mirror of
https://github.com/prometheus-operator/prometheus-operator.git
synced 2025-04-16 09:16:38 +00:00
62baa3f73c
89fc4e3069 introduced the new Prometheus
rule file custom resource definition. This patch adjusts the
kube-prometheus project to use the new custom resource definition.
796 lines
32 KiB
YAML
796 lines
32 KiB
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: RuleFile
|
|
metadata:
|
|
labels:
|
|
prometheus: k8s
|
|
role: alert-rules
|
|
name: prometheus-k8s-rules
|
|
namespace: monitoring
|
|
spec:
|
|
groups:
|
|
- name: k8s.rules
|
|
rules:
|
|
- expr: |
|
|
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[5m])) by (namespace)
|
|
record: namespace:container_cpu_usage_seconds_total:sum_rate
|
|
- expr: |
|
|
sum(container_memory_usage_bytes{job="kubelet", image!=""}) by (namespace)
|
|
record: namespace:container_memory_usage_bytes:sum
|
|
- expr: |
|
|
sum by (namespace, label_name) (
|
|
sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!=""}[5m])) by (namespace, pod_name)
|
|
* on (namespace, pod_name) group_left(label_name)
|
|
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
|
|
)
|
|
record: namespace_name:container_cpu_usage_seconds_total:sum_rate
|
|
- expr: |
|
|
sum by (namespace, label_name) (
|
|
sum(container_memory_usage_bytes{job="kubelet",image!=""}) by (pod_name, namespace)
|
|
* on (namespace, pod_name) group_left(label_name)
|
|
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
|
|
)
|
|
record: namespace_name:container_memory_usage_bytes:sum
|
|
- expr: |
|
|
sum by (namespace, label_name) (
|
|
sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}) by (namespace, pod)
|
|
* on (namespace, pod) group_left(label_name)
|
|
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
|
|
)
|
|
record: namespace_name:kube_pod_container_resource_requests_memory_bytes:sum
|
|
- expr: |
|
|
sum by (namespace, label_name) (
|
|
sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} and on(pod) kube_pod_status_scheduled{condition="true"}) by (namespace, pod)
|
|
* on (namespace, pod) group_left(label_name)
|
|
label_replace(kube_pod_labels{job="kube-state-metrics"}, "pod_name", "$1", "pod", "(.*)")
|
|
)
|
|
record: namespace_name:kube_pod_container_resource_requests_cpu_cores:sum
|
|
- name: kube-scheduler.rules
|
|
rules:
|
|
- expr: |
|
|
histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.99"
|
|
record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.99"
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.99, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.99"
|
|
record: cluster_quantile:scheduler_binding_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.9"
|
|
record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.9"
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.9, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.9"
|
|
record: cluster_quantile:scheduler_binding_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.5"
|
|
record: cluster_quantile:scheduler_e2e_scheduling_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.5"
|
|
record: cluster_quantile:scheduler_scheduling_algorithm_latency:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.5, sum(rate(scheduler_binding_latency_microseconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.5"
|
|
record: cluster_quantile:scheduler_binding_latency:histogram_quantile
|
|
- name: kube-apiserver.rules
|
|
rules:
|
|
- expr: |
|
|
histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.99"
|
|
record: cluster_quantile:apiserver_request_latencies:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.9, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.9"
|
|
record: cluster_quantile:apiserver_request_latencies:histogram_quantile
|
|
- expr: |
|
|
histogram_quantile(0.5, sum(rate(apiserver_request_latencies_bucket{job="apiserver"}[5m])) without(instance, pod)) / 1e+06
|
|
labels:
|
|
quantile: "0.5"
|
|
record: cluster_quantile:apiserver_request_latencies:histogram_quantile
|
|
- name: node.rules
|
|
rules:
|
|
- expr: sum(min(kube_pod_info) by (node))
|
|
record: ':kube_pod_info_node_count:'
|
|
- expr: |
|
|
max(label_replace(kube_pod_info{job="kube-state-metrics"}, "pod", "$1", "pod", "(.*)")) by (node, namespace, pod)
|
|
record: 'node_namespace_pod:kube_pod_info:'
|
|
- expr: |
|
|
count by (node) (sum by (node, cpu) (
|
|
node_cpu{job="node-exporter"}
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
))
|
|
record: node:node_num_cpu:sum
|
|
- expr: |
|
|
1 - avg(rate(node_cpu{job="node-exporter",mode="idle"}[1m]))
|
|
record: :node_cpu_utilisation:avg1m
|
|
- expr: |
|
|
1 - avg by (node) (
