CadolesKube/typhoon
7
0
Fork 0
mirror of https://github.com/puppetmaster/typhoon.git synced 2025-07-31 16:01:35 +02:00
Code Issues Packages Projects Releases Wiki Activity

Refresh Prometheus rules and Grafana dashboards

Browse Source 
* Refresh rules and dashboards from upstreams
* Organize dashboards and stay below the ConfigMap size
limit
This commit is contained in:
Dalton Hubble
2019-03-13 23:05:14 -07:00
parent bf97a45b9d
commit aa630003a4
5 changed files with 1637 additions and 1357 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
addons/prometheus/rules.yaml
View File

@ -366,19 +366,19 @@ data:
"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.+\"}[1m]))\n",
"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.+\"}[1m])\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_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.+\"}[1m]) / 1e3)\n",
"expr": "avg(irate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\",device=~\"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+\"}[1m]) / 1e3)\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.+\"}[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]) / 1e3\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n)\n",
"record": "node:node_disk_saturation:avg_irate"
},
{
@ -840,7 +840,7 @@ data:
"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])) without(instance, pod)\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) without(instance, pod) * 100 > 10\n",
"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"
@ -852,7 +852,31 @@ data:
"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])) without(instance, pod)\n /\nsum(rate(apiserver_request_count{job=\"apiserver\"}[5m])) without(instance, pod) * 100 > 5\n",
"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"
@ -1040,7 +1064,7 @@ data:
"description": "{{$labels.job}} at {{$labels.instance}} has a corrupted write-ahead log (WAL).",
"summary": "Prometheus write-ahead log is corrupted"
},
"expr": "tsdb_wal_corruptions_total{job=\"prometheus\"} > 0\n",
"expr": "prometheus_tsdb_wal_corruptions_total{job=\"prometheus\"} > 0\n",
"for": "4h",
"labels": {
"severity": "warning"