CadolesKube/typhoon
7
0
Fork 0
mirror of https://github.com/puppetmaster/typhoon.git synced 2025-07-30 02:41:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

Refresh Prometheus rules/alerts and Grafana dashboards

Browse Source 
* Refresh upstream Prometheus rules/alerts and Grafana dashboards
This commit is contained in:
Dalton Hubble
2020-09-13 14:42:07 -07:00
parent 979c092ef6
commit e838d4dc3d
11 changed files with 2476 additions and 749 deletions
Download Patch File Download Diff File Expand all files Collapse all files

701
addons/prometheus/rules.yaml
View File

@ -11,8 +11,8 @@ data:
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }})."
},
"expr": "max by (job) (\n sum by (job) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count by (job,endpoint) (\n sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[3m])) > 0.01\n )\n)\n> 0\n",
"for": "3m",
"expr": "max without (endpoint) (\n sum without (instance) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count without (To) (\n sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[120s])) > 0.01\n )\n)\n> 0\n",
"for": "10m",
"labels": {
"severity": "critical"
}
@ -22,7 +22,7 @@ data:
"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",
"expr": "sum(up{job=~\".*etcd.*\"} == bool 1) without (instance) < ((count(up{job=~\".*etcd.*\"}) without (instance) + 1) / 2)\n",
"for": "3m",
"labels": {
"severity": "critical"
@ -44,18 +44,40 @@ data:
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated."
},
"expr": "increase((max by (job) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 3\n",
"expr": "increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 4\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedGRPCRequests",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}."
},
"expr": "100 * sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", grpc_code!=\"OK\"}[5m])) without (grpc_type, grpc_code)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 1\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedGRPCRequests",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}."
},
"expr": "100 * sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", grpc_code!=\"OK\"}[5m])) without (grpc_type, grpc_code)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 5\n",
"for": "5m",
"labels": {
"severity": "critical"
}
},
{
"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",
"expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) without(grpc_type))\n> 0.15\n",
"for": "10m",
"labels": {
"severity": "critical"
@ -110,7 +132,7 @@ data:
"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",
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nwithout (code) > 0.01\n",
"for": "10m",
"labels": {
"severity": "warning"
@ -121,7 +143,7 @@ data:
"annotations": {
"message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}."
},
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.05\n",
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nwithout (code) > 0.05\n",
"for": "10m",
"labels": {
"severity": "critical"
@ -145,112 +167,137 @@ data:
kube.yaml: |-
{
"groups": [
{
"name": "kube-apiserver-error",
"rules": [
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[5m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate5m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[30m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate30m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[2h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate2h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[6h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate6h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate1d"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[3d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"labels": {
"job": "apiserver"
},
"record": "status_class:apiserver_request_total:rate3d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate5m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate5m{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate5m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate30m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate30m{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate30m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate2h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate2h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate2h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate6h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate6h{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate6h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1d{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate3d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate3d{job=\"apiserver\"})\n",
"labels": {
"job": "apiserver"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate3d"
}
]
},
{
"name": "kube-apiserver.rules",
"rules": [
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[1d]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[1d]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[1d]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate1d"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[1h]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[1h]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[1h]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate1h"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[2h]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[2h]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[2h]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate2h"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30m]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30m]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30m]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate30m"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[3d]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[3d]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[3d]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate3d"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[5m]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[5m]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[5m]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate5m"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n -\n (\n (\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[6h]))\n or\n vector(0)\n )\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[6h]))\n +\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[6h]))\n )\n )\n +\n # errors\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:burnrate6h"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[1d]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate1d"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[1h]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate1h"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[2h]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate2h"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30m]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate30m"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[3d]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate3d"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[5m]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate5m"
},
{
"expr": "(\n (\n # too slow\n sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n -\n sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[6h]))\n )\n +\n sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:burnrate6h"
},
{
"expr": "sum by (code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
"labels": {
"verb": "read"
},
"record": "code_resource:apiserver_request_total:rate5m"
},
{
"expr": "sum by (code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
