2017-10-23 02:00:41 +02:00
apiVersion : v1
data :
2019-02-18 21:05:27 +01:00
etcd.yaml : |-
{
"groups": [
{
"name": "etcd" ,
"rules": [
2019-10-20 02:43:47 +02:00
{
"alert": "etcdMembersDown" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }})."
},
"expr": "max by (job) (\n sum by (job) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count by (job,endpoint) (\n sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[3m])) > 0.01\n )\n)\n> 0\n" ,
"for": "3m" ,
"labels": {
"severity": "critical"
}
},
2019-02-18 21:05:27 +01:00
{
"alert": "etcdInsufficientMembers" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": insufficient members ({{ $value }})."
},
"expr": "sum(up{job=~\".*etcd.*\"} == bool 1) by (job) < ((count(up{job=~\".*etcd.*\"}) by (job) + 1) / 2)\n" ,
"for": "3m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdNoLeader" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": member {{ $labels.instance }} has no leader."
},
"expr": "etcd_server_has_leader{job=~\".*etcd.*\"} == 0\n" ,
"for": "1m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdHighNumberOfLeaderChanges" ,
"annotations": {
2020-03-02 08:20:33 +01:00
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated."
2019-02-18 21:05:27 +01:00
},
2020-03-02 08:20:33 +01:00
"expr": "increase((max by (job) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 3\n" ,
"for": "5m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdGRPCRequestsSlow" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}."
},
"expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) by (job, instance, grpc_service, grpc_method, le))\n> 0.15\n" ,
"for": "10m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdMemberCommunicationSlow" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}."
},
"expr": "histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.15\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedProposals" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}."
},
"expr": "rate(etcd_server_proposals_failed_total{job=~\".*etcd.*\"}[15m]) > 5\n" ,
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighFsyncDurations" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}."
},
"expr": "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.5\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighCommitDurations" ,
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}."
},
"expr": "histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.25\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedHTTPRequests" ,
"annotations": {
"message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}"
},
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.01\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedHTTPRequests" ,
"annotations": {
"message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}."
},
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.05\n" ,
"for": "10m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdHTTPRequestsSlow" ,
"annotations": {
"message": "etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow."
},
"expr": "histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))\n> 0.15\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
}
]
}
]
}
kube.yaml : |-
{
"groups": [
2020-03-02 08:20:33 +01:00
{
"name": "kube-apiserver-error" ,
"rules": [
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[5m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate5m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[30m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate30m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[2h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate2h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[6h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate6h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1d"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[3d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate3d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate5m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate5m{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate5m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate30m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate30m{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate30m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1h{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate2h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate2h{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate2h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate6h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate6h{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate6h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1d{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate3d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate3d{job=\"apiserver\"})\n" ,
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate3d"
}
]
},
2019-10-28 10:22:15 +01:00
{
"name": "kube-apiserver.rules" ,
"rules": [
{
2020-03-31 09:50:16 +02:00
"expr": "sum(rate(apiserver_request_duration_seconds_sum{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n/\nsum(rate(apiserver_request_duration_seconds_count{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n" ,
2020-03-02 08:20:33 +01:00
"record": "cluster:apiserver_request_duration_seconds:mean5m"
},
{
2020-03-31 09:50:16 +02:00
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n" ,
2019-10-28 10:22:15 +01:00
"labels": {
"quantile": "0.99"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
2020-03-31 09:50:16 +02:00
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n" ,
2019-10-28 10:22:15 +01:00
"labels": {
