1192 lines
61 KiB
YAML
1192 lines
61 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: prometheus-rules
|
|
namespace: monitoring
|
|
data:
|
|
etcd.yaml: |-
|
|
{
|
|
"groups": [
|
|
{
|
|
"name": "etcd",
|
|
"rules": [
|
|
{
|
|
"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": {
|
|
"message": "etcd cluster \"{{ $labels.job }}\": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last 30 minutes."
|
|
},
|
|
"expr": "rate(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}[15m]) > 3\n",
|
|
"for": "15m",
|
|
"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"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
extra.yaml: |-
|
|
{
|
|
"groups": [
|
|
{
|
|
"name": "extra.rules",
|
|
"rules": [
|
|
{
|
|
"alert": "InactiveRAIDDisk",
|
|
"annotations": {
|
|
"message": "{{ $value }} RAID disk(s) on node {{ $labels.instance }} are inactive."
|
|
},
|
|
"expr": "node_md_disks - node_md_disks_active > 0",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
kube.yaml: |-
|
|
{
|
|
"groups": [
|
|
{
|
|
"name": "k8s.rules",
|
|
"rules": [
|
|
{
|
|
"expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container_name!=\"\"}[5m])) by (namespace)\n",
|
|
"record": "namespace:container_cpu_usage_seconds_total:sum_rate"
|
|
},
|
|
{
|
|
"expr": "sum by (namespace, pod_name, container_name) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container_name!=\"\"}[5m])\n)\n",
|
|
"record": "namespace_pod_name_container_name:container_cpu_usage_seconds_total:sum_rate"
|
|
},
|
|
{
|
|
"expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", image!=\"\", container_name!=\"\"}) by (namespace)\n",
|
|
"record": "namespace:container_memory_usage_bytes:sum"
|
|
},
|
|
{
|
|
"expr": "sum by (namespace, label_name) (\n sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container_name!=\"\"}[5m])) by (namespace, pod_name)\n * on (namespace, pod_name) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
|
|
"record": "namespace_name:container_cpu_usage_seconds_total:sum_rate"
|
|
},
|
|
{
|
|
"expr": "sum by (namespace, label_name) (\n sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\",image!=\"\", container_name!=\"\"}) by (pod_name, namespace)\n* on (namespace, pod_name) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
|
|
"record": "namespace_name:container_memory_usage_bytes:sum"
|
|
},
|
|
{
|
|
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"^(Pending|Running)$\"} == 1)) by (namespace, pod)\n* on (namespace, pod) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
|
|
"record": "namespace_name:kube_pod_container_resource_requests_memory_bytes:sum"
|
|
},
|
|
{
|
|
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"^(Pending|Running)$\"} == 1)) by (namespace, pod)\n* on (namespace, pod) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
|
|
"record": "namespace_name:kube_pod_container_resource_requests_cpu_cores:sum"
|
|
},
|
|
{
|
|
"expr": "sum(\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) kube_replicaset_owner{job=\"kube-state-metrics\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
|
|
"labels": {
|
|
"workload_type": "deployment"
|
|
},
|
|
"record": "mixin_pod_workload"
|
|
},
|
|
{
|
|
"expr": "sum(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
|
|
"labels": {
|
|
"workload_type": "daemonset"
|
|
},
|
|
"record": "mixin_pod_workload"
|
|
},
|
|
{
|
|
"expr": "sum(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n) by (namespace, workload, pod)\n",
|
|
"labels": {
|
|
"workload_type": "statefulset"
|
|
},
|
|
"record": "mixin_pod_workload"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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\n",
|
|
"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)\n",
|
|
"record": "node_namespace_pod:kube_pod_info:"
|
|
},
|
|
{
|
|
"expr": "count by (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",
|
|
"record": "node:node_num_cpu:sum"
|
|
},
|
|
{
|
|
"expr": "1 - avg(rate(node_cpu_seconds_total{job=\"node-exporter\",mode=\"idle\"}[1m]))\n",
|
|
"record": ":node_cpu_utilisation:avg1m"
|
|
},
|
|
{
|
|
"expr": "1 - avg by (node) (\n rate(node_cpu_seconds_total{job=\"node-exporter\",mode=\"idle\"}[1m])\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:)\n",
|
|
