From 5f390a835bfae85b17fda50c80a647c46044703f Mon Sep 17 00:00:00 2001 From: Billy Tat Date: Thu, 25 Aug 2022 23:41:32 -0700 Subject: [PATCH] 2.0-2.4: Fix validation errors --- .../cluster-monitoring/expression.md | 16 +- .../populate-private-registry.md | 2 +- .../generic-troubleshooting.md | 2 +- .../troubleshooting/job-complete-status.md | 2 +- .../cluster-and-project-roles.md | 21 +- .../import-existing-clusters.md | 6 +- .../hpa-for-rancher-before-2.0.7.md | 130 +++++---- .../test-hpas-with-kubectl.md | 276 +++++++++--------- .../amazon-eks-permissions.md | 1 + .../rancher-project-tools/project-alerts.md | 6 +- 10 files changed, 237 insertions(+), 225 deletions(-) diff --git a/versioned_docs/version-2.0-2.4/explanations/integrations-in-rancher/cluster-monitoring/expression.md b/versioned_docs/version-2.0-2.4/explanations/integrations-in-rancher/cluster-monitoring/expression.md index 163a0041dc0..514e3097436 100644 --- a/versioned_docs/version-2.0-2.4/explanations/integrations-in-rancher/cluster-monitoring/expression.md +++ b/versioned_docs/version-2.0-2.4/explanations/integrations-in-rancher/cluster-monitoring/expression.md @@ -119,15 +119,15 @@ For more information about querying Prometheus, refer to the official [Prometheu | Catalog | Expression | | --- | --- | -| Detail |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
| -| Summary |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
| +| Detail |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
| +| Summary |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
| ### Cluster Network I/O | Catalog | Expression | | --- | --- | -| Detail |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
| -| Summary |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
| +| Detail |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m])) by (instance)
| +| Summary |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*"}[5m]))
| # Node Metrics @@ -170,15 +170,15 @@ For more information about querying Prometheus, refer to the official [Prometheu | Catalog | Expression | | --- | --- | -| Detail |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
| -| Summary |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
| +| Detail |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
| +| Summary |
receive-droppedsum(rate(node_network_receive_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
receive-errssum(rate(node_network_receive_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
receive-packetssum(rate(node_network_receive_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-droppedsum(rate(node_network_transmit_drop_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-errssum(rate(node_network_transmit_errs_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmit-packetssum(rate(node_network_transmit_packets_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
| ### Node Network I/O | Catalog | Expression | | --- | --- | -| Detail |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
| -| Summary |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
| +| Detail |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m])) by (device)
| +| Summary |
receivesum(rate(node_network_receive_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
transmitsum(rate(node_network_transmit_bytes_total{device!~"lo | veth.* | docker.* | flannel.* | cali.* | cbr.*",instance=~"$instance"}[5m]))
| # Etcd Metrics diff --git a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/air-gap-helm2/populate-private-registry.md b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/air-gap-helm2/populate-private-registry.md index 8b82e241c3b..c325b1bf15a 100644 --- a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/air-gap-helm2/populate-private-registry.md +++ b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/air-gap-helm2/populate-private-registry.md @@ -121,7 +121,7 @@ C. Prepare the Docker daemon
D. Populate the private registry
- Collecting and Populating Windows Images into the Private Registry"%}} + Collecting and Populating Windows Images into the Private Registry"%}} ### Prerequisites diff --git a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/generic-troubleshooting.md b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/generic-troubleshooting.md index 170557ccca7..64f0a10cd47 100644 --- a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/generic-troubleshooting.md +++ b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/generic-troubleshooting.md @@ -45,7 +45,7 @@ If a pod is not in **Running** state, you can dig into the root cause by running kubectl --kubeconfig kube_config_rancher-cluster.yml describe pod POD_NAME -n NAMESPACE ``` -#### Pod container logs +#### Pod container logs ``` kubectl --kubeconfig kube_config_rancher-cluster.yml logs POD_NAME -n NAMESPACE diff --git a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/job-complete-status.md b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/job-complete-status.md index e32b4dfadb9..1c2c6167507 100644 --- a/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/job-complete-status.md +++ b/versioned_docs/version-2.0-2.4/getting-started/installation-and-upgrade/advanced-options/advanced-use-cases/helm2/rke-add-on/troubleshooting/job-complete-status.md @@ -34,7 +34,7 @@ The structure of the addons definition in `rancher-cluster.yml` is wrong. In the
  • Is each of the base64 encoded certificate string placed directly after the key, for example: `tls.crt: LS01...`, there should be no newline/space before, in between or after.