"labels": {
"verb": "write"
},
"record": "code_resource:apiserver_request_total:rate5m"
},
{
"expr": "histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))) > 0\n",
"labels": {
"quantile": "0.99",
"verb": "read"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))) > 0\n",
"labels": {
"quantile": "0.99",
"verb": "write"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "sum(rate(apiserver_request_duration_seconds_sum{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n/\nsum(rate(apiserver_request_duration_seconds_count{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n",
"record": "cluster:apiserver_request_duration_seconds:mean5m"
@ -278,6 +325,143 @@ data:
}
]
},
{
"interval": "3m",
"name": "kube-apiserver-availability.rules",
"rules": [
{
"expr": "1 - (\n (\n # write too slow\n sum(increase(apiserver_request_duration_seconds_count{verb=~\"POST|PUT|PATCH|DELETE\"}[30d]))\n -\n sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30d]))\n ) +\n (\n # read too slow\n sum(increase(apiserver_request_duration_seconds_count{verb=~\"LIST|GET\"}[30d]))\n -\n (\n (\n sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30d]))\n or\n vector(0)\n )\n +\n sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30d]))\n +\n sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30d]))\n )\n ) +\n # errors\n sum(code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d)\n",
"labels": {
"verb": "all"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "1 - (\n sum(increase(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30d]))\n -\n (\n # too slow\n (\n sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30d]))\n or\n vector(0)\n )\n +\n sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30d]))\n +\n sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30d]))\n )\n +\n # errors\n sum(code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d{verb=\"read\"})\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "1 - (\n (\n # too slow\n sum(increase(apiserver_request_duration_seconds_count{verb=~\"POST|PUT|PATCH|DELETE\"}[30d]))\n -\n sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30d]))\n )\n +\n # errors\n sum(code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d{verb=\"write\"})\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"2..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"3..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"4..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"5..\"}[30d]))\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~\"LIST|GET\"})\n",
"labels": {
"verb": "read"
},
"record": "code:apiserver_request_total:increase30d"
},
{
"expr": "sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n",
"labels": {
"verb": "write"
},
"record": "code:apiserver_request_total:increase30d"
}
]
},
{
"name": "k8s.rules",
"rules": [
@ -286,23 +470,23 @@ data:
"record": "namespace:container_cpu_usage_seconds_total:sum_rate"
},
{
"expr": "sum by (cluster, namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "sum by (cluster, namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\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) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\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) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_rss"
},
{
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_cache"
},
{
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_swap"
},
{
@ -322,21 +506,21 @@ data:
"labels": {
"workload_type": "deployment"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "daemonset"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "statefulset"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
}
]
},
@ -412,11 +596,11 @@ data:
"name": "node.rules",
"rules": [
{
"expr": "sum(min(kube_pod_info) by (cluster, node))\n",
"expr": "sum(min(kube_pod_info{node!=\"\"}) by (cluster, node))\n",
"record": ":kube_pod_info_node_count:"
},
{
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\",node!=\"\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
"record": "node_namespace_pod:kube_pod_info:"
},
{
@ -464,10 +648,10 @@ data:
"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",
"expr": "rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\"}[5m]) * 60 * 5 > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -476,10 +660,10 @@ data:
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
},
"expr": "sum by (namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}) * on(namespace, pod) group_left(owner_kind) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})) > 0\n",
"expr": "sum by (namespace, pod) (\n max by(namespace, pod) (\n kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}\n ) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (\n 1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})\n )\n) > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -491,7 +675,7 @@ data:
"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"
"severity": "warning"
}
},
{
@ -503,7 +687,7 @@ data:
"expr": "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -515,7 +699,7 @@ data:
"expr": "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -527,7 +711,7 @@ data:
"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"
"severity": "warning"
}
},
{
@ -536,22 +720,22 @@ data:
"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",
"expr": "(\n 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) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeDaemonSetRolloutStuck",
"annotations": {
"message": "Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.",
"message": "DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes.",
"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\"} < 1.00\n",
"expr": "(\n (\n kube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"}\n !=\n 0\n ) or (\n kube_daemonset_updated_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_available{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_daemonset_updated_number_scheduled{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -585,19 +769,7 @@ data:
"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",
"for": "15m",
"labels": {
"severity": "warning"
}
@ -605,11 +777,11 @@ data:
{
"alert": "KubeJobCompletion",
"annotations": {
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete.",
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than 12 hours 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",
"for": "12h",
"labels": {
"severity": "warning"
}
@ -668,10 +840,10 @@ data:
}
},
{
"alert": "KubeMemOvercommit",
"alert": "KubeMemoryOvercommit",
"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"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit"
},
"expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})\n /\nsum(kube_node_status_allocatable_memory_bytes)\n >\n(count(kube_node_status_allocatable_memory_bytes)-1)\n /\ncount(kube_node_status_allocatable_memory_bytes)\n",
"for": "5m",
@ -680,10 +852,10 @@ data:
}
},
{
"alert": "KubeCPUOvercommit",
"alert": "KubeCPUQuotaOvercommit",
"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"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit"
},
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n > 1.5\n",
"for": "5m",
@ -692,10 +864,10 @@ data:
}
},
{
"alert": "KubeMemOvercommit",
"alert": "KubeMemoryQuotaOvercommit",
"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"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit"
},
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n /\nsum(kube_node_status_allocatable_memory_bytes{job=\"node-exporter\"})\n > 1.5\n",
"for": "5m",
@ -704,12 +876,38 @@ data:
}
},
{
"alert": "KubeQuotaExceeded",
"alert": "KubeQuotaAlmostFull",
"annotations": {
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull",
"summary": "Namespace quota is going to be full."
