diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/.helmignore b/lib/aws/bootstrap/charts/aws-node-termination-handler/.helmignore index 50af0317..69a52314 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/.helmignore +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/.helmignore @@ -20,3 +20,4 @@ .idea/ *.tmproj .vscode/ +example-values*.yaml diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/Chart.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/Chart.yaml index 47ed2baa..9de84506 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/Chart.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/Chart.yaml @@ -1,27 +1,25 @@ -apiVersion: v1 -appVersion: 1.5.0 -description: A Helm chart for the AWS Node Termination Handler +apiVersion: v2 +appVersion: 1.14.1 +description: A Helm chart for the AWS Node Termination Handler. home: https://github.com/aws/eks-charts icon: https://raw.githubusercontent.com/aws/eks-charts/master/docs/logo/aws.png keywords: +- aws - eks - ec2 - node-termination - spot +kubeVersion: '>= 1.16-0' maintainers: -- email: nckturner@users.noreply.github.com - name: Nicholas Turner - url: https://github.com/nckturner -- email: stefanprodan@users.noreply.github.com - name: Stefan Prodan - url: https://github.com/stefanprodan +- email: bwagner5@users.noreply.github.com + name: Brandon Wagner + url: https://github.com/bwagner5 - email: jillmon@users.noreply.github.com - name: Jillian Montalvo + name: Jillian Kuentz url: https://github.com/jillmon -- email: mattrandallbecker@users.noreply.github.com - name: Matthew Becker - url: https://github.com/mattrandallbecker name: aws-node-termination-handler sources: -- https://github.com/aws/eks-charts -version: 0.8.0 +- https://github.com/aws/aws-node-termination-handler/ +- https://github.com/aws/eks-charts/ +type: application +version: 0.16.1 diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/README.md b/lib/aws/bootstrap/charts/aws-node-termination-handler/README.md index f1847304..48766925 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/README.md +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/README.md @@ -1,96 +1,170 @@ # AWS Node Termination Handler -AWS Node Termination Handler Helm chart for Kubernetes. For more information on this project see the project repo at https://github.com/aws/aws-node-termination-handler. +AWS Node Termination Handler Helm chart for Kubernetes. For more information on this project see the project repo at [github.com/aws/aws-node-termination-handler](https://github.com/aws/aws-node-termination-handler). ## Prerequisites -* Kubernetes >= 1.11 +- _Kubernetes_ >= v1.16 ## Installing the Chart -Add the EKS repository to Helm: -```sh -helm repo add eks https://aws.github.io/eks-charts -``` -Install AWS Node Termination Handler: -To install the chart with the release name aws-node-termination-handler and default configuration: +Before you can install the chart you will need to add the `aws` repo to [Helm](https://helm.sh/). -```sh -helm install --name aws-node-termination-handler \ - --namespace kube-system eks/aws-node-termination-handler +```shell +helm repo add eks https://aws.github.io/eks-charts/ ``` -To install into an EKS cluster where the Node Termination Handler is already installed, you can run: +After you've installed the repo you can install the chart, the following command will install the chart with the release name `aws-node-termination-handler` and the default configuration to the `kube-system` namespace. -```sh -helm upgrade --install --recreate-pods --force \ - aws-node-termination-handler --namespace kube-system eks/aws-node-termination-handler +```shell +helm upgrade --install --namespace kube-system aws-node-termination-handler eks/aws-node-termination-handler ``` -If you receive an error similar to `Error: release aws-node-termination-handler -failed: "aws-node-termination-handler" already exists`, simply rerun -the above command. +To install the chart on an EKS cluster where the AWS Node Termination Handler is already installed, you can run the following command. -The [configuration](#configuration) section lists the parameters that can be configured during installation. - -## Uninstalling the Chart - -To uninstall/delete the `aws-node-termination-handler` deployment: - -```sh -helm delete --purge aws-node-termination-handler +```shell +helm upgrade --install --namespace kube-system aws-node-termination-handler eks/aws-node-termination-handler --recreate-pods --force ``` -The command removes all the Kubernetes