  • Is the YAML properly formatted, each indentation should be 2 spaces as shown in the template files.
    • -
  • Verify the integrity of your certificate by running this command `cat MyCertificate | base64 -d` on Linux, `cat MyCertificate | base64 -D` on Mac OS . If any error exists, the command output will tell you. +
  • Verify the integrity of your certificate by running this command `cat MyCertificate | base64 -d` on Linux, `cat MyCertificate | base64 -D` on Mac OS . If any error exists, the command output will tell you.
diff --git a/versioned_docs/version-2.0-2.4/how-to-guides/advanced-user-guides/authentication-permissions-and-global-configuration/manage-role-based-access-control-rbac/cluster-and-project-roles.md b/versioned_docs/version-2.0-2.4/how-to-guides/advanced-user-guides/authentication-permissions-and-global-configuration/manage-role-based-access-control-rbac/cluster-and-project-roles.md index c6336068498..3067a8c0328 100644 --- a/versioned_docs/version-2.0-2.4/how-to-guides/advanced-user-guides/authentication-permissions-and-global-configuration/manage-role-based-access-control-rbac/cluster-and-project-roles.md +++ b/versioned_docs/version-2.0-2.4/how-to-guides/advanced-user-guides/authentication-permissions-and-global-configuration/manage-role-based-access-control-rbac/cluster-and-project-roles.md @@ -164,20 +164,21 @@ You can change the cluster or project role(s) that are automatically assigned to 1. Find the custom or individual role that you want to use as default. Then edit the role by selecting **⋮ > Edit**. 1. Enable the role as default. -
- For Clusters -1. From **Cluster Creator Default**, choose **Yes: Default role for new cluster creation**. -1. Click **Save**. +
+ For Clusters -
-
+ 1. From **Cluster Creator Default**, choose **Yes: Default role for new cluster creation**. + 1. Click **Save**. - For Projects -1. From **Project Creator Default**, choose **Yes: Default role for new project creation**. -1. Click **Save**. +
+
+ For Projects -
+ 1. From **Project Creator Default**, choose **Yes: Default role for new project creation**. + 1. Click **Save**. + +
1. If you want to remove a default role, edit the permission and select **No** from the default roles option. diff --git a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-clusters-in-rancher-setup/import-existing-clusters.md b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-clusters-in-rancher-setup/import-existing-clusters.md index d2bc2a4b058..68e73acaa26 100644 --- a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-clusters-in-rancher-setup/import-existing-clusters.md +++ b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-clusters-in-rancher-setup/import-existing-clusters.md @@ -72,7 +72,7 @@ By default, GKE users are not given this privilege, so you will need to run the **Result:** -- Your cluster is imported and assigned a state of **Pending.** Rancher is deploying resources to manage your cluster. +- Your cluster is imported and assigned a state of **Pending.** Rancher is deploying resources to manage your cluster. - You can access your cluster after its state is updated to **Active.** - **Active** clusters are assigned two Projects: `Default` (containing the namespace `default`) and `System` (containing the namespaces `cattle-system`, `ingress-nginx`, `kube-public` and `kube-system`, if present). @@ -124,7 +124,7 @@ $ curl -sfL https://get.k3s.io | K3S_KUBECONFIG_MODE="644" sh -s - ### Debug Logging and Troubleshooting for Imported K3s Clusters -Nodes are upgraded by the system upgrade controller running in the downstream cluster. Based on the cluster configuration, Rancher deploys two [plans](https://github.com/rancher/system-upgrade-controller#example-upgrade-plan) to upgrade K3s nodes: one for controlplane nodes and one for workers. The system upgrade controller follows the plans and upgrades the nodes. +Nodes are upgraded by the system upgrade controller running in the downstream cluster. Based on the cluster configuration, Rancher deploys two [plans](https://github.com/rancher/system-upgrade-controller#example-upgrade-plan) to upgrade K3s nodes: one for controlplane nodes and one for workers. The system upgrade controller follows the plans and upgrades the nodes. To enable debug logging on the system upgrade controller deployment, edit the [configmap](https://github.com/rancher/system-upgrade-controller/blob/50a4c8975543d75f1d76a8290001d87dc298bdb4/manifests/system-upgrade-controller.yaml#L32) to set the debug environment variable to true. Then restart the `system-upgrade-controller` pod. @@ -163,7 +163,7 @@ This example annotation indicates that a pod security policy is enabled: The following annotation indicates Ingress capabilities. Note that that the values of non-primitive objects need to be JSON encoded, with quotations escaped. ``` -"capabilities.cattle.io/ingressCapabilities": "[ +"capabilities.cattle.io/ingressCapabilities": "[ { "customDefaultBackend":true, "ingressProvider":"asdf" diff --git a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/hpa-for-rancher-before-2.0.7.md b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/hpa-for-rancher-before-2.0.7.md index 79a39eb73d6..4a46e27fe95 100644 --- a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/hpa-for-rancher-before-2.0.7.md +++ b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/hpa-for-rancher-before-2.0.7.md @@ -82,8 +82,9 @@ To create HPA resources based on resource metrics such as CPU and memory use, yo Then review the log to confirm that the `metrics-server` package is running.
