mirror of
https://github.com/puppetmaster/typhoon.git
synced 2025-08-04 11:51:34 +02:00
Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 444363be2d | |||
| bc7ad25c60 | |||
| e838d4dc3d | |||
| 979c092ef6 | |||
| db8e94bb4b | |||
| eb093af9ed | |||
| 36096f844d | |||
| d236628e53 | |||
| 577b927a2b | |||
| 000c11edf6 | |||
| 29b16c3fc0 | |||
| 0c7a879bc4 | |||
| 1e654c9e4e | |||
| 28ee693e6b | |||
| 8c7d95aefd |
31
CHANGES.md
31
CHANGES.md
@ -4,6 +4,37 @@ Notable changes between versions.
|
||||
|
||||
## Latest
|
||||
|
||||
* Kubernetes [v1.19.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1192)
|
||||
* Update flannel from v0.12.0 to v0.13.0-rc2 ([#216](https://github.com/poseidon/terraform-render-bootstrap/pull/216))
|
||||
* Update flannel-cni from v0.4.0 to v0.4.1
|
||||
* Update CNI plugins from v0.8.6 to v0.8.7
|
||||
|
||||
### Addons
|
||||
|
||||
* Refresh Prometheus rules/alerts and Grafana dashboards ([#831](https://github.com/poseidon/typhoon/pull/831))
|
||||
* Reduce apiserver metrics cardinality for non-core APIs ([#830](https://github.com/poseidon/typhoon/pull/830))
|
||||
|
||||
## v1.19.1
|
||||
|
||||
* Kubernetes [v1.19.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1191)
|
||||
* Change control plane seccomp annotations to GA `seccompProfile` ([#822](https://github.com/poseidon/typhoon/pull/822))
|
||||
* Update Cilium from v1.8.2 to [v1.8.3](https://github.com/cilium/cilium/releases/tag/v1.8.3)
|
||||
* Promote Cilium from experimental to general availability ([#827](https://github.com/poseidon/typhoon/pull/827))
|
||||
* Update Calico from v1.15.2 to [v1.15.3](https://github.com/projectcalico/calico/releases/tag/v3.15.3)
|
||||
|
||||
### Fedora CoreOS
|
||||
|
||||
* Update Fedora CoreOS Config version from v1.0.0 to v1.1.0
|
||||
* Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.1.0
|
||||
|
||||
### Addons
|
||||
|
||||
* Update IngressClass resources to `networking.k8s.io/v1` ([#824](https://github.com/poseidon/typhoon/pull/824))
|
||||
* Update Prometheus from v2.20.0 to [v2.21.0](https://github.com/prometheus/prometheus/releases/tag/v2.21.0)
|
||||
* Remove Kubernetes node name labelmap `relabel_config` from etcd, Kubelet, and CAdvisor scrape config ([#828](https://github.com/poseidon/typhoon/pull/828))
|
||||
|
||||
## v1.19.0
|
||||
|
||||
* Kubernetes [v1.19.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1190)
|
||||
* Update etcd from v3.4.10 to [v3.4.12](https://github.com/etcd-io/etcd/releases/tag/v3.4.12)
|
||||
* Update Calico from v3.15.1 to [v3.15.2](https://docs.projectcalico.org/v3.15/release-notes/)
|
||||
|
||||
10
README.md
10
README.md
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/cl/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
@ -54,7 +54,7 @@ Define a Kubernetes cluster by using the Terraform module for your chosen platfo
|
||||
|
||||
```tf
|
||||
module "yavin" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Google Cloud
|
||||
cluster_name = "yavin"
|
||||
@ -93,9 +93,9 @@ In 4-8 minutes (varies by platform), the cluster will be ready. This Google Clou
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/yavin-config
|
||||
$ kubectl get nodes
|
||||
NAME ROLES STATUS AGE VERSION
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.0
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.2
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -49,6 +49,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -140,6 +141,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -231,6 +233,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -335,6 +338,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -440,6 +444,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -544,6 +549,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -649,6 +655,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -767,6 +774,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -858,6 +866,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
|
||||
@ -11,7 +11,6 @@ data:
|
||||
"editable": true,
|
||||
"gnetId": null,
|
||||
"hideControls": false,
|
||||
"id": 6,
|
||||
"links": [
|
||||
|
||||
],
|
||||
@ -343,7 +342,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "etcd_debugging_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
|
||||
"expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
|
||||
"hide": false,
|
||||
"interval": "",
|
||||
"intervalFactor": 2,
|
||||
|
||||
@ -172,7 +172,7 @@ data:
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
|
||||
"expr": "sum(kubelet_running_pods{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{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
|
||||
"expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}}",
|
||||
@ -565,6 +565,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -656,6 +657,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -760,6 +762,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -864,6 +867,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -962,6 +966,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1075,6 +1080,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1168,6 +1174,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1274,6 +1281,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1378,6 +1386,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1469,6 +1478,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1574,6 +1584,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1665,6 +1676,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1769,6 +1781,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1873,6 +1886,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1998,6 +2012,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -2021,7 +2036,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"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))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}} {{verb}} {{url}}",
|
||||
@ -2102,6 +2117,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2193,6 +2209,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2284,6 +2301,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2470,7 +2488,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Kubelet",
|
||||
"uid": "3138fa155d5915769fbded898ac09fd9",
|
||||
"version": 0
|
||||
@ -2607,6 +2625,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2698,6 +2717,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -2802,6 +2822,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2893,6 +2914,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -2997,6 +3019,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3109,6 +3132,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3132,7 +3156,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -3213,6 +3237,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -3236,7 +3261,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -3317,6 +3342,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3408,6 +3434,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3499,6 +3526,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3659,7 +3687,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Proxy",
|
||||
"uid": "632e265de029684c40b21cb76bca4f94",
|
||||
"version": 0
|
||||
|
||||
@ -31,6 +31,7 @@ data:
|
||||
"fill": 1,
|
||||
"format": "percentunit",
|
||||
"id": 1,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -686,6 +687,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
|
||||
"pattern": "Value #A",
|
||||
@ -704,6 +706,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to workloads",
|
||||
"linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
|
||||
"pattern": "Value #B",
|
||||
@ -722,6 +725,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -740,6 +744,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -758,6 +763,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -776,6 +782,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -794,6 +801,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #G",
|
||||
@ -812,6 +820,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
|
||||
"pattern": "namespace",
|
||||
@ -839,7 +848,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
|
||||
"expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -848,7 +857,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
|
||||
"expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -1105,6 +1114,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
|
||||
"pattern": "Value #A",
|
||||
@ -1123,6 +1133,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to workloads",
|
||||
"linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
|
||||
"pattern": "Value #B",
|
||||
@ -1141,6 +1152,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -1159,6 +1171,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -1177,6 +1190,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -1195,6 +1209,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -1213,6 +1228,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #G",
|
||||
@ -1231,6 +1247,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
|
||||
"pattern": "namespace",
|
||||
@ -1258,7 +1275,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
|
||||
"expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -1267,7 +1284,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
|
||||
"expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -1384,6 +1401,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 11,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1426,6 +1444,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -1444,6 +1463,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -1462,6 +1482,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -1480,6 +1501,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -1498,6 +1520,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -1516,6 +1539,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -1534,6 +1558,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
|
||||
"pattern": "namespace",
|
||||
@ -2472,33 +2497,6 @@ data:
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
"text": "prod",
|
||||
"value": "prod"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 2,
|
||||
"includeAll": false,
|
||||
"label": "cluster",
|
||||
"multi": false,
|
||||
"name": "cluster",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(node_cpu_seconds_total, cluster)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 2,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [
|
||||
|
||||
],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
@ -2557,7 +2555,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Cluster",
|
||||
"uid": "efa86fd1d0c121a26444b636a3f509a8",
|
||||
"version": 0
|
||||
@ -2789,7 +2787,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2873,7 +2871,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})",
|
||||
"format": "time_series",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -3115,6 +3113,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -3133,6 +3132,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -3151,6 +3151,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -3169,6 +3170,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -3187,6 +3189,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -3205,6 +3208,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -3387,7 +3391,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}) by (pod)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3515,6 +3519,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -3533,6 +3538,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -3551,6 +3557,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -3569,6 +3576,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -3587,6 +3595,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -3605,6 +3614,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -3623,6 +3633,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #G",
|
||||
@ -3641,6 +3652,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #H",
|
||||
@ -3659,6 +3671,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -3686,7 +3699,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -3704,7 +3717,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -3722,7 +3735,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -3821,6 +3834,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 9,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -3863,6 +3877,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -3881,6 +3896,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -3899,6 +3915,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -3917,6 +3934,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -3935,6 +3953,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -3953,6 +3972,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -3971,6 +3991,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -4798,7 +4819,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Namespace (Pods)",
|
||||
"uid": "85a562078cdf77779eaa1add43ccec1e",
|
||||
"version": 0
|
||||
@ -4861,7 +4882,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -4973,6 +4994,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -4991,6 +5013,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -5009,6 +5032,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -5027,6 +5051,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -5045,6 +5070,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -5063,6 +5089,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "pod",
|
||||
@ -5090,7 +5117,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5099,7 +5126,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5108,7 +5135,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5117,7 +5144,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5126,7 +5153,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5226,7 +5253,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\", container!=\"\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -5338,6 +5365,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -5356,6 +5384,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -5374,6 +5403,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -5392,6 +5422,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -5410,6 +5441,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -5428,6 +5460,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -5446,6 +5479,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #G",
|
||||
@ -5464,6 +5498,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #H",
|
||||
@ -5482,6 +5517,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "pod",
|
||||
