feat(views): kubernetes chart

adityathebe · adityathebe · commit ca9de35b2720 · 2025-08-18T10:03:48.000+05:45
diff --git a/charts/kubernetes/Makefile b/charts/kubernetes/Makefile
@@ -33,3 +33,8 @@ values.schema.deref.json: values.schema.json
 .PHONY: lint
 lint: chart
 	ct lint --charts .
+
+
+.PHONY: install
+install:
+	helm install kubernetes . --values values.test.yaml
diff --git a/charts/kubernetes/README.md b/charts/kubernetes/README.md
@@ -8,33 +8,11 @@ A Helm chart for the Kubernetes bundle of Flanksource Mission Control
 |-----|------|---------|-------------|
 | clusterName | string | `""` |  |
 | kubeconfig | object | `{}` |  |
-| kubernetesConnection.cnrm.clusterResource | string | `""` |  |
-| kubernetesConnection.cnrm.clusterResourceNamespace | string | `""` |  |
-| kubernetesConnection.cnrm.gke.cluster | string | `""` |  |
-| kubernetesConnection.cnrm.gke.connection | string | `""` |  |
-| kubernetesConnection.cnrm.gke.credentials | object | `{}` |  |
-| kubernetesConnection.cnrm.gke.endpoint | string | `""` |  |
-| kubernetesConnection.cnrm.gke.projectID | string | `""` |  |
-| kubernetesConnection.cnrm.gke.skipTLSVerify | bool | `false` |  |
-| kubernetesConnection.cnrm.gke.zone | string | `""` |  |
+| kubernetesConnection.cnrm | string | `nil` |  |
 | kubernetesConnection.connection | string | `""` |  |
-| kubernetesConnection.eks.accessKey | object | `{}` |  |
-| kubernetesConnection.eks.assumeRole | string | `""` |  |
-| kubernetesConnection.eks.cluster | string | `""` |  |
-| kubernetesConnection.eks.connection | string | `""` |  |
-| kubernetesConnection.eks.endpoint | string | `""` |  |
-| kubernetesConnection.eks.region | string | `""` |  |
-| kubernetesConnection.eks.secretKey | object | `{}` |  |
-| kubernetesConnection.eks.sessionToken | object | `{}` |  |
-| kubernetesConnection.eks.skipTLSVerify | bool | `false` |  |
-| kubernetesConnection.gke.cluster | string | `""` |  |
-| kubernetesConnection.gke.connection | string | `""` |  |
-| kubernetesConnection.gke.credentials | object | `{}` |  |
-| kubernetesConnection.gke.endpoint | string | `""` |  |
-| kubernetesConnection.gke.projectID | string | `""` |  |
-| kubernetesConnection.gke.skipTLSVerify | bool | `false` |  |
-| kubernetesConnection.gke.zone | string | `""` |  |
-| kubernetesConnection.kubeconfig | object | `{}` |  |
+| kubernetesConnection.eks | string | `nil` |  |
+| kubernetesConnection.gke | string | `nil` |  |
+| kubernetesConnection.kubeconfig | string | `nil` |  |
 | labels | object | `{}` |  |
 | metrics.enabled | bool | `true` |  |
 | metrics.queries | object | `{"gke":{"cluster_cpu":"1000 * sum(rate(kubernetes_io:container_cpu_core_usage_time{container_name!=\"\",cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}[5m]))","cluster_max_cpu":"1000 * sum(kubernetes_io:container_cpu_limit_cores{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}})","cluster_max_memory":"sum(kubernetes_io:container_memory_limit_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}})","cluster_memory":"sum(kubernetes_io:container_memory_used_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}})","cluster_name":"","namespace_cpu":"sum(rate(label_replace(kubernetes_io:container_cpu_core_usage_time{container_name!=\"\",cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"namespace\",\"$1\",\"namespace_name\", \"(.+)\")[5m])) by (namespace)","namespace_memory":"sum(label_replace(kubernetes_io:container_memory_used_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"namespace\",\"$1\",\"namespace_name\", \"(.+)\")) by (namespace)","node_cpu":"sum(rate(label_replace(kubernetes_io:node_cpu_core_usage_time{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"node\",\"$1\",\"node_name\", \"(.+)\")[5m:])) by (node)","node_memory":"sum(label_replace(kubernetes_io:container_memory_used_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"node\",\"$1\",\"node_name\", \"(.+)\")) by (node)","node_storage":"sum(label_replace(kubernetes_io:node_ephemeral_storage_used_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}},  \"node\",\"$1\",\"node_name\", \"(.+)\")) by (node)","pod_cpu":"sum(rate(label_replace(kubernetes_io:container_cpu_core_usage_time{container_name!