- Metrics Server Log Output + Metrics Server Log Output + ``` I0723 08:09:56.193136 1 heapster.go:71] /metrics-server --source=kubernetes.summary_api:'' I0723 08:09:56.193574 1 heapster.go:72] Metrics Server version v0.2.1 I0723 08:09:56.194480 1 configs.go:61] Using Kubernetes client with master "https://10.43.0.1:443" and version @@ -94,6 +95,8 @@ To create HPA resources based on resource metrics such as CPU and memory use, yo [restful] 2018/07/23 08:09:57 log.go:33: [restful/swagger] listing is available at https:///swaggerapi [restful] 2018/07/23 08:09:57 log.go:33: [restful/swagger] https:///swaggerui/ is mapped to folder /swagger-ui/ I0723 08:09:57.394080 1 serve.go:85] Serving securely on 0.0.0.0:443 + ``` +
@@ -129,68 +132,73 @@ To do it, follow these steps: 1. Copy the ClusterRole and ClusterRoleBinding manifest for the type of metrics you're using for your HPA.
- Resource Metrics: ApiGroups resource.metrics.k8s.io + Resource Metrics: ApiGroups resource.metrics.k8s.io - apiVersion: rbac.authorization.k8s.io/v1 - kind: ClusterRole - metadata: - name: view-resource-metrics - rules: - - apiGroups: - - metrics.k8s.io - resources: - - pods - - nodes - verbs: - - get - - list - - watch - --- - apiVersion: rbac.authorization.k8s.io/v1 - kind: ClusterRoleBinding - metadata: - name: view-resource-metrics - roleRef: - apiGroup: rbac.authorization.k8s.io - kind: ClusterRole - name: view-resource-metrics - subjects: - - apiGroup: rbac.authorization.k8s.io - kind: User - name: system:anonymous -
-
- Custom Metrics: ApiGroups custom.metrics.k8s.io - - ``` - apiVersion: rbac.authorization.k8s.io/v1 - kind: ClusterRole - metadata: - name: view-custom-metrics - rules: - - apiGroups: - - custom.metrics.k8s.io - resources: - - "*" - verbs: - - get - - list - - watch - --- - apiVersion: rbac.authorization.k8s.io/v1 - kind: ClusterRoleBinding - metadata: - name: view-custom-metrics - roleRef: - apiGroup: rbac.authorization.k8s.io + ``` + apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole - name: view-custom-metrics - subjects: - - apiGroup: rbac.authorization.k8s.io - kind: User - name: system:anonymous - ``` -
+ metadata: + name: view-resource-metrics + rules: + - apiGroups: + - metrics.k8s.io + resources: + - pods + - nodes + verbs: + - get + - list + - watch + --- + apiVersion: rbac.authorization.k8s.io/v1 + kind: ClusterRoleBinding + metadata: + name: view-resource-metrics + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: view-resource-metrics + subjects: + - apiGroup: rbac.authorization.k8s.io + kind: User + name: system:anonymous + ``` + +
+
+ Custom Metrics: ApiGroups custom.metrics.k8s.io + + ``` + apiVersion: rbac.authorization.k8s.io/v1 + kind: ClusterRole + metadata: + name: view-custom-metrics + rules: + - apiGroups: + - custom.metrics.k8s.io + resources: + - "*" + verbs: + - get + - list + - watch + --- + apiVersion: rbac.authorization.k8s.io/v1 + kind: ClusterRoleBinding + metadata: + name: view-custom-metrics + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: view-custom-metrics + subjects: + - apiGroup: rbac.authorization.k8s.io + kind: User + name: system:anonymous + ``` + +
+ 1. Create them in your cluster using one of the follow commands, depending on the metrics you're using. ``` # kubectl create -f diff --git a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/test-hpas-with-kubectl.md b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/test-hpas-with-kubectl.md index 65240fa671d..1715c2a5b21 100644 --- a/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/test-hpas-with-kubectl.md +++ b/versioned_docs/version-2.0-2.4/how-to-guides/new-user-guides/kubernetes-resources-setup/horizontal-pod-autoscaler/test-hpas-with-kubectl.md @@ -67,7 +67,7 @@ For HPA to work correctly, service deployments should have resources request def app: hello-world ``` - + 1. Deploy it to your cluster. @@ -168,6 +168,7 @@ For HPA to work correctly, service deployments should have resources request def ScalingLimited False DesiredWithinRange the desired count is within the acceptable range Events: ``` +
Custom Metrics @@ -201,11 +202,10 @@ For HPA to work correctly, service deployments should have resources request def
- 1. Generate a load for the service to test that your pods autoscale as intended. You can use any load-testing tool (Hey, Gatling, etc.), but we're using [Hey](https://github.com/rakyll/hey). 1. Test that pod autoscaling works as intended.