},
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.9 < 1\n",
"for": "15m",
"labels": {
"severity": "info"
}
},
{
"alert": "KubeQuotaFullyUsed",
"annotations": {
"message": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused"
},
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.90\n",
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n == 1\n",
"for": "15m",
"labels": {
"severity": "info"
}
},
{
"alert": "KubeQuotaExceeded",
"annotations": {
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded",
"summary": "Namespace quota has exceeded the limits."
},
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 1\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -721,10 +919,10 @@ data:
"message": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh"
},
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n > ( 100 / 100 )\n",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n > ( 80 / 100 )\n",
"for": "15m",
"labels": {
"severity": "warning"
"severity": "info"
}
}
]
@ -733,10 +931,10 @@ data:
"name": "kubernetes-storage",
"rules": [
{
"alert": "KubePersistentVolumeUsageCritical",
"alert": "KubePersistentVolumeFillingUp",
"annotations": {
"message": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup"
},
"expr": "kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n < 0.03\n",
"for": "1m",
@ -745,15 +943,15 @@ data:
}
},
{
"alert": "KubePersistentVolumeFullInFourDays",
"alert": "KubePersistentVolumeFillingUp",
"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 {{ $value | humanizePercentage }} is available.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup"
},
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n",
"for": "1h",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
@ -779,7 +977,7 @@ data:
"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!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*.[0-9]*).*\"))) > 1\n",
"expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*).*\"))) > 1\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -800,30 +998,62 @@ data:
]
},
{
"name": "kube-apiserver-error-alerts",
"name": "kube-apiserver-slos",
"rules": [
{
"alert": "ErrorBudgetBurn",
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
"message": "The API server is burning too much error budget",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1h{job=\"apiserver\"} > (14.4*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate5m{job=\"apiserver\"} > (14.4*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (6*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate30m{job=\"apiserver\"} > (6*0.010000)\n)\n",
"expr": "sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)\nand\nsum(apiserver_request:burnrate5m) > (14.40 * 0.01000)\n",
"for": "2m",
"labels": {
"job": "apiserver",
"severity": "critical"
"long": "1h",
"severity": "critical",
"short": "5m"
}
},
{
"alert": "ErrorBudgetBurn",
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
"message": "The API server is burning too much error budget",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn"
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1d{job=\"apiserver\"} > (3*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate2h{job=\"apiserver\"} > (3*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate3d{job=\"apiserver\"} > (0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (0.010000)\n)\n",
"expr": "sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)\nand\nsum(apiserver_request:burnrate30m) > (6.00 * 0.01000)\n",
"for": "15m",
"labels": {
"job": "apiserver",
"severity": "warning"
"long": "6h",
"severity": "critical",
"short": "30m"
}
},
{
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "The API server is burning too much error budget",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn"
},
"expr": "sum(apiserver_request:burnrate1d) > (3.00 * 0.01000)\nand\nsum(apiserver_request:burnrate2h) > (3.00 * 0.01000)\n",
"for": "1h",
"labels": {
"long": "1d",
"severity": "warning",
"short": "2h"
}
},
{
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "The API server is burning too much error budget",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn"
},
"expr": "sum(apiserver_request:burnrate3d) > (1.00 * 0.01000)\nand\nsum(apiserver_request:burnrate6h) > (1.00 * 0.01000)\n",
"for": "3h",
"labels": {
"long": "3d",
"severity": "warning",
"short": "6h"
}
}
]
@ -831,54 +1061,6 @@ data:
{
"name": "kubernetes-system-apiserver",
"rules": [
{
"alert": "KubeAPILatencyHigh",
"annotations": {
"message": "The API server has an abnormal 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": "(\n cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"}\n >\n on (verb) group_left()\n (\n avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n +\n 2*stddev by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n )\n) > on (verb) group_left()\n1.2 * avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\nand on (verb,resource)\ncluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"}\n>\n1\n",
