:00","value":4,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.deployment.desired","labels":{"k8s.deployment.name":"pp-dep","k8s.namespace.name":"ns-pp","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":7,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.deployment.available","labels":{"k8s.deployment.name":"pp-dep","k8s.namespace.name":"ns-pp","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":4,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-1-uid", "k8s.pod.name": "pp-run-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-run-2-uid", "k8s.pod.name": "pp-run-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-3-uid", "k8s.pod.name": "pp-run-3", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-run-4-uid", "k8s.pod.name": "pp-run-4", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pen-1-uid", "k8s.pod.name": "pp-pen-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pen-1-uid", "k8s.pod.name": "pp-pen-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-pen-1-uid", "k8s.pod.name": "pp-pen-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "pp-fail-1-uid", "k8s.pod.name": "pp-fail-1", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pp-fail-2-uid", "k8s.pod.name": "pp-fail-2", "k8s.deployment.name": "pp-dep", "k8s.namespace.name": "ns-pp", "k8s.cluster.name": "cluster-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/pods_phases.jsonl

@@ -103,3 +103,45 @@
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"unk-p-uid","k8s.pod.name":"unk-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:00:00+00:00","value":5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"unk-p-uid","k8s.pod.name":"unk-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:02:00+00:00","value":5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"unk-p-uid","k8s.pod.name":"unk-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:04:00+00:00","value":5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pend-p-uid", "k8s.pod.name": "pend-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pend-p-uid", "k8s.pod.name": "pend-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "pend-p-uid", "k8s.pod.name": "pend-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "run-p-uid", "k8s.pod.name": "run-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Completed"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Completed"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Completed"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "succ-p-uid", "k8s.pod.name": "succ-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "fail-p-uid", "k8s.pod.name": "fail-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom", "k8s.container.status.reason": "OOMKilled"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom", "k8s.container.status.reason": "OOMKilled"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom", "k8s.container.status.reason": "OOMKilled"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-oom"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 8, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 8, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "unk-p-uid", "k8s.pod.name": "unk-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "c-clbo"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 8, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/pods_phases_grouped.jsonl

@@ -124,3 +124,42 @@
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"g-pend-1-uid","k8s.pod.name":"g-pend-1","k8s.namespace.name":"ns-mixed","k8s.node.name":"node-b","k8s.deployment.name":"dep-y","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:00:00+00:00","value":1,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"g-pend-1-uid","k8s.pod.name":"g-pend-1","k8s.namespace.name":"ns-mixed","k8s.node.name":"node-b","k8s.deployment.name":"dep-y","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:02:00+00:00","value":1,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"g-pend-1-uid","k8s.pod.name":"g-pend-1","k8s.namespace.name":"ns-mixed","k8s.node.name":"node-b","k8s.deployment.name":"dep-y","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:04:00+00:00","value":1,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-1-uid", "k8s.pod.name": "g-run-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-3-uid", "k8s.pod.name": "g-run-3", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-run-2-uid", "k8s.pod.name": "g-run-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "Error"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-1-uid", "k8s.pod.name": "g-fail-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "g-fail-2-uid", "k8s.pod.name": "g-fail-2", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-pend-1-uid", "k8s.pod.name": "g-pend-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-pend-1-uid", "k8s.pod.name": "g-pend-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "g-pend-1-uid", "k8s.pod.name": "g-pend-1", "k8s.namespace.name": "ns-mixed", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-y", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/pods_phases_transition.jsonl

@@ -19,3 +19,10 @@
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"trans-p-uid","k8s.pod.name":"trans-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:00:00+00:00","value":1,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"trans-p-uid","k8s.pod.name":"trans-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:02:00+00:00","value":1,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"trans-p-uid","k8s.pod.name":"trans-p","k8s.namespace.name":"ns-x","k8s.node.name":"node-a","k8s.deployment.name":"phase-test","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:04:00+00:00","value":2,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff", "container.id": "aaa"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff", "container.id": "bbb"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "container.id": "aaa"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "trans-p-uid", "k8s.pod.name": "trans-p", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-a", "k8s.deployment.name": "phase-test", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "container.id": "bbb"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/pods_value_accuracy.jsonl