- **To Test Autoscaling Using Resource Metrics:** + **To Test Autoscaling Using Resource Metrics:**
Upscale to 2 Pods: CPU Usage Up to Target @@ -386,147 +386,149 @@ For HPA to work correctly, service deployments should have resources request def
- Upscale to 3 Pods: CPU Usage Up to Target + Upscale to 3 Pods: CPU Usage Up to Target - Use your load testing tool to scale up to three pods when the cpu_system usage limit is up to target. + Use your load testing tool to scale up to three pods when the cpu_system usage limit is up to target. - 1. Enter the following command. - ``` - # kubectl describe hpa - ``` - You should receive output similar to what follows: - ``` - Name: hello-world - Namespace: default - Labels: - Annotations: - CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 - Reference: Deployment/hello-world - Metrics: ( current / target ) - resource memory on pods: 8374272 / 100Mi - "cpu_system" on pods: 27m / 20m - resource cpu on pods (as a percentage of request): 71% (357m) / 50% - Min replicas: 1 - Max replicas: 10 - Conditions: - Type Status Reason Message - ---- ------ ------ ------- - AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 3 - ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from cpu resource utilization (percentage of request) - ScalingLimited False DesiredWithinRange the desired count is within the acceptable range - Events: - Type Reason Age From Message - ---- ------ ---- ---- ------- - Normal SuccessfulRescale 3m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target - Normal SuccessfulRescale 3s horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target - ``` - 1. Enter the following command to confirm three pods are running. - ``` - # kubectl get pods - ``` - You should receive output similar to what follows: - ``` - # kubectl get pods - NAME READY STATUS RESTARTS AGE - hello-world-54764dfbf8-5pfdr 1/1 Running 0 3m - hello-world-54764dfbf8-m2hrl 1/1 Running 0 1s - hello-world-54764dfbf8-q6l82 1/1 Running 0 6h - ``` - -
-
- Upscale to 4 Pods: CPU Usage Up to Target - - Use your load testing tool to upscale to four pods based on CPU usage. `horizontal-pod-autoscaler-upscale-delay` is set to three minutes by default. - - 1. Enter the following command. - ``` - # kubectl describe hpa - ``` - You should receive output similar to what follows. - ``` - Name: hello-world - Namespace: default - Labels: - Annotations: - CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 - Reference: Deployment/hello-world - Metrics: ( current / target ) - resource memory on pods: 8374272 / 100Mi - "cpu_system" on pods: 27m / 20m - resource cpu on pods (as a percentage of request): 71% (357m) / 50% - Min replicas: 1 - Max replicas: 10 - Conditions: - Type Status Reason Message - ---- ------ ------ ------- - AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 3 - ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from cpu resource utilization (percentage of request) - ScalingLimited False DesiredWithinRange the desired count is within the acceptable range - Events: - Type Reason Age From Message - ---- ------ ---- ---- ------- - Normal SuccessfulRescale 5m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target - Normal SuccessfulRescale 3m horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target - Normal SuccessfulRescale 4s horizontal-pod-autoscaler New size: 4; reason: cpu resource utilization (percentage of request) above target - ``` - 1. Enter the following command to confirm four pods are running. - ``` - # kubectl get pods - ``` - You should receive output similar to what follows. - ``` - NAME READY STATUS RESTARTS AGE - hello-world-54764dfbf8-2p9xb 1/1 Running 0 5m - hello-world-54764dfbf8-5pfdr 1/1 Running 0 2m - hello-world-54764dfbf8-m2hrl 1/1 Running 0 1s - hello-world-54764dfbf8-q6l82 1/1 Running 0 6h - ``` -
-
