feat(dashboards): new Pod Count per Workload panel

.github/workflows/check-with-upstream.yaml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     name: Check if KSM selectors are present on applicable metrics.
     steps:
-      - uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           persist-credentials: false
       - run: make --always-make check-selectors-ksm

.github/workflows/ci.yaml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     name: Build Go Tools
     steps:
-      - uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           persist-credentials: false
       - uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v6.1.0
@@ -22,7 +22,7 @@ jobs:
           mkdir -p tmp/bin
           cd scripts && go list -e -mod=mod -tags tools -f '{{ range .Imports }}{{ printf "%s\n" .}}{{end}}' ./ | xargs -tI % go build -mod=mod -o ../tmp/bin %
       - name: Upload built tools
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: go-tools
           path: tmp/bin/
@@ -57,11 +57,11 @@ jobs:
             run: make test
 
     steps:
-      - uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           persist-credentials: false
       - name: Download built tools
-        uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0
+        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7.0.0
         with:
           name: go-tools
           path: tmp/bin/

.github/workflows/release.yaml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
 
       - name: Set up Go
         uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v6.1.0
@@ -29,7 +29,7 @@ jobs:
           zip -r kubernetes-mixin-${{ github.ref_name }}.zip dashboards_out prometheus_alerts.yaml prometheus_rules.yaml
 
       - name: Upload artifact
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: kubernetes-mixin-${{ github.ref_name }}.zip
           path: ./
@@ -40,12 +40,12 @@ jobs:
     needs: build
     steps:
       - name: Download artifact
-        uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0
+        uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7.0.0
         with:
           name: kubernetes-mixin-${{ github.ref_name }}.zip
 
       - name: Create release on kubernetes-mixin
-        uses: softprops/action-gh-release@5be0e66d93ac7ed76da52eca8bb058f665c3a5fe # v2.4.2
+        uses: softprops/action-gh-release@a06a81a03ee405af7f2048a818ed3f03bbf83c7b # v2.5.0
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.github/workflows/stale.yml

@@ -10,7 +10,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@5f858e3efba33a5ca4407a664cc011ad407f2008 # v10.1.0
+      - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # v10.1.1
         with:
           days-before-stale: 30
           days-before-close: 7

alerts/apps_alerts.libsonnet

@@ -38,8 +38,8 @@ local utils = import '../lib/utils.libsonnet';
             // label exists for 2 values. This avoids "many-to-many matching
             // not allowed" errors when joining with kube_pod_status_phase.
             expr: |||
-              sum by (namespace, pod, %(clusterLabel)s) (
-                max by(namespace, pod, %(clusterLabel)s) (
+              sum by (namespace, pod, job, %(clusterLabel)s) (
+                max by(namespace, pod, job, %(clusterLabel)s) (
                   kube_pod_status_phase{%(prefixedNamespaceSelector)s%(kubeStateMetricsSelector)s, phase=~"Pending|Unknown"}
                 ) * on(namespace, pod, %(clusterLabel)s) group_left(owner_kind) topk by(namespace, pod, %(clusterLabel)s) (
                   1, max by(namespace, pod, owner_kind, %(clusterLabel)s) (kube_pod_owner{owner_kind!="Job"})

dashboards/resources/multi-cluster.libsonnet

@@ -146,15 +146,15 @@ local var = g.dashboard.variable;
                   'Time 3': 2,
                   'Time 4': 3,
                   'Time 5': 4,
-                  cluster: 5,
+                  [$._config.clusterLabel]: 5,
                   'Value #A': 6,
                   'Value #B': 7,
                   'Value #C': 8,
                   'Value #D': 9,
                   'Value #E': 10,
                 },
                 renameByName: {
-                  cluster: 'Cluster',
+                  [$._config.clusterLabel]: 'Cluster',
                   'Value #A': 'CPU Usage',
                   'Value #B': 'CPU Requests',
                   'Value #C': 'CPU Requests %',
@@ -245,15 +245,15 @@ local var = g.dashboard.variable;
                   'Time 3': 2,
                   'Time 4': 3,
                   'Time 5': 4,
-                  cluster: 5,
+                  [$._config.clusterLabel]: 5,
                   'Value #A': 6,
                   'Value #B': 7,
                   'Value #C': 8,
                   'Value #D': 9,
                   'Value #E': 10,
                 },
                 renameByName: {
-                  cluster: 'Cluster',
+                  [$._config.clusterLabel]: 'Cluster',
                   'Value #A': 'Memory Usage',
                   'Value #B': 'Memory Requests',
                   'Value #C': 'Memory Requests %',

dashboards/resources/variables/cluster.libsonnet

@@ -5,6 +5,6 @@ local common = import './common.libsonnet';
     local datasource = common.datasource(config);
     {
       datasource: datasource,
-      cluster: common.cluster(config, datasource, 'up{%(cadvisorSelector)s}'),
+      cluster: common.cluster(config, datasource),
     },
 }