@ -5509,7 +5545,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5518,7 +5554,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5527,7 +5563,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5536,7 +5572,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5545,7 +5581,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=\"$node\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=~\"$node\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5554,7 +5590,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5563,7 +5599,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5572,7 +5608,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
|
||||
"expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -5691,7 +5727,7 @@ data:
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": null,
|
||||
"multi": false,
|
||||
"multi": true,
|
||||
"name": "node",
|
||||
"options": [
|
||||
|
||||
@ -5739,7 +5775,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Node (Pods)",
|
||||
"uid": "200ac8fdbfbb74b39aff88118e4d1c2c",
|
||||
"version": 0
|
||||
|
||||
@ -189,7 +189,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container)",
|
||||
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{container}}",
|
||||
@ -203,7 +203,7 @@ data:
|
||||
"fill": true,
|
||||
"line": true,
|
||||
"op": "gt",
|
||||
"value": 1,
|
||||
"value": 0.80000000000000004,
|
||||
"yaxis": "left"
|
||||
}
|
||||
],
|
||||
@ -308,6 +308,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -326,6 +327,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -344,6 +346,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -362,6 +365,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -380,6 +384,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -398,6 +403,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "container",
|
||||
@ -580,7 +586,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{container}}",
|
||||
@ -708,6 +714,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -726,6 +733,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -744,6 +752,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -762,6 +771,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -780,6 +790,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -798,6 +809,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -816,6 +828,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #G",
|
||||
@ -834,6 +847,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #H",
|
||||
@ -852,6 +866,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "container",
|
||||
@ -879,7 +894,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -897,7 +912,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -915,7 +930,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -1014,6 +1029,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 6,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1112,6 +1128,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 7,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1210,6 +1227,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 8,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1308,6 +1326,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 9,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1406,6 +1425,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 10,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1504,6 +1524,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 10,
|
||||
"id": 11,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -1724,7 +1745,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Pod",
|
||||
"uid": "6581e46e4e5c7ba40a07646395ef7b23",
|
||||
"version": 0
|
||||
@ -1787,7 +1808,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -1899,6 +1920,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -1917,6 +1939,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -1935,6 +1958,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -1953,6 +1977,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -1971,6 +1996,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -1989,6 +2015,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -2016,7 +2043,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2025,7 +2052,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2034,7 +2061,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2043,7 +2070,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2052,7 +2079,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2152,7 +2179,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -2264,6 +2291,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -2282,6 +2310,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -2300,6 +2329,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -2318,6 +2348,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -2336,6 +2367,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -2354,6 +2386,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -2381,7 +2414,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2390,7 +2423,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2399,7 +2432,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2408,7 +2441,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2417,7 +2450,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2489,6 +2522,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -2531,6 +2565,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -2549,6 +2584,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -2567,6 +2603,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -2585,6 +2622,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -2603,6 +2641,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -2621,6 +2660,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -2639,6 +2679,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
|
||||
"pattern": "pod",
|
||||
@ -2666,7 +2707,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2675,7 +2716,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2684,7 +2725,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2693,7 +2734,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2702,7 +2743,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2711,7 +2752,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -2811,7 +2852,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -2909,7 +2950,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3007,7 +3048,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3105,7 +3146,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3203,7 +3244,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3301,7 +3342,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3399,7 +3440,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3497,7 +3538,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{pod}}",
|
||||
@ -3646,7 +3687,7 @@ data:
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
|
||||
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
@ -3673,7 +3714,7 @@ data:
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
|
||||
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
@ -3716,7 +3757,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Workload",
|
||||
"uid": "a164a7f0339f99e89cea5cb47e9be617",
|
||||
"version": 0
|
||||
@ -3798,7 +3839,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}} - {{workload_type}}",
|
||||
@ -3926,6 +3967,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -3944,6 +3986,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -3962,6 +4005,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -3980,6 +4024,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -3998,6 +4043,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -4016,6 +4062,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -4034,6 +4081,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
|
||||
"pattern": "workload",
|
||||
@ -4052,6 +4100,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "workload_type",
|
||||
@ -4079,7 +4128,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
|
||||
"expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4088,7 +4137,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4097,7 +4146,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4106,7 +4155,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4115,7 +4164,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4124,7 +4173,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4243,7 +4292,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}} - {{workload_type}}",
|
||||
@ -4371,6 +4420,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 0,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -4389,6 +4439,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -4407,6 +4458,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -4425,6 +4477,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -4443,6 +4496,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -4461,6 +4515,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -4479,6 +4534,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
|
||||
"pattern": "workload",
|
||||
@ -4497,6 +4553,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "workload_type",
|
||||
@ -4524,7 +4581,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
|
||||
"expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4533,7 +4590,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4542,7 +4599,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4551,7 +4608,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4560,7 +4617,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4569,7 +4626,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4641,6 +4698,7 @@ data:
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"id": 5,
|
||||
"interval": "1m",
|
||||
"legend": {
|
||||
"avg": false,
|
||||
"current": false,
|
||||
@ -4683,6 +4741,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -4701,6 +4760,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -4719,6 +4779,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #C",
|
||||
@ -4737,6 +4798,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #D",
|
||||
@ -4755,6 +4817,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #E",
|
||||
@ -4773,6 +4836,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #F",
|
||||
@ -4791,6 +4855,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": true,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down to pods",
|
||||
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
|
||||
"pattern": "workload",
|
||||
@ -4809,6 +4874,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "workload_type",
|
||||
@ -4836,7 +4902,7 @@ data:
|
||||
],
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4845,7 +4911,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4854,7 +4920,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4863,7 +4929,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4872,7 +4938,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4881,7 +4947,7 @@ data:
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"intervalFactor": 2,
|
||||
@ -4981,7 +5047,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5079,7 +5145,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5177,7 +5243,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5275,7 +5341,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5373,7 +5439,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5471,7 +5537,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5569,7 +5635,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5667,7 +5733,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{workload}}",
|
||||
@ -5757,7 +5823,7 @@ data:
|
||||
"value": "deployment"
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
|
||||
"definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": null,
|
||||
@ -5766,7 +5832,7 @@ data:
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
|
||||
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"skipUrlSync": false,
|
||||
@ -5864,7 +5930,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Compute Resources / Namespace (Workloads)",
|
||||
"uid": "a87fb0d919ec0ea5f6543124e16c42a5",
|
||||
"version": 0
|
||||
|
||||
@ -20,6 +20,24 @@ data:
|
||||
"id": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"panels": [
|
||||
{
|
||||
"content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
|
||||
"datasource": null,
|
||||
"description": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
|
||||
"gridPos": {
|
||||
"h": 2,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 2,
|
||||
"mode": "markdown",
|
||||
"span": 12,
|
||||
"title": "Notice",
|
||||
"type": "text"
|
||||
}
|
||||
],
|
||||
"refresh": "10s",
|
||||
"rows": [
|
||||
@ -37,7 +55,9 @@ data:
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"decimals": 3,
|
||||
"description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?",
|
||||
"format": "percentunit",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
@ -48,7 +68,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 2,
|
||||
"id": 3,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
@ -78,7 +98,7 @@ data:
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 2,
|
||||
"span": 4,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
@ -88,7 +108,7 @@ data:
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(up{job=\"apiserver\", cluster=\"$cluster\"})",
|
||||
"expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
@ -96,7 +116,7 @@ data:
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Up",
|
||||
"title": "Availability (30d) > 99.000%",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
@ -109,7 +129,7 @@ data:
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "min"
|
||||
"valueName": "avg"
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
@ -119,11 +139,13 @@ data:
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"decimals": 3,
|
||||
"description": "How much error budget is left looking at our 0.990% availability gurantees?",
|
||||
"fill": 10,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 3,
|
||||
"id": 4,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -132,6 +154,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -150,37 +173,16 @@ data:
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 5,
|
||||
"span": 8,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"2..\", cluster=\"$cluster\"}[5m]))",
|
||||
"expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "2xx",
|
||||
"legendFormat": "errorbudget",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"3..\", cluster=\"$cluster\"}[5m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "3xx",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"4..\", cluster=\"$cluster\"}[5m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "4xx",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"5..\", cluster=\"$cluster\"}[5m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "5xx",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
@ -188,7 +190,7 @@ data:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "RPC Rate",
|
||||
"title": "ErrorBudget (30d) > 99.000%",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
@ -206,7 +208,8 @@ data:
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "ops",
|
||||
"decimals": 3,