- Downscale to 1 Pod: All Metrics Below Target - - Use your load testing tool to scale down to one pod when all metrics below target for `horizontal-pod-autoscaler-downscale-delay`. - - 1. Enter the following command. + 1. Enter the following command. ``` # kubectl describe hpa ``` - You should receive similar output to what follows. + You should receive output similar to what follows: ``` - Name: hello-world - Namespace: default - Labels: - Annotations: - CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 - Reference: Deployment/hello-world - Metrics: ( current / target ) - resource memory on pods: 8101888 / 100Mi - "cpu_system" on pods: 8m / 20m - resource cpu on pods (as a percentage of request): 0% (0) / 50% - Min replicas: 1 - Max replicas: 10 - Conditions: - Type Status Reason Message - ---- ------ ------ ------- - AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 1 - ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from memory resource - ScalingLimited False DesiredWithinRange the desired count is within the acceptable range - Events: - Type Reason Age From Message - ---- ------ ---- ---- ------- - Normal SuccessfulRescale 10m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target - Normal SuccessfulRescale 8m horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target - Normal SuccessfulRescale 5m horizontal-pod-autoscaler New size: 4; reason: cpu resource utilization (percentage of request) above target - Normal SuccessfulRescale 13s horizontal-pod-autoscaler New size: 1; reason: All metrics below target + Name: hello-world + Namespace: default + Labels: + Annotations: + CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 + Reference: Deployment/hello-world + Metrics: ( current / target ) + resource memory on pods: 8374272 / 100Mi + "cpu_system" on pods: 27m / 20m + resource cpu on pods (as a percentage of request): 71% (357m) / 50% + Min replicas: 1 + Max replicas: 10 + Conditions: + Type Status Reason Message + ---- ------ ------ ------- + AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 3 + ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from cpu resource utilization (percentage of request) + ScalingLimited False DesiredWithinRange the desired count is within the acceptable range + Events: + Type Reason Age From Message + ---- ------ ---- ---- ------- + Normal SuccessfulRescale 3m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target + Normal SuccessfulRescale 3s horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target + ``` + 1. Enter the following command to confirm three pods are running. ``` - 1. Enter the following command to confirm a single pods is running. + # kubectl get pods ``` - # kubectl get pods + You should receive output similar to what follows: ``` - You should receive output similar to what follows. + # kubectl get pods + NAME READY STATUS RESTARTS AGE + hello-world-54764dfbf8-5pfdr 1/1 Running 0 3m + hello-world-54764dfbf8-m2hrl 1/1 Running 0 1s + hello-world-54764dfbf8-q6l82 1/1 Running 0 6h ``` - NAME READY STATUS RESTARTS AGE - hello-world-54764dfbf8-q6l82 1/1 Running 0 6h - ``` -
+ + +
+ Upscale to 4 Pods: CPU Usage Up to Target + + Use your load testing tool to upscale to four pods based on CPU usage. `horizontal-pod-autoscaler-upscale-delay` is set to three minutes by default. + + 1. Enter the following command. + ``` + # kubectl describe hpa + ``` + You should receive output similar to what follows. + ``` + Name: hello-world + Namespace: default + Labels: + Annotations: + CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 + Reference: Deployment/hello-world + Metrics: ( current / target ) + resource memory on pods: 8374272 / 100Mi + "cpu_system" on pods: 27m / 20m + resource cpu on pods (as a percentage of request): 71% (357m) / 50% + Min replicas: 1 + Max replicas: 10 + Conditions: + Type Status Reason Message + ---- ------ ------ ------- + AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 3 + ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from cpu resource utilization (percentage of request) + ScalingLimited False DesiredWithinRange the desired count is within the acceptable range + Events: + Type Reason Age From Message + ---- ------ ---- ---- ------- + Normal SuccessfulRescale 5m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target + Normal SuccessfulRescale 3m horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target + Normal SuccessfulRescale 4s horizontal-pod-autoscaler New size: 4; reason: cpu resource utilization (percentage of request) above target + ``` + 1. Enter the following command to confirm four pods are running. + ``` + # kubectl get pods + ``` + You should receive output similar to what follows. + ``` + NAME READY STATUS RESTARTS AGE + hello-world-54764dfbf8-2p9xb 1/1 Running 0 5m + hello-world-54764dfbf8-5pfdr 1/1 Running 0 2m + hello-world-54764dfbf8-m2hrl 1/1 Running 0 1s + hello-world-54764dfbf8-q6l82 1/1 Running 0 6h + ``` + +