|
|
rate(node_cpu{job="node-exporter",mode="idle"}[1m])
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:)
|
|
record: node:node_cpu_utilisation:avg1m
|
|
- expr: |
|
|
sum(node_load1{job="node-exporter"})
|
|
/
|
|
sum(node:node_num_cpu:sum)
|
|
record: ':node_cpu_saturation_load1:'
|
|
- expr: |
|
|
sum by (node) (
|
|
node_load1{job="node-exporter"}
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
/
|
|
node:node_num_cpu:sum
|
|
record: 'node:node_cpu_saturation_load1:'
|
|
- expr: |
|
|
1 -
|
|
sum(node_memory_MemFree{job="node-exporter"} + node_memory_Cached{job="node-exporter"} + node_memory_Buffers{job="node-exporter"})
|
|
/
|
|
sum(node_memory_MemTotal{job="node-exporter"})
|
|
record: ':node_memory_utilisation:'
|
|
- expr: |
|
|
sum by (node) (
|
|
(node_memory_MemFree{job="node-exporter"} + node_memory_Cached{job="node-exporter"} + node_memory_Buffers{job="node-exporter"})
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_memory_bytes_available:sum
|
|
- expr: |
|
|
sum by (node) (
|
|
node_memory_MemTotal{job="node-exporter"}
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_memory_bytes_total:sum
|
|
- expr: |
|
|
(node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)
|
|
/
|
|
scalar(sum(node:node_memory_bytes_total:sum))
|
|
record: node:node_memory_utilisation:ratio
|
|
- expr: |
|
|
1e3 * sum(
|
|
(rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
|
|
+ rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
|
|
)
|
|
record: :node_memory_swap_io_bytes:sum_rate
|
|
- expr: |
|
|
1 -
|
|
sum by (node) (
|
|
(node_memory_MemFree{job="node-exporter"} + node_memory_Cached{job="node-exporter"} + node_memory_Buffers{job="node-exporter"})
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
/
|
|
sum by (node) (
|
|
node_memory_MemTotal{job="node-exporter"}
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: 'node:node_memory_utilisation:'
|
|
- expr: |
|
|
1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum)
|
|
record: 'node:node_memory_utilisation_2:'
|
|
- expr: |
|
|
1e3 * sum by (node) (
|
|
(rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
|
|
+ rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_memory_swap_io_bytes:sum_rate
|
|
- expr: |
|
|
avg(irate(node_disk_io_time_ms{job="node-exporter",device=~"(sd|xvd).+"}[1m]) / 1e3)
|
|
record: :node_disk_utilisation:avg_irate
|
|
- expr: |
|
|
avg by (node) (
|
|
irate(node_disk_io_time_ms{job="node-exporter",device=~"(sd|xvd).+"}[1m]) / 1e3
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_disk_utilisation:avg_irate
|
|
- expr: |
|
|
avg(irate(node_disk_io_time_weighted{job="node-exporter",device=~"(sd|xvd).+"}[1m]) / 1e3)
|
|
record: :node_disk_saturation:avg_irate
|
|
- expr: |
|
|
avg by (node) (
|
|
irate(node_disk_io_time_weighted{job="node-exporter",device=~"(sd|xvd).+"}[1m]) / 1e3
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_disk_saturation:avg_irate
|
|
- expr: |
|
|
sum(irate(node_network_receive_bytes{job="node-exporter",device="eth0"}[1m])) +
|
|
sum(irate(node_network_transmit_bytes{job="node-exporter",device="eth0"}[1m]))
|
|
record: :node_net_utilisation:sum_irate
|
|
- expr: |
|
|
sum by (node) (
|
|
(irate(node_network_receive_bytes{job="node-exporter",device="eth0"}[1m]) +
|
|
irate(node_network_transmit_bytes{job="node-exporter",device="eth0"}[1m]))
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_net_utilisation:sum_irate
|
|
- expr: |
|
|
sum(irate(node_network_receive_drop{job="node-exporter",device="eth0"}[1m])) +
|
|
sum(irate(node_network_transmit_drop{job="node-exporter",device="eth0"}[1m]))
|
|
record: :node_net_saturation:sum_irate
|
|
- expr: |
|
|
sum by (node) (
|
|
(irate(node_network_receive_drop{job="node-exporter",device="eth0"}[1m]) +
|
|
irate(node_network_transmit_drop{job="node-exporter",device="eth0"}[1m]))
|
|
* on (namespace, pod) group_left(node)
|
|
node_namespace_pod:kube_pod_info:
|
|
)
|
|
record: node:node_net_saturation:sum_irate
|
|
- name: kube-prometheus-node-recording.rules
|
|
rules:
|
|
- expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[3m])) BY (instance)
|
|
record: instance:node_cpu:rate:sum
|
|
- expr: sum((node_filesystem_size{mountpoint="/"} - node_filesystem_free{mountpoint="/"}))
|
|
BY (instance)
|
|
record: instance:node_filesystem_usage:sum
|
|
- expr: sum(rate(node_network_receive_bytes[3m])) BY (instance)
|
|
record: instance:node_network_receive_bytes:rate:sum
|
|
- expr: sum(rate(node_network_transmit_bytes[3m])) BY (instance)
|
|
record: instance:node_network_transmit_bytes:rate:sum
|
|
- expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode)