"record": "node:node_cpu_utilisation:avg1m"
|
|
},
|
|
{
|
|
"expr": "node:node_cpu_utilisation:avg1m\n *\nnode:node_num_cpu:sum\n /\nscalar(sum(node:node_num_cpu:sum))\n",
|
|
"record": "node:cluster_cpu_utilisation:ratio"
|
|
},
|
|
{
|
|
"expr": "sum(node_load1{job=\"node-exporter\"})\n/\nsum(node:node_num_cpu:sum)\n",
|
|
"record": ":node_cpu_saturation_load1:"
|
|
},
|
|
{
|
|
"expr": "sum by (node) (\n node_load1{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n/\nnode:node_num_cpu:sum\n",
|
|
"record": "node:node_cpu_saturation_load1:"
|
|
},
|
|
{
|
|
"expr": "1 -\nsum(node_memory_MemFree_bytes{job=\"node-exporter\"} + node_memory_Cached_bytes{job=\"node-exporter\"} + node_memory_Buffers_bytes{job=\"node-exporter\"})\n/\nsum(node_memory_MemTotal_bytes{job=\"node-exporter\"})\n",
|
|
"record": ":node_memory_utilisation:"
|
|
},
|
|
{
|
|
"expr": "sum(node_memory_MemFree_bytes{job=\"node-exporter\"} + node_memory_Cached_bytes{job=\"node-exporter\"} + node_memory_Buffers_bytes{job=\"node-exporter\"})\n",
|
|
"record": ":node_memory_MemFreeCachedBuffers_bytes:sum"
|
|
},
|
|
{
|
|
"expr": "sum(node_memory_MemTotal_bytes{job=\"node-exporter\"})\n",
|
|
"record": ":node_memory_MemTotal_bytes:sum"
|
|
},
|
|
{
|
|
"expr": "sum by (node) (\n (node_memory_MemFree_bytes{job=\"node-exporter\"} + node_memory_Cached_bytes{job=\"node-exporter\"} + node_memory_Buffers_bytes{job=\"node-exporter\"})\n * on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_memory_bytes_available:sum"
|
|
},
|
|
{
|
|
"expr": "sum by (node) (\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n * on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_memory_bytes_total:sum"
|
|
},
|
|
{
|
|
"expr": "(node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)\n/\nnode:node_memory_bytes_total:sum\n",
|
|
"record": "node:node_memory_utilisation:ratio"
|
|
},
|
|
{
|
|
"expr": "(node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)\n/\nscalar(sum(node:node_memory_bytes_total:sum))\n",
|
|
"record": "node:cluster_memory_utilisation:ratio"
|
|
},
|
|
{
|
|
"expr": "1e3 * sum(\n (rate(node_vmstat_pgpgin{job=\"node-exporter\"}[1m])\n + rate(node_vmstat_pgpgout{job=\"node-exporter\"}[1m]))\n)\n",
|
|
"record": ":node_memory_swap_io_bytes:sum_rate"
|
|
},
|
|
{
|
|
"expr": "1 -\nsum by (node) (\n (node_memory_MemFree_bytes{job=\"node-exporter\"} + node_memory_Cached_bytes{job=\"node-exporter\"} + node_memory_Buffers_bytes{job=\"node-exporter\"})\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n/\nsum by (node) (\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_memory_utilisation:"
|
|
},
|
|
{
|
|
"expr": "1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum)\n",
|
|
"record": "node:node_memory_utilisation_2:"
|
|
},
|
|
{
|
|
"expr": "1e3 * sum by (node) (\n (rate(node_vmstat_pgpgin{job=\"node-exporter\"}[1m])\n + rate(node_vmstat_pgpgout{job=\"node-exporter\"}[1m]))\n * on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_memory_swap_io_bytes:sum_rate"
|
|
},
|
|
{
|
|
"expr": "avg(irate(node_disk_io_time_seconds_total{job=\"node-exporter\",device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+\"}[1m]))\n",
|
|
"record": ":node_disk_utilisation:avg_irate"
|
|
},
|
|
{
|
|
"expr": "avg by (node) (\n irate(node_disk_io_time_seconds_total{job=\"node-exporter\",device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+\"}[1m])\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_disk_utilisation:avg_irate"
|
|
},
|
|
{
|
|
"expr": "avg(irate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\",device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+\"}[1m]))\n",
|
|
"record": ":node_disk_saturation:avg_irate"
|
|
},
|
|
{
|
|
"expr": "avg by (node) (\n irate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\",device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+\"}[1m])\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_disk_saturation:avg_irate"
|
|
},
|
|
{
|
|
"expr": "max by (namespace, pod, device) ((node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"}\n- node_filesystem_avail_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"})\n/ node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"})\n",
|
|
"record": "node:node_filesystem_usage:"
|
|
},
|
|
{
|
|