"quantile": "0.9"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
2020-03-31 09:50:16 +02:00
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n" ,
2019-10-28 10:22:15 +01:00
"labels": {
"quantile": "0.5"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
}
]
},
2019-02-18 21:05:27 +01:00
{
"name": "k8s.rules" ,
"rules": [
{
2019-07-21 20:02:18 +02:00
"expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])) by (namespace)\n" ,
2019-02-18 21:05:27 +01:00
"record": "namespace:container_cpu_usage_seconds_total:sum_rate"
},
{
2020-03-02 08:20:33 +01:00
"expr": "sum by (cluster, namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info)\n)\n" ,
2019-10-20 02:43:47 +02:00
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate"
2019-02-18 21:05:27 +01:00
},
2019-10-28 10:22:15 +01:00
{
2020-03-02 08:20:33 +01:00
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n" ,
2019-10-28 10:22:15 +01:00
"record": "node_namespace_pod_container:container_memory_working_set_bytes"
},
{
2020-03-02 08:20:33 +01:00
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n" ,
2019-10-28 10:22:15 +01:00
"record": "node_namespace_pod_container:container_memory_rss"
},
{
2020-03-02 08:20:33 +01:00
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n" ,
2019-10-28 10:22:15 +01:00
"record": "node_namespace_pod_container:container_memory_cache"
},
{
2020-03-02 08:20:33 +01:00
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n" ,
2019-10-28 10:22:15 +01:00
"record": "node_namespace_pod_container:container_memory_swap"
},
2019-02-18 21:05:27 +01:00
{
2019-07-21 20:02:18 +02:00
"expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}) by (namespace)\n" ,
2019-02-18 21:05:27 +01:00
"record": "namespace:container_memory_usage_bytes:sum"
},
{
2020-03-02 08:20:33 +01:00
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n" ,
2019-07-21 20:02:18 +02:00
"record": "namespace:kube_pod_container_resource_requests_memory_bytes:sum"
2019-02-18 21:05:27 +01:00
},
{
2020-03-02 08:20:33 +01:00
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n" ,
2019-07-21 20:02:18 +02:00
"record": "namespace:kube_pod_container_resource_requests_cpu_cores:sum"
2019-04-07 08:27:11 +02:00
},
{
2020-03-02 08:20:33 +01:00
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"},\n \"replicaset\", \"$1\", \"owner_name\", \"(.*)\"\n ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (\n 1, max by (replicaset, namespace, owner_name) (\n kube_replicaset_owner{job=\"kube-state-metrics\"}\n )\n ),\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n" ,
2019-04-07 08:27:11 +02:00
"labels": {
"workload_type": "deployment"
},
"record": "mixin_pod_workload"
},
{
2020-03-02 08:20:33 +01:00
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n" ,
2019-04-07 08:27:11 +02:00
"labels": {
"workload_type": "daemonset"
},
"record": "mixin_pod_workload"
},
{
2020-03-02 08:20:33 +01:00
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n" ,
2019-04-07 08:27:11 +02:00
"labels": {
"workload_type": "statefulset"
},
"record": "mixin_pod_workload"
2019-02-18 21:05:27 +01:00
}
]
},
{
"name": "kube-scheduler.rules" ,
"rules": [
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.99"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.99"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.99"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.9"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.9"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.9"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.5"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.5"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
},
{
2019-07-21 20:02:18 +02:00
"expr": "histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\"}[5m])) without(instance, pod))\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"quantile": "0.5"
},
2019-07-21 20:02:18 +02:00
"record": "cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile"
2019-02-18 21:05:27 +01:00
}
]
},
{
"name": "node.rules" ,
"rules": [
{
2020-03-02 08:20:33 +01:00
"expr": "sum(min(kube_pod_info) by (cluster, node))\n" ,
2019-02-18 21:05:27 +01:00
"record": ":kube_pod_info_node_count:"
},
{
2020-03-02 08:20:33 +01:00
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n" ,
2019-02-18 21:05:27 +01:00
"record": "node_namespace_pod:kube_pod_info:"
},
{
2020-03-02 08:20:33 +01:00
"expr": "count by (cluster, node) (sum by (node, cpu) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n))\n" ,
2019-02-18 21:05:27 +01:00
"record": "node:node_num_cpu:sum"
},
{
2020-03-02 08:20:33 +01:00
"expr": "sum(\n node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"} +\n node_memory_Cached_bytes{job=\"node-exporter\"} +\n node_memory_MemFree_bytes{job=\"node-exporter\"} +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n) by (cluster)\n" ,
2019-10-28 10:22:15 +01:00
"record": ":node_memory_MemAvailable_bytes:sum"
2019-02-18 21:05:27 +01:00
}
]
},
2020-03-02 08:20:33 +01:00
{
"name": "kubelet.rules" ,
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n" ,
"labels": {
"quantile": "0.99"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n" ,
"labels": {
"quantile": "0.9"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n" ,
"labels": {
"quantile": "0.5"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
}
]
},
2019-02-18 21:05:27 +01:00
{
"name": "kubernetes-apps" ,
"rules": [
{
"alert": "KubePodCrashLooping" ,
"annotations": {
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) 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]) * 60 * 5 > 0\n" ,
2019-10-20 02:43:47 +02:00
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
},
{
"alert": "KubePodNotReady" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
},