|
|
/ ON(instance) GROUP_LEFT() count(sum(node_cpu) BY (instance, cpu)) BY (instance)
|
|
record: instance:node_cpu:ratio
|
|
- expr: sum(rate(node_cpu{mode!="idle",mode!="iowait"}[5m]))
|
|
record: cluster:node_cpu:sum_rate5m
|
|
- expr: cluster:node_cpu:rate5m / count(sum(node_cpu) BY (instance, cpu))
|
|
record: cluster:node_cpu:ratio
|
|
- name: kubernetes-absent
|
|
rules:
|
|
- alert: AlertmanagerDown
|
|
annotations:
|
|
message: Alertmanager has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="alertmanager-main"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeAPIDown
|
|
annotations:
|
|
message: KubeAPI has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="apiserver"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeControllerManagerDown
|
|
annotations:
|
|
message: KubeControllerManager has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="kube-controller-manager"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeSchedulerDown
|
|
annotations:
|
|
message: KubeScheduler has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="kube-scheduler"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStateMetricsDown
|
|
annotations:
|
|
message: KubeStateMetrics has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="kube-state-metrics"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeletDown
|
|
annotations:
|
|
message: Kubelet has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="kubelet"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: NodeExporterDown
|
|
annotations:
|
|
message: NodeExporter has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="node-exporter"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusDown
|
|
annotations:
|
|
message: Prometheus has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="prometheus-k8s"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusOperatorDown
|
|
annotations:
|
|
message: PrometheusOperator has disappeared from Prometheus target discovery.
|
|
expr: |
|
|
absent(up{job="prometheus-operator"} == 1)
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- name: kubernetes-apps
|
|
rules:
|
|
- alert: KubePodCrashLooping
|
|
annotations:
|
|
message: '{{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
|
|
}}) is restarting {{ printf "%.2f" $value }} / second'
|
|
expr: |
|
|
rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) > 0
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: KubePodNotReady
|
|
annotations:
|
|
message: '{{ $labels.namespace }}/{{ $labels.pod }} is not ready.'
|
|
expr: |
|
|
sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase!~"Running|Succeeded"}) > 0
|
|
for: 1h
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeDeploymentGenerationMismatch
|
|
annotations:
|
|
message: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} generation
|
|
mismatch
|
|
expr: |
|
|
kube_deployment_status_observed_generation{job="kube-state-metrics"}
|
|
!=
|
|
kube_deployment_metadata_generation{job="kube-state-metrics"}
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeDeploymentReplicasMismatch
|
|
annotations:
|
|
message: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replica
|
|
mismatch
|
|
expr: |
|
|
kube_deployment_spec_replicas{job="kube-state-metrics"}
|
|
!=
|
|
kube_deployment_status_replicas_available{job="kube-state-metrics"}
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStatefulSetReplicasMismatch
|
|
annotations:
|
|
message: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} replica
|
|
mismatch
|
|
expr: |
|
|
kube_statefulset_status_replicas_ready{job="kube-state-metrics"}
|
|
!=
|
|
kube_statefulset_status_replicas{job="kube-state-metrics"}
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeStatefulSetGenerationMismatch
|
|
annotations:
|
|
message: StatefulSet {{ $labels.namespace }}/{{ labels.statefulset }} generation
|
|
mismatch
|
|
expr: |
|
|
kube_statefulset_status_observed_generation{job="kube-state-metrics"}
|
|
!=
|
|
kube_statefulset_metadata_generation{job="kube-state-metrics"}
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeDaemonSetRolloutStuck
|
|
annotations:
|
|
message: Only {{$value}}% of desired pods scheduled and ready for daemon set
|
|
{{$labels.namespace}}/{{$labels.daemonset}}
|
|
expr: |
|
|
kube_daemonset_status_number_ready{job="kube-state-metrics"}
|
|
/
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} * 100 < 100
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeDaemonSetNotScheduled
|
|
annotations:
|
|
message: A number of pods of daemonset {{$labels.namespace}}/{{$labels.daemonset}}
|
|
are not scheduled.