components associated with the chart and deletes the release. +If you receive an error similar to the one below simply rerun the above command. + +> Error: release aws-node-termination-handler failed: "aws-node-termination-handler" already exists + +To uninstall the `aws-node-termination-handler` chart installation from the `kube-system` namespace run the following command. + +```shell +helm delete --namespace kube-system aws-node-termination-handler +``` ## Configuration -The following tables lists the configurable parameters of the chart and their default values. +The following tables lists the configurable parameters of the chart and their default values. These values are split up into the [common configuration](#common-configuration) shared by all AWS Node Termination Handler modes, [queue configuration](#queue-processor-mode-configuration) used when AWS Node Termination Handler is in in queue-processor mode, and [IMDS configuration](#imds-mode-configuration) used when AWS Node Termination Handler is in IMDS mode; for more information about the different modes see the project [README](https://github.com/aws/aws-node-termination-handler/blob/main/README.md). -Parameter | Description | Default ---- | --- | --- -`image.repository` | image repository | `amazon/aws-node-termination-handler` -`image.tag` | image tag | `` -`image.pullPolicy` | image pull policy | `IfNotPresent` -`image.pullSecrets` | image pull secrets (for private docker registries) | `[]` -`deleteLocalData` | Tells kubectl to continue even if there are pods using emptyDir (local data that will be deleted when the node is drained). | `false` -`gracePeriod` | (DEPRECATED: Renamed to podTerminationGracePeriod) The time in seconds given to each pod to terminate gracefully. If negative, the default value specified in the pod will be used. | `30` -`podTerminationGracePeriod` | The time in seconds given to each pod to terminate gracefully. If negative, the default value specified in the pod will be used. | `30` -`nodeTerminationGracePeriod` | Period of time in seconds given to each NODE to terminate gracefully. Node draining will be scheduled based on this value to optimize the amount of compute time, but still safely drain the node before an event. | `120` -`ignoreDaemonsSets` | Causes kubectl to skip daemon set managed pods | `true` -`instanceMetadataURL` | The URL of EC2 instance metadata. This shouldn't need to be changed unless you are testing. | `http://169.254.169.254:80` -`webhookURL` | Posts event data to URL upon instance interruption action | `` -`webhookProxy` | Uses the specified HTTP(S) proxy for sending webhooks | `` -`webhookHeaders` | Replaces the default webhook headers. | `{"Content-type":"application/json"}` -`webhookTemplate` | Replaces the default webhook message template. | `{"text":"[NTH][Instance Interruption] EventID: {{ .EventID }} - Kind: {{ .Kind }} - Description: {{ .Description }} - State: {{ .State }} - Start Time: {{ .StartTime }}"}` -`dryRun` | If true, only log if a node would be drained | `false` -`enableScheduledEventDraining` | [EXPERIMENTAL] If true, drain nodes before the maintenance window starts for an EC2 instance scheduled event | `false` -`enableSpotInterruptionDraining` | If true, drain nodes when the spot interruption termination notice is received | `true` -`metadataTries` | The number of times to try requesting metadata. If you would like 2 retries, set metadata-tries to 3. | `3` -`cordonOnly` | If true, nodes will be cordoned but not drained when an interruption event occurs. | `false` -`taintNode` | If true, nodes will be tainted when an interruption event occurs. Currently used taint keys are `aws-node-termination-handler/scheduled-maintenance` and `aws-node-termination-handler/spot-itn` | `false` -`jsonLogging` | If true, use JSON-formatted logs instead of human readable logs. | `false` -`affinity` | node/pod affinities | None -`podAnnotations` | annotations to add to each pod | `{}` -`priorityClassName` | Name of the priorityClass | `system-node-critical` -`resources` | Resources for the pods | `requests.cpu: 50m, requests.memory: 64Mi, limits.cpu: 100m, limits.memory: 128Mi` -`dnsPolicy` | DaemonSet DNS policy | `ClusterFirstWithHostNet` -`nodeSelector` | Tells the daemon set where to place the node-termination-handler pods. For example: `lifecycle: "Ec2Spot"`, `on-demand: "false"`, `aws.amazon.com/purchaseType: "spot"`, etc. Value must be a valid yaml expression. | `{}` -`tolerations` | list of node taints to tolerate | `[ {"operator": "Exists"} ]` -`rbac.create` | if `true`, create and use RBAC resources | `true` -`rbac.pspEnabled` | If `true`, create and use a restricted pod security policy | `false` -`serviceAccount.create` | If `true`, create a new service account | `true` -`serviceAccount.name` | Service account to be used | None -`serviceAccount.annotations` | Specifies the annotations for ServiceAccount | `{}` -`procUptimeFile` | (Used for Testing) Specify the uptime file | `/proc/uptime` -`securityContext.runAsUserID` | User ID to run the container | `1000` -`securityContext.runAsGroupID` | Group ID to run the container | `1000` -`nodeSelectorTermsOs` | Operating System Node Selector Key | `beta.kubernetes.io/os` -`nodeSelectorTermsArch` | CPU Architecture Node Selector Key | `beta.kubernetes.io/arch` -`enablePrometheusServer` | If true, start an http server exposing `/metrics` endpoint for prometheus. | `false` -`prometheusServerPort` | Replaces the default HTTP port for exposing prometheus metrics. | `9092` +### Common Configuration -## Metrics endpoint consideration -If prometheus server is enabled and since NTH is a daemonset with `host_networking=true`, nothing else will be able to bind to `:9092` (or the port configured) in the root network namespace -since it's listening on all interfaces. -Therefore, it will need to have a firewall/security group configured on the nodes to block access to the `/metrics` endpoint. +The configuration in this table applies to all AWS Node Termination Handler modes. + +| Parameter | Description | Default | +| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------- | +| `image.repository` | Image repository. | `public.ecr.aws/aws-ec2/aws-node-termination-handler` | +| `image.tag` | Image tag. | `v{{ .Chart.AppVersion}}` | +| `image.pullPolicy` | Image pull policy. | `IfNotPresent` | +| `image.pullSecrets` | Image pull secrets. | `[]` | +| `nameOverride` | Override the `name` of the chart. | `""` | +| `fullnameOverride` | Override the `fullname` of the chart. | `""` | +| `serviceAccount.create` | If `true`, create a new service account. | `true` | +| `serviceAccount.name` | Service account to be used. If not set and `serviceAccount.create` is `true`, a name is generated using the full name template. | `nil` | +| `serviceAccount.annotations` | Annotations to add to the service account. | `{}` | +| `rbac.create` | If `true`, create the RBAC resources. | `true` | +| `rbac.pspEnabled` | If `true`, create a pod security policy resource. | `true` | +| `customLabels` | Labels to add to all resource metadata. | `{}` | +| `podLabels` | Labels to add to the pod. | `{}` | +| `podAnnotations` | Annotations to add to the pod. | `{}` | +| `podSecurityContext` | Security context for the pod. | _See values.yaml_ | +| `securityContext` | Security context for the _aws-node-termination-handler_ container. | _See values.yaml_ | +| `terminationGracePeriodSeconds` | The termination grace period for the pod. | `nil` | +| `resources` | Resource requests and limits for the _aws-node-termination-handler_ container. | `{}` | +| `nodeSelector` | Expressions to select a node by it's labels for pod assignment. In IMDS mode this has a higher priority than `daemonsetNodeSelector` (for backwards compatibility) but shouldn't be used. | `{}` | +| `affinity` | Affinity settings for pod assignment. In IMDS mode this has a higher priority than `daemonsetAffinity` (for backwards compatibility) but shouldn't be used. | `{}` | +| `tolerations` | Tolerations for pod assignment. In IMDS mode this has a higher priority than `daemonsetTolerations` (for backwards compatibility) but shouldn't be used. | `[]` | +| `extraEnv` | Additional environment variables for the _aws-node-termination-handler_ container. | `[]` | +| `probes` | The Kubernetes liveness probe configuration. | _See values.yaml_ | +| `logLevel` | Sets the log level (`info`,`debug`, or `error`) | `info` | +| `jsonLogging` | If `true`, use JSON-formatted logs instead of human readable logs. | `false` | +| `enablePrometheusServer` | If `true`, start an http server exposing `/metrics` endpoint for _Prometheus_. | `false` | +| `prometheusServerPort` | Replaces the default HTTP port for exposing _Prometheus_ metrics. | `9092` | +| `dryRun` | If `true`, only log if a node would be drained. | `false` | +| `cordonOnly` | If `true`, nodes will be cordoned but not drained when an interruption event occurs. | `false` | +| `taintNode` | If `true`, nodes will be tainted when an interruption event occurs. Currently used taint