mirror/ typhoon
1
0
Fork 0
mirror of https://github.com/poseidon/typhoon synced 2024-06-10 00:36:11 +02:00
Code Issues

Improve Kubelet and Compute Resource dashboards 

* Add cluster filter to Kubelet dashboard
* Add network details in resource dashboards
* https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/275
* https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/284
* https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/285
This commit is contained in:
Dalton Hubble 2019-10-28 02:22:15 -07:00
parent 4775e9d0f7
commit d4573092b5
5 changed files with 11367 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
addons/grafana/dashboards-k8s-nodes.yaml
View File

@ -88,7 +88,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(up{job=\"kubelet\"})",
"expr": "sum(up{cluster=\"$cluster\", job=\"kubelet\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -172,7 +172,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_pod_count{job=\"kubelet\", instance=~\"$instance\"})",
"expr": "sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -256,7 +256,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_container_count{job=\"kubelet\", instance=~\"$instance\"})",
"expr": "sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -340,7 +340,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -424,7 +424,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -508,7 +508,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(rate(kubelet_node_config_error{job=\"kubelet\", instance=~\"$instance\"}[5m]))",
"expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -588,7 +588,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
"expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
@ -679,7 +679,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_errors_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
@ -783,7 +783,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
@ -887,14 +887,14 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pod_start_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
@ -985,14 +985,14 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
@ -1098,7 +1098,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_duration_seconds_count{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@ -1191,7 +1191,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_errors_total{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@ -1297,7 +1297,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
"expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
@ -1401,7 +1401,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{operation_type}}",
@ -1492,7 +1492,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
@ -1597,7 +1597,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -1688,7 +1688,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -1792,7 +1792,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -1896,28 +1896,28 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
@ -2021,7 +2021,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{verb}} {{url}}",
@ -2125,7 +2125,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{job=\"kubelet\",instance=~\"$instance\"}",
"expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2216,7 +2216,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{job=\"kubelet\",instance=~\"$instance\"}[5m])",
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2307,7 +2307,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{job=\"kubelet\",instance=~\"$instance\"}",
"expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2391,6 +2391,32 @@ data:
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 0,
@ -2401,10 +2427,10 @@ data:
"options": [
],
"query": "label_values(kubelet_runtime_operations{job=\"kubelet\"}, instance)",
"query": "label_values(kubelet_runtime_operations{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -3593,7 +3619,7 @@ data:
"query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [

5375
addons/grafana/dashboards-k8s-resources-1.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

5753
addons/grafana/dashboards-k8s-resources-2.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

26
addons/grafana/dashboards-k8s.yaml
View File

@ -1236,7 +1236,7 @@ data:
"query": "label_values(apiserver_request_total{job=\"apiserver\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -2347,7 +2347,7 @@ data:
"query": "label_values(process_cpu_seconds_total{job=\"kube-controller-manager\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -2846,7 +2846,7 @@ data:
"query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -2872,7 +2872,7 @@ data:
"query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -2898,7 +2898,7 @@ data:
"query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\"}, persistentvolumeclaim)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -3478,7 +3478,7 @@ data:
"query": "label_values(kube_pod_info, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -3504,7 +3504,7 @@ data:
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -3530,7 +3530,7 @@ data:
"query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=~\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -3556,7 +3556,7 @@ data:
"query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}, container)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -4592,7 +4592,7 @@ data:
"query": "label_values(process_cpu_seconds_total{job=\"kube-scheduler\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -5444,7 +5444,7 @@ data:
"query": "label_values(kube_statefulset_metadata_generation, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -5470,7 +5470,7 @@ data:
"query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [
@ -5496,7 +5496,7 @@ data:
"query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)",
"refresh": 2,
"regex": "",
"sort": 0,
"sort": 1,
"tagValuesQuery": "",
"tags": [

282
addons/prometheus/rules.yaml
View File

@ -145,6 +145,32 @@ data:
kube.yaml: |-
{
"groups": [
{
"name": "kube-apiserver.rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.99"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.9"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.5"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
}
]
},
{
"name": "k8s.rules",
"rules": [
@ -156,16 +182,32 @@ data:
"expr": "sum by (namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate"
},
{
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"record": "node_namespace_pod_container:container_memory_working_set_bytes"
},
{
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"record": "node_namespace_pod_container:container_memory_rss"
},
{
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"record": "node_namespace_pod_container:container_memory_cache"
},
{
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
"record": "node_namespace_pod_container:container_memory_swap"
},
{
"expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}) by (namespace)\n",
"record": "namespace: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)$\"} == 1)) by (namespace, pod)\n * on (namespace, pod)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)) by (namespace, pod)\n * on (namespace, pod)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"record": "namespace:kube_pod_container_resource_requests_memory_bytes:sum"
},
{
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"^(Pending|Running)$\"} == 1)) by (namespace, pod)\n * on (namespace, pod)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"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)\n group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
"record": "namespace:kube_pod_container_resource_requests_cpu_cores:sum"
},
{
@ -259,32 +301,6 @@ data:
}
]
},
{
"name": "kube-apiserver.rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.99"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.9"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
"labels": {
"quantile": "0.5"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
}
]
},
{
"name": "node.rules",
"rules": [
@ -301,61 +317,8 @@ data:
"record": "node:node_num_cpu:sum"
},
{
"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"
}
]
},
{
"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"
}
"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)\n",
"record": ":node_memory_MemAvailable_bytes:sum"
}
]
},
@ -458,6 +421,18 @@ data:
"severity": "critical"
}
},
{
"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"
}
},
{
"alert": "KubeDaemonSetNotScheduled",
"annotations": {
@ -665,18 +640,6 @@ data:
{
"name": "kubernetes-system",
"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": "KubeVersionMismatch",
"annotations": {
@ -700,26 +663,19 @@ data:
"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"
},
"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\"}) by(node) > 0.95\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
}
]
},
{
"name": "kubernetes-system-apiserver",
"rules": [
{
"alert": "KubeAPILatencyHigh",
"annotations": {
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$\"} > 1\n",
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 1\n",
"for": "10m",
"labels": {
"severity": "warning"
@ -731,7 +687,7 @@ data:
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$\"} > 4\n",
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 4\n",
"for": "10m",
"labels": {
"severity": "critical"
@ -743,7 +699,7 @@ data:
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.03\n",
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.03\n",
"for": "10m",
"labels": {
"severity": "critical"
@ -755,7 +711,7 @@ data:
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.01\n",
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m]))\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.01\n",
"for": "10m",
"labels": {
"severity": "warning"
@ -767,7 +723,7 @@ data:
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.10\n",
"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",
"for": "10m",
"labels": {
"severity": "critical"
@ -779,7 +735,7 @@ data:
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"^(?:5..)$\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.05\n",
"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",
"for": "10m",
"labels": {
"severity": "warning"
@ -806,6 +762,104 @@ data:
"labels": {
"severity": "critical"
}
},
{
"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",
"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"
},
"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\"}) by(node) > 0.95\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"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"
}
}
]
}