move changes to _data/rules.yml

_data/rules.yml

@@ -1693,32 +1693,32 @@ groups:
             slug: kubestate-exporter
             doc_url: https://github.com/kubernetes/kube-state-metrics/tree/master/docs
             rules:
-              - name: Kubernetes node not ready
+              - name: Kubernetes Node not ready
                 description: Node {{ $labels.node }} has been unready for a long time
                 query: 'kube_node_status_condition{condition="Ready",status="true"} == 0'
                 severity: critical
                 for: 10m
-              - name: Kubernetes memory pressure
+              - name: Kubernetes Node memory pressure
-                description: "{{ $labels.node }} has MemoryPressure condition"
+                description: "Node {{ $labels.node }} has MemoryPressure condition"
                 query: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1'
                 severity: critical
                 for: 2m
-              - name: Kubernetes disk pressure
+              - name: Kubernetes Node disk pressure
-                description: "{{ $labels.node }} has DiskPressure condition"
+                description: "Node {{ $labels.node }} has DiskPressure condition"
                 query: 'kube_node_status_condition{condition="DiskPressure",status="true"} == 1'
                 severity: critical
                 for: 2m
-              - name: Kubernetes network unavailable
+              - name: Kubernetes Node network unavailable
-                description: "{{ $labels.node }} has NetworkUnavailable condition"
+                description: "Node {{ $labels.node }} has NetworkUnavailable condition"
                 query: 'kube_node_status_condition{condition="NetworkUnavailable",status="true"} == 1'
                 severity: critical
                 for: 2m
-              - name: Kubernetes out of capacity
+              - name: Kubernetes Node out of pod capacity
-                description: "{{ $labels.node }} is out of capacity"
+                description: "Node {{ $labels.node }} is out of pod capacity"
                 query: 'sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90'
                 severity: warning
                 for: 2m
-              - name: Kubernetes container oom killer
+              - name: Kubernetes Container oom killer
                 description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes."
                 query: '(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1'
                 severity: warning
@@ -1741,83 +1741,83 @@ groups:
                 severity: warning
                 for: 2m
               - name: Kubernetes Volume full in four days
-                description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."
+                description: "Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available."
                 query: 'predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0'
                 severity: critical
               - name: Kubernetes PersistentVolume error
-                description: "Persistent volume is in bad state"
+                description: "Persistent volume {{ $labels.persistentvolume }} is in bad state"
                 query: 'kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0'
                 severity: critical
               - name: Kubernetes StatefulSet down
-                description: A StatefulSet went down
+                description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} went down
                 query: 'kube_statefulset_replicas != kube_statefulset_status_replicas_ready > 0'
                 severity: critical
                 for: 1m
-              - name: Kubernetes HPA scaling ability
+              - name: Kubernetes HPA scale inability
-                description: Pod is unable to scale
+                description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to scale
                 query: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1'
                 severity: warning
                 for: 2m
-              - name: Kubernetes HPA metric availability
+              - name: Kubernetes HPA metrics unavailability
-                description: HPA is not able to collect metrics
+                description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to collect metrics
                 query: 'kube_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1'
                 severity: warning
-              - name: Kubernetes HPA scale capability
+              - name: Kubernetes HPA scale maximum
-                description: The maximum number of desired Pods has been hit
+                description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods
                 query: 'kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas'
                 severity: info
                 for: 2m
               - name: Kubernetes HPA underutilized
-                description: HPA is constantly at minimum replicas for 50% of the time. Potential cost saving here.
+                description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is constantly at minimum replicas for 50% of the time. Potential cost saving here.
                 query: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler) > 3'  # allow minimum 3 replicas running
                 severity: info
               - name: Kubernetes Pod not healthy
-                description: Pod has been in a non-ready state for longer than 15 minutes.
+                description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-running state for longer than 15 minutes.
                 query: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0'
                 severity: critical
                 for: 15m
               - name: Kubernetes pod crash looping
-                description: Pod {{ $labels.pod }} is crash looping
+                description: Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping
                 query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'
                 severity: warning
                 for: 2m
-              - name: Kubernetes ReplicasSet mismatch
+              - name: Kubernetes ReplicaSet replicas mismatch
-                description: Deployment Replicas mismatch
+                description: ReplicaSet {{ $labels.namespace }}/{{ $labels.replicaset }} replicas mismatch
                 query: 'kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas'
                 severity: warning
                 for: 10m
               - name: Kubernetes Deployment replicas mismatch
-                description: Deployment Replicas mismatch
+                description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replicas mismatch
                 query: 'kube_deployment_spec_replicas != kube_deployment_status_replicas_available'
                 severity: warning
                 for: 10m
               - name: Kubernetes StatefulSet replicas mismatch
-                description: A StatefulSet does not match the expected number of replicas.
+                description: StatefulSet does not match the expected number of replicas.
                 query: 'kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas'
                 severity: warning
                 for: 10m
               - name: Kubernetes Deployment generation mismatch
-                description: A Deployment has failed but has not been rolled back.
+                description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has failed but has not been rolled back.
                 query: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation'
                 severity: critical
                 for: 10m
               - name: Kubernetes StatefulSet generation mismatch
-                description: A StatefulSet has failed but has not been rolled back.
+                description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has failed but has not been rolled back.
                 query: 'kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation'
                 severity: critical
                 for: 10m
               - name: Kubernetes StatefulSet update not rolled out
-                description: StatefulSet update has not been rolled out.
+                description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.
                 query: 'max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)'
                 severity: warning
                 for: 10m
               - name: Kubernetes DaemonSet rollout stuck
-                description: Some Pods of DaemonSet are not scheduled or not ready
+                description: Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled or not ready
                 query: 'kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0'
                 severity: warning
                 for: 10m
               - name: Kubernetes DaemonSet misscheduled
-                description: Some DaemonSet Pods are running where they are not supposed to run
+                description: Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} arerunning where they are not supposed to run
                 query: 'kube_daemonset_status_number_misscheduled > 0'
                 severity: critical
                 for: 1m
@@ -1827,7 +1827,7 @@ groups:
                 severity: warning
                 comments: |
                   Threshold should be customized for each cronjob name.
-              - name: Kubernetes job slow completion
+              - name: Kubernetes Job slow completion
                 description: Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.
                 query: 'kube_job_spec_completions - kube_job_status_succeeded - kube_job_status_failed > 0'
                 severity: critical