=\"\",cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"pod\",\"$1\",\"pod_name\", \"(.+)\")[5m:])) by (pod)","pod_memory":"sum(label_replace(kubernetes_io:container_memory_used_bytes{cluster_name=\"{{.Values.metrics.queries.gke.cluster_name}}\"{{.Values.prometheus.labels}}}, \"pod\",\"$1\",\"pod_name\", \"(.+)\")) by (pod)"},"prometheus":{"cluster_cpu":"1000 * sum(rate(container_cpu_usage_seconds_total{container!=\"\"{{.Values.prometheus.labels}}}[5m]))","cluster_max_cpu":"1000 * sum(kube_pod_container_resource_limits{resource=\"cpu\"{{.Values.prometheus.labels}}})","cluster_max_memory":"sum(kube_pod_container_resource_limits{resource=\"memory\"{{.Values.prometheus.labels}}})","cluster_memory":"sum(container_memory_working_set_bytes{container!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}})","namespace_cpu":"1000 * sum(rate(container_cpu_usage_seconds_total{container!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}}[5m])) by (namespace)","namespace_memory":"sum(container_memory_working_set_bytes{container!=\"\",pod!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}} * on(pod, namespace) group_left kube_pod_status_phase{phase=\"Running\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}} > 0) by (namespace)","node_cpu":"1000 * sum(rate(container_cpu_usage_seconds_total{container!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}}[5m])) by (node)","node_memory":"sum(container_memory_working_set_bytes{container!=\"\",pod!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}} * on(pod, namespace) group_left kube_pod_status_phase{phase=\"Running\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}} > 0) by (node)","node_storage":"max by (instance) (avg_over_time(node_filesystem_avail_bytes{mountpoint=\"/\",fstype!=\"rootfs\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}}[5m]))","pod_cpu":"1000 * sum(rate(container_cpu_usage_seconds_total{container!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}}[5m])) by (pod)","pod_memory":"sum(container_memory_working_set_bytes{container!=\"\"{{.Values.prometheus.labels | default .Values.prometheusLabels}}}) by (pod)"}}` | queries to retrieve cpu/memory metrics for cluster/node/pod |
@@ -174,6 +152,13 @@ A Helm chart for the Kubernetes bundle of Flanksource Mission Control
 | topology.ingress.nameExpr | string | `"r.config.spec.rules.size() > 0 ? r.config.spec.rules[0].host : r.name"` |  |
 | topology.name | string | `"{{ .Values.clusterName }}"` |  |
 | topology.schedule | string | `"@every 5m"` |  |
+| views.cluster.enabled | bool | `true` |  |
+| views.cluster.sidebar | bool | `true` |  |
+| views.enabled | bool | `true` |  |
+| views.helm_releases.enabled | bool | `true` |  |
+| views.helm_releases.sidebar | bool | `true` |  |
+| views.pods.enabled | bool | `true` | if true, the view will be enabled A prometheus connection is required. |
+| views.pods.sidebar | bool | `true` |  |
 
 ## Maintainers
 
diff --git a/charts/kubernetes/templates/views/deployments.yaml b/charts/kubernetes/templates/views/deployments.yaml
@@ -0,0 +1,87 @@
+{{- if and .Values.views.enabled .Values.views.helm_releases.enabled }}
+apiVersion: mission-control.flanksource.com/v1
+kind: View
+metadata:
+  name: helm_releases
+  labels:
+    {{- include "kubernetes.labels" . | nindent 4 }}
+spec:
+  display:
+    title: Helm Releases
+    icon: rocket
+    {{- if .Values.views.helm_releases.sidebar }}
+    sidebar: true
+    {{- end }}
+  panels:
+    - name: Health
+      description: Helm Releases grouped by health
+      type: piechart
+      piechart:
+        showLabels: true
+        colors:
+          healthy: "#28C19B"
+          unhealthy: "#F04E6E"
+          unknown: "#666666"
+          warning: "#F4B23C"
+      query: SELECT COUNT(*) AS count, health FROM helm_releases GROUP BY health
+    - name: Status
+      description: Helm Releases grouped by status
+      type: piechart
+      piechart:
+        colors:
+          InstallSucceeded: "#28C19B"
+          RollbackSucceeded: "#F4B23C"
+          UpgradeFailed: "#F04E6E"
+          UpgradeSucceeded: "#5965F2"
+          Reconciling: "#666666"
+      query: SELECT COUNT(*) AS count, status FROM helm_releases GROUP BY status
+  columns:
+    - name: id
+      type: string
+      description: The id of the deployment.