2020-03-02 08:20:33 +01:00
"expr": "sum by (namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}) * on(namespace, pod) group_left(owner_kind) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})) > 0\n" ,
2019-10-20 02:43:47 +02:00
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeDeploymentGenerationMismatch" ,
"annotations": {
"message": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch"
},
"expr": "kube_deployment_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_deployment_metadata_generation{job=\"kube-state-metrics\"}\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeDeploymentReplicasMismatch" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
},
2020-03-02 08:20:33 +01:00
"expr": "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n" ,
2019-10-20 02:43:47 +02:00
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeStatefulSetReplicasMismatch" ,
"annotations": {
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch"
},
2020-03-02 08:20:33 +01:00
"expr": "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeStatefulSetGenerationMismatch" ,
"annotations": {
"message": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch"
},
"expr": "kube_statefulset_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_metadata_generation{job=\"kube-state-metrics\"}\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeStatefulSetUpdateNotRolledOut" ,
"annotations": {
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout"
},
"expr": "max without (revision) (\n kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n unless\n kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n)\n *\n(\n kube_statefulset_replicas{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n)\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeDaemonSetRolloutStuck" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck"
},
2019-10-20 02:43:47 +02:00
"expr": "kube_daemonset_status_number_ready{job=\"kube-state-metrics\"}\n /\nkube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"} < 1.00\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
2019-10-28 10:22:15 +01:00
{
"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\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
2019-02-18 21:05:27 +01:00
{
"alert": "KubeDaemonSetNotScheduled" ,
"annotations": {
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled"
},
"expr": "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeDaemonSetMisScheduled" ,
"annotations": {
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled"
},
"expr": "kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"} > 0\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeCronJobRunning" ,
"annotations": {
"message": "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning"
},
"expr": "time() - kube_cronjob_next_schedule_time{job=\"kube-state-metrics\"} > 3600\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeJobCompletion" ,
"annotations": {
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion"
},
"expr": "kube_job_spec_completions{job=\"kube-state-metrics\"} - kube_job_status_succeeded{job=\"kube-state-metrics\"} > 0\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeJobFailed" ,
"annotations": {
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed"
},
2019-10-20 02:43:47 +02:00
"expr": "kube_job_failed{job=\"kube-state-metrics\"} > 0\n" ,
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeHpaReplicasMismatch" ,
"annotations": {
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch"
},
"expr": "(kube_hpa_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_hpa_status_current_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_hpa_status_current_replicas[15m]) == 0\n" ,
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeHpaMaxedOut" ,
"annotations": {
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout"
},
"expr": "kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_hpa_spec_max_replicas{job=\"kube-state-metrics\"}\n" ,
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
}
]
},
{
"name": "kubernetes-resources" ,
"rules": [
{
"alert": "KubeCPUOvercommit" ,
"annotations": {
"message": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
},
2020-03-02 08:20:33 +01:00
"expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n" ,
2019-02-18 21:05:27 +01:00
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeMemOvercommit" ,
"annotations": {
"message": "Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
},
2020-03-02 08:20:33 +01:00
"expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})\n /\nsum(kube_node_status_allocatable_memory_bytes)\n >\n(count(kube_node_status_allocatable_memory_bytes)-1)\n /\ncount(kube_node_status_allocatable_memory_bytes)\n" ,
2019-02-18 21:05:27 +01:00
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeCPUOvercommit" ,
"annotations": {
"message": "Cluster has overcommitted CPU resource requests for Namespaces." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
},
2019-07-21 20:02:18 +02:00
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n > 1.5\n" ,
2019-02-18 21:05:27 +01:00
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeMemOvercommit" ,
"annotations": {
"message": "Cluster has overcommitted memory resource requests for Namespaces." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
},
2019-07-21 20:02:18 +02:00
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n /\nsum(kube_node_status_allocatable_memory_bytes{job=\"node-exporter\"})\n > 1.5\n" ,
2019-02-18 21:05:27 +01:00
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeQuotaExceeded" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded"
},
2019-10-20 02:43:47 +02:00