keys are `aws-node-termination-handler/scheduled-maintenance`, `aws-node-termination-handler/spot-itn`, `aws-node-termination-handler/asg-lifecycle-termination` and `aws-node-termination-handler/rebalance-recommendation`. | `false` | +| `deleteLocalData` | If `true`, continue even if there are pods using local data that will be deleted when the node is drained. | `true` | +| `ignoreDaemonSets` | If `true`, skip terminating daemon set managed pods. | `true` | +| `podTerminationGracePeriod` | The time in seconds given to each pod to terminate gracefully. If negative, the default value specified in the pod will be used, which defaults to 30 seconds if not specified for the pod. | `-1` | +| `nodeTerminationGracePeriod` | Period of time in seconds given to each node to terminate gracefully. Node draining will be scheduled based on this value to optimize the amount of compute time, but still safely drain the node before an event. | `120` | +| `emitKubernetesEvents` | If `true`, Kubernetes events will be emitted when interruption events are received and when actions are taken on Kubernetes nodes. In IMDS Processor mode a default set of annotations with all the node metadata gathered from IMDS will be attached to each event. More information [here](https://github.com/aws/aws-node-termination-handler/blob/main/docs/kubernetes_events.md). | `false` | +| `kubernetesEventsExtraAnnotations` | A comma-separated list of `key=value` extra annotations to attach to all emitted Kubernetes events (e.g. `first=annotation,sample.annotation/number=two"`). | `""` | +| `webhookURL` | Posts event data to URL upon instance interruption action. | `""` | +| `webhookURLSecretName` | Pass the webhook URL as a Secret using the key `webhookurl`. | `""` | +| `webhookHeaders` | Replace the default webhook headers (e.g. `{"Content-type":"application/json"}`). | `""` | +| `webhookProxy` | Uses the specified HTTP(S) proxy for sending webhook data. | `""` | +| `webhookTemplate` | Replaces the default webhook message template (e.g. `{"text":"[NTH][Instance Interruption] EventID: {{ .EventID }} - Kind: {{ .Kind }} - Instance: {{ .InstanceID }} - Node: {{ .NodeName }} - Description: {{ .Description }} - Start Time: {{ .StartTime }}"}`). | `""` | +| `webhookTemplateConfigMapName` | Pass the webhook template file as a configmap. | "``" | +| `webhookTemplateConfigMapKey` | Name of the Configmap key storing the template file. | `""` | +| `enableSqsTerminationDraining` | If `true`, this turns on queue-processor mode which drains nodes when an SQS termination event is received. | `false` | + +### Queue-Processor Mode Configuration + +The configuration in this table applies to AWS Node Termination Handler in queue-processor mode. + +| Parameter | Description | Default | +| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- | +| `replicas` | The number of replicas in the deployment when using queue-processor mode (NOTE: increasing replicas may cause duplicate webhooks since pods are stateless). | `1` | +| `strategy` | Specify the update strategy for the deployment. | `{}` | +| `podDisruptionBudget` | Limit the disruption for controller pods, requires at least 2 controller replicas. | `{}` | +| `serviceMonitor.create` | If `true`, create a ServiceMonitor. This requires `enablePrometheusServer: true`. | `false` | +| `serviceMonitor.namespace` | Override ServiceMonitor _Helm_ release namespace. | `nil` | +| `serviceMonitor.labels` | Additional ServiceMonitor metadata labels. | `{}` | +| `serviceMonitor.interval` | _Prometheus_ scrape interval. | `30s` | +| `serviceMonitor.sampleLimit` | Number of scraped samples accepted. | `5000` | +| `priorityClassName` | Name of the PriorityClass to use for the Deployment. | `system-cluster-critical` | +| `awsRegion` | If specified, use the AWS region for AWS API calls, else NTH will try to find the region through the `AWS_REGION` environment variable, IMDS, or the specified queue URL. | `""` | +| `queueURL` | Listens for messages on the specified SQS queue URL. | `""` | +| `workers` | The maximum amount of parallel event processors to handle concurrent events. | `10` | +| `checkASGTagBeforeDraining` | If `true`, check that the instance is tagged with the `managedAsgTag` before draining the node. | `true` | +| `managedAsgTag` | The node tag to check if `checkASGTagBeforeDraining` is `true`. | `aws-node-termination-handler/managed` | +| `assumeAsgTagPropagation` | If `true`, assume that ASG tags will be appear on the ASG's instances. | `false` | + +### IMDS Mode