+      primaryKey: true
+      hidden: true
+    - name: application
+      type: string
+      description: The application name.
+      url:
+        config: row.id
+    - name: namespace
+      type: string
+      description: The namespace name.
+      filter:
+        type: multiselect
+      url:
+        config: f("name=$(tags.namespace) tags.cluster=$(tags.cluster) type=Kubernetes::Namespace", row)
+    - name: chart
+      type: string
+      description: The chart name.
+    - name: version
+      type: string
+      description: The version of the deployment.
+    - name: status
+      type: status
+      description: The status of the deployment.
+      filter:
+        type: multiselect
+    - name: health
+      type: health
+      description: The health of the deployment.
+      filter:
+        type: multiselect
+    - name: lastUpdated
+      type: datetime
+      description: The last updated time.
+  queries:
+    helm_releases:
+      configs:
+        tagSelector: "cluster={{ .Values.clusterName }}"
+        types:
+          - Kubernetes::HelmRelease
+  mapping:
+    application: row.name
+    namespace: row.tags.namespace
+    chart: row.config.status.history[0].chartName
+    version: row.config.status.history[0].chartVersion
+    lastUpdated: row.updated_at
+{{- end }}
diff --git a/charts/kubernetes/templates/views/overview.yaml b/charts/kubernetes/templates/views/overview.yaml
@@ -0,0 +1,71 @@
+{{- if and .Values.views.enabled .Values.views.cluster.enabled .Values.prometheus.connection }}
+apiVersion: mission-control.flanksource.com/v1
+kind: View
+metadata:
+  name: cluster-overview
+  labels:
+    {{- include "kubernetes-view.labels" . | nindent 4 }}
+spec:
+  display:
+    title: Cluster
+    icon: overview
+    {{- if .Values.views.cluster.sidebar }}
+    sidebar: true
+    {{- end }}
+    plugins:
+      - configTab:
+          types:
+            - Kubernetes::Cluster
+  panels:
+    - name: Resources
+      description: Count of resources grouped by type
+      type: table
+      query: SELECT * FROM resource_count_by_type
+    - name: Total CPU Cores
+      description: Total CPU cores available
+      type: number
+      query: SELECT value FROM cpu_cores_count
+    - name: Total Memory Available
+      description: Total memory available (GB)
+      type: number
+      number:
+        unit: GB
+        precision: 2
+      query: SELECT value FROM memory_available_count
+    - name: Current Memory Usage
+      description: Current memory usage (GB)
+      type: number
+      number:
+        unit: GB
+      query: SELECT value FROM memory_usage_count
+  queries:
+    cpu_cores_count:
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          sum(kube_node_status_allocatable{resource="cpu"})
+    memory_available_count:
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          sum(kube_node_status_allocatable{resource="memory"}) / 1024 / 1024 / 1024
+    memory_usage_count:
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          sum(container_memory_working_set_bytes{container!="POD"}) / 1024 / 1024 / 1024
+    resource_count_by_type:
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          (label_replace(count(kube_node_info), "resource_type", "Nodes", "", "")) or 
+          (label_replace(count(kube_namespace_status_phase{phase="Active"}), "resource_type", "Namespaces", "", "")) or 
+          (label_replace(count(kube_pod_status_phase{phase="Running"}), "resource_type", "Running Pods", "", "")) or 
+          (label_replace(count(kube_deployment_status_replicas), "resource_type", "Deployments", "", "")) or 
+          (label_replace(count(kube_statefulset_status_replicas), "resource_type", "StatefulSets", "", "")) or 
+          (label_replace(count(kube_daemonset_status_number_ready), "resource_type", "DaemonSets", "", "")) or 
+          (label_replace(count(kube_persistentvolume_info), "resource_type", "Persistent Volumes", "", "")) or 
