jsonnet: Update to latest kubernetes-mixin

Pick up new alerts for unreachable nodes.

manifests/grafana-deployment.yaml

@@ -45,6 +45,9 @@ spec:
         - mountPath: /grafana-dashboard-definitions/0/apiserver
           name: grafana-dashboard-apiserver
           readOnly: false
+        - mountPath: /grafana-dashboard-definitions/0/cluster-total
+          name: grafana-dashboard-cluster-total
+          readOnly: false
         - mountPath: /grafana-dashboard-definitions/0/controller-manager
           name: grafana-dashboard-controller-manager
           readOnly: false
@@ -69,6 +72,12 @@ spec:
         - mountPath: /grafana-dashboard-definitions/0/kubelet
           name: grafana-dashboard-kubelet
           readOnly: false
+        - mountPath: /grafana-dashboard-definitions/0/namespace-by-pod
+          name: grafana-dashboard-namespace-by-pod
+          readOnly: false
+        - mountPath: /grafana-dashboard-definitions/0/namespace-by-workload
+          name: grafana-dashboard-namespace-by-workload
+          readOnly: false
         - mountPath: /grafana-dashboard-definitions/0/node-cluster-rsrc-use
           name: grafana-dashboard-node-cluster-rsrc-use
           readOnly: false
@@ -81,6 +90,9 @@ spec:
         - mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage
           name: grafana-dashboard-persistentvolumesusage
           readOnly: false
+        - mountPath: /grafana-dashboard-definitions/0/pod-total
+          name: grafana-dashboard-pod-total
+          readOnly: false
         - mountPath: /grafana-dashboard-definitions/0/pods
           name: grafana-dashboard-pods
           readOnly: false
@@ -99,6 +111,9 @@ spec:
         - mountPath: /grafana-dashboard-definitions/0/statefulset
           name: grafana-dashboard-statefulset
           readOnly: false
+        - mountPath: /grafana-dashboard-definitions/0/workload-total
+          name: grafana-dashboard-workload-total
+          readOnly: false
       nodeSelector:
         beta.kubernetes.io/os: linux
       securityContext:
@@ -117,6 +132,9 @@ spec:
       - configMap:
           name: grafana-dashboard-apiserver
         name: grafana-dashboard-apiserver
+      - configMap:
+          name: grafana-dashboard-cluster-total
+        name: grafana-dashboard-cluster-total
       - configMap:
           name: grafana-dashboard-controller-manager
         name: grafana-dashboard-controller-manager
@@ -141,6 +159,12 @@ spec:
       - configMap:
           name: grafana-dashboard-kubelet
         name: grafana-dashboard-kubelet
+      - configMap:
+          name: grafana-dashboard-namespace-by-pod
+        name: grafana-dashboard-namespace-by-pod
+      - configMap:
+          name: grafana-dashboard-namespace-by-workload
+        name: grafana-dashboard-namespace-by-workload
       - configMap:
           name: grafana-dashboard-node-cluster-rsrc-use
         name: grafana-dashboard-node-cluster-rsrc-use
@@ -153,6 +177,9 @@ spec:
       - configMap:
           name: grafana-dashboard-persistentvolumesusage
         name: grafana-dashboard-persistentvolumesusage
+      - configMap:
+          name: grafana-dashboard-pod-total
+        name: grafana-dashboard-pod-total
       - configMap:
           name: grafana-dashboard-pods
         name: grafana-dashboard-pods
@@ -171,3 +198,6 @@ spec:
       - configMap:
           name: grafana-dashboard-statefulset
         name: grafana-dashboard-statefulset
+      - configMap:
+          name: grafana-dashboard-workload-total
+        name: grafana-dashboard-workload-total

manifests/prometheus-rules.yaml

@@ -79,6 +79,22 @@ spec:
           rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])
         ) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
       record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
+    - expr: |
+        container_memory_working_set_bytes{job="kubelet", image!=""}
+        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
+      record: node_namespace_pod_container:container_memory_working_set_bytes
+    - expr: |
+        container_memory_rss{job="kubelet", image!=""}
+        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
+      record: node_namespace_pod_container:container_memory_rss
+    - expr: |
+        container_memory_cache{job="kubelet", image!=""}
+        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
+      record: node_namespace_pod_container:container_memory_cache
+    - expr: |
+        container_memory_swap{job="kubelet", image!=""}
+        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
+      record: node_namespace_pod_container:container_memory_swap
     - expr: |
         sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace)
       record: namespace:container_memory_usage_bytes:sum
@@ -583,6 +599,16 @@ spec:
       for: 15m
       labels:
         severity: critical
+    - alert: KubeContainerWaiting
+      annotations:
+        message: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}}
+          has been in waiting state for longer than 1 hour.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
+      expr: |
+        sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
+      for: 1h
+      labels:
+        severity: warning
     - alert: KubeDaemonSetNotScheduled
       annotations:
         message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
@@ -797,6 +823,14 @@ spec:
       for: 15m
       labels:
         severity: warning
+    - alert: KubeNodeUnreachable
+      annotations:
+        message: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.'
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable
+      expr: |
+        kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1
+      labels:
+        severity: warning
     - alert: KubeVersionMismatch
       annotations:
         message: There are {{ $value }} different semantic versions of Kubernetes