@@ -40,3 +40,21 @@
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"acc-p2-uid","k8s.pod.name":"acc-p2","k8s.namespace.name":"ns-b","k8s.node.name":"node-b","k8s.deployment.name":"dep-2","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:00:00+00:00","value":2,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"acc-p2-uid","k8s.pod.name":"acc-p2","k8s.namespace.name":"ns-b","k8s.node.name":"node-b","k8s.deployment.name":"dep-2","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:02:00+00:00","value":2,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
 {"metric_name":"k8s.pod.phase","labels":{"k8s.pod.uid":"acc-p2-uid","k8s.pod.name":"acc-p2","k8s.namespace.name":"ns-b","k8s.node.name":"node-b","k8s.deployment.name":"dep-2","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"","k8s.daemonset.name":"","k8s.job.name":"","k8s.cronjob.name":"","k8s.pod.start_time":"__START_TIME__"},"timestamp":"2025-01-10T10:04:00+00:00","value":2,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p1-uid", "k8s.pod.name": "acc-p1", "k8s.namespace.name": "ns-a", "k8s.node.name": "node-a", "k8s.deployment.name": "dep-1", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.status_reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.restarts", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.container.status.reason", "labels": {"k8s.pod.uid": "acc-p2-uid", "k8s.pod.name": "acc-p2", "k8s.namespace.name": "ns-b", "k8s.node.name": "node-b", "k8s.deployment.name": "dep-2", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "", "k8s.daemonset.name": "", "k8s.job.name": "", "k8s.cronjob.name": "", "k8s.pod.start_time": "__START_TIME__", "k8s.container.name": "app", "k8s.container.status.reason": "CrashLoopBackOff"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/pods_value_accuracy_expected.json

@@ -9,7 +9,17 @@
       "podMemoryRequest": 0.5,
       "podMemoryLimit": 0.25,
       "podPhase": "running",
-      "podCountsByPhase": {"pending": 0, "running": 1, "succeeded": 0, "failed": 0, "unknown": 0}
+      "podCountsByPhase": {"pending": 0, "running": 1, "succeeded": 0, "failed": 0, "unknown": 0},
+      "podStatus": "running",
+      "podRestarts": 0,
+      "podCountsByStatus": {
+        "pending": 0, "running": 1, "failed": 0, "unknown": 0,
+        "crashLoopBackOff": 0, "imagePullBackOff": 0, "errImagePull": 0,
+        "createContainerConfigError": 0, "containerCreating": 0, "oomKilled": 0,
+        "completed": 0, "error": 0, "containerCannotRun": 0,
+        "evicted": 0, "nodeAffinity": 0, "nodeLost": 0, "shutdown": 0,
+        "unexpectedAdmissionError": 0
+      }
     },
     {
       "podName": "acc-p2",
@@ -20,7 +30,17 @@
       "podMemoryRequest": 0.75,
       "podMemoryLimit": 0.5,
       "podPhase": "running",
-      "podCountsByPhase": {"pending": 0, "running": 1, "succeeded": 0, "failed": 0, "unknown": 0}
+      "podCountsByPhase": {"pending": 0, "running": 1, "succeeded": 0, "failed": 0, "unknown": 0},
+      "podStatus": "running",
+      "podRestarts": 0,
+      "podCountsByStatus": {
+        "pending": 0, "running": 1, "failed": 0, "unknown": 0,
+        "crashLoopBackOff": 0, "imagePullBackOff": 0, "errImagePull": 0,
+        "createContainerConfigError": 0, "containerCreating": 0, "oomKilled": 0,
+        "completed": 0, "error": 0, "containerCannotRun": 0,
+        "evicted": 0, "nodeAffinity": 0, "nodeLost": 0, "shutdown": 0,
+        "unexpectedAdmissionError": 0
+      }
     }
   ]
 }

tests/integration/tests/inframonitoring/02_pods.py

@@ -10,6 +10,7 @@ import requests
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.fs import get_testdata_file_path
+from fixtures.inframonitoring import STATUS_BUCKETS, STATUS_TO_BUCKET
 from fixtures.metrics import Metrics
 from fixtures.querier import compare_values, get_all_warnings
 from fixtures.time import parse_timestamp
@@ -121,6 +122,9 @@ def test_pods_accuracy(
             "podMemoryLimit",
             "podPhase",
             "podCountsByPhase",
+            "podStatus",
+            "podCountsByStatus",
+            "podRestarts",
             "podAge",
             "meta",
         ):
@@ -131,6 +135,11 @@ def test_pods_accuracy(
             assert bucket in record["podCountsByPhase"], f"missing phase bucket {bucket} in {record['podCountsByPhase']!r}"
             assert isinstance(record["podCountsByPhase"][bucket], int)
 