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.90\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "CPUThrottlingHigh" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh"
},
2019-10-20 02:43:47 +02:00
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n > ( 100 / 100 )\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
}
]
},
{
"name": "kubernetes-storage" ,
"rules": [
{
"alert": "KubePersistentVolumeUsageCritical" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical"
},
2019-10-20 02:43:47 +02:00
"expr": "kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n < 0.03\n" ,
2019-02-18 21:05:27 +01:00
"for": "1m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubePersistentVolumeFullInFourDays" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
},
2019-10-20 02:43:47 +02:00
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n" ,
2020-03-02 08:20:33 +01:00
"for": "1h" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
},
{
"alert": "KubePersistentVolumeErrors" ,
"annotations": {
"message": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors"
},
"expr": "kube_persistentvolume_status_phase{phase=~\"Failed|Pending\",job=\"kube-state-metrics\"} > 0\n" ,
"for": "5m" ,
"labels": {
"severity": "critical"
}
}
]
},
{
"name": "kubernetes-system" ,
"rules": [
{
"alert": "KubeVersionMismatch" ,
"annotations": {
"message": "There are {{ $value }} different semantic versions of Kubernetes components running." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch"
},
2019-10-20 02:43:47 +02:00
"expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*.[0-9]*).*\"))) > 1\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeClientErrors" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'" ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
},
2019-10-20 02:43:47 +02:00
"expr": "(sum(rate(rest_client_requests_total{code=~\"5..\"}[5m])) by (instance, job)\n /\nsum(rate(rest_client_requests_total[5m])) by (instance, job))\n> 0.01\n" ,
2019-02-18 21:05:27 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
2019-10-28 10:22:15 +01:00
}
]
},
2020-03-02 08:20:33 +01:00
{
"name": "kube-apiserver-error-alerts" ,
"rules": [
{
"alert": "ErrorBudgetBurn" ,
"annotations": {
2020-03-31 09:50:16 +02:00
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})" ,
2020-03-02 08:20:33 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1h{job=\"apiserver\"} > (14.4*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate5m{job=\"apiserver\"} > (14.4*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (6*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate30m{job=\"apiserver\"} > (6*0.010000)\n)\n" ,
"labels": {
"job": "apiserver" ,
"severity": "critical"
}
},
{
"alert": "ErrorBudgetBurn" ,
"annotations": {
2020-03-31 09:50:16 +02:00
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})" ,
2020-03-02 08:20:33 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1d{job=\"apiserver\"} > (3*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate2h{job=\"apiserver\"} > (3*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate3d{job=\"apiserver\"} > (0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (0.010000)\n)\n" ,
"labels": {
"job": "apiserver" ,
"severity": "warning"
}
}
]
},
2019-10-28 10:22:15 +01:00
{
"name": "kubernetes-system-apiserver" ,
"rules": [
2019-02-18 21:05:27 +01:00
{
"alert": "KubeAPILatencyHigh" ,
"annotations": {
2020-03-02 08:20:33 +01:00
"message": "The API server has an abnormal latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
2020-03-02 08:20:33 +01:00
"expr": "(\n cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"}\n >\n on (verb) group_left()\n (\n avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n +\n 2*stddev by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n )\n) > on (verb) group_left()\n1.2 * avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\nand on (verb,resource)\ncluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"}\n>\n1\n" ,
"for": "5m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeAPILatencyHigh" ,
"annotations": {
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
2020-03-02 08:20:33 +01:00
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"} > 4\n" ,
2019-02-18 21:05:27 +01:00
"for": "10m" ,
"labels": {
"severity": "critical"
}
},
2019-03-14 07:05:14 +01:00
{
"alert": "KubeAPIErrorsHigh" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}." ,
2019-03-14 07:05:14 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
2019-10-28 10:22:15 +01:00
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.10\n" ,
2019-03-14 07:05:14 +01:00
"for": "10m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh" ,
"annotations": {
2019-10-20 02:43:47 +02:00
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}." ,
2019-03-14 07:05:14 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
2019-10-28 10:22:15 +01:00
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.05\n" ,
2019-02-18 21:05:27 +01:00
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeClientCertificateExpiration" ,
"annotations": {
2020-04-26 01:50:51 +02:00
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 1.0 hours." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
},
2020-04-26 01:50:51 +02:00
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 3600\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeClientCertificateExpiration" ,
"annotations": {
2020-04-26 01:50:51 +02:00
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 0.1 hours." ,
2019-02-18 21:05:27 +01:00
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
},
2020-04-26 01:50:51 +02:00
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 300\n" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
2019-10-28 10:22:15 +01:00
},