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
@ -214,7 +217,215 @@ data:
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "ops",
|
||||
"decimals": 3,
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"decimals": 3,
|
||||
"description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?",
|
||||
"format": "percentunit",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 5,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Read Availability (30d)",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "N/A",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "avg"
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many read requests (LIST,GET) per second do the apiservers get by code?",
|
||||
"fill": 10,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 6,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "/2../i",
|
||||
"color": "#56A64B"
|
||||
},
|
||||
{
|
||||
"alias": "/3../i",
|
||||
"color": "#F2CC0C"
|
||||
},
|
||||
{
|
||||
"alias": "/4../i",
|
||||
"color": "#3274D9"
|
||||
},
|
||||
{
|
||||
"alias": "/5../i",
|
||||
"color": "#E02F44"
|
||||
}
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 3,
|
||||
"stack": true,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ code }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Read SLI - Requests",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "reqps",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "reqps",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
@ -231,21 +442,23 @@ data:
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 4,
|
||||
"id": 7,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": true,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
@ -262,15 +475,15 @@ data:
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 5,
|
||||
"span": 3,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", verb!=\"WATCH\", cluster=\"$cluster\"}[5m])) by (verb, le))",
|
||||
"expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}}",
|
||||
"legendFormat": "{{ resource }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -279,7 +492,493 @@ data:
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Request duration 99th quantile",
|
||||
"title": "Read SLI - Errors",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many seconds is the 99th percentile for reading (LIST|GET) a given resource?",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 8,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 3,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ resource }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Read SLI - Duration",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "s",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "s",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"decimals": 3,
|
||||
"description": "How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?",
|
||||
"format": "percentunit",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 9,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Write Availability (30d)",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "N/A",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "avg"
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?",
|
||||
"fill": 10,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 10,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
{
|
||||
"alias": "/2../i",
|
||||
"color": "#56A64B"
|
||||
},
|
||||
{
|
||||
"alias": "/3../i",
|
||||
"color": "#F2CC0C"
|
||||
},
|
||||
{
|
||||
"alias": "/4../i",
|
||||
"color": "#3274D9"
|
||||
},
|
||||
{
|
||||
"alias": "/5../i",
|
||||
"color": "#E02F44"
|
||||
}
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 3,
|
||||
"stack": true,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ code }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Write SLI - Requests",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "reqps",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "reqps",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": null,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 11,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 3,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ resource }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Write SLI - Errors",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "percentunit",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 12,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"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": 3,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{ resource }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Write SLI - Duration",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
@ -339,7 +1038,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 5,
|
||||
"id": 13,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -348,6 +1047,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": false,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -430,7 +1130,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 6,
|
||||
"id": 14,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -439,6 +1139,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": false,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -521,7 +1222,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 7,
|
||||
"id": 15,
|
||||
"legend": {
|
||||
"alignAsTable": true,
|
||||
"avg": false,
|
||||
@ -530,6 +1231,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -625,307 +1327,7 @@ data:
|
||||
"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": "etcd_helper_cache_entry_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "ETCD Cache Entry Total",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "short",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$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": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(etcd_helper_cache_hit_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}} hit",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "sum(rate(etcd_helper_cache_miss_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}} miss",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "ETCD Cache Hit/Miss Rate",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "ops",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "ops",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 10,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"span": 4,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_get_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}} get",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_add_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{instance}} miss",
|
||||
"refId": "B"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "ETCD Cache Duration 99th Quantile",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"sort": 0,
|
||||
"value_type": "individual"
|
||||
},
|
||||
"type": "graph",
|
||||
"xaxis": {
|
||||
"buckets": null,
|
||||
"mode": "time",
|
||||
"name": null,
|
||||
"show": true,
|
||||
"values": [
|
||||
|
||||
]
|
||||
},
|
||||
"yaxes": [
|
||||
{
|
||||
"format": "s",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
},
|
||||
{
|
||||
"format": "s",
|
||||
"label": null,
|
||||
"logBase": 1,
|
||||
"max": null,
|
||||
"min": 0,
|
||||
"show": true
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 11,
|
||||
"id": 16,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -934,6 +1336,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1016,7 +1419,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 12,
|
||||
"id": 17,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -1025,6 +1428,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1107,7 +1511,7 @@ data:
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 13,
|
||||
"id": 18,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
@ -1116,6 +1520,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1222,20 +1627,19 @@ data:
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
"text": "prod",
|
||||
"value": "prod"
|
||||
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 2,
|
||||
"includeAll": false,
|
||||
"label": null,
|
||||
"label": "cluster",
|
||||
"multi": false,
|
||||
"name": "cluster",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(apiserver_request_total, cluster)",
|
||||
"refresh": 1,
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
@ -1303,7 +1707,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / API server",
|
||||
"uid": "09ec8aa1e996d6ffcd6817bbaff4db1b",
|
||||
"version": 0
|
||||
@ -1440,6 +1844,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1544,6 +1949,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1648,6 +2054,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1752,6 +2159,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1864,6 +2272,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1887,7 +2296,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -1968,6 +2377,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -1991,7 +2401,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -2072,6 +2482,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2163,6 +2574,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2254,6 +2666,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -2414,7 +2827,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Controller Manager",
|
||||
"uid": "72e0e05bef5099e5f049b05fdc429ed4",
|
||||
"version": 0
|
||||
@ -2467,6 +2880,7 @@ data:
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -2662,6 +3076,7 @@ data:
|
||||
"min": true,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -2965,7 +3380,7 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Persistent Volumes",
|
||||
"uid": "919b92a8e8041bd567af9edab12c840c",
|
||||
"version": 0
|
||||
@ -3102,6 +3517,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -3214,6 +3630,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -3339,6 +3756,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3451,6 +3869,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3474,7 +3893,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -3555,6 +3974,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": true,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": true
|
||||
},
|
||||
@ -3578,7 +3998,7 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{verb}} {{url}}",
|
||||
@ -3659,6 +4079,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3750,6 +4171,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -3841,6 +4263,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -4001,11 +4424,916 @@ data:
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "",
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / Scheduler",
|
||||
"uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
|
||||
"version": 0
|
||||
}
|
||||
statefulset.json: |-
|
||||
{
|
||||
"__inputs": [
|
||||
|
||||
],
|
||||
"__requires": [
|
||||
|
||||
],
|
||||
"annotations": {
|
||||
"list": [
|
||||
|
||||
]
|
||||
},
|
||||
"editable": false,
|
||||
"gnetId": null,
|
||||
"graphTooltip": 0,
|
||||
"hideControls": false,
|
||||
"id": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"refresh": "",
|
||||
"rows": [
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 2,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "cores",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 4,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": true
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "CPU",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
},
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 3,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "GB",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 4,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": true
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Memory",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
},
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 4,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "Bps",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 4,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": true
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\",pod=~\"$statefulset.*\"}[3m]))",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Network",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"height": "100px",
|
||||
"panels": [
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 5,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Desired Replicas",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
},
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 6,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Replicas of current version",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
},
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 7,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Observed Generation",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
},
|
||||
{
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"datasource": "$datasource",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
"maxValue": 100,
|
||||
"minValue": 0,
|
||||
"show": false,
|
||||
"thresholdLabels": false,
|
||||
"thresholdMarkers": true
|
||||
},
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 8,
|
||||
"interval": null,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"mappingType": 1,
|
||||
"mappingTypes": [
|
||||
{
|
||||
"name": "value to text",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"name": "range to text",
|
||||
"value": 2
|
||||
}
|
||||
],
|
||||
"maxDataPoints": 100,
|
||||
"nullPointMode": "connected",
|
||||
"nullText": null,
|
||||
"postfix": "",
|
||||
"postfixFontSize": "50%",
|
||||
"prefix": "",
|
||||
"prefixFontSize": "50%",
|
||||
"rangeMaps": [
|
||||
{
|
||||
"from": "null",
|
||||
"text": "N/A",
|
||||
"to": "null"
|
||||
}
|
||||
],
|
||||
"span": 3,
|
||||
"sparkline": {
|
||||
"fillColor": "rgba(31, 118, 189, 0.18)",
|
||||
"full": false,
|
||||
"lineColor": "rgb(31, 120, 193)",
|
||||
"show": false
|
||||
},
|
||||
"tableColumn": "",
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"thresholds": "",
|
||||
"title": "Metadata Generation",
|
||||
"tooltip": {
|
||||
"shared": false
|
||||
},
|
||||
"type": "singlestat",
|
||||
"valueFontSize": "80%",
|
||||
"valueMaps": [
|
||||
{
|
||||
"op": "=",
|
||||
"text": "0",
|
||||
"value": "null"
|
||||
}
|
||||
],
|
||||
"valueName": "current"
|
||||
}
|
||||
],
|
||||
"repeat": null,
|
||||
"repeatIteration": null,
|
||||
"repeatRowId": null,
|
||||
"showTitle": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"collapse": false,
|
||||
"collapsed": false,
|
||||
"panels": [
|
||||
{
|
||||
"aliasColors": {
|
||||
|
||||
},
|
||||
"bars": false,
|
||||
"dashLength": 10,
|
||||
"dashes": false,
|
||||
"datasource": "$datasource",
|
||||
"fill": 1,
|
||||
"gridPos": {
|
||||
|
||||
},
|
||||
"id": 9,
|
||||
"legend": {
|
||||
"alignAsTable": false,
|
||||
"avg": false,