"for": "5m",
"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_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"} > 4\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"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",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"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",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeClientCertificateExpiration",
"annotations": {
@ -915,10 +1097,10 @@ data:
{
"alert": "AggregatedAPIDown",
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} is down. It has not been available at least for the past five minutes.",
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 5m.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown"
},
"expr": "sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0\n",
"expr": "(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[5m]))) * 100 < 90\n",
"for": "5m",
"labels": {
"severity": "warning"
@ -959,8 +1141,7 @@ data:
"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",
"for": "2m",
"expr": "(kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} unless ignoring(key,value) kube_node_spec_taint{job=\"kube-state-metrics\",key=~\"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn\"}) == 1\n",
"labels": {
"severity": "warning"
}
@ -971,7 +1152,7 @@ data:
"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\"} != 1) by(node) > 0.95\n",
"expr": "count by(node) (\n (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(node) (\n kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1\n) > 0.95\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -1007,7 +1188,7 @@ data:
"message": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh"
},
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 60\n",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"} > 60\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -1350,14 +1531,25 @@ data:
{
"alert": "NodeHighNumberConntrackEntriesUsed",
"annotations": {
"description": "{{ $value | humanizePercentage }} of conntrack entries are used",
"summary": "Number of conntrack are getting close to the limit"
"description": "{{ $value | humanizePercentage }} of conntrack entries are used.",
"summary": "Number of conntrack are getting close to the limit."
},
"expr": "(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeTextFileCollectorScrapeError",
"annotations": {
"description": "Node Exporter text file collector failed to scrape.",
"summary": "Node Exporter text file collector failed to scrape."
},
"expr": "node_textfile_scrape_error{job=\"node-exporter\"} == 1\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeClockSkewDetected",
"annotations": {
@ -1381,6 +1573,29 @@ data:
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeRAIDDegraded",
"annotations": {
"description": "RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.",
"summary": "RAID Array is degraded"
},
"expr": "node_md_disks_required - ignoring (state) (node_md_disks{state=\"active\"}) > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeRAIDDiskFailure",
"annotations": {
"description": "At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.",
"summary": "Failed device in RAID array"
},
"expr": "node_md_disks{state=\"fail\"} > 0\n",
"labels": {
"severity": "warning"
}
}
]
}
@ -1515,7 +1730,7 @@ data:
{
"alert": "PrometheusRemoteStorageFailures",
"annotations": {
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}",
"summary": "Prometheus fails to send samples to remote storage."
},
"expr": "(\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n (\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n +\n rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n )\n)\n* 100\n> 1\n",
@ -1527,7 +1742,7 @@ data:
{
"alert": "PrometheusRemoteWriteBehind",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.",
"summary": "Prometheus remote write is behind."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
@ -1539,7 +1754,7 @@ data:
{
"alert": "PrometheusRemoteWriteDesiredShards",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
@ -1571,6 +1786,18 @@ data:
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusTargetLimitHit",
"annotations": {
"description": "Prometheus {{$labels.instance}} has dropped {{ printf \"%.0f\" $value }} targets because the number of targets exceeded the configured target_limit.",
"summary": "Prometheus has dropped targets because some scrape configs have exceeded the targets limit."
},
"expr": "increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job=\"prometheus\"}[5m]) > 0\n",
"for": "15m",
"labels": {
"severity": "warning"
}
}
]
}