2020-03-02 08:20:33 +01:00
{
"alert": "AggregatedAPIErrors" ,
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors"
},
"expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "AggregatedAPIDown" ,
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} is down. It has not been available at least for the past five minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown"
},
"expr": "sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0\n" ,
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
2019-10-28 10:22:15 +01:00
{
"alert": "KubeAPIDown" ,
"annotations": {
"message": "KubeAPI has disappeared from Prometheus target discovery." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown"
},
"expr": "absent(up{job=\"apiserver\"} == 1)\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
}
]
},
{
"name": "kubernetes-system-kubelet" ,
"rules": [
{
"alert": "KubeNodeNotReady" ,
"annotations": {
"message": "{{ $labels.node }} has been unready for more than 15 minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready"
},
"expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\n" ,
"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\n" ,
2020-03-02 08:20:33 +01:00
"for": "2m" ,
2019-10-28 10:22:15 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletTooManyPods" ,
"annotations": {
"message": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods"
},
2020-03-31 09:50:16 +02:00
"expr": "max(max(kubelet_running_pod_count{job=\"kubelet\"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"}) by(node) / max(kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1) by(node) > 0.95\n" ,
2019-10-28 10:22:15 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
2020-03-02 08:20:33 +01:00
{
"alert": "KubeNodeReadinessFlapping" ,
"annotations": {
"message": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping"
},
"expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n" ,
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletPlegDurationHigh" ,
"annotations": {
"message": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh"
},
"expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n" ,
"for": "5m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletPodStartUpLatencyHigh" ,
"annotations": {
"message": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh"
},
2020-03-31 09:50:16 +02:00
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 60\n" ,
2020-03-02 08:20:33 +01:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
2019-10-28 10:22:15 +01:00
{
"alert": "KubeletDown" ,
"annotations": {
"message": "Kubelet has disappeared from Prometheus target discovery." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown"
},
"expr": "absent(up{job=\"kubelet\"} == 1)\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
}
]
},
{
"name": "kubernetes-system-scheduler" ,
"rules": [
{
"alert": "KubeSchedulerDown" ,
"annotations": {
"message": "KubeScheduler has disappeared from Prometheus target discovery." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown"
},
"expr": "absent(up{job=\"kube-scheduler\"} == 1)\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
}
]
},
{
"name": "kubernetes-system-controller-manager" ,
"rules": [
{
"alert": "KubeControllerManagerDown" ,
"annotations": {
"message": "KubeControllerManager has disappeared from Prometheus target discovery." ,
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown"
},
"expr": "absent(up{job=\"kube-controller-manager\"} == 1)\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
2019-02-18 21:05:27 +01:00
}
]
}
]
}
2020-03-31 09:50:16 +02:00
loki.yaml : |-
{
"groups": [
{
"name": "loki_rules" ,
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))" ,
"record": "job:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))" ,
"record": "job:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job) / sum(rate(loki_request_duration_seconds_count[1m])) by (job)" ,
"record": "job:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job)" ,
"record": "job:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job)" ,
"record": "job:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job)" ,
"record": "job:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))" ,
"record": "job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))" ,
"record": "job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)" ,
"record": "job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route)" ,
"record": "job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route)" ,
"record": "job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)" ,
"record": "job_route:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))" ,
"record": "namespace_job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))" ,
"record": "namespace_job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)" ,
"record": "namespace_job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route)" ,
"record": "namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route)" ,
"record": "namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)" ,
"record": "namespace_job_route:loki_request_duration_seconds_count:sum_rate"
}
]
},
{
"name": "loki_alerts" ,
"rules": [
{
"alert": "LokiRequestErrors" ,
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n"
},
"expr": "100 * sum(rate(loki_request_duration_seconds_count{status_code=~\"5..\"}[1m])) by (namespace, job, route)\n /\nsum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)\n > 10\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "LokiRequestLatency" ,
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n"
},
"expr": "namespace_job_route:loki_request_duration_seconds:99quantile{route!~\"(?i).*tail.*\"} > 1\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
