*: Update to Prometheus v2.4.3

README.md

@@ -223,7 +223,7 @@ These are the available fields with their respective default values:
         kubeRbacProxy: "v0.3.1",
         addonResizer: "1.0",
         prometheusOperator: "v0.23.2",
-        prometheus: "v2.3.2",
+        prometheus: "v2.4.3",
     },
 
     imageRepos+:: {

jsonnet/kube-prometheus/prometheus/prometheus.libsonnet

@@ -5,7 +5,7 @@ local k = import 'ksonnet/ksonnet.beta.3/k.libsonnet';
     namespace: 'default',
 
     versions+:: {
-      prometheus: 'v2.4.2',
+      prometheus: 'v2.4.3',
     },
 
     imageRepos+:: {

jsonnetfile.lock.json

@@ -8,7 +8,7 @@
                     "subdir": "contrib/kube-prometheus/jsonnet/kube-prometheus"
                 }
             },
-            "version": "004e648d186bc7be6f1f519da26f96bc2533f1b6"
+            "version": "e53530d13d400496721104c2d30f52fe2b6ff427"
         },
         {
             "name": "ksonnet",
@@ -28,7 +28,7 @@
                     "subdir": ""
                 }
             },
-            "version": "19da1eb2f2558dad0f8d9e280cc1fe7bc835677b"
+            "version": "d24c4066aa2653370e1403812202eb38b2e70210"
         },
         {
             "name": "grafonnet",
@@ -58,7 +58,7 @@
                     "subdir": "grafana"
                 }
             },
-            "version": "9a20f81c9007e4c7409dd0b3edda1a7a78ad2c63"
+            "version": "850525cfa7a82115cf7a8a85f5ca632f4632be3d"
         },
         {
             "name": "prometheus-operator",
@@ -78,7 +78,7 @@
                     "subdir": "Documentation/etcd-mixin"
                 }
             },
-            "version": "c74998267c71ef4a0fa847ce16d620b7fe3580bf"
+            "version": "ba606bf85edfb3007f27a97d41f54e3fe3f70ce6"
         }
     ]
 }

manifests/grafana-deployment.yaml

@@ -16,7 +16,7 @@ spec:
         app: grafana
     spec:
       containers:
-      - image: grafana/grafana:5.2.1
+      - image: grafana/grafana:5.2.4
         name: grafana
         ports:
         - containerPort: 3000

manifests/prometheus-prometheus.yaml

@@ -25,4 +25,4 @@ spec:
   serviceAccountName: prometheus-k8s
   serviceMonitorNamespaceSelector: {}
   serviceMonitorSelector: {}
-  version: v2.4.2
+  version: v2.4.3

manifests/prometheus-rules.yaml

@@ -565,10 +565,10 @@ spec:
     - alert: KubePodCrashLooping
       annotations:
         message: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
-          }}) is restarting {{ printf "%.2f" $value }} times / second.
+          }}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
       expr: |
-        rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) > 0
+        rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0
       for: 1h
       labels:
         severity: critical
@@ -784,6 +784,17 @@ spec:
       for: 15m
       labels:
         severity: warning
+    - alert: CPUThrottlingHigh
+      annotations:
+        message: '{{ printf "%0.0f" $value }}% throttling of CPU in namespace {{ $labels.namespace
+          }} for {{ $labels.container_name }}.'
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
+      expr: "100 * sum(increase(container_cpu_cfs_throttled_periods_total[5m])) by
+        (container_name, pod_name, namespace) \n  / \nsum(increase(container_cpu_cfs_periods_total[5m]))
+        by (container_name, pod_name, namespace)\n  > 25 \n"
+      for: 15m
+      labels:
+        severity: warning
   - name: kubernetes-storage
     rules:
     - alert: KubePersistentVolumeUsageCritical
@@ -807,7 +818,13 @@ spec:
           days. Currently {{ $value }} bytes are available.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays
       expr: |
-        kubelet_volume_stats_available_bytes{job="kubelet"} and predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
+        (
+          kubelet_volume_stats_used_bytes{job="kubelet"}
+            /
+          kubelet_volume_stats_capacity_bytes{job="kubelet"}
+        ) > 0.85
+        and
+        predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
       for: 5m
       labels:
         severity: critical