|
|
expr: |
|
|
kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
|
|
-
|
|
kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeDaemonSetMisScheduled
|
|
annotations:
|
|
message: A number of pods of daemonset {{$labels.namespace}}/{{$labels.daemonset}}
|
|
are running where they are not supposed to run.
|
|
expr: |
|
|
kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- name: kubernetes-resources
|
|
rules:
|
|
- alert: KubeCPUOvercommit
|
|
annotations:
|
|
message: Overcommited CPU resource requests on Pods, cannot tolerate node
|
|
failure.
|
|
expr: |
|
|
sum(namespace_name:kube_pod_container_resource_requests_cpu_cores:sum)
|
|
/
|
|
sum(node:node_num_cpu:sum)
|
|
>
|
|
(count(node:node_num_cpu:sum)-1) / count(node:node_num_cpu:sum)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemOvercommit
|
|
annotations:
|
|
message: Overcommited Memory resource requests on Pods, cannot tolerate node
|
|
failure.
|
|
expr: |
|
|
sum(namespace_name:kube_pod_container_resource_requests_memory_bytes:sum)
|
|
/
|
|
sum(node_memory_MemTotal)
|
|
>
|
|
(count(node:node_num_cpu:sum)-1)
|
|
/
|
|
count(node:node_num_cpu:sum)
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeCPUOvercommit
|
|
annotations:
|
|
message: Overcommited CPU resource request quota on Namespaces.
|
|
expr: |
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.cpu"})
|
|
/
|
|
sum(node:node_num_cpu:sum)
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeMemOvercommit
|
|
annotations:
|
|
message: Overcommited Memory resource request quota on Namespaces.
|
|
expr: |
|
|
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="requests.memory"})
|
|
/
|
|
sum(node_memory_MemTotal{job="node-exporter"})
|
|
> 1.5
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeQuotaExceeded
|
|
annotations:
|
|
message: '{{ printf "%0.0f" $value }}% usage of {{ $labels.resource }} in
|
|
namespace {{ $labels.namespace }}.'
|
|
expr: |
|
|
100 * kube_resourcequota{job="kube-state-metrics", type="used"}
|
|
/ ignoring(instance, job, type)
|
|
kube_resourcequota{job="kube-state-metrics", type="hard"}
|
|
> 90
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- name: kubernetes-storage
|
|
rules:
|
|
- alert: KubePersistentVolumeUsageCritical
|
|
annotations:
|
|
message: The persistent volume claimed by {{ $labels.persistentvolumeclaim
|
|
}} in namespace {{ $labels.namespace }} has {{ printf "%0.0f" $value }}%
|
|
free.
|
|
expr: |
|
|
100 * kubelet_volume_stats_available_bytes{job="kubelet"}
|
|
/
|
|
kubelet_volume_stats_capacity_bytes{job="kubelet"}
|
|
< 3
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubePersistentVolumeFullInFourDays
|
|
annotations:
|
|
message: Based on recent sampling, the persistent volume claimed by {{ $labels.persistentvolumeclaim
|
|
}} in namespace {{ $labels.namespace }} is expected to fill up within four
|
|
days.
|
|
expr: |
|
|
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[1h], 4 * 24 * 3600) < 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- name: kubernetes-system
|
|
rules:
|
|
- alert: KubeNodeNotReady
|
|
annotations:
|
|
message: '{{ $labels.node }} has been unready for more than an hour'
|
|
expr: |
|
|
kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeVersionMismatch
|
|
annotations:
|
|
message: There are {{ $value }} different versions of Kubernetes components
|
|
running.