+        # All status buckets always present, integer-typed.
+        for bucket in STATUS_BUCKETS:
+            assert bucket in record["podCountsByStatus"], f"missing status bucket {bucket} in {record['podCountsByStatus']!r}"
+            assert isinstance(record["podCountsByStatus"][bucket], int)
+
         # Exact values.
         pod_name = record["meta"]["k8s.pod.name"]
         exp = exp_by_name[pod_name]
@@ -145,6 +154,9 @@ def test_pods_accuracy(
             assert compare_values(record[field], exp[field], 1e-9), f"{pod_name}.{field}: got {record[field]}, expected {exp[field]}"
         assert record["podPhase"] == exp["podPhase"]
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
+        assert record["podStatus"] == exp["podStatus"], f"{pod_name}.podStatus: got {record['podStatus']}, expected {exp['podStatus']}"
+        assert record["podCountsByStatus"] == exp["podCountsByStatus"], f"{pod_name}.podCountsByStatus mismatch: got {record['podCountsByStatus']}"
+        assert record["podRestarts"] == exp["podRestarts"], f"{pod_name}.podRestarts: got {record['podRestarts']}, expected {exp['podRestarts']}"
         assert record["podAge"] == expected_age_ms, f"{pod_name}.podAge: got {record['podAge']}, expected {expected_age_ms}"
 