}
]
}
]
}
2019-11-14 08:39:19 +01:00
node-exporter.yaml : |-
{
"groups": [
2020-03-31 09:50:16 +02:00
{
"name": "node-exporter.rules" ,
"rules": [
{
"expr": "count without (cpu) (\n count without (mode) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n )\n)\n" ,
"record": "instance:node_num_cpu:sum"
},
{
"expr": "1 - avg without (cpu, mode) (\n rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\"}[1m])\n)\n" ,
"record": "instance:node_cpu_utilisation:rate1m"
},
{
"expr": "(\n node_load1{job=\"node-exporter\"}\n/\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n" ,
"record": "instance:node_load1_per_cpu:ratio"
},
{
"expr": "1 - (\n node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n" ,
"record": "instance:node_memory_utilisation:ratio"
},
{
"expr": "rate(node_vmstat_pgmajfault{job=\"node-exporter\"}[1m])\n" ,
"record": "instance:node_vmstat_pgmajfault:rate1m"
},
{
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n" ,
"record": "instance_device:node_disk_io_time_seconds:rate1m"
},
{
"expr": "rate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n" ,
"record": "instance_device:node_disk_io_time_weighted_seconds:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n" ,
"record": "instance:node_network_receive_bytes_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n" ,
"record": "instance:node_network_transmit_bytes_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n" ,
"record": "instance:node_network_receive_drop_excluding_lo:rate1m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n" ,
"record": "instance:node_network_transmit_drop_excluding_lo:rate1m"
}
]
},
2019-11-14 08:39:19 +01:00
{
"name": "node-exporter" ,
"rules": [
{
"alert": "NodeFilesystemSpaceFillingUp" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left and is filling up." ,
"summary": "Filesystem is predicted to run out of space within the next 24 hours."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 40\nand\n predict_linear(node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 24*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemSpaceFillingUp" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left and is filling up fast." ,
"summary": "Filesystem is predicted to run out of space within the next 4 hours."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 20\nand\n predict_linear(node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 4*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemAlmostOutOfSpace" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left." ,
"summary": "Filesystem has less than 5% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemAlmostOutOfSpace" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available space left." ,
"summary": "Filesystem has less than 3% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemFilesFillingUp" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left and is filling up." ,
"summary": "Filesystem is predicted to run out of inodes within the next 24 hours."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 40\nand\n predict_linear(node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 24*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemFilesFillingUp" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left and is filling up fast." ,
"summary": "Filesystem is predicted to run out of inodes within the next 4 hours."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 20\nand\n predict_linear(node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"}[6h], 4*60*60) < 0\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeFilesystemAlmostOutOfFiles" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left." ,
"summary": "Filesystem has less than 5% inodes left."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFilesystemAlmostOutOfFiles" ,
"annotations": {
"description": "Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf \"%.2f\" $value }}% available inodes left." ,
"summary": "Filesystem has less than 3% inodes left."
},
"expr": "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_files{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n" ,
"for": "1h" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeNetworkReceiveErrs" ,
"annotations": {
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes." ,
"summary": "Network interface is reporting many receive errors."
},
"expr": "increase(node_network_receive_errs_total[2m]) > 10\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeNetworkTransmitErrs" ,
"annotations": {
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes." ,
"summary": "Network interface is reporting many transmit errors."
},
"expr": "increase(node_network_transmit_errs_total[2m]) > 10\n" ,
"for": "1h" ,
"labels": {
"severity": "warning"
}
2020-03-31 09:50:16 +02:00
},
{
"alert": "NodeHighNumberConntrackEntriesUsed" ,
"annotations": {
"description": "{{ $value | humanizePercentage }} of conntrack entries are used" ,
"summary": "Number of conntrack are getting close to the limit"
},
"expr": "(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75\n" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeClockSkewDetected" ,
"annotations": {
"message": "Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host." ,
"summary": "Clock skew detected."
},
"expr": "(\n node_timex_offset_seconds > 0.05\nand\n deriv(node_timex_offset_seconds[5m]) >= 0\n)\nor\n(\n node_timex_offset_seconds < -0.05\nand\n deriv(node_timex_offset_seconds[5m]) <= 0\n)\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeClockNotSynchronising" ,
"annotations": {
"message": "Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host." ,
"summary": "Clock not synchronising."