dashboards/resources/variables/common.libsonnet

@@ -15,20 +15,16 @@ local var = g.dashboard.variable;
       },
     },
 
-  cluster(config, datasourceVar, selectorTemplate)::
+  cluster(config, datasourceVar)::
     var.query.new('cluster')
     + var.query.withDatasourceFromVariable(datasourceVar)
     + var.query.queryTypes.withLabelValues(
       config.clusterLabel,
-      selectorTemplate % config,
+      'up{%(kubeStateMetricsSelector)s}' % config,
     )
     + var.query.generalOptions.withLabel('cluster')
     + var.query.refresh.onTime()
-    + (
-      if config.showMultiCluster
-      then var.query.generalOptions.showOnDashboard.withLabelAndValue()
-      else var.query.generalOptions.showOnDashboard.withNothing()
-    )
+    + var.query.generalOptions.showOnDashboard.withLabelAndValue()
     + var.query.withSort(type='alphabetical'),
 
   namespace(config, datasourceVar)::

dashboards/resources/variables/namespace.libsonnet

@@ -3,7 +3,7 @@ local common = import './common.libsonnet';
 {
   namespace(config)::
     local datasource = common.datasource(config);
-    local clusterVar = common.cluster(config, datasource, 'up{%(kubeStateMetricsSelector)s}');
+    local clusterVar = common.cluster(config, datasource);
     {
       datasource: datasource,
       cluster: clusterVar,

dashboards/resources/variables/pod.libsonnet

@@ -3,7 +3,7 @@ local common = import './common.libsonnet';
 {
   pod(config)::
     local datasource = common.datasource(config);
-    local clusterVar = common.cluster(config, datasource, 'up{%(kubeStateMetricsSelector)s}');
+    local clusterVar = common.cluster(config, datasource);
     {
       datasource: datasource,
       cluster: clusterVar,

dashboards/resources/workload.libsonnet

@@ -80,6 +80,7 @@ local var = g.dashboard.variable;
 
         workload:
           var.query.new('workload')
+          + var.query.selectionOptions.withIncludeAll()
           + var.query.withDatasourceFromVariable(self.datasource)
           + var.query.queryTypes.withLabelValues(
             'workload',
@@ -105,15 +106,15 @@ local var = g.dashboard.variable;
         sum(
             max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate5m{%(clusterLabel)s="$cluster", namespace="$namespace"})
           * on(%(clusterLabel)s, namespace, pod)
-            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload="$workload", workload_type=~"$type"}
+            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload=~"$workload", workload_type=~"$type"}
         ) by (pod)
       ||| % $._config;
 
       local cpuRequestsQuery = |||
         sum(
             max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(kube_pod_container_resource_requests{%(kubeStateMetricsSelector)s, %(clusterLabel)s="$cluster", namespace="$namespace", resource="cpu"})
           * on(%(clusterLabel)s, namespace, pod)
-            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload="$workload", workload_type=~"$type"}
+            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload=~"$workload", workload_type=~"$type"}
         ) by (pod)
       ||| % $._config;
 
@@ -123,7 +124,7 @@ local var = g.dashboard.variable;
         sum(
             max by (%(clusterLabel)s, %(namespaceLabel)s, pod, container)(container_memory_working_set_bytes{%(clusterLabel)s="$cluster", namespace="$namespace", container!="", image!=""})
           * on(%(clusterLabel)s, namespace, pod)
-            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload="$workload", workload_type=~"$type"}
+            group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{%(clusterLabel)s="$cluster", namespace="$namespace", workload=~"$workload", workload_type=~"$type"}
         ) by (pod)
       ||| % $._config;
       local memRequestsQuery = std.strReplace(cpuRequestsQuery, 'cpu', 'memory');
@@ -163,6 +164,45 @@ local var = g.dashboard.variable;
       ];
 
       local panels = [
+        tsPanel.new('Pod Count per Workload')
+        + tsPanel.gridPos.withW(24)
+        + tsPanel.queryOptions.withTargets([
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, deployment) (kube_deployment_spec_replicas{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", deployment="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{deployment}} desired')
+          + prometheus.withRefId('D'),
+
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, deployment) (kube_deployment_status_replicas_available{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", deployment="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{deployment}} available')
+          + prometheus.withRefId('E'),
+
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, statefulset) (kube_statefulset_replicas{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", statefulset="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{statefulset}} desired')
+          + prometheus.withRefId('F'),
+
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, statefulset) (kube_statefulset_status_replicas_ready{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", statefulset="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{statefulset}} available')
+          + prometheus.withRefId('G'),
+
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, daemonset) (kube_daemonset_status_desired_number_scheduled{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", daemonset="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{daemonset}} desired')
+          + prometheus.withRefId('H'),
+
+          prometheus.new(
+            '${datasource}',
+            'sum by (%(clusterLabel)s, %(namespaceLabel)s, daemonset) (kube_daemonset_status_number_available{%(clusterLabel)s="$cluster", %(namespaceLabel)s="$namespace", daemonset="$workload"})' % $._config
+          ) + prometheus.withLegendFormat('{{daemonset}} available')
+          + prometheus.withRefId('I'),
+        ]),
         tsPanel.new('CPU Usage')
         + tsPanel.gridPos.withW(24)
         + tsPanel.queryOptions.withTargets([