Configuration + +The configuration in this table applies to AWS Node Termination Handler in IMDS mode. + +| Parameter | Description | Default | +| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------- | +| `targetNodeOs` | Space separated list of node OS's to target (e.g. `"linux"`, `"windows"`, `"linux windows"`). Windows support is **EXPERIMENTAL**. | `"linux"` | +| `linuxPodLabels` | Labels to add to each Linux pod. | `{}` | +| `windowsPodLabels` | Labels to add to each Windows pod. | `{}` | +| `linuxPodAnnotations` | Annotations to add to each Linux pod. | `{}` | +| `windowsPodAnnotations` | Annotations to add to each Windows pod. | `{}` | +| `updateStrategy` | Update strategy for the all DaemonSets. | _See values.yaml_ | +| `daemonsetPriorityClassName` | Name of the PriorityClass to use for all DaemonSets. | `system-node-critical` | +| `podMonitor.create` | If `true`, create a PodMonitor. This requires `enablePrometheusServer: true`. | `false` | +| `podMonitor.namespace` | Override PodMonitor _Helm_ release namespace. | `nil` | +| `podMonitor.labels` | Additional PodMonitor metadata labels | `{}` | +| `podMonitor.interval` | _Prometheus_ scrape interval. | `30s` | +| `podMonitor.sampleLimit` | Number of scraped samples accepted. | `5000` | +| `useHostNetwork` | If `true`, enables `hostNetwork` for the Linux DaemonSet. NOTE: setting this to `false` may cause issues accessing IMDSv2 if your account is not configured with an IP hop count of 2 see [Metrics Endpoint Considerations](#metrics-endpoint-considerations) | `true` | +| `dnsPolicy` | If specified, this overrides `linuxDnsPolicy` and `windowsDnsPolicy` with a single policy. | `""` | +| `linuxDnsPolicy` | DNS policy for the Linux DaemonSet. | `""` | +| `windowsDnsPolicy` | DNS policy for the Windows DaemonSet. | `""` | +| `daemonsetNodeSelector` | Expressions to select a node by it's labels for DaemonSet pod assignment. For backwards compatibility the `nodeSelector` value has priority over this but shouldn't be used. | `{}` | +| `linuxNodeSelector` | Override `daemonsetNodeSelector` for the Linux DaemonSet. | `{}` | +| `windowsNodeSelector` | Override `daemonsetNodeSelector` for the Windows DaemonSet. | `{}` | +| `daemonsetAffinity` | Affinity settings for DaemonSet pod assignment. For backwards compatibility the `affinity` has priority over this but shouldn't be used. | `{}` | +| `linuxAffinity` | Override `daemonsetAffinity` for the Linux DaemonSet. | `{}` | +| `windowsAffinity` | Override `daemonsetAffinity` for the Windows DaemonSet. | `{}` | +| `daemonsetTolerations` | Tolerations for DaemonSet pod assignment. For backwards compatibility the `tolerations` has priority over this but shouldn't be used. | `[]` | +| `linuxTolerations` | Override `daemonsetTolerations` for the Linux DaemonSet. | `[]` | +| `windowsTolerations` | Override `daemonsetTolerations` for the Linux DaemonSet. | `[]` | +| `enableProbesServer` | If `true`, start an http server exposing `/healthz` endpoint for probes. | `false` | +| `metadataTries` | The number of times to try requesting metadata. | `3` | +| `enableSpotInterruptionDraining` | If `true`, drain nodes when the spot interruption termination notice is received. | `true` | +| `enableScheduledEventDraining` | If `true`, drain nodes before the maintenance window starts for an EC2 instance scheduled event. This is **EXPERIMENTAL**. | `false` | +| `enableRebalanceMonitoring` | If `true`, cordon nodes when the rebalance recommendation notice is received. If you'd like to drain the node in addition to cordoning, then also set `enableRebalanceDraining`. | `false` | +| `enableRebalanceDraining` | If `true`, drain nodes when the rebalance recommendation notice is received. | `false` | + +### Testing Configuration + +The configuration in this table applies to AWS Node Termination Handler testing and is **NOT RECOMMENDED** FOR PRODUCTION DEPLOYMENTS. + +| Parameter | Description | Default | +| --------------------- | --------------------------------------------------------------------------------- | -------------- | +| `awsEndpoint` | (Used for testing) If specified, use the provided AWS endpoint to make API calls. | `""` | +| `awsSecretAccessKey` | (Used for testing) Pass-thru environment variable. | `nil` | +| `awsAccessKeyID` | (Used for testing) Pass-thru environment variable. | `nil` | +| `instanceMetadataURL` | (Used for testing) If specified, use the provided metadata URL. | `""` | +| `procUptimeFile` | (Used for Testing) Specify the uptime file. | `/proc/uptime` | + +## Metrics