},
"expr": "min_over_time(node_timex_sync_status[5m]) == 0\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
2019-11-14 08:39:19 +01:00
}
]
}
]
}
2019-07-21 20:02:18 +02:00
prom.yaml : |-
{
"groups": [
{
"name": "prometheus" ,
"rules": [
{
"alert": "PrometheusBadConfig" ,
"annotations": {
"description": "Prometheus {{$labels.instance}} has failed to reload its configuration." ,
"summary": "Failed Prometheus configuration reload."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\nmax_over_time(prometheus_config_last_reload_successful{job=\"prometheus\"}[5m]) == 0\n" ,
"for": "10m" ,
"labels": {
"severity": "critical"
}
2019-02-18 21:05:27 +01:00
},
{
"alert": "PrometheusNotificationQueueRunningFull" ,
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "Alert notification queue of Prometheus {{$labels.instance}} is running full." ,
"summary": "Prometheus alert notification queue predicted to run full in less than 30m."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "# Without min_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n predict_linear(prometheus_notifications_queue_length{job=\"prometheus\"}[5m], 60 * 30)\n>\n min_over_time(prometheus_notifications_queue_capacity{job=\"prometheus\"}[5m])\n)\n" ,
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
2019-07-21 20:02:18 +02:00
"alert": "PrometheusErrorSendingAlertsToSomeAlertmanagers" ,
2019-02-18 21:05:27 +01:00
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "{{ printf \"%.1f\" $value }}% errors while sending alerts from Prometheus {{$labels.instance}} to Alertmanager {{$labels.alertmanager}}." ,
"summary": "Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "(\n rate(prometheus_notifications_errors_total{job=\"prometheus\"}[5m])\n/\n rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m])\n)\n* 100\n> 1\n" ,
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
2019-07-21 20:02:18 +02:00
"alert": "PrometheusErrorSendingAlertsToAnyAlertmanager" ,
2019-02-18 21:05:27 +01:00
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "{{ printf \"%.1f\" $value }}% minimum errors while sending alerts from Prometheus {{$labels.instance}} to any Alertmanager." ,
"summary": "Prometheus encounters more than 3% errors sending alerts to any Alertmanager."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "min without(alertmanager) (\n rate(prometheus_notifications_errors_total{job=\"prometheus\"}[5m])\n/\n rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m])\n)\n* 100\n> 3\n" ,
"for": "15m" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "critical"
}
},
{
"alert": "PrometheusNotConnectedToAlertmanagers" ,
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "Prometheus {{$labels.instance}} is not connected to any Alertmanagers." ,
"summary": "Prometheus is not connected to any Alertmanagers."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\nmax_over_time(prometheus_notifications_alertmanagers_discovered{job=\"prometheus\"}[5m]) < 1\n" ,
2019-02-18 21:05:27 +01:00
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusTSDBReloadsFailing" ,
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "Prometheus {{$labels.instance}} has detected {{$value | humanize}} reload failures over the last 3h." ,
"summary": "Prometheus has issues reloading blocks from disk."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "increase(prometheus_tsdb_reloads_failures_total{job=\"prometheus\"}[3h]) > 0\n" ,
"for": "4h" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusTSDBCompactionsFailing" ,
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "Prometheus {{$labels.instance}} has detected {{$value | humanize}} compaction failures over the last 3h." ,
"summary": "Prometheus has issues compacting blocks."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "increase(prometheus_tsdb_compactions_failed_total{job=\"prometheus\"}[3h]) > 0\n" ,
"for": "4h" ,
2019-02-18 21:05:27 +01:00
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusNotIngestingSamples" ,
"annotations": {
2019-07-21 20:02:18 +02:00
"description": "Prometheus {{$labels.instance}} is not ingesting samples." ,
"summary": "Prometheus is not ingesting samples."
2019-02-18 21:05:27 +01:00
},
"expr": "rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\n" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
},
{
2019-07-21 20:02:18 +02:00
"alert": "PrometheusDuplicateTimestamps" ,
2019-02-18 21:05:27 +01:00
"annotations": {
2019-10-20 02:43:47 +02:00
"description": "Prometheus {{$labels.instance}} is dropping {{ printf \"%.4g\" $value }} samples/s with different values but duplicated timestamp." ,
2019-07-21 20:02:18 +02:00
"summary": "Prometheus is dropping samples with duplicate timestamps."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job=\"prometheus\"}[5m]) > 0\n" ,
2019-02-18 21:05:27 +01:00
"for": "10m" ,
"labels": {
"severity": "warning"
}
2019-07-21 20:02:18 +02:00
},
2019-02-18 21:05:27 +01:00
{
2019-07-21 20:02:18 +02:00
"alert": "PrometheusOutOfOrderTimestamps" ,
2019-02-18 21:05:27 +01:00
"annotations": {
2019-10-20 02:43:47 +02:00
"description": "Prometheus {{$labels.instance}} is dropping {{ printf \"%.4g\" $value }} samples/s with timestamps arriving out of order." ,
2019-07-21 20:02:18 +02:00
"summary": "Prometheus drops samples with out-of-order timestamps."
2019-02-18 21:05:27 +01:00
},
2019-07-21 20:02:18 +02:00
"expr": "rate(prometheus_target_scrapes_sample_out_of_order_total{job=\"prometheus\"}[5m]) > 0\n" ,
2019-02-18 21:05:27 +01:00
"for": "10m" ,
"labels": {
"severity": "warning"
}
2019-07-21 20:02:18 +02:00
},
{
"alert": "PrometheusRemoteStorageFailures" ,
"annotations": {
2020-03-02 08:20:33 +01:00
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}." ,
2019-07-21 20:02:18 +02:00
"summary": "Prometheus fails to send samples to remote storage."
},
"expr": "(\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n (\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n +\n rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n )\n)\n* 100\n> 1\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "PrometheusRemoteWriteBehind" ,
"annotations": {
2020-03-02 08:20:33 +01:00
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}." ,
2019-07-21 20:02:18 +02:00
"summary": "Prometheus remote write is behind."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
2019-10-20 02:43:47 +02:00
{
"alert": "PrometheusRemoteWriteDesiredShards" ,
"annotations": {
2020-03-02 08:20:33 +01:00
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}." ,
2019-10-20 02:43:47 +02:00
"summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
},
2020-03-02 08:20:33 +01:00
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n" ,
2019-10-20 02:43:47 +02:00
"for": "15m" ,
"labels": {
"severity": "warning"
}
},
2019-07-21 20:02:18 +02:00
{
"alert": "PrometheusRuleFailures" ,
"annotations": {
"description": "Prometheus {{$labels.instance}} has failed to evaluate {{ printf \"%.0f\" $value }} rules in the last 5m." ,
"summary": "Prometheus is failing rule evaluations."
},
"expr": "increase(prometheus_rule_evaluation_failures_total{job=\"prometheus\"}[5m]) > 0\n" ,
"for": "15m" ,
"labels": {
"severity": "critical"
}
},
{
"alert": "PrometheusMissingRuleEvaluations" ,
"annotations": {
"description": "Prometheus {{$labels.instance}} has missed {{ printf \"%.0f\" $value }} rule group evaluations in the last 5m." ,
"summary": "Prometheus is missing rule evaluations due to slow rule group evaluation."
},
"expr": "increase(prometheus_rule_group_iterations_missed_total{job=\"prometheus\"}[5m]) > 0\n" ,
"for": "15m" ,
"labels": {
"severity": "warning"
}
2019-02-18 21:05:27 +01:00
}
]
}
]
}
2019-10-20 02:43:47 +02:00
typhoon.yaml : |-
{
"groups": [
{
"name": "general.rules" ,
"rules": [
{
"alert": "TargetDown" ,
"annotations": {
"message": "{{ printf \"%.4g\" $value }}% of the {{ $labels.job }} targets are down."
},
"expr": "100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10" ,
"for": "10m" ,
"labels": {
"severity": "warning"
}
2020-03-02 08:20:33 +01:00
},
{
"alert": "BlackboxProbeFailure" ,
"annotations": {
"message": "Blackbox probe {{$labels.instance}} failed"
},
"expr": "probe_success == 0" ,
"for": "2m" ,
"labels": {
"severity": "critical"
}
2019-10-20 02:43:47 +02:00
}
]
},
{
"name": "extra.rules" ,
"rules": [
{
"alert": "InactiveRAIDDisk" ,
"annotations": {
"message": "{{ $value }} RAID disk(s) on node {{ $labels.instance }} are inactive."
},
2020-02-26 07:26:24 +01:00
"expr": "node_md_disks{state=\"failed\"} > 0" ,
2019-10-20 02:43:47 +02:00
"for": "10m" ,
"labels": {
"severity": "warning"
}
}
]
}
]
}
kind : ConfigMap
metadata :
name : prometheus-rules
namespace : monitoring