"expr": "max by (namespace, pod, device) (node_filesystem_avail_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"} / node_filesystem_size_bytes{fstype=~\"ext[234]|btrfs|xfs|zfs\"})\n",
|
|
"record": "node:node_filesystem_avail:"
|
|
},
|
|
{
|
|
"expr": "sum(irate(node_network_receive_bytes_total{job=\"node-exporter\",device!~\"veth.+\"}[1m])) +\nsum(irate(node_network_transmit_bytes_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]))\n",
|
|
"record": ":node_net_utilisation:sum_irate"
|
|
},
|
|
{
|
|
"expr": "sum by (node) (\n (irate(node_network_receive_bytes_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]) +\n irate(node_network_transmit_bytes_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]))\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_net_utilisation:sum_irate"
|
|
},
|
|
{
|
|
"expr": "sum(irate(node_network_receive_drop_total{job=\"node-exporter\",device!~\"veth.+\"}[1m])) +\nsum(irate(node_network_transmit_drop_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]))\n",
|
|
"record": ":node_net_saturation:sum_irate"
|
|
},
|
|
{
|
|
"expr": "sum by (node) (\n (irate(node_network_receive_drop_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]) +\n irate(node_network_transmit_drop_total{job=\"node-exporter\",device!~\"veth.+\"}[1m]))\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
|
|
"record": "node:node_net_saturation:sum_irate"
|
|
},
|
|
{
|
|
"expr": "max(\n max(\n kube_pod_info{job=\"kube-state-metrics\", host_ip!=\"\"}\n ) by (node, host_ip)\n * on (host_ip) group_right (node)\n label_replace(\n (max(node_filesystem_files{job=\"node-exporter\", mountpoint=\"/\"}) by (instance)), \"host_ip\", \"$1\", \"instance\", \"(.*):.*\"\n )\n) by (node)\n",
|
|
"record": "node:node_inodes_total:"
|
|
},
|
|
{
|
|
"expr": "max(\n max(\n kube_pod_info{job=\"kube-state-metrics\", host_ip!=\"\"}\n ) by (node, host_ip)\n * on (host_ip) group_right (node)\n label_replace(\n (max(node_filesystem_files_free{job=\"node-exporter\", mountpoint=\"/\"}) by (instance)), \"host_ip\", \"$1\", \"instance\", \"(.*):.*\"\n )\n) by (node)\n",
|
|
"record": "node:node_inodes_free:"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "kubernetes-absent",
|
|
"rules": [
|
|
{
|
|
"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"
|
|
}
|
|
},
|
|
{
|
|
"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"
|
|
}
|
|
},
|
|
{
|
|
"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"
|
|
}
|
|
},
|
|
{
|
|
"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-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",
|
|
"for": "1h",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubePodNotReady",
|
|
"annotations": {
|
|
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than an hour.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
|
|
},
|
|
"expr": "sum by (namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}) > 0\n",
|
|
"for": "1h",
|
|
"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": {
|
|
"message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than an hour.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
|
|
},
|
|
"expr": "kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\nkube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n",
|
|
"for": "1h",
|
|
"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"
|
|
},
|
|
"expr": "kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n",
|
|
"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": {
|
|
"message": "Only {{ $value }}% of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck"
|
|
},
|
|
"expr": "kube_daemonset_status_number_ready{job=\"kube-state-metrics\"}\n /\nkube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"} * 100 < 100\n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"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"
|
|
},
|
|
"expr": "kube_job_status_failed{job=\"kube-state-metrics\"} > 0\n",
|
|
"for": "1h",
|
|
"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"
|
|
},
|
|
"expr": "sum(namespace_name:kube_pod_container_resource_requests_cpu_cores:sum)\n /\nsum(node:node_num_cpu:sum)\n >\n(count(node:node_num_cpu:sum)-1) / count(node:node_num_cpu:sum)\n",
|
|
"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"
|
|
},
|
|