Endpoint Considerations + +AWS Node Termination HAndler in IMDS mode runs as a DaemonSet with `useHostNetwork: true` by default. If the Prometheus server is enabled with `enablePrometheusServer: true` nothing else will be able to bind to the configured port (by default `prometheusServerPort: 9092`) in the root network namespace. Therefore, it will need to have a firewall/security group configured on the nodes to block access to the `/metrics` endpoint. + +You can switch NTH in IMDS mode to run w/ `useHostNetwork: false`, but you will need to make sure that IMDSv1 is enabled or IMDSv2 IP hop count will need to be incremented to 2 (see the [IMDSv2 documentation](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/configuring-instance-metadata-service.html). diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/_helpers.tpl b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/_helpers.tpl index 902844a7..45f06f4b 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/_helpers.tpl +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/_helpers.tpl @@ -1,4 +1,5 @@ {{/* vim: set filetype=mustache: */}} + {{/* Expand the name of the chart. */}} @@ -25,17 +26,11 @@ If release name contains chart name it will be used as a full name. {{- end -}} {{/* -Common labels +Equivalent to "aws-node-termination-handler.fullname" except that "-win" indicator is appended to the end. +Name will not exceed 63 characters. */}} -{{- define "aws-node-termination-handler.labels" -}} -app.kubernetes.io/name: {{ include "aws-node-termination-handler.name" . }} -helm.sh/chart: {{ include "aws-node-termination-handler.chart" . }} -app.kubernetes.io/instance: {{ .Release.Name }} -k8s-app: aws-node-termination-handler -{{- if .Chart.AppVersion }} -app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} -{{- end }} -app.kubernetes.io/managed-by: {{ .Release.Service }} +{{- define "aws-node-termination-handler.fullnameWindows" -}} +{{- include "aws-node-termination-handler.fullname" . | trunc 59 | trimSuffix "-" | printf "%s-win" -}} {{- end -}} {{/* @@ -45,6 +40,47 @@ Create chart name and version as used by the chart label. {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}} {{- end -}} +{{/* +Common labels +*/}} +{{- define "aws-node-termination-handler.labels" -}} +{{ include "aws-node-termination-handler.selectorLabels" . }} +{{- if .Chart.AppVersion }} +app.kubernetes.io/version: {{ .Chart.AppVersion | quote }} +{{- end }} +app.kubernetes.io/component: {{ .Release.Name }} +app.kubernetes.io/part-of: {{ .Release.Name }} +app.kubernetes.io/managed-by: {{ .Release.Service }} +helm.sh/chart: {{ include "aws-node-termination-handler.chart" . }} +{{- with .Values.customLabels }} +{{ toYaml . }} +{{- end }} +{{- end -}} + +{{/* +Selector labels +*/}} +{{- define "aws-node-termination-handler.selectorLabels" -}} +app.kubernetes.io/name: {{ include "aws-node-termination-handler.name" . }} +app.kubernetes.io/instance: {{ .Release.Name }} +{{- end -}} + +{{/* +Selector labels for the deployment +*/}} +{{- define "aws-node-termination-handler.selectorLabelsDeployment" -}} +{{ include "aws-node-termination-handler.selectorLabels" . }} +app.kubernetes.io/component: deployment +{{- end -}} + +{{/* +Selector labels for the daemonset +*/}} +{{- define "aws-node-termination-handler.selectorLabelsDaemonset" -}} +{{ include "aws-node-termination-handler.selectorLabels" . }} +app.kubernetes.io/component: daemonset +{{- end -}} + {{/* Create the name of the service account to use */}} @@ -55,3 +91,19 @@ Create the name of the service account to use {{ default "default" .Values.serviceAccount.name }} {{- end -}} {{- end -}} + +{{/* +The image to use +*/}} +{{- define "aws-node-termination-handler.image" -}} +{{- printf "%s:%s" .Values.image.repository (default (printf "v%s" .Chart.AppVersion) .Values.image.tag) }} +{{- end }} + +{{/* Get PodDisruptionBudget API Version */}} +{{- define "aws-node-termination-handler.pdb.apiVersion" -}} + {{- if and (.Capabilities.APIVersions.Has "policy/v1") (semverCompare ">= 1.21-0" .Capabilities.KubeVersion.Version) -}} + {{- print "policy/v1" -}} + {{- else -}} + {{- print "policy/v1beta1" -}} + {{- end -}} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrole.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrole.yaml index dc800866..43c2b030 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrole.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrole.yaml @@ -1,7 +1,10 @@ +{{- if .Values.rbac.create -}} kind: ClusterRole apiVersion: rbac.authorization.k8s.io/v1 metadata: name: {{ include "aws-node-termination-handler.fullname" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} rules: - apiGroups: - "" @@ -9,6 +12,7 @@ rules: - nodes verbs: - get + - list - patch - update - apiGroups: @@ -17,6 +21,7 @@ rules: - pods verbs: - list + - get - apiGroups: - "" resources: @@ -35,3 +40,13 @@ rules: - daemonsets verbs: - get +{{- if .Values.emitKubernetesEvents }} +- apiGroups: + - "" + resources: + - events + verbs: + - create + - patch +{{- end }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrolebinding.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrolebinding.yaml index b5c25327..1058df1b 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrolebinding.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/clusterrolebinding.yaml @@ -1,12 +1,16 @@ +{{- if .Values.rbac.create -}} kind: ClusterRoleBinding apiVersion: rbac.authorization.k8s.io/v1 metadata: name: {{ include "aws-node-termination-handler.fullname" . }} -subjects: -- kind: ServiceAccount - name: {{ template "aws-node-termination-handler.serviceAccountName" . }} - namespace: {{ .Release.Namespace }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} roleRef: + apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: {{ include "aws-node-termination-handler.fullname" . }} - apiGroup: rbac.authorization.k8s.io +subjects: + - kind: ServiceAccount + name: {{ template "aws-node-termination-handler.serviceAccountName" . }} + namespace: {{ .Release.Namespace }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.linux.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.linux.yaml new file mode 100644 index 00000000..199879c3 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.linux.yaml @@ -0,0 +1,198 @@ +{{- if and (not .Values.enableSqsTerminationDraining) (lower .Values.targetNodeOs | contains "linux") -}} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "aws-node-termination-handler.fullname" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} +spec: + {{- with .Values.updateStrategy }} + updateStrategy: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDaemonset" . | nindent 6 }} + kubernetes.io/os: linux + template: + metadata: + labels: + {{- include "aws-node-termination-handler.selectorLabelsDaemonset" . | nindent 8 }} + kubernetes.io/os: linux + k8s-app: aws-node-termination-handler + {{- with (mergeOverwrite (dict) .Values.podLabels .Values.linuxPodLabels) }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if or .Values.podAnnotations .Values.linuxPodAnnotations }} + annotations: + {{- toYaml (mergeOverwrite (dict) .Values.podAnnotations .Values.linuxPodAnnotations) | nindent 8 }} + {{- end }} + spec: + {{- with .Values.image.pullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "aws-node-termination-handler.serviceAccountName" . }} + {{- with .Values.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.daemonsetPriorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.terminationGracePeriodSeconds }} + terminationGracePeriodSeconds: {{ . }} + {{- end }} + hostNetwork: {{ .Values.useHostNetwork }} + dnsPolicy: {{ default .Values.linuxDnsPolicy .Values.dnsPolicy }} + containers: + - name: aws-node-termination-handler + {{- with .Values.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "aws-node-termination-handler.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + - name: ENABLE_PROBES_SERVER + value: {{ .Values.enableProbesServer | quote }} + - name: PROBES_SERVER_PORT + value: {{ .Values.probes.httpGet.port | quote }} + - name: PROBES_SERVER_ENDPOINT + value: {{ .Values.probes.httpGet.path | quote }} + - name: LOG_LEVEL + value: {{ .Values.logLevel | quote }} + - name: JSON_LOGGING + value: {{ .Values.jsonLogging | quote }} + - name: ENABLE_PROMETHEUS_SERVER + value: {{ .Values.enablePrometheusServer | quote }} + - name: PROMETHEUS_SERVER_PORT + value: {{ .Values.prometheusServerPort | quote }} + {{- with .Values.instanceMetadataURL }} + - name: INSTANCE_METADATA_URL + value: {{ . | quote }} + {{- end }} + - name: METADATA_TRIES + value: {{ .Values.metadataTries | quote }} + - name: DRY_RUN + value: {{ .Values.dryRun | quote }} + - name: CORDON_ONLY + value: {{ .Values.cordonOnly | quote }} + - name: TAINT_NODE + value: {{ .Values.taintNode | quote }} + - name: DELETE_LOCAL_DATA + value: {{ .Values.deleteLocalData | quote }} + - name: IGNORE_DAEMON_SETS + value: {{ .Values.ignoreDaemonSets | quote }} + - name: POD_TERMINATION_GRACE_PERIOD + value: {{ .Values.podTerminationGracePeriod | quote }} + - name: NODE_TERMINATION_GRACE_PERIOD + value: {{ .Values.nodeTerminationGracePeriod | quote }} + - name: EMIT_KUBERNETES_EVENTS + value: {{ .Values.emitKubernetesEvents | quote }} + {{- with .Values.kubernetesEventsExtraAnnotations }} + - name: KUBERNETES_EVENTS_EXTRA_ANNOTATIONS + value: {{ . | quote }} + {{- end }} + {{- if or .Values.webhookURL .Values.webhookURLSecretName }} + - name: WEBHOOK_URL + {{- if .Values.webhookURLSecretName }} + valueFrom: + secretKeyRef: + name: {{ .Values.webhookURLSecretName }} + key: webhookurl + {{- else }} + value: {{ .Values.webhookURL | quote }} + {{- end }} + {{- end }} + {{- with .Values.webhookHeaders }} + - name: WEBHOOK_HEADERS + value: {{ . | quote }} + {{- end }} + {{- with .Values.webhookProxy }} + - name: WEBHOOK_PROXY + value: {{ . | quote }} + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + - name: WEBHOOK_TEMPLATE_FILE + value: {{ print "/config/" .Values.webhookTemplateConfigMapKey | quote }} + {{- else if .Values.webhookTemplate }} + - name: WEBHOOK_TEMPLATE + value: {{ .Values.webhookTemplate | quote }} + {{- end }} + - name: ENABLE_SPOT_INTERRUPTION_DRAINING + value: {{ .Values.enableSpotInterruptionDraining | quote }} + - name: ENABLE_SCHEDULED_EVENT_DRAINING + value: {{ .Values.enableScheduledEventDraining | quote }} + - name: ENABLE_REBALANCE_MONITORING + value: {{ .Values.enableRebalanceMonitoring | quote }} + - name: ENABLE_REBALANCE_DRAINING + value: {{ .Values.enableRebalanceDraining | quote }} + - name: ENABLE_SQS_TERMINATION_DRAINING + value: "false" + - name: UPTIME_FROM_FILE + value: {{ .Values.procUptimeFile | quote }} + {{- if or .Values.enablePrometheusServer .Values.enableProbesServer }} + ports: + {{- if .Values.enableProbesServer }} + - name: liveness-probe + protocol: TCP + containerPort: {{ .Values.probes.httpGet.port }} + {{- end }} + {{- if .Values.enablePrometheusServer }} + - name: http-metrics + protocol: TCP + containerPort: {{ .Values.prometheusServerPort }} + {{- end }} + {{- end }} + {{- if .Values.enableProbesServer }} + livenessProbe: + {{- toYaml .Values.probes | nindent 12 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + volumeMounts: + - name: uptime + mountPath: {{ .Values.procUptimeFile }} + readOnly: true + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + - name: webhook-template + mountPath: /config/ + {{- end }} + volumes: + - name: uptime + hostPath: + path: {{ .Values.procUptimeFile | default "/proc/uptime" }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + - name: webhook-template + configMap: + name: {{ .Values.webhookTemplateConfigMapName }} + {{- end }} + nodeSelector: + kubernetes.io/os: linux + {{- with default .Values.daemonsetNodeSelector (default .Values.nodeSelector .Values.linuxNodeSelector) }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if or .Values.daemonsetAffinity (or .Values.affinity .Values.linuxAffinity) }} + affinity: + {{- toYaml (default .Values.daemonsetAffinity (default .Values.affinity .Values.linuxAffinity)) | nindent 8 }} + {{- end }} + {{- if or .Values.daemonsetTolerations (or .Values.tolerations .Values.linuxTolerations) }} + tolerations: + {{- toYaml (default .Values.daemonsetTolerations (default .Values.tolerations .Values.linuxTolerations )) | nindent 8 }} + {{- end }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.windows.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.windows.yaml new file mode 100644 index 00000000..ea7f8337 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.windows.yaml @@ -0,0 +1,192 @@ +{{- if and (not .Values.enableSqsTerminationDraining) (lower .Values.targetNodeOs | contains "windows") -}} +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: {{ include "aws-node-termination-handler.fullnameWindows" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} +spec: + {{- with .Values.updateStrategy }} + updateStrategy: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDaemonset" . | nindent 6 }} + kubernetes.io/os: windows + template: + metadata: + labels: + {{- include "aws-node-termination-handler.selectorLabelsDaemonset" . | nindent 8 }} + kubernetes.io/os: windows + k8s-app: aws-node-termination-handler + {{- with (mergeOverwrite (dict) .Values.podLabels .Values.windowsPodLabels) }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if or .Values.podAnnotations .Values.windowsPodAnnotations }} + annotations: + {{- toYaml (mergeOverwrite (dict) .Values.podAnnotations .Values.windowsPodAnnotations) | nindent 8 }} + {{- end }} + spