CadolesKube/typhoon
7
0
Fork 0
mirror of https://github.com/puppetmaster/typhoon.git synced 2025-07-24 21:51:34 +02:00
Code Issues Packages Projects Releases Wiki Activity

Refresh Prometheus rules and Grafana dashboards

Browse Source 
* Refresh rules and dashboards from upstreams
* Add new Kubernetes "workload" dashboards
  * View pods in a workload (deployment/daemonset/statefulset)
  * View workloads in a namespace
This commit is contained in:
Dalton Hubble
2019-04-06 23:27:11 -07:00
parent 29a3035245
commit ce78d5988e
5 changed files with 5329 additions and 3291 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
addons/prometheus/rules.yaml
View File

@ -183,12 +183,33 @@ data:
"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\"}) by (namespace, pod)\n* on (namespace, pod) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"^(Pending|Running)$\"} == 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\"} and on(pod) kube_pod_status_scheduled{condition=\"true\"}) by (namespace, pod)\n* on (namespace, pod) group_left(label_name)\n label_replace(kube_pod_labels{job=\"kube-state-metrics\"}, \"pod_name\", \"$1\", \"pod\", \"(.*)\")\n)\n",
"expr": "sum by (namespace, label_name) (\n sum(kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"^(Pending|Running)$\"} == 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"
}
]
},
@ -374,11 +395,11 @@ data:
"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]) / 1e3)\n",
"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]) / 1e3\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
"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"
},
{
@ -662,7 +683,7 @@ data:
"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=\"requests.cpu\"})\n /\nsum(node:node_num_cpu:sum)\n > 1.5\n",
"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"
@ -674,7 +695,7 @@ data:
"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=\"requests.memory\"})\n /\nsum(node_memory_MemTotal_bytes{job=\"node-exporter\"})\n > 1.5\n",
"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"
@ -885,10 +906,10 @@ data:
{
"alert": "KubeClientCertificateExpiration",
"annotations": {
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 7 days.",
"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": "histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
"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"
}
@ -896,10 +917,10 @@ data:
{
"alert": "KubeClientCertificateExpiration",
"annotations": {
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 24 hours.",
"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": "histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
"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"
}