"expr": "sum(namespace_name:kube_pod_container_resource_requests_memory_bytes:sum)\n /\nsum(node_memory_MemTotal_bytes)\n >\n(count(node:node_num_cpu:sum)-1)\n /\ncount(node:node_num_cpu:sum)\n",
|
|
"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"
|
|
},
|
|
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n /\nsum(node:node_num_cpu:sum)\n > 1.5\n",
|
|
"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"
|
|
},
|
|
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n /\nsum(node_memory_MemTotal_bytes{job=\"node-exporter\"})\n > 1.5\n",
|
|
"for": "5m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeQuotaExceeded",
|
|
"annotations": {
|
|
"message": "Namespace {{ $labels.namespace }} is using {{ printf \"%0.0f\" $value }}% of its {{ $labels.resource }} quota.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded"
|
|
},
|
|
"expr": "100 * kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 90\n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "CPUThrottlingHigh",
|
|
"annotations": {
|
|
"message": "{{ printf \"%0.0f\" $value }}% throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container_name }} in pod {{ $labels.pod_name }}.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh"
|
|
},
|
|
"expr": "100 * sum(increase(container_cpu_cfs_throttled_periods_total{container_name!=\"\", }[5m])) by (container_name, pod_name, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container_name, pod_name, namespace)\n > 100 \n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "kubernetes-storage",
|
|
"rules": [
|
|
{
|
|
"alert": "KubePersistentVolumeUsageCritical",
|
|
"annotations": {
|
|
"message": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ printf \"%0.2f\" $value }}% free.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical"
|
|
},
|
|
"expr": "100 * kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n < 3\n",
|
|
"for": "1m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubePersistentVolumeFullInFourDays",
|
|
"annotations": {
|
|
"message": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ printf \"%0.2f\" $value }}% is available.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
|
|
},
|
|
"expr": "100 * (\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n",
|
|
"for": "5m",
|
|
"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": "KubeNodeNotReady",
|
|
"annotations": {
|
|
"message": "{{ $labels.node }} has been unready for more than an hour.",
|
|
"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": "1h",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"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"
|
|
},
|
|
"expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!=\"coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*.[0-9]*).*\"))) > 1\n",
|
|
"for": "1h",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeClientErrors",
|
|
"annotations": {
|
|
"message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ printf \"%0.0f\" $value }}% errors.'",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
|
|
},
|
|
"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* 100 > 1\n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeClientErrors",
|
|
"annotations": {
|
|
"message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ printf \"%0.0f\" $value }} errors / second.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
|
|
},
|
|
"expr": "sum(rate(ksm_scrape_error_total{job=\"kube-state-metrics\"}[5m])) by (instance, job) > 0.1\n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeletTooManyPods",
|
|
"annotations": {
|
|
"message": "Kubelet {{ $labels.instance }} is running {{ $value }} Pods, close to the limit of 110.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods"
|
|
},
|
|
"expr": "kubelet_running_pod_count{job=\"kubelet\"} > 110 * 0.9\n",
|
|
"for": "15m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPILatencyHigh",
|
|
"annotations": {
|
|
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
|
|
},
|
|
"expr": "cluster_quantile:apiserver_request_latencies:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$\"} > 1\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPILatencyHigh",
|
|
"annotations": {
|
|
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
|
|
},
|
|