+          (label_replace(count(kube_persistentvolumeclaim_info), "resource_type", "Persistent Volume Claims", "", "")) or 
+          (label_replace(count(kube_ingress_info), "resource_type", "Ingresses", "", "")) or 
+          (label_replace(count(kube_cronjob_info), "resource_type", "CronJobs", "", ""))
+{{- end }}
diff --git a/charts/kubernetes/templates/views/pods.yaml b/charts/kubernetes/templates/views/pods.yaml
@@ -0,0 +1,125 @@
+{{- if and .Values.views.enabled .Values.views.pods.enabled .Values.prometheus.connection }}
+apiVersion: mission-control.flanksource.com/v1
+kind: View
+metadata:
+  name: pods
+  labels:
+    {{- include "kubernetes.labels" . | nindent 4 }}
+spec:
+  display:
+    title: Pods
+    icon: pod
+    {{- if .Values.views.pods.sidebar }}
+    sidebar: true
+    {{- end }}
+  columns:
+    - name: namespace
+      type: badge
+      primaryKey: true
+      filter:
+        type: multiselect
+    - name: name
+      type: string
+      primaryKey: true
+      url:
+        config: row.id
+    - name: status
+      type: status
+      icon: row.health
+      filter:
+        type: multiselect
+    - name: health
+      type: health
+      hidden: true
+      filter:
+        type: multiselect
+    - name: memory
+      type: gauge
+      unit: bytes
+      description: Memory usage
+      gauge:
+        max: row.memory_limit
+        thresholds:
+          - percent: 0
+            color: green
+          - percent: 50
+            color: orange
+          - percent: 80
+            color: red
+    - name: cpu
+      type: gauge
+      unit: millicore
+      gauge:
+        max: row.cpu_limit
+        thresholds:
+          - percent: 0
+            color: '#8BC34A'
+          - percent: 50
+            color: '#FF8C42'
+          - percent: 80
+            color: '#E8589C'
+    - name: updated_at
+      type: datetime
+  merge: |
+    SELECT
+      pod.id,
+      pod.name,
+      json_extract(pod.tags, '$.namespace') AS namespace,
+      pod.status,
+      pod.health,
+      pod.updated_at,
+      CAST(memory.value AS TEXT) as memory,
+      to_bytes(COALESCE(
+        json_extract(pod.config, '$.spec.containers[0].resources.limits.memory'), 
+        ''
+      )) AS memory_limit,
+      COALESCE(CAST(cpu.value AS TEXT), '0') as cpu,
+      to_millicores(COALESCE(
+        json_extract(pod.config, '$.spec.containers[0].resources.limits.cpu'), 
+        ''
+      )) AS cpu_limit
+    FROM pod
+    LEFT JOIN memory
+      ON pod.name = memory.pod 
+      AND json_extract(pod.tags, '$.namespace') = memory.namespace
+    LEFT JOIN cpu
+      ON pod.name = cpu.pod 
+      AND json_extract(pod.tags, '$.namespace') = cpu.namespace
+    ORDER BY namespace, name
+  queries:
+    memory:
+      columns:
+        namespace: string
+        pod: string
+        value: decimal
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          sum by (namespace, pod) (
+            container_memory_working_set_bytes{
+              container!="POD", # Skip The pause/infra container
+              image!="" # Skip dead containers
+            }
+          )
+    cpu:
+      columns:
+        namespace: string
+        pod: string
+        value: decimal
+      prometheus:
+        connection: {{ .Values.prometheus.connection }}
+        query: |
+          sum by (namespace, pod) (
+            irate(container_cpu_usage_seconds_total{
+              container!="POD", # Skip The pause/infra container
+              image!="" # Skip dead containers
+            }[30s])
+          ) * 1000
+    pod:
+      configs:
+        tagSelector: "cluster={{ .Values.clusterName }}"
+        types:
+          - Kubernetes::Pod
+  mapping:
+    created: row.created_at
+{{- end }}
diff --git a/charts/kubernetes/values.schema.json b/charts/kubernetes/values.schema.json
diff --git a/charts/kubernetes/values.yaml b/charts/kubernetes/values.yaml