|
||||
"current": false,
|
||||
"max": false,
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
"lines": true,
|
||||
"linewidth": 1,
|
||||
"links": [
|
||||
|
||||
],
|
||||
"nullPointMode": "null",
|
||||
"percentage": false,
|
||||
"pointradius": 5,
|
||||
"points": false,
|
||||
"renderer": "flot",
|
||||
"repeat": null,
|
||||
"seriesOverrides": [
|
||||
|
||||
],
|
||||
"spaceLength": 10,
|
||||
"stack": false,
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "replicas specified",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"expr": "max(kube_statefulset_status_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "replicas created",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "ready",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "replicas of current version",
|
||||
"refId": "D"
|
||||
},
|
||||
{
|
||||
"expr": "min(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "updated",
|
||||
"refId": "E"
|
||||
}
|
||||
],
|
||||
"thresholds": [
|
||||
|
||||
],
|
||||
"timeFrom": null,
|
||||
"timeShift": null,
|
||||
"title": "Replicas",
|
||||
"tooltip": {
|
||||
"shared": false,
|
||||
"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": false,
|
||||
"title": "Dashboard Row",
|
||||
"titleSize": "h6",
|
||||
"type": "row"
|
||||
}
|
||||
],
|
||||
"schemaVersion": 14,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"kubernetes-mixin"
|
||||
],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {
|
||||
"text": "default",
|
||||
"value": "default"
|
||||
},
|
||||
"hide": 0,
|
||||
"label": null,
|
||||
"name": "datasource",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 2,
|
||||
"includeAll": false,
|
||||
"label": "cluster",
|
||||
"multi": false,
|
||||
"name": "cluster",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(kube_statefulset_metadata_generation, cluster)",
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [
|
||||
|
||||
],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "Namespace",
|
||||
"multi": false,
|
||||
"name": "namespace",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [
|
||||
|
||||
],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
},
|
||||
{
|
||||
"allValue": null,
|
||||
"current": {
|
||||
|
||||
},
|
||||
"datasource": "$datasource",
|
||||
"hide": 0,
|
||||
"includeAll": false,
|
||||
"label": "Name",
|
||||
"multi": false,
|
||||
"name": "statefulset",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)",
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 1,
|
||||
"tagValuesQuery": "",
|
||||
"tags": [
|
||||
|
||||
],
|
||||
"tagsQuery": "",
|
||||
"type": "query",
|
||||
"useTags": false
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5s",
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
},
|
||||
"timezone": "UTC",
|
||||
"title": "Kubernetes / StatefulSets",
|
||||
"uid": "a31c1f46e6f727cb37c0d731a7245005",
|
||||
"version": 0
|
||||
}
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: grafana-dashboards-k8s
|
||||
|
||||
@ -308,6 +308,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": "true",
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -399,6 +400,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": "true",
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -503,6 +505,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": "true",
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -621,6 +624,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -719,6 +723,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
@ -810,6 +815,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": "true",
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": "true"
|
||||
},
|
||||
|
||||
@ -48,6 +48,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -140,6 +141,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -265,6 +267,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -471,6 +474,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -586,6 +590,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -704,6 +709,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -796,6 +802,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
|
||||
@ -48,6 +48,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -71,10 +72,10 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n",
|
||||
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -139,6 +140,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -162,10 +164,10 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n",
|
||||
"expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -243,6 +245,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -266,10 +269,10 @@ data:
|
||||
"steppedLine": false,
|
||||
"targets": [
|
||||
{
|
||||
"expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n",
|
||||
"expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -347,6 +350,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -374,7 +378,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -439,6 +443,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -465,7 +470,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -530,6 +535,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -556,7 +562,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -621,6 +627,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -647,7 +654,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -725,6 +732,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -751,7 +759,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -816,6 +824,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -842,7 +851,7 @@ data:
|
||||
"expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -920,6 +929,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1011,6 +1021,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1037,7 +1048,7 @@ data:
|
||||
"expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -1115,6 +1126,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1141,7 +1153,7 @@ data:
|
||||
"expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -1206,6 +1218,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1232,7 +1245,7 @@ data:
|
||||
"expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -1297,6 +1310,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1323,7 +1337,7 @@ data:
|
||||
"expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -1388,6 +1402,7 @@ data:
|
||||
"min": false,
|
||||
"rightSide": false,
|
||||
"show": true,
|
||||
"sideWidth": null,
|
||||
"total": false,
|
||||
"values": false
|
||||
},
|
||||
@ -1414,7 +1429,7 @@ data:
|
||||
"expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
|
||||
"format": "time_series",
|
||||
"intervalFactor": 2,
|
||||
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
|
||||
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
@ -1567,11 +1582,11 @@ data:
|
||||
"includeAll": true,
|
||||
"label": null,
|
||||
"multi": false,
|
||||
"name": "queue",
|
||||
"name": "url",
|
||||
"options": [
|
||||
|
||||
],
|
||||
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, queue)",
|
||||
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
|
||||
"refresh": 2,
|
||||
"regex": "",
|
||||
"sort": 0,
|
||||
@ -1690,6 +1705,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #A",
|
||||
@ -1708,6 +1724,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "Value #B",
|
||||
@ -1726,6 +1743,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "instance",
|
||||
@ -1744,6 +1762,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "job",
|
||||
@ -1762,6 +1781,7 @@ data:
|
||||
"dateFormat": "YYYY-MM-DD HH:mm:ss",
|
||||
"decimals": 2,
|
||||
"link": false,
|
||||
"linkTargetBlank": false,
|
||||
"linkTooltip": "Drill down",
|
||||
"linkUrl": "",
|
||||
"pattern": "version",
|
||||
@ -2814,7 +2834,7 @@ data:
|
||||
]
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Prometheus",
|
||||
"title": "Prometheus Overview",
|
||||
"uid": "",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
@ -18,9 +18,10 @@ spec:
|
||||
labels:
|
||||
name: grafana
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: grafana
|
||||
image: docker.io/grafana/grafana:7.1.5
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: IngressClass
|
||||
metadata:
|
||||
name: public
|
||||
|
||||
@ -17,9 +17,10 @@ spec:
|
||||
labels:
|
||||
name: nginx-ingress-controller
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: nginx-ingress-controller
|
||||
image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: IngressClass
|
||||
metadata:
|
||||
name: public
|
||||
|
||||
@ -17,9 +17,10 @@ spec:
|
||||
labels:
|
||||
name: nginx-ingress-controller
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: nginx-ingress-controller
|
||||
image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: IngressClass
|
||||
metadata:
|
||||
name: public
|
||||
|
||||
@ -17,9 +17,10 @@ spec:
|
||||
labels:
|
||||
name: nginx-ingress-controller
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: nginx-ingress-controller
|
||||
image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: IngressClass
|
||||
metadata:
|
||||
name: public
|
||||
|
||||
@ -17,9 +17,10 @@ spec:
|
||||
labels:
|
||||
name: nginx-ingress-controller
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: nginx-ingress-controller
|
||||
image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
apiVersion: networking.k8s.io/v1
|
||||
kind: IngressClass
|
||||
metadata:
|
||||
name: public
|
||||
|
||||
@ -17,9 +17,10 @@ spec:
|
||||
labels:
|
||||
name: nginx-ingress-controller
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
containers:
|
||||
- name: nginx-ingress-controller
|
||||
image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
|
||||
|
||||
@ -34,7 +34,7 @@ data:
|
||||
- job_name: 'kubernetes-apiservers'
|
||||
kubernetes_sd_configs:
|
||||
- role: endpoints
|
||||
|
||||
|
||||
scheme: https
|
||||
tls_config:
|
||||
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||||
@ -68,13 +68,16 @@ data:
|
||||
- source_labels: [__name__, group]
|
||||
regex: apiserver_request_duration_seconds_bucket;.+
|
||||
action: drop
|
||||
- source_labels: [__name__, group]
|
||||
regex: apiserver_request_duration_seconds_count;.+
|
||||
action: drop
|
||||
|
||||
# Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
|
||||
# metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
|
||||
- job_name: 'kubelet'
|
||||
kubernetes_sd_configs:
|
||||
- role: node
|
||||
|
||||
|
||||
scheme: https
|
||||
tls_config:
|
||||
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||||
@ -82,10 +85,6 @@ data:
|
||||
insecure_skip_verify: true
|
||||
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
|
||||
relabel_configs:
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_node_name
|
||||
|
||||
# Scrape config for Kubelet cAdvisor. Explore metrics from a node by
|
||||
# scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
|
||||
- job_name: 'kubernetes-cadvisor'
|
||||
@ -100,9 +99,6 @@ data:
|
||||
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||||
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
|
||||
relabel_configs:
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_node_name
|
||||
metric_relabel_configs:
|
||||
- source_labels: [__name__, image]
|
||||
action: drop
|
||||
@ -121,13 +117,11 @@ data:
|
||||
- source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
|
||||
action: keep
|
||||
regex: 'true'
|
||||
- action: labelmap
|
||||
regex: __meta_kubernetes_node_name
|
||||
- source_labels: [__meta_kubernetes_node_address_InternalIP]
|
||||
action: replace
|
||||
target_label: __address__
|
||||
replacement: '${1}:2381'
|
||||
|
||||
|
||||
# Scrape config for service endpoints.
|
||||
#
|
||||
# The relabeling allows the actual service scrape endpoint to be configured
|
||||
@ -172,7 +166,7 @@ data:
|
||||
- source_labels: [__meta_kubernetes_service_name]
|
||||
action: replace
|
||||
target_label: job
|
||||
|
||||
|
||||
metric_relabel_configs:
|
||||
- source_labels: [__name__]
|
||||
action: drop
|
||||
|
||||
@ -14,13 +14,14 @@ spec:
|
||||
labels:
|
||||
name: prometheus
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
serviceAccountName: prometheus
|
||||
containers:
|
||||
- name: prometheus
|
||||
image: quay.io/prometheus/prometheus:v2.20.0
|
||||
image: quay.io/prometheus/prometheus:v2.21.0
|
||||
args:
|
||||
- --web.listen-address=0.0.0.0:9090
|
||||
- --config.file=/etc/prometheus/prometheus.yaml
|
||||
|
||||
@ -18,9 +18,10 @@ spec:
|
||||
labels:
|
||||
name: kube-state-metrics
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
serviceAccountName: kube-state-metrics
|
||||
containers:
|
||||
- name: kube-state-metrics
|
||||
|
||||
@ -17,13 +17,13 @@ spec:
|
||||
labels:
|
||||
name: node-exporter
|
||||
phase: prod
|
||||
annotations:
|
||||
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
|
||||
spec:
|
||||
serviceAccountName: node-exporter
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
hostNetwork: true
|
||||
hostPID: true
|
||||
containers:
|
||||
|
||||
@ -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:"
|
||||
},
|
||||
{
|
||||
@ -461,104 +645,113 @@ data:
|
||||
{
|
||||
"alert": "KubePodCrashLooping",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Pod is crash looping."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubePodNotReady",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Pod has been in a non-ready state for more than 15 minutes."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeDeploymentGenerationMismatch",
|
||||
"annotations": {
|
||||
"message": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch"
|
||||
"description": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch",
|
||||
"summary": "Deployment generation mismatch due to possible roll-back"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeDeploymentReplicasMismatch",
|
||||
"annotations": {
|
||||
"message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
|
||||
"description": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch",
|
||||
"summary": "Deployment has not matched the expected number of replicas."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeStatefulSetReplicasMismatch",
|
||||
"annotations": {
|
||||
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch"
|
||||
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch",
|
||||
"summary": "Deployment has not matched the expected number of replicas."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeStatefulSetGenerationMismatch",
|
||||
"annotations": {
|
||||
"message": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch"
|
||||
"description": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch",
|
||||
"summary": "StatefulSet generation mismatch due to possible roll-back"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeStatefulSetUpdateNotRolledOut",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "StatefulSet update has not been rolled out."