"expr": "cluster_quantile:apiserver_request_latencies:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$\"} > 4\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPIErrorsHigh",
|
|
"annotations": {
|
|
"message": "API server is returning errors for {{ $value }}% of requests.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
|
|
},
|
|
"expr": "sum(rate(apiserver_request_count{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m]))\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) * 100 > 3\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPIErrorsHigh",
|
|
"annotations": {
|
|
"message": "API server is returning errors for {{ $value }}% of requests.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
|
|
},
|
|
"expr": "sum(rate(apiserver_request_count{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m]))\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) * 100 > 1\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPIErrorsHigh",
|
|
"annotations": {
|
|
"message": "API server is returning errors for {{ $value }}% of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
|
|
},
|
|
"expr": "sum(rate(apiserver_request_count{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) by (resource,subresource,verb) * 100 > 10\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeAPIErrorsHigh",
|
|
"annotations": {
|
|
"message": "API server is returning errors for {{ $value }}% of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
|
|
},
|
|
"expr": "sum(rate(apiserver_request_count{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) by (resource,subresource,verb) * 100 > 5\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeClientCertificateExpiration",
|
|
"annotations": {
|
|
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
|
|
},
|
|
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "KubeClientCertificateExpiration",
|
|
"annotations": {
|
|
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
|
|
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
|
|
},
|
|
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
kubeprom.yaml: |-
|
|
{
|
|
"groups": [
|
|
{
|
|
"name": "kube-prometheus-node-recording.rules",
|
|
"rules": [
|
|
{
|
|
"expr": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\"}[3m])) BY (instance)",
|
|
"record": "instance:node_cpu:rate:sum"
|
|
},
|
|
{
|
|
"expr": "sum((node_filesystem_size_bytes{mountpoint=\"/\"} - node_filesystem_free_bytes{mountpoint=\"/\"})) BY (instance)",
|
|
"record": "instance:node_filesystem_usage:sum"
|
|
},
|
|
{
|
|
"expr": "sum(rate(node_network_receive_bytes_total[3m])) BY (instance)",
|
|
"record": "instance:node_network_receive_bytes:rate:sum"
|
|
},
|
|
{
|
|
"expr": "sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)",
|
|
"record": "instance:node_network_transmit_bytes:rate:sum"
|
|
},
|
|
{
|
|
"expr": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)",
|
|
"record": "instance:node_cpu:ratio"
|
|
},
|
|
{
|
|
"expr": "sum(rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\"}[5m]))",
|
|
"record": "cluster:node_cpu:sum_rate5m"
|
|
},
|
|
{
|
|
"expr": "cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))",
|
|
"record": "cluster:node_cpu:ratio"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "kube-prometheus-node-alerting.rules",
|
|
"rules": [
|
|
{
|
|
"alert": "NodeDiskRunningFull",
|
|
"annotations": {
|
|
"message": "Device {{ $labels.device }} of node-exporter {{ $labels.namespace }}/{{ $labels.pod }} will be full within the next 24 hours."
|
|
},
|
|
"expr": "(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[6h], 3600 * 24) < 0)\n",
|
|
"for": "30m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "NodeDiskRunningFull",
|
|
"annotations": {
|
|
"message": "Device {{ $labels.device }} of node-exporter {{ $labels.namespace }}/{{ $labels.pod }} will be full within the next 2 hours."
|
|
},
|
|
"expr": "(node:node_filesystem_usage: > 0.85) and (predict_linear(node:node_filesystem_avail:[30m], 3600 * 2) < 0)\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "node-time",
|
|
"rules": [
|
|
{
|
|
"alert": "ClockSkewDetected",
|
|
"annotations": {
|
|
"message": "Clock skew detected on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}. Ensure NTP is configured correctly on this host."