 
@@ -793,3 +805,343 @@ def test_pods_validation_errors(
     error = response.json()["error"]
     assert error["code"] == "invalid_input"
     assert err_substr.lower() in error["message"].lower(), f"expected substring {err_substr!r} not found in: {error['message']!r}"
+
+
+@pytest.mark.parametrize(
+    "pod_name,expected_status",
+    [
+        # Expectations are what `kubectl get pods` STATUS would show for the
+        # seeded K8s state in pods_phases.jsonl (not the query internals).
+        pytest.param("pend-p", "pending", id="pending_phase_fallback"),
+        pytest.param("run-p", "crashloopbackoff", id="container_reason_beats_running_phase"),
+        pytest.param("succ-p", "completed", id="completed_terminated_reason"),
+        pytest.param("fail-p", "evicted", id="pod_reason_beats_phase"),
+        pytest.param("unk-p", "crashloopbackoff", id="multi_container_priority"),
+    ],
+)
+def test_pods_status_list_mode(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+    pod_name: str,
+    expected_status: str,
+) -> None:
+    """List mode: podStatus is the kubectl-style display status derived from
+    k8s.pod.phase + k8s.pod.status_reason + k8s.container.status.reason.
+
+    Seeded states -> what kubectl would print:
+      pend-p  Pending          (unscheduled; phase fallback, no container reason)
+      run-p   CrashLoopBackOff (container crashlooping; phase still Running)
+      succ-p  Completed        (container terminated Completed; phase Succeeded)
+      fail-p  Evicted          (pod-level Status.Reason overrides phase)
+      unk-p   CrashLoopBackOff (2 containers: OOMKilled + CrashLoopBackOff)
+
+    NOTE unk-p: a multi-container pod. kubectl picks the reason by container
+    order; we pick by reason priority (waiting>terminated), so CrashLoopBackOff
+    wins over OOMKilled. Documented divergence for multi-container pods — metrics
+    carry no container ordering.
+    """
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases.jsonl",
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "filter": {"expression": f"k8s.pod.name = '{pod_name}'"},
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"]["k8s.pod.name"] == pod_name
+    assert rec["podStatus"] == expected_status
+
+    # List mode: pod is its own group -> exactly its status bucket is 1.
+    bucket = STATUS_TO_BUCKET[expected_status]
+    assert rec["podCountsByStatus"][bucket] == 1
+    for other in STATUS_BUCKETS:
+        if other != bucket:
+            assert rec["podCountsByStatus"][other] == 0, f"expected {other}=0 when status={expected_status}, got {rec['podCountsByStatus']}"
+
+
+@pytest.mark.parametrize(
+    "pod_name,expected_restarts",
+    [
+        # Mirrors kubectl RESTARTS (sum across the pod's containers).
+        pytest.param("run-p", 5, id="single_container"),
+        pytest.param("succ-p", 0, id="zero_restarts"),
+        pytest.param("unk-p", 10, id="multi_container_sum"),  # 2 + 8
+        pytest.param("pend-p", -1, id="no_series_sentinel"),  # unscheduled -> no metric -> -1
+    ],
+)
+def test_pods_restarts_list_mode(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+    pod_name: str,
+    expected_restarts: int,
+) -> None:
+    """podRestarts is the sum of k8s.container.restarts across the pod's
+    containers (kubectl RESTARTS). pend-p never scheduled so emits no restart
+    series -> -1 no-data sentinel (kubectl would show 0)."""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases.jsonl",
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "filter": {"expression": f"k8s.pod.name = '{pod_name}'"},
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"]["k8s.pod.name"] == pod_name
+    assert rec["podRestarts"] == expected_restarts
+
+
+def test_pods_status_latest_wins(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """A stale container reason from an old incarnation must not win. trans-p's
+    first incarnation (container.id=aaa) reported CrashLoopBackOff, then it
+    recovered in a new incarnation (container.id=bbb, CrashLoopBackOff=0) while
+    phase went Running. kubectl shows Running; the frozen stale series is
+    ignored via argMax-by-latest-timestamp per (pod, container, reason)."""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases_transition.jsonl",
+            base_time=now - timedelta(minutes=8),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=10)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"]["k8s.pod.name"] == "trans-p"
+    assert rec["podStatus"] == "running"
+
+
+def test_pods_restarts_latest_wins(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """restartCount is cumulative per container. Across incarnations
+    (container.id=aaa reported 1, then container.id=bbb reported 5) podRestarts
+    is the LATEST value 5 (kubectl RESTARTS), not the sum 6 — incarnations must
+    not be double-counted."""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases_transition.jsonl",
+            base_time=now - timedelta(minutes=8),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=10)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"]["k8s.pod.name"] == "trans-p"
+    assert rec["podRestarts"] == 5
+
+
+def test_pods_status_grouped_mode(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """groupBy=[k8s.namespace.name] aggregates each pod's display status across
+    ns-mixed. podStatus is no-data (no single pod identifies the group). Seeded
+    states -> kubectl: g-run-1/g-run-3 Running, g-run-2 CrashLoopBackOff,
+    g-fail-1 Error, g-fail-2 Evicted, g-pend-1 Pending."""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases_grouped.jsonl",
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "groupBy": [
+                {
+                    "name": "k8s.namespace.name",
+                    "fieldDataType": "string",
+                    "fieldContext": "resource",
+                }
+            ],
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"].get("k8s.namespace.name") == "ns-mixed"
+    assert rec["podStatus"] == "no_data"
+
+    expected_counts = {bucket: 0 for bucket in STATUS_BUCKETS}
+    expected_counts.update(
+        {
+            "running": 2,
+            "crashLoopBackOff": 1,
+            "error": 1,
+            "evicted": 1,
+            "pending": 1,
+        }
+    )
+    assert rec["podCountsByStatus"] == expected_counts
+
+
+def test_pods_restarts_grouped_mode(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """Grouped podRestarts is the sum of restarts across all pods in the group.
+    In ns-mixed only g-run-2 has restarts (3); all others 0 -> group total 3."""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_phases_grouped.jsonl",
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "groupBy": [
+                {
+                    "name": "k8s.namespace.name",
+                    "fieldDataType": "string",
+                    "fieldContext": "resource",
+                }
+            ],
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["meta"].get("k8s.namespace.name") == "ns-mixed"
+    assert rec["podRestarts"] == 3
+
+
+def test_pods_status_missing_metric_warning(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """When the status metrics were never ingested, the status query is gated
+    off: a warning naming the missing metric(s) is surfaced, podStatus is the
+    no-data sentinel, and all status buckets are 0. (pods_missing_metrics.jsonl
+    seeds only k8s.pod.cpu.usage.)"""
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        _load_pods_metrics(
+            "inframonitoring/pods_missing_metrics.jsonl",
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "filter": {"expression": "k8s.pod.name = 'miss-p1'"},
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    body = response.json()
+    data = body["data"]
+
+    # Collect primary + additional warning messages.
+    warning = data.get("warning") or {}
+    msgs = ([warning["message"]] if warning.get("message") else []) + [w["message"] for w in warning.get("warnings", [])]
+    assert any("Pod status could not be computed" in m for m in msgs), f"status-gate warning missing: {msgs!r}"
+    assert any("k8s.container.status.reason" in m for m in msgs), f"missing metric not named: {msgs!r}"
+
+    rec = data["records"][0]
+    assert rec["meta"]["k8s.pod.name"] == "miss-p1"
+    assert rec["podStatus"] == "no_data"
+    for bucket in STATUS_BUCKETS:
+        assert rec["podCountsByStatus"][bucket] == 0, f"expected {bucket}=0 when gated off, got {rec['podCountsByStatus']}"
+    assert rec["podRestarts"] == -1