|
||||
},
|
||||
"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.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck"
|
||||
"description": "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",
|
||||
"summary": "DaemonSet rollout is stuck."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Pod container waiting longer than 1 hour"
|
||||
},
|
||||
"expr": "sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0\n",
|
||||
"for": "1h",
|
||||
@ -569,8 +762,9 @@ data:
|
||||
{
|
||||
"alert": "KubeDaemonSetNotScheduled",
|
||||
"annotations": {
|
||||
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled"
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled",
|
||||
"summary": "DaemonSet pods are not scheduled."
|
||||
},
|
||||
"expr": "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n",
|
||||
"for": "10m",
|
||||
@ -581,23 +775,12 @@ data:
|
||||
{
|
||||
"alert": "KubeDaemonSetMisScheduled",
|
||||
"annotations": {
|
||||
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled"
|
||||
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled",
|
||||
"summary": "DaemonSet pods are misscheduled."
|
||||
},
|
||||
"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 +788,12 @@ data:
|
||||
{
|
||||
"alert": "KubeJobCompletion",
|
||||
"annotations": {
|
||||
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion"
|
||||
"description": "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",
|
||||
"summary": "Job did not complete in time"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
@ -617,8 +801,9 @@ data:
|
||||
{
|
||||
"alert": "KubeJobFailed",
|
||||
"annotations": {
|
||||
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed"
|
||||
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed",
|
||||
"summary": "Job failed to complete."
|
||||
},
|
||||
"expr": "kube_job_failed{job=\"kube-state-metrics\"} > 0\n",
|
||||
"for": "15m",
|
||||
@ -629,8 +814,9 @@ data:
|
||||
{
|
||||
"alert": "KubeHpaReplicasMismatch",
|
||||
"annotations": {
|
||||
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch"
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch",
|
||||
"summary": "HPA has not matched descired number of replicas."
|
||||
},
|
||||
"expr": "(kube_hpa_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_hpa_status_current_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_hpa_status_current_replicas[15m]) == 0\n",
|
||||
"for": "15m",
|
||||
@ -641,8 +827,9 @@ data:
|
||||
{
|
||||
"alert": "KubeHpaMaxedOut",
|
||||
"annotations": {
|
||||
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout"
|
||||
"description": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout",
|
||||
"summary": "HPA is running at max replicas"
|
||||
},
|
||||
"expr": "kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_hpa_spec_max_replicas{job=\"kube-state-metrics\"}\n",
|
||||
"for": "15m",
|
||||
@ -658,8 +845,9 @@ data:
|
||||
{
|
||||
"alert": "KubeCPUOvercommit",
|
||||
"annotations": {
|
||||
"message": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
|
||||
"description": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit",
|
||||
"summary": "Cluster has overcommitted CPU resource requests."
|
||||
},
|
||||
"expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n",
|
||||
"for": "5m",
|
||||
@ -668,10 +856,11 @@ 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"
|
||||
"description": "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-kubememoryovercommit",
|
||||
"summary": "Cluster has overcommitted memory resource requests."
|
||||
},
|
||||
"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 +869,11 @@ 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"
|
||||
"description": "Cluster has overcommitted CPU resource requests for Namespaces.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit",
|
||||
"summary": "Cluster has overcommitted CPU resource requests."
|
||||
},
|
||||
"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 +882,11 @@ 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"
|
||||
"description": "Cluster has overcommitted memory resource requests for Namespaces.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit",
|
||||
"summary": "Cluster has overcommitted memory resource requests."
|
||||
},
|
||||
"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",
|
||||
@ -703,13 +894,40 @@ data:
|
||||
"severity": "warning"
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": {
|
||||
"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-kubequotafullyused",
|
||||
"summary": "Namespace quota is fully used."
|
||||
},
|
||||
"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": {
|
||||
"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"
|
||||
"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 > 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": "warning"
|
||||
@ -718,13 +936,14 @@ data:
|
||||
{
|
||||
"alert": "CPUThrottlingHigh",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "{{ $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",
|
||||
"summary": "Processes experience elevated CPU throttling."
|
||||
},
|
||||
"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 +952,11 @@ 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"
|
||||
"description": "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-kubepersistentvolumefillingup",
|
||||
"summary": "PersistentVolume is filling up."
|
||||
},
|
||||
"expr": "kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n < 0.03\n",
|
||||
"for": "1m",
|
||||
@ -745,22 +965,24 @@ 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"
|
||||
"description": "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-kubepersistentvolumefillingup",
|
||||
"summary": "PersistentVolume is filling up."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubePersistentVolumeErrors",
|
||||
"annotations": {
|
||||
"message": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors"
|
||||
"description": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors",
|
||||
"summary": "PersistentVolume is having issues with provisioning."
|
||||
},
|
||||
"expr": "kube_persistentvolume_status_phase{phase=~\"Failed|Pending\",job=\"kube-state-metrics\"} > 0\n",
|
||||
"for": "5m",
|
||||
@ -776,10 +998,11 @@ data:
|
||||
{
|
||||
"alert": "KubeVersionMismatch",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Different semantic versions of Kubernetes components running."
|
||||
},
|
||||
"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"
|
||||
@ -788,8 +1011,9 @@ data:
|
||||
{
|
||||
"alert": "KubeClientErrors",
|
||||
"annotations": {
|
||||
"message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
|
||||
"description": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors",
|
||||
"summary": "Kubernetes API server client is experiencing errors."
|
||||
},
|
||||
"expr": "(sum(rate(rest_client_requests_total{code=~\"5..\"}[5m])) by (instance, job)\n /\nsum(rate(rest_client_requests_total[5m])) by (instance, job))\n> 0.01\n",
|
||||
"for": "15m",
|
||||
@ -800,30 +1024,66 @@ 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"
|
||||
"description": "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",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
"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": {
|
||||
"description": "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",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
"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": {
|
||||
"description": "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",
|
||||
"summary": "The API server is burning too much error budget."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
}
|
||||
]
|
||||
@ -831,59 +1091,12 @@ 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": {
|
||||
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 1.0 hours.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
|
||||
"description": "A client certificate used to authenticate to the apiserver is expiring in less than 1.0 hours.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
|
||||
"summary": "Client certificate is about to expire."
|
||||
},
|
||||
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 3600\n",
|
||||
"labels": {
|
||||
@ -893,8 +1106,9 @@ data:
|
||||
{
|
||||
"alert": "KubeClientCertificateExpiration",
|
||||
"annotations": {
|
||||
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 0.1 hours.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
|
||||
"description": "A client certificate used to authenticate to the apiserver is expiring in less than 0.1 hours.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
|
||||
"summary": "Client certificate is about to expire."
|
||||
},
|
||||
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 300\n",
|
||||
"labels": {
|
||||
@ -904,8 +1118,9 @@ data:
|
||||
{
|
||||
"alert": "AggregatedAPIErrors",
|
||||
"annotations": {
|
||||
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors"
|
||||
"description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors",
|
||||
"summary": "An aggregated API has reported errors."
|
||||
},
|
||||
"expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n",
|
||||
"labels": {
|
||||
@ -915,10 +1130,11 @@ 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.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown"
|
||||
"description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown",
|
||||
"summary": "An aggregated API is down."
|
||||
},
|
||||
"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[10m]))) * 100 < 85\n",
|
||||
"for": "5m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
@ -927,8 +1143,9 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "KubeAPI has disappeared from Prometheus target discovery.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown",
|
||||
"summary": "Target disappeared from Prometheus target discovery."
|
||||
},
|
||||
"expr": "absent(up{job=\"apiserver\"} == 1)\n",
|
||||
"for": "15m",
|
||||
@ -944,8 +1161,9 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "{{ $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",
|
||||
"summary": "Node is not ready."
|
||||
},
|
||||
"expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\n",
|
||||
"for": "15m",
|
||||
@ -956,11 +1174,12 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "{{ $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",
|
||||
"summary": "Node is unreachable."
|
||||
},
|
||||
"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",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
@ -968,10 +1187,11 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Kubelet is running at capacity."
|
||||
},
|
||||
"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"
|
||||
@ -980,8 +1200,9 @@ data:
|
||||
{
|
||||
"alert": "KubeNodeReadinessFlapping",
|
||||
"annotations": {
|
||||
"message": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping"
|
||||
"description": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping",
|
||||
"summary": "Node readiness status is flapping."
|
||||
},
|
||||
"expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n",
|
||||
"for": "15m",
|
||||
@ -992,8 +1213,9 @@ data:
|
||||
{
|
||||
"alert": "KubeletPlegDurationHigh",
|
||||
"annotations": {
|
||||
"message": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh"
|
||||
"description": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh",
|
||||
"summary": "Kubelet Pod Lifecycle Event Generator is taking too long to relist."
|
||||
},
|
||||
"expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n",
|
||||
"for": "5m",
|
||||
@ -1004,10 +1226,85 @@ data:
|
||||
{
|
||||
"alert": "KubeletPodStartUpLatencyHigh",
|
||||
"annotations": {
|
||||
"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"
|
||||
"description": "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",
|
||||
"summary": "Kubelet Pod startup latency is too high."