|
|
},
|
|
"expr": "abs(node_timex_offset_seconds{job=\"node-exporter\"}) > 0.03\n",
|
|
"for": "2m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "node-network",
|
|
"rules": [
|
|
{
|
|
"alert": "NetworkReceiveErrors",
|
|
"annotations": {
|
|
"message": "Network interface \"{{ $labels.device }}\" showing receive errors on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}\""
|
|
},
|
|
"expr": "rate(node_network_receive_errs_total{job=\"node-exporter\",device!~\"veth.+|tunl.+\"}[2m]) > 0\n",
|
|
"for": "2m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "NetworkTransmitErrors",
|
|
"annotations": {
|
|
"message": "Network interface \"{{ $labels.device }}\" showing transmit errors on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}\""
|
|
},
|
|
"expr": "rate(node_network_transmit_errs_total{job=\"node-exporter\",device!~\"veth.+|tunl.+\"}[2m]) > 0\n",
|
|
"for": "2m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "NodeNetworkInterfaceFlapping",
|
|
"annotations": {
|
|
"message": "Network interface \"{{ $labels.device }}\" changing it's up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}\""
|
|
},
|
|
"expr": "changes(node_network_up{job=\"node-exporter\",device!~\"veth.+|tunl.+\"}[2m]) > 2\n",
|
|
"for": "2m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "prometheus.rules",
|
|
"rules": [
|
|
{
|
|
"alert": "PrometheusConfigReloadFailed",
|
|
"annotations": {
|
|
"description": "Reloading Prometheus' configuration has failed for {{$labels.namespace}}/{{$labels.pod}}",
|
|
"summary": "Reloading Prometheus' configuration failed"
|
|
},
|
|
"expr": "prometheus_config_last_reload_successful{job=\"prometheus\"} == 0\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusNotificationQueueRunningFull",
|
|
"annotations": {
|
|
"description": "Prometheus' alert notification queue is running full for {{$labels.namespace}}/{{ $labels.pod}}",
|
|
"summary": "Prometheus' alert notification queue is running full"
|
|
},
|
|
"expr": "predict_linear(prometheus_notifications_queue_length{job=\"prometheus\"}[5m], 60 * 30) > prometheus_notifications_queue_capacity{job=\"prometheus\"}\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusErrorSendingAlerts",
|
|
"annotations": {
|
|
"description": "Errors while sending alerts from Prometheus {{$labels.namespace}}/{{ $labels.pod}} to Alertmanager {{$labels.Alertmanager}}",
|
|
"summary": "Errors while sending alert from Prometheus"
|
|
},
|
|
"expr": "rate(prometheus_notifications_errors_total{job=\"prometheus\"}[5m]) / rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m]) > 0.01\n",
|
|
"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\"}[5m]) / rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m]) > 0.03\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "critical"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusNotConnectedToAlertmanagers",
|
|
"annotations": {
|
|
"description": "Prometheus {{ $labels.namespace }}/{{ $labels.pod}} is not connected to any Alertmanagers",
|
|
"summary": "Prometheus is not connected to any Alertmanagers"
|
|
},
|
|
"expr": "prometheus_notifications_alertmanagers_discovered{job=\"prometheus\"} < 1\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusTSDBReloadsFailing",
|
|
"annotations": {
|
|
"description": "{{$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\"}[2h]) > 0\n",
|
|
"for": "12h",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusTSDBCompactionsFailing",
|
|
"annotations": {
|
|
"description": "{{$labels.job}} at {{$labels.instance}} had {{$value | humanize}} compaction failures over the last four hours.",
|
|
"summary": "Prometheus has issues compacting sample blocks"
|
|
},
|
|
"expr": "increase(prometheus_tsdb_compactions_failed_total{job=\"prometheus\"}[2h]) > 0\n",
|
|
"for": "12h",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusTSDBWALCorruptions",
|
|
"annotations": {
|
|
"description": "{{$labels.job}} at {{$labels.instance}} has a corrupted write-ahead log (WAL).",
|
|
"summary": "Prometheus write-ahead log is corrupted"
|
|
},
|
|
"expr": "prometheus_tsdb_wal_corruptions_total{job=\"prometheus\"} > 0\n",
|
|
"for": "4h",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusNotIngestingSamples",
|
|
"annotations": {
|
|
"description": "Prometheus {{ $labels.namespace }}/{{ $labels.pod}} isn't ingesting samples.",
|
|
"summary": "Prometheus isn't ingesting samples"
|
|
},
|
|
"expr": "rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
},
|
|
{
|
|
"alert": "PrometheusTargetScrapesDuplicate",
|
|
"annotations": {
|
|
"description": "{{$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\"}[5m]) > 0\n",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "general.rules",
|
|
"rules": [
|
|
{
|
|
"alert": "TargetDown",
|
|
"annotations": {
|
|
"message": "{{ $value }}% of the {{ $labels.job }} targets are down."
|
|
},
|
|
"expr": "100 * (count(up == 0) BY (job) / count(up) BY (job)) > 10",
|
|
"for": "10m",
|
|
"labels": {
|
|
"severity": "warning"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|