|
|
expr: |
|
|
count(count(kubernetes_build_info{job!="kube-dns"}) by (gitVersion)) > 1
|
|
for: 1h
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientErrors
|
|
annotations:
|
|
message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance
|
|
}}' is experiencing {{ printf "%0.0f" $value }}% errors.'
|
|
expr: |
|
|
sum(rate(rest_client_requests_total{code!~"2.."}[5m])) by (instance, job) * 100
|
|
/
|
|
sum(rate(rest_client_requests_total[5m])) by (instance, job)
|
|
> 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientErrors
|
|
annotations:
|
|
message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance
|
|
}}' is experiencing {{ printf "%0.0f" $value }} errors / sec.'
|
|
expr: |
|
|
sum(rate(ksm_scrape_error_total{job="kube-state-metrics"}[5m])) by (instance, job) > 0.1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeletTooManyPods
|
|
annotations:
|
|
message: Kubelet {{$labels.instance}} is running {{$value}} pods, close to
|
|
the limit of 110.
|
|
expr: |
|
|
kubelet_running_pod_count{job="kubelet"} > 100
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeAPILatencyHigh
|
|
annotations:
|
|
message: The API server has a 99th percentile latency of {{ $value }} seconds
|
|
for {{$labels.verb}} {{$labels.resource}}.
|
|
expr: |
|
|
cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeAPILatencyHigh
|
|
annotations:
|
|
message: The API server has a 99th percentile latency of {{ $value }} seconds
|
|
for {{$labels.verb}} {{$labels.resource}}.
|
|
expr: |
|
|
cluster_quantile:apiserver_request_latencies:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeAPIErrorsHigh
|
|
annotations:
|
|
message: API server is erroring for {{ $value }}% of requests.
|
|
expr: |
|
|
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
|
|
/
|
|
sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 5
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: KubeAPIErrorsHigh
|
|
annotations:
|
|
message: API server is erroring for {{ $value }}% of requests.
|
|
expr: |
|
|
sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
|
|
/
|
|
sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 5
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientCertificateExpiration
|
|
annotations:
|
|
message: Kubernetes API certificate is expiring in less than 7 days.
|
|
expr: |
|
|
histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
|
|
labels:
|
|
severity: warning
|
|
- alert: KubeClientCertificateExpiration
|
|
annotations:
|
|
message: Kubernetes API certificate is expiring in less than 1 day.
|
|
expr: |
|
|
histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
|
|
labels:
|
|
severity: critical
|
|
- name: alertmanager.rules
|
|
rules:
|
|
- alert: AlertmanagerConfigInconsistent
|
|
annotations:
|
|
description: The configuration of the instances of the Alertmanager cluster
|
|
`{{$labels.service}}` are out of sync.
|
|
summary: Configuration out of sync
|
|
expr: |
|
|
count_values("config_hash", alertmanager_config_hash{job="alertmanager-main"}) BY (service) / ON(service) GROUP_LEFT() label_replace(prometheus_operator_alertmanager_spec_replicas{job="prometheus-operator"}, "service", "alertmanager-$1", "alertmanager", "(.*)") != 1
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
- alert: AlertmanagerDownOrMissing
|
|
annotations:
|
|
description: An unexpected number of Alertmanagers are scraped or Alertmanagers
|
|
disappeared from discovery.
|
|
summary: Alertmanager down or missing
|
|
expr: |
|
|
label_replace(prometheus_operator_alertmanager_spec_replicas{job="prometheus-operator"}, "job", "alertmanager-$1", "alertmanager", "(.*)") / ON(job) GROUP_RIGHT() sum(up{job="alertmanager-main"}) BY (job) != 1
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
- alert: AlertmanagerFailedReload
|
|
annotations:
|
|
description: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
|
|
}}/{{ $labels.pod}}.
|
|
summary: Alertmanager's configuration reload failed
|
|
expr: |
|
|
alertmanager_config_last_reload_successful{job="alertmanager-main"} == 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- name: general.rules
|
|
rules:
|
|
- alert: TargetDown
|
|
annotations:
|
|
description: '{{ $value }}% of {{ $labels.job }} targets are down.'
|
|
summary: Targets are down
|
|
expr: 100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: DeadMansSwitch
|
|
annotations:
|
|
description: This is a DeadMansSwitch meant to ensure that the entire Alerting
|
|
pipeline is functional.