|
||||
},
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletClientCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
|
||||
"summary": "Kubelet client certificate is about to expire."
|
||||
},
|
||||
"expr": "kubelet_certificate_manager_client_ttl_seconds < 3600\n",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletClientCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
|
||||
"summary": "Kubelet client certificate is about to expire."
|
||||
},
|
||||
"expr": "kubelet_certificate_manager_client_ttl_seconds < 300\n",
|
||||
"labels": {
|
||||
"severity": "critical"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletServerCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
|
||||
"summary": "Kubelet server certificate is about to expire."
|
||||
},
|
||||
"expr": "kubelet_certificate_manager_server_ttl_seconds < 3600\n",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletServerCertificateExpiration",
|
||||
"annotations": {
|
||||
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
|
||||
"summary": "Kubelet server certificate is about to expire."
|
||||
},
|
||||
"expr": "kubelet_certificate_manager_server_ttl_seconds < 300\n",
|
||||
"labels": {
|
||||
"severity": "critical"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletClientCertificateRenewalErrors",
|
||||
"annotations": {
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors",
|
||||
"summary": "Kubelet has failed to renew its client certificate."
|
||||
},
|
||||
"expr": "increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "KubeletServerCertificateRenewalErrors",
|
||||
"annotations": {
|
||||
"description": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors",
|
||||
"summary": "Kubelet has failed to renew its server certificate."
|
||||
},
|
||||
"expr": "increase(kubelet_server_expiration_renew_errors[5m]) > 0\n",
|
||||
"for": "15m",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
@ -1016,8 +1313,9 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "Kubelet has disappeared from Prometheus target discovery.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown",
|
||||
"summary": "Target disappeared from Prometheus target discovery."
|
||||
},
|
||||
"expr": "absent(up{job=\"kubelet\"} == 1)\n",
|
||||
"for": "15m",
|
||||
@ -1033,8 +1331,9 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "KubeScheduler has disappeared from Prometheus target discovery.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown",
|
||||
"summary": "Target disappeared from Prometheus target discovery."
|
||||
},
|
||||
"expr": "absent(up{job=\"kube-scheduler\"} == 1)\n",
|
||||
"for": "15m",
|
||||
@ -1050,8 +1349,9 @@ data:
|
||||
{
|
||||
"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"
|
||||
"description": "KubeControllerManager has disappeared from Prometheus target discovery.",
|
||||
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown",
|
||||
"summary": "Target disappeared from Prometheus target discovery."
|
||||
},
|
||||
"expr": "absent(up{job=\"kube-controller-manager\"} == 1)\n",
|
||||
"for": "15m",
|
||||
@ -1350,14 +1650,25 @@ 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 +1692,29 @@ 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 '{{ $labels.device }}' needs attention and possibly a disk swap.",
|
||||
"summary": "Failed device in RAID array"
|
||||
},
|
||||
"expr": "node_md_disks{state=\"fail\"} > 0\n",
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@ -1515,7 +1849,7 @@ data:
|
||||
{
|
||||
"alert": "PrometheusRemoteStorageFailures",
|
||||
"annotations": {
|
||||
"description": "Prometheus {{$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}}:{{ $labels.url }}",
|
||||
"summary": "Prometheus fails to send samples to remote storage."
|
||||
},
|
||||
"expr": "(\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n (\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n +\n rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n )\n)\n* 100\n> 1\n",
|
||||
@ -1527,7 +1861,7 @@ data:
|
||||
{
|
||||
"alert": "PrometheusRemoteWriteBehind",
|
||||
"annotations": {
|
||||
"description": "Prometheus {{$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}}:{{ $labels.url }}.",
|
||||
"summary": "Prometheus remote write is behind."
|
||||
},
|
||||
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
|
||||
@ -1539,7 +1873,7 @@ data:
|
||||
{
|
||||
"alert": "PrometheusRemoteWriteDesiredShards",
|
||||
"annotations": {
|
||||
"description": "Prometheus {{$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\"}` $labels.instance | query | first | value }}.",
|
||||
"summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
|
||||
},
|
||||
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
|
||||
@ -1571,6 +1905,18 @@ data:
|
||||
"labels": {
|
||||
"severity": "warning"
|
||||
}
|
||||
},
|
||||
{
|
||||
"alert": "PrometheusTargetLimitHit",
|
||||
"annotations": {
|
||||
"description": "Prometheus {{$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"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -52,7 +52,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -134,7 +134,7 @@ systemd:
|
||||
--volume script,kind=host,source=/opt/bootstrap/apply \
|
||||
--mount volume=script,target=/apply \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/apply
|
||||
|
||||
@ -25,7 +25,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -129,7 +129,7 @@ storage:
|
||||
--volume config,kind=host,source=/etc/kubernetes \
|
||||
--mount volume=config,target=/etc/kubernetes \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: etcd-member.service
|
||||
@ -55,7 +55,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -124,7 +124,7 @@ systemd:
|
||||
--volume /opt/bootstrap/assets:/assets:ro,Z \
|
||||
--volume /opt/bootstrap/apply:/apply:ro,Z \
|
||||
--entrypoint=/apply \
|
||||
quay.io/poseidon/kubelet:v1.19.0
|
||||
quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
|
||||
ExecStartPost=-/usr/bin/podman stop bootstrap
|
||||
storage:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: docker.service
|
||||
@ -25,7 +25,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -89,7 +89,7 @@ systemd:
|
||||
Type=oneshot
|
||||
RemainAfterExit=true
|
||||
ExecStart=/bin/true
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.2 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
storage:
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [low-priority](https://typhoon.psdn.io/cl/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -52,7 +52,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -134,7 +134,7 @@ systemd:
|
||||
--volume script,kind=host,source=/opt/bootstrap/apply \
|
||||
--mount volume=script,target=/apply \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/apply
|
||||
|
||||
@ -25,7 +25,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -129,7 +129,7 @@ storage:
|
||||
--volume config,kind=host,source=/etc/kubernetes \
|
||||
--mount volume=config,target=/etc/kubernetes \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname | tr '[:upper:]' '[:lower:]')
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot priority](https://typhoon.psdn.io/fedora-coreos/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: etcd-member.service
|
||||
@ -54,7 +54,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -123,7 +123,7 @@ systemd:
|
||||
--volume /opt/bootstrap/assets:/assets:ro,Z \
|
||||
--volume /opt/bootstrap/apply:/apply:ro,Z \
|
||||
--entrypoint=/apply \
|
||||
quay.io/poseidon/kubelet:v1.19.0
|
||||
quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
|
||||
ExecStartPost=-/usr/bin/podman stop bootstrap
|
||||
storage:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: docker.service
|
||||
@ -24,7 +24,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -88,7 +88,7 @@ systemd:
|
||||
Type=oneshot
|
||||
RemainAfterExit=true
|
||||
ExecStart=/bin/true
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.2 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
storage:
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
|
||||
* Advanced features like [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [var.k8s_domain_name]
|
||||
|
||||
@ -60,7 +60,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -147,7 +147,7 @@ systemd:
|
||||
--volume script,kind=host,source=/opt/bootstrap/apply \
|
||||
--mount volume=script,target=/apply \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/apply
|
||||
|
||||
@ -33,7 +33,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [var.k8s_domain_name]
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: etcd-member.service
|
||||
@ -53,7 +53,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -134,7 +134,7 @@ systemd:
|
||||
--volume /opt/bootstrap/assets:/assets:ro,Z \
|
||||
--volume /opt/bootstrap/apply:/apply:ro,Z \
|
||||
--entrypoint=/apply \
|
||||
quay.io/poseidon/kubelet:v1.19.0
|
||||
quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
|
||||
ExecStartPost=-/usr/bin/podman stop bootstrap
|
||||
storage:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: docker.service
|
||||
@ -23,7 +23,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
|
||||
* Advanced features like [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -62,7 +62,7 @@ systemd:
|
||||
After=coreos-metadata.service
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
EnvironmentFile=/run/metadata/coreos
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -144,7 +144,7 @@ systemd:
|
||||
--volume script,kind=host,source=/opt/bootstrap/apply \
|
||||
--mount volume=script,target=/apply \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/apply
|
||||
|
||||
@ -35,7 +35,7 @@ systemd:
|
||||
After=coreos-metadata.service
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
EnvironmentFile=/run/metadata/coreos
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -134,7 +134,7 @@ storage:
|
||||
--volume config,kind=host,source=/etc/kubernetes \
|
||||
--mount volume=config,target=/etc/kubernetes \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [snippets](https://typhoon.psdn.io/advanced/customization/) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: etcd-member.service
|
||||
@ -55,7 +55,7 @@ systemd:
|
||||
After=afterburn.service
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
EnvironmentFile=/run/metadata/afterburn
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -135,7 +135,7 @@ systemd:
|
||||
--volume /opt/bootstrap/assets:/assets:ro,Z \
|
||||
--volume /opt/bootstrap/apply:/apply:ro,Z \
|
||||
--entrypoint=/apply \
|
||||
quay.io/poseidon/kubelet:v1.19.0
|
||||
quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
|
||||
ExecStartPost=-/usr/bin/podman stop bootstrap
|
||||
storage:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: docker.service
|
||||
@ -26,7 +26,7 @@ systemd:
|
||||
After=afterburn.service
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
EnvironmentFile=/run/metadata/afterburn
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
@ -98,7 +98,7 @@ systemd:
|
||||
Type=oneshot
|
||||
RemainAfterExit=true
|
||||
ExecStart=/bin/true
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.2 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
storage:
|
||||
|
||||
@ -6,7 +6,7 @@ Declare a Zincati `fleet_lock` strategy when provisioning Fedora CoreOS nodes vi
|
||||
|
||||
```yaml
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
storage:
|
||||
files:
|
||||
- path: /etc/zincati/config.d/55-update-strategy.toml
|
||||
|
||||
@ -37,7 +37,7 @@ For example, ensure an `/opt/hello` file is created with permissions 0644.