+
+ Downscale to 1 Pod: All Metrics Below Target + + Use your load testing tool to scale down to one pod when all metrics below target for `horizontal-pod-autoscaler-downscale-delay`. + + 1. Enter the following command. + ``` + # kubectl describe hpa + ``` + You should receive similar output to what follows. + ``` + Name: hello-world + Namespace: default + Labels: + Annotations: + CreationTimestamp: Tue, 24 Jul 2018 18:01:11 +0200 + Reference: Deployment/hello-world + Metrics: ( current / target ) + resource memory on pods: 8101888 / 100Mi + "cpu_system" on pods: 8m / 20m + resource cpu on pods (as a percentage of request): 0% (0) / 50% + Min replicas: 1 + Max replicas: 10 + Conditions: + Type Status Reason Message + ---- ------ ------ ------- + AbleToScale True SucceededRescale the HPA controller was able to update the target scale to 1 + ScalingActive True ValidMetricFound the HPA was able to successfully calculate a replica count from memory resource + ScalingLimited False DesiredWithinRange the desired count is within the acceptable range + Events: + Type Reason Age From Message + ---- ------ ---- ---- ------- + Normal SuccessfulRescale 10m horizontal-pod-autoscaler New size: 2; reason: cpu resource utilization (percentage of request) above target + Normal SuccessfulRescale 8m horizontal-pod-autoscaler New size: 3; reason: pods metric cpu_system above target + Normal SuccessfulRescale 5m horizontal-pod-autoscaler New size: 4; reason: cpu resource utilization (percentage of request) above target + Normal SuccessfulRescale 13s horizontal-pod-autoscaler New size: 1; reason: All metrics below target + ``` + 1. Enter the following command to confirm a single pods is running. + ``` + # kubectl get pods + ``` + You should receive output similar to what follows. + ``` + NAME READY STATUS RESTARTS AGE + hello-world-54764dfbf8-q6l82 1/1 Running 0 6h + ``` + +
diff --git a/versioned_docs/version-2.0-2.4/reference-guides/installation-references/amazon-eks-permissions.md b/versioned_docs/version-2.0-2.4/reference-guides/installation-references/amazon-eks-permissions.md index c28cf2123fe..dc98a57a813 100644 --- a/versioned_docs/version-2.0-2.4/reference-guides/installation-references/amazon-eks-permissions.md +++ b/versioned_docs/version-2.0-2.4/reference-guides/installation-references/amazon-eks-permissions.md @@ -153,6 +153,7 @@ If you're using **Custom: Choose from your existing VPC and Subnets**: 1. Click **Next: Select Subnets**. Then choose one of the **Subnets** that displays. 1. Click **Next: Select Security Group**. + If your worker nodes have Private IPs only, you must also choose a **VPC & Subnet** that allow your instances to access the internet. This access is required so that your worker nodes can connect to the Kubernetes control plane. diff --git a/versioned_docs/version-2.0-2.4/reference-guides/rancher-project-tools/project-alerts.md b/versioned_docs/version-2.0-2.4/reference-guides/rancher-project-tools/project-alerts.md index 3423ccdc240..b101398ccc5 100644 --- a/versioned_docs/version-2.0-2.4/reference-guides/rancher-project-tools/project-alerts.md +++ b/versioned_docs/version-2.0-2.4/reference-guides/rancher-project-tools/project-alerts.md @@ -109,7 +109,7 @@ Select a pod status that triggers an alert: - **Not Running** - **Not Scheduled** -- **Restarted times within the last Minutes** +- **Restarted <x> times within the last <x> Minutes** ### Send a @@ -123,7 +123,7 @@ Select the urgency level of the alert based on pod state. For example, select ** ### Advanced Options -By default, the below options will apply to all alert rules within the group. +By default, the below options will apply to all alert rules within the group. You can disable these advanced options when configuring a specific rule. @@ -157,7 +157,7 @@ Select the urgency level of the alert based on the percentage you choose and the ### Advanced Options -By default, the below options will apply to all alert rules within the group. +By default, the below options will apply to all alert rules within the group. You can disable these advanced options when configuring a specific rule.