|
|
summary: Alerting DeadMansSwitch
|
|
expr: vector(1)
|
|
labels:
|
|
severity: none
|
|
- name: kube-prometheus-node-alerting.rules
|
|
rules:
|
|
- alert: NodeDiskRunningFull
|
|
annotations:
|
|
description: device {{$labels.device}} on node {{$labels.instance}} is running
|
|
full within the next 24 hours (mounted at {{$labels.mountpoint}})
|
|
summary: Node disk is running full within 24 hours
|
|
expr: |
|
|
predict_linear(node_filesystem_free{job="node-exporter"}[6h], 3600 * 24) < 0
|
|
for: 30m
|
|
labels:
|
|
severity: warning
|
|
- alert: NodeDiskRunningFull
|
|
annotations:
|
|
description: device {{$labels.device}} on node {{$labels.instance}} is running
|
|
full within the next 2 hours (mounted at {{$labels.mountpoint}})
|
|
summary: Node disk is running full within 2 hours
|
|
expr: |
|
|
predict_linear(node_filesystem_free{job="node-exporter"}[30m], 3600 * 2) < 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- name: prometheus.rules
|
|
rules:
|
|
- alert: PrometheusConfigReloadFailed
|
|
annotations:
|
|
description: Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}}
|
|
summary: Reloading Promehteus' configuration failed
|
|
expr: |
|
|
prometheus_config_last_reload_successful{job="prometheus-k8s"} == 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotificationQueueRunningFull
|
|
annotations:
|
|
description: Prometheus' alert notification queue is running full for {{$labels.namespace}}/{{
|
|
$labels.pod}}
|
|
summary: Prometheus' alert notification queue is running full
|
|
expr: |
|
|
predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job="prometheus-k8s"}
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusErrorSendingAlerts
|
|
annotations:
|
|
description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
|
|
$labels.pod}} to Alertmanager {{$labels.Alertmanager}}
|
|
summary: Errors while sending alert from Prometheus
|
|
expr: |
|
|
rate(prometheus_notifications_errors_total{job="prometheus-k8s"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s"}[5m]) > 0.01
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusErrorSendingAlerts
|
|
annotations:
|
|
description: Errors while sending alerts from Prometheus {{$labels.namespace}}/{{
|
|
$labels.pod}} to Alertmanager {{$labels.Alertmanager}}
|
|
summary: Errors while sending alerts from Prometheus
|
|
expr: |
|
|
rate(prometheus_notifications_errors_total{job="prometheus-k8s"}[5m]) / rate(prometheus_notifications_sent_total{job="prometheus-k8s"}[5m]) > 0.03
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
- alert: PrometheusNotConnectedToAlertmanagers
|
|
annotations:
|
|
description: Prometheus {{ $labels.namespace }}/{{ $labels.pod}} is not connected
|
|
to any Alertmanagers
|
|
summary: Prometheus is not connected to any Alertmanagers
|
|
expr: |
|
|
prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s"} < 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTSDBReloadsFailing
|
|
annotations:
|
|
description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}}
|
|
reload failures over the last four hours.'
|
|
summary: Prometheus has issues reloading data blocks from disk
|
|
expr: |
|
|
increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s"}[2h]) > 0
|
|
for: 12h
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTSDBCompactionsFailing
|
|
annotations:
|
|
description: '{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}}
|
|
compaction failures over the last four hours.'
|
|
summary: Prometheus has issues compacting sample blocks
|
|
expr: |
|
|
increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s"}[2h]) > 0
|
|
for: 12h
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTSDBWALCorruptions
|
|
annotations:
|
|
description: '{{$labels.job}} at {{$labels.instance}} has a corrupted write-ahead
|
|
log (WAL).'
|
|
summary: Prometheus write-ahead log is corrupted
|
|
expr: |
|
|
tsdb_wal_corruptions_total{job="prometheus-k8s"} > 0
|
|
for: 4h
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusNotIngestingSamples
|
|
annotations:
|
|
description: Prometheus {{ $labels.namespace }}/{{ $labels.pod}} isn't ingesting
|
|
samples.
|
|
summary: Prometheus isn't ingesting samples
|
|
expr: |
|
|
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s"}[5m]) <= 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
- alert: PrometheusTargetScapesDuplicate
|
|
annotations:
|
|
description: '{{$labels.namespace}}/{{$labels.pod}} has many samples rejected
|
|
due to duplicate timestamps but different values'
|
|
summary: Prometheus has many samples rejected
|
|
expr: |
|
|
increase(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s"}[5m]) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|