|
||||
```yaml
|
||||
# custom-files
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
storage:
|
||||
files:
|
||||
- path: /opt/hello
|
||||
@ -183,7 +183,7 @@ To set an alternative Kubelet image, use a snippet to set a systemd dropin.
|
||||
```
|
||||
# host-image-override.yaml
|
||||
variant: fcos <- remove for Flatcar Linux
|
||||
version: 1.0.0 <- remove for Flatcar Linux
|
||||
version: 1.1.0 <- remove for Flatcar Linux
|
||||
systemd:
|
||||
units:
|
||||
- name: kubelet.service
|
||||
|
||||
@ -19,7 +19,7 @@ Create a cluster following the AWS [tutorial](../flatcar-linux/aws.md#cluster).
|
||||
|
||||
```tf
|
||||
module "tempest-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/fedora-coreos/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/fedora-coreos/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# AWS
|
||||
vpc_id = module.tempest.vpc_id
|
||||
@ -42,7 +42,7 @@ Create a cluster following the AWS [tutorial](../flatcar-linux/aws.md#cluster).
|
||||
|
||||
```tf
|
||||
module "tempest-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/container-linux/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/container-linux/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# AWS
|
||||
vpc_id = module.tempest.vpc_id
|
||||
@ -110,7 +110,7 @@ Create a cluster following the Azure [tutorial](../flatcar-linux/azure.md#cluste
|
||||
|
||||
```tf
|
||||
module "ramius-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/fedora-coreos/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/fedora-coreos/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# Azure
|
||||
region = module.ramius.region
|
||||
@ -136,7 +136,7 @@ Create a cluster following the Azure [tutorial](../flatcar-linux/azure.md#cluste
|
||||
|
||||
```tf
|
||||
module "ramius-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/container-linux/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/container-linux/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# Azure
|
||||
region = module.ramius.region
|
||||
@ -205,7 +205,7 @@ Create a cluster following the Google Cloud [tutorial](../flatcar-linux/google-c
|
||||
|
||||
```tf
|
||||
module "yavin-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# Google Cloud
|
||||
region = "europe-west2"
|
||||
@ -229,7 +229,7 @@ Create a cluster following the Google Cloud [tutorial](../flatcar-linux/google-c
|
||||
|
||||
```tf
|
||||
module "yavin-worker-pool" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes/workers?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes/workers?ref=v1.19.2"
|
||||
|
||||
# Google Cloud
|
||||
region = "europe-west2"
|
||||
@ -260,11 +260,11 @@ Verify a managed instance group of workers joins the cluster within a few minute
|
||||
```
|
||||
$ kubectl get nodes
|
||||
NAME STATUS AGE VERSION
|
||||
yavin-controller-0.c.example-com.internal Ready 6m v1.19.0
|
||||
yavin-worker-jrbf.c.example-com.internal Ready 5m v1.19.0
|
||||
yavin-worker-mzdm.c.example-com.internal Ready 5m v1.19.0
|
||||
yavin-16x-worker-jrbf.c.example-com.internal Ready 3m v1.19.0
|
||||
yavin-16x-worker-mzdm.c.example-com.internal Ready 3m v1.19.0
|
||||
yavin-controller-0.c.example-com.internal Ready 6m v1.19.2
|
||||
yavin-worker-jrbf.c.example-com.internal Ready 5m v1.19.2
|
||||
yavin-worker-mzdm.c.example-com.internal Ready 5m v1.19.2
|
||||
yavin-16x-worker-jrbf.c.example-com.internal Ready 3m v1.19.2
|
||||
yavin-16x-worker-mzdm.c.example-com.internal Ready 3m v1.19.2
|
||||
```
|
||||
|
||||
### Variables
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# AWS
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on AWS with Fedora CoreOS.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on AWS with Fedora CoreOS.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a VPC, gateway, subnets, security groups, controller instances, worker auto-scaling group, network load balancer, and TLS assets.
|
||||
|
||||
@ -55,7 +55,7 @@ terraform {
|
||||
}
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "3.3.0"
|
||||
version = "3.6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -72,7 +72,7 @@ Define a Kubernetes cluster using the module `aws/fedora-coreos/kubernetes`.
|
||||
|
||||
```tf
|
||||
module "tempest" {
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# AWS
|
||||
cluster_name = "tempest"
|
||||
@ -145,9 +145,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/tempest-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
ip-10-0-3-155 Ready <none> 10m v1.19.0
|
||||
ip-10-0-26-65 Ready <none> 10m v1.19.0
|
||||
ip-10-0-41-21 Ready <none> 10m v1.19.0
|
||||
ip-10-0-3-155 Ready <none> 10m v1.19.2
|
||||
ip-10-0-26-65 Ready <none> 10m v1.19.2
|
||||
ip-10-0-41-21 Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Azure
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on Azure with Fedora CoreOS.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on Azure with Fedora CoreOS.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a resource group, virtual network, subnets, security groups, controller availability set, worker scale set, load balancer, and TLS assets.
|
||||
|
||||
@ -52,7 +52,7 @@ terraform {
|
||||
}
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "2.25.0"
|
||||
version = "2.27.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -86,7 +86,7 @@ Define a Kubernetes cluster using the module `azure/fedora-coreos/kubernetes`.
|
||||
|
||||
```tf
|
||||
module "ramius" {
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Azure
|
||||
cluster_name = "ramius"
|
||||
@ -161,9 +161,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/ramius-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
ramius-controller-0 Ready <none> 24m v1.19.0
|
||||
ramius-worker-000001 Ready <none> 25m v1.19.0
|
||||
ramius-worker-000002 Ready <none> 24m v1.19.0
|
||||
ramius-controller-0 Ready <none> 24m v1.19.2
|
||||
ramius-worker-000001 Ready <none> 25m v1.19.2
|
||||
ramius-worker-000002 Ready <none> 24m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Bare-Metal
|
||||
|
||||
In this tutorial, we'll network boot and provision a Kubernetes v1.19.0 cluster on bare-metal with Fedora CoreOS.
|
||||
In this tutorial, we'll network boot and provision a Kubernetes v1.19.2 cluster on bare-metal with Fedora CoreOS.
|
||||
|
||||
First, we'll deploy a [Matchbox](https://github.com/poseidon/matchbox) service and setup a network boot environment. Then, we'll declare a Kubernetes cluster using the Typhoon Terraform module and power on machines. On PXE boot, machines will install Fedora CoreOS to disk, reboot into the disk install, and provision themselves as Kubernetes controllers or workers via Ignition.
|
||||
|
||||
@ -154,7 +154,7 @@ Define a Kubernetes cluster using the module `bare-metal/fedora-coreos/kubernete
|
||||
|
||||
```tf
|
||||
module "mercury" {
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# bare-metal
|
||||
cluster_name = "mercury"
|
||||
@ -283,9 +283,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/mercury-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
node1.example.com Ready <none> 10m v1.19.0
|
||||
node2.example.com Ready <none> 10m v1.19.0
|
||||
node3.example.com Ready <none> 10m v1.19.0
|
||||
node1.example.com Ready <none> 10m v1.19.2
|
||||
node2.example.com Ready <none> 10m v1.19.2
|
||||
node3.example.com Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# DigitalOcean
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on DigitalOcean with Fedora CoreOS.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on DigitalOcean with Fedora CoreOS.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create controller droplets, worker droplets, DNS records, tags, and TLS assets.
|
||||
|
||||
@ -81,7 +81,7 @@ Define a Kubernetes cluster using the module `digital-ocean/fedora-coreos/kubern
|
||||
|
||||
```tf
|
||||
module "nemo" {
|
||||
source = "git::https://github.com/poseidon/typhoon//digital-ocean/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//digital-ocean/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Digital Ocean
|
||||
cluster_name = "nemo"
|
||||
@ -155,9 +155,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/nemo-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
10.132.110.130 Ready <none> 10m v1.19.0
|
||||
10.132.115.81 Ready <none> 10m v1.19.0
|
||||
10.132.124.107 Ready <none> 10m v1.19.0
|
||||
10.132.110.130 Ready <none> 10m v1.19.2
|
||||
10.132.115.81 Ready <none> 10m v1.19.2
|
||||
10.132.124.107 Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Google Cloud
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on Google Compute Engine with Fedora CoreOS.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on Google Compute Engine with Fedora CoreOS.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a network, firewall rules, health checks, controller instances, worker managed instance group, load balancers, and TLS assets.
|
||||
|
||||
@ -56,7 +56,7 @@ terraform {
|
||||
}
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "3.36.0"
|
||||
version = "3.38.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -147,9 +147,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/yavin-config
|
||||
$ kubectl get nodes
|
||||
NAME ROLES STATUS AGE VERSION
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.0
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.2
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# AWS
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on AWS with CoreOS Container Linux or Flatcar Linux.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on AWS with CoreOS Container Linux or Flatcar Linux.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a VPC, gateway, subnets, security groups, controller instances, worker auto-scaling group, network load balancer, and TLS assets.
|
||||
|
||||
@ -55,7 +55,7 @@ terraform {
|
||||
}
|
||||
aws = {
|
||||
source = "hashicorp/aws"
|
||||
version = "3.3.0"
|
||||
version = "3.6.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -72,7 +72,7 @@ Define a Kubernetes cluster using the module `aws/container-linux/kubernetes`.
|
||||
|
||||
```tf
|
||||
module "tempest" {
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//aws/container-linux/kubernetes?ref=v1.19.2"
|
||||
|
||||
# AWS
|
||||
cluster_name = "tempest"
|
||||
@ -145,9 +145,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/tempest-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
ip-10-0-3-155 Ready <none> 10m v1.19.0
|
||||
ip-10-0-26-65 Ready <none> 10m v1.19.0
|
||||
ip-10-0-41-21 Ready <none> 10m v1.19.0
|
||||
ip-10-0-3-155 Ready <none> 10m v1.19.2
|
||||
ip-10-0-26-65 Ready <none> 10m v1.19.2
|
||||
ip-10-0-41-21 Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Azure
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on Azure with CoreOS Container Linux or Flatcar Linux.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on Azure with CoreOS Container Linux or Flatcar Linux.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a resource group, virtual network, subnets, security groups, controller availability set, worker scale set, load balancer, and TLS assets.
|
||||
|
||||
@ -52,7 +52,7 @@ terraform {
|
||||
}
|
||||
azurerm = {
|
||||
source = "hashicorp/azurerm"
|
||||
version = "2.25.0"
|
||||
version = "2.27.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -75,7 +75,7 @@ Define a Kubernetes cluster using the module `azure/container-linux/kubernetes`.
|
||||
|
||||
```tf
|
||||
module "ramius" {
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//azure/container-linux/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Azure
|
||||
cluster_name = "ramius"
|
||||
@ -149,9 +149,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/ramius-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
ramius-controller-0 Ready <none> 24m v1.19.0
|
||||
ramius-worker-000001 Ready <none> 25m v1.19.0
|
||||
ramius-worker-000002 Ready <none> 24m v1.19.0
|
||||
ramius-controller-0 Ready <none> 24m v1.19.2
|
||||
ramius-worker-000001 Ready <none> 25m v1.19.2
|
||||
ramius-worker-000002 Ready <none> 24m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Bare-Metal
|
||||
|
||||
In this tutorial, we'll network boot and provision a Kubernetes v1.19.0 cluster on bare-metal with CoreOS Container Linux or Flatcar Linux.
|
||||
In this tutorial, we'll network boot and provision a Kubernetes v1.19.2 cluster on bare-metal with CoreOS Container Linux or Flatcar Linux.
|
||||
|
||||
First, we'll deploy a [Matchbox](https://github.com/poseidon/matchbox) service and setup a network boot environment. Then, we'll declare a Kubernetes cluster using the Typhoon Terraform module and power on machines. On PXE boot, machines will install Container Linux to disk, reboot into the disk install, and provision themselves as Kubernetes controllers or workers via Ignition.
|
||||
|
||||
@ -154,7 +154,7 @@ Define a Kubernetes cluster using the module `bare-metal/container-linux/kuberne
|
||||
|
||||
```tf
|
||||
module "mercury" {
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/container-linux/kubernetes?ref=v1.19.2"
|
||||
|
||||
# bare-metal
|
||||
cluster_name = "mercury"
|
||||
@ -293,9 +293,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/mercury-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
node1.example.com Ready <none> 10m v1.19.0
|
||||
node2.example.com Ready <none> 10m v1.19.0
|
||||
node3.example.com Ready <none> 10m v1.19.0
|
||||
node1.example.com Ready <none> 10m v1.19.2
|
||||
node2.example.com Ready <none> 10m v1.19.2
|
||||
node3.example.com Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# DigitalOcean
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on DigitalOcean with CoreOS Container Linux or Flatcar Linux.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on DigitalOcean with CoreOS Container Linux or Flatcar Linux.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create controller droplets, worker droplets, DNS records, tags, and TLS assets.
|
||||
|
||||
@ -81,7 +81,7 @@ Define a Kubernetes cluster using the module `digital-ocean/container-linux/kube
|
||||
|
||||
```tf
|
||||
module "nemo" {
|
||||
source = "git::https://github.com/poseidon/typhoon//digital-ocean/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//digital-ocean/container-linux/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Digital Ocean
|
||||
cluster_name = "nemo"
|
||||
@ -155,9 +155,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/nemo-config
|
||||
$ kubectl get nodes
|
||||
NAME STATUS ROLES AGE VERSION
|
||||
10.132.110.130 Ready <none> 10m v1.19.0
|
||||
10.132.115.81 Ready <none> 10m v1.19.0
|
||||
10.132.124.107 Ready <none> 10m v1.19.0
|
||||
10.132.110.130 Ready <none> 10m v1.19.2
|
||||
10.132.115.81 Ready <none> 10m v1.19.2
|
||||
10.132.124.107 Ready <none> 10m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Google Cloud
|
||||
|
||||
In this tutorial, we'll create a Kubernetes v1.19.0 cluster on Google Compute Engine with CoreOS Container Linux or Flatcar Linux.
|
||||
In this tutorial, we'll create a Kubernetes v1.19.2 cluster on Google Compute Engine with CoreOS Container Linux or Flatcar Linux.
|
||||
|
||||
We'll declare a Kubernetes cluster using the Typhoon Terraform module. Then apply the changes to create a network, firewall rules, health checks, controller instances, worker managed instance group, load balancers, and TLS assets.
|
||||
|
||||
@ -56,7 +56,7 @@ terraform {
|
||||
}
|
||||
google = {
|
||||
source = "hashicorp/google"
|
||||
version = "3.36.0"
|
||||
version = "3.38.0"
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -92,7 +92,7 @@ Define a Kubernetes cluster using the module `google-cloud/container-linux/kuber
|
||||
|
||||
```tf
|
||||
module "yavin" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Google Cloud
|
||||
cluster_name = "yavin"
|
||||
@ -167,9 +167,9 @@ List nodes in the cluster.
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/yavin-config
|
||||
$ kubectl get nodes
|
||||
NAME ROLES STATUS AGE VERSION
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.0
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.2
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [worker pools](advanced/worker-pools/), [preemptible](fedora-coreos/google-cloud/#preemption) workers, and [snippets](advanced/customization/#container-linux) customization
|
||||
@ -53,7 +53,7 @@ Define a Kubernetes cluster by using the Terraform module for your chosen platfo
|
||||
|
||||
```tf
|
||||
module "yavin" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
|
||||
# Google Cloud
|
||||
cluster_name = "yavin"
|
||||
@ -91,9 +91,9 @@ In 4-8 minutes (varies by platform), the cluster will be ready. This Google Clou
|
||||
$ export KUBECONFIG=/home/user/.kube/configs/yavin-config
|
||||
$ kubectl get nodes
|
||||
NAME ROLES STATUS AGE VERSION
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.0
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.0
|
||||
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.19.2
|
||||
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.19.2
|
||||
```
|
||||
|
||||
List the pods.
|
||||
|
||||
@ -13,12 +13,12 @@ Typhoon provides tagged releases to allow clusters to be versioned using ordinar
|
||||
|
||||
```
|
||||
module "yavin" {
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.2"
|
||||
...
|
||||
}
|
||||
|
||||
module "mercury" {
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/container-linux/kubernetes?ref=v1.19.0"
|
||||
source = "git::https://github.com/poseidon/typhoon//bare-metal/container-linux/kubernetes?ref=v1.19.2"
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/cl/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -52,7 +52,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -132,7 +132,7 @@ systemd:
|
||||
--volume script,kind=host,source=/opt/bootstrap/apply \
|
||||
--mount volume=script,target=/apply \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/apply
|
||||
|
||||
@ -25,7 +25,7 @@ systemd:
|
||||
Description=Kubelet
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -127,7 +127,7 @@ storage:
|
||||
--volume config,kind=host,source=/etc/kubernetes \
|
||||
--mount volume=config,target=/etc/kubernetes \
|
||||
--insecure-options=image \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.0 \
|
||||
docker://quay.io/poseidon/kubelet:v1.19.2 \
|
||||
--net=host \
|
||||
--dns=host \
|
||||
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
|
||||
|
||||
@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
|
||||
|
||||
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
|
||||
|
||||
* Kubernetes v1.19.0 (upstream)
|
||||
* Kubernetes v1.19.2 (upstream)
|
||||
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
|
||||
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
|
||||
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/fedora-coreos/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/) customization
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Kubernetes assets (kubeconfig, manifests)
|
||||
module "bootstrap" {
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
|
||||
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=d0f2123c5971410dc14aecde2307eb13e89c2bdf"
|
||||
|
||||
cluster_name = var.cluster_name
|
||||
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: etcd-member.service
|
||||
@ -54,7 +54,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -123,7 +123,7 @@ systemd:
|
||||
--volume /opt/bootstrap/assets:/assets:ro,Z \
|
||||
--volume /opt/bootstrap/apply:/apply:ro,Z \
|
||||
--entrypoint=/apply \
|
||||
quay.io/poseidon/kubelet:v1.19.0
|
||||
quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
|
||||
ExecStartPost=-/usr/bin/podman stop bootstrap
|
||||
storage:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
---
|
||||
variant: fcos
|
||||
version: 1.0.0
|
||||
version: 1.1.0
|
||||
systemd:
|
||||
units:
|
||||
- name: docker.service
|
||||
@ -24,7 +24,7 @@ systemd:
|
||||
Description=Kubelet (System Container)
|
||||
Wants=rpc-statd.service
|
||||
[Service]
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
|
||||
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.2
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
|
||||
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
|
||||
ExecStartPre=/bin/mkdir -p /opt/cni/bin
|
||||
@ -88,7 +88,7 @@ systemd:
|
||||
Type=oneshot
|
||||
RemainAfterExit=true
|
||||
ExecStart=/bin/true
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.19.2 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
storage:
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
mkdocs==1.1.2
|
||||
mkdocs-material==5.5.9
|
||||
mkdocs-material==5.5.12
|
||||
pygments==2.6.1
|
||||
pymdown-extensions==7.1.0
|
||||
|
||||
Reference in New Issue
Block a user