tests/integration/tests/inframonitoring/05_clusters.py

@@ -10,6 +10,7 @@ import requests
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.fs import get_testdata_file_path
+from fixtures.inframonitoring import expected_status_counts
 from fixtures.metrics import Metrics
 from fixtures.querier import compare_values, get_all_warnings
 
@@ -404,6 +405,49 @@ def test_clusters_pod_phase_aggregation(
     }
 
 
+def test_clusters_pod_status_aggregation(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """Cluster's pods aggregated by kubectl-style display status. Seeded states
+    in clusters_pod_phases.jsonl -> what kubectl would show:
+      pp-run-1/3/4 Running, pp-run-2 CrashLoopBackOff (phase Running),
+      pp-fail-1 Error, pp-fail-2 Evicted (pod-level), pp-pend-1 Pending.
+    """
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        Metrics.load_from_file(
+            get_testdata_file_path("inframonitoring/clusters_pod_phases.jsonl"),
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "filter": {"expression": "k8s.cluster.name = 'pp-cluster'"},
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["clusterName"] == "pp-cluster"
+    assert rec["podCountsByStatus"] == expected_status_counts(running=3, crashLoopBackOff=1, error=1, evicted=1, pending=1)
+    # Phase counts unchanged by the status enrichment.
+    assert rec["podCountsByPhase"] == {"pending": 1, "running": 4, "succeeded": 0, "failed": 2, "unknown": 0}
+    # All status metrics present -> gate satisfied -> no status warning.
+    assert all("Pod status could not be computed" not in w["message"] for w in get_all_warnings(response.json()))
+
+
 @pytest.mark.parametrize(
     "group_key,expected",
     [

tests/integration/tests/inframonitoring/07_deployments.py

@@ -10,6 +10,7 @@ import requests
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.fs import get_testdata_file_path
+from fixtures.inframonitoring import expected_status_counts
 from fixtures.metrics import Metrics
 from fixtures.querier import compare_values, get_all_warnings
 
@@ -385,6 +386,49 @@ def test_deployments_pod_phase_aggregation(
     }
 
 
+def test_deployments_pod_status_aggregation(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token,
+    insert_metrics,
+) -> None:
+    """Deployment's pods aggregated by kubectl-style display status. Seeded states
+    in deployments_pod_phases.jsonl -> what kubectl would show:
+      pp-run-1/3/4 Running, pp-run-2 CrashLoopBackOff (phase Running),
+      pp-fail-1 Error, pp-fail-2 Evicted (pod-level), pp-pen-1 Pending.
+    """
+    now = datetime.now(tz=UTC).replace(microsecond=0)
+    insert_metrics(
+        Metrics.load_from_file(
+            get_testdata_file_path("inframonitoring/deployments_pod_phases.jsonl"),
+            base_time=now - timedelta(minutes=4),
+        )
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = requests.post(
+        signoz.self.host_configs["8080"].get(ENDPOINT),
+        headers={"authorization": f"Bearer {token}"},
+        json={
+            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+            "end": int(now.timestamp() * 1000),
+            "limit": 50,
+            "filter": {"expression": "k8s.deployment.name = 'pp-dep'"},
+        },
+        timeout=5,
+    )
+    assert response.status_code == HTTPStatus.OK, response.text
+    data = response.json()["data"]
+    assert data["total"] == 1
+    rec = data["records"][0]
+    assert rec["deploymentName"] == "pp-dep"
+    assert rec["podCountsByStatus"] == expected_status_counts(running=3, crashLoopBackOff=1, error=1, evicted=1, pending=1)
+    # Phase counts unchanged by the status enrichment.
+    assert rec["podCountsByPhase"] == {"pending": 1, "running": 4, "succeeded": 0, "failed": 2, "unknown": 0}
+    # All status metrics present -> gate satisfied -> no status warning.
+    assert all("Pod status could not be computed" not in w["message"] for w in get_all_warnings(response.json()))
+
+
 def test_deployments_desired_available_counts(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument

tests/integration/tests/inframonitoring/11_checks.py

@@ -45,6 +45,13 @@ _PODS_OPT = [
     "k8s.pod.memory_limit_utilization",
 ]
 
+# Default-off pod-status metrics (k8sclusterreceiver), optional on every tab
+# that surfaces pod status counts.
+_POD_STATUS_OPT = [
+    "k8s.pod.status_reason",
+    "k8s.container.status.reason",
+]
+
 # Mirror of checkSpecs: type -> {default|optional: {component: [metrics]}, attrs: {component: [attrs]}}.
 SPECS = {
     "hosts": {
@@ -58,8 +65,8 @@ SPECS = {
         "attrs": {HMR: ["process.pid"]},
     },
     "pods": {
-        "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase"]},
-        "optional": {KSR: list(_PODS_OPT)},
+        "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase", "k8s.container.restarts"]},
+        "optional": {KSR: list(_PODS_OPT), KCR: ["k8s.pod.status_reason", "k8s.container.status.reason"]},
         "attrs": {KAP: ["k8s.pod.uid"]},
     },
     "nodes": {
@@ -67,37 +74,37 @@ SPECS = {
             KSR: ["k8s.node.cpu.usage", "k8s.node.memory.working_set"],
             KCR: ["k8s.node.allocatable_cpu", "k8s.node.allocatable_memory", "k8s.node.condition_ready", "k8s.pod.phase"],
         },
-        "optional": {},
+        "optional": {KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.node.name"]},
     },
     "deployments": {
         "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase", "k8s.deployment.desired", "k8s.deployment.available"]},
-        "optional": {KSR: list(_PODS_OPT)},
+        "optional": {KSR: list(_PODS_OPT), KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.deployment.name", "k8s.namespace.name"], RDP: ["k8s.cluster.name"]},
     },
     "daemonsets": {
         "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase", "k8s.daemonset.desired_scheduled_nodes", "k8s.daemonset.current_scheduled_nodes"]},
-        "optional": {KSR: list(_PODS_OPT)},
+        "optional": {KSR: list(_PODS_OPT), KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.daemonset.name", "k8s.namespace.name"], RDP: ["k8s.cluster.name"]},
     },
     "statefulsets": {
         "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase", "k8s.statefulset.desired_pods", "k8s.statefulset.current_pods"]},
-        "optional": {KSR: list(_PODS_OPT)},
+        "optional": {KSR: list(_PODS_OPT), KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.statefulset.name", "k8s.namespace.name"], RDP: ["k8s.cluster.name"]},
     },
     "jobs": {
         "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase", "k8s.job.desired_successful_pods", "k8s.job.active_pods", "k8s.job.failed_pods", "k8s.job.successful_pods"]},
-        "optional": {KSR: list(_PODS_OPT)},
+        "optional": {KSR: list(_PODS_OPT), KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.job.name", "k8s.namespace.name"], RDP: ["k8s.cluster.name"]},
     },
     "namespaces": {
         "default": {KSR: ["k8s.pod.cpu.usage", "k8s.pod.memory.working_set"], KCR: ["k8s.pod.phase"]},
-        "optional": {},
+        "optional": {KCR: list(_POD_STATUS_OPT)},
         "attrs": {KAP: ["k8s.namespace.name"], RDP: ["k8s.cluster.name"]},
     },
     "clusters": {
         "default": {KSR: ["k8s.node.cpu.usage", "k8s.node.memory.working_set"], KCR: ["k8s.node.allocatable_cpu", "k8s.node.allocatable_memory", "k8s.node.condition_ready", "k8s.pod.phase"]},
-        "optional": {},
+        "optional": {KCR: list(_POD_STATUS_OPT)},
         "attrs": {RDP: ["k8s.cluster.name"]},
     },
     "volumes": {