manifests: regenerate
This commit is contained in:
@@ -1752,6 +1752,8 @@ items:
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Current Status",
|
||||
"type": "table"
|
||||
},
|
||||
@@ -17985,6 +17987,8 @@ items:
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Current Status",
|
||||
"type": "table"
|
||||
},
|
||||
@@ -19288,6 +19292,8 @@ items:
|
||||
"step": 10
|
||||
}
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Current Status",
|
||||
"type": "table"
|
||||
},
|
||||
@@ -25920,45 +25926,21 @@ items:
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": "queue",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "/max_shards/",
|
||||
"yaxis": 2
|
||||
}
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 12,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "max_shards:{{queue}}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "min_shards:{{queue}}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "desired_shards:{{queue}}",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "current_shards:{{queue}}",
|
||||
"refId": "D"
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
@@ -25966,7 +25948,7 @@ items:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Shards: $queue",
|
||||
"title": "Current Shards",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
@@ -26000,20 +25982,7 @@ items:
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Shards",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
@@ -26048,17 +26017,17 @@ items:
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": "queue",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
@@ -26070,7 +26039,7 @@ items:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Shard Capacity: $queue",
|
||||
"title": "Max Shards",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
@@ -26139,7 +26108,293 @@ items:
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": "queue",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Min Shards",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 8,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Desired Shards",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": true,
|
||||
"title": "Shards",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 9,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 6,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Shard Capacity",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 10,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
@@ -26161,7 +26416,7 @@ items:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Pending Samples: $queue",
|
||||
"title": "Pending Samples",
|
||||
"tooltip": {
|
||||
"shared": true,
|
||||
"sort": 0,
|
||||
@@ -26221,7 +26476,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 8,
|
||||
"id": 11,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26312,7 +26567,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 9,
|
||||
"id": 12,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26416,7 +26671,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 10,
|
||||
"id": 13,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26507,7 +26762,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 11,
|
||||
"id": 14,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26598,7 +26853,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 12,
|
||||
"id": 15,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26689,7 +26944,7 @@ items:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 13,
|
||||
"id": 16,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@@ -26870,16 +27125,7 @@ items:
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
"text": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"value": {
|
||||
"selected": true,
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
}
|
||||
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
@@ -26890,7 +27136,7 @@ items:
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(prometheus_remote_storage_shards, queue)",
|
||||
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, queue)",
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 0,
|
||||
|
||||
@@ -762,6 +762,156 @@ spec:
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: kube-apiserver-error
|
||||
rules:
|
||||
- alert: ErrorBudgetBurn
|
||||
annotations:
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn
|
||||
expr: |
|
||||
(
|
||||
status_class_5xx:apiserver_request_total:ratio_rate1h{job="apiserver"} > (14.4*0.010000)
|
||||
and
|
||||
status_class_5xx:apiserver_request_total:ratio_rate5m{job="apiserver"} > (14.4*0.010000)
|
||||
)
|
||||
or
|
||||
(
|
||||
status_class_5xx:apiserver_request_total:ratio_rate6h{job="apiserver"} > (6*0.010000)
|
||||
and
|
||||
status_class_5xx:apiserver_request_total:ratio_rate30m{job="apiserver"} > (6*0.010000)
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
severity: critical
|
||||
- alert: ErrorBudgetBurn
|
||||
annotations:
|
||||
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn
|
||||
expr: |
|
||||
(
|
||||
status_class_5xx:apiserver_request_total:ratio_rate1d{job="apiserver"} > (3*0.010000)
|
||||
and
|
||||
status_class_5xx:apiserver_request_total:ratio_rate2h{job="apiserver"} > (3*0.010000)
|
||||
)
|
||||
or
|
||||
(
|
||||
status_class_5xx:apiserver_request_total:ratio_rate3d{job="apiserver"} > (0.010000)
|
||||
and
|
||||
status_class_5xx:apiserver_request_total:ratio_rate6h{job="apiserver"} > (0.010000)
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
severity: warning
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[5m]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate5m
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[30m]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate30m
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[1h]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate1h
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[2h]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate2h
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[6h]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate6h
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[1d]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate1d
|
||||
- expr: |
|
||||
sum by (status_class) (
|
||||
label_replace(
|
||||
rate(apiserver_request_total{job="apiserver"}[3d]
|
||||
), "status_class", "${1}xx", "code", "([0-9])..")
|
||||
)
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class:apiserver_request_total:rate3d
|
||||
- expr: |
|
||||
sum(status_class:apiserver_request_total:rate5m{job="apiserver",status_class="5xx"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate5m{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate30m{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate1h{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate2h{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate6h{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate1d{job="apiserver"})
|
||||
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"})
|
||||
/
|
||||
sum(status_class:apiserver_request_total:rate3d{job="apiserver"})
|
||||
labels:
|
||||
job: apiserver
|
||||
record: status_class_5xx:apiserver_request_total:ratio_rate3d
|
||||
- name: kubernetes-system-apiserver
|
||||
rules:
|
||||
- alert: KubeAPILatencyHigh
|
||||
|
||||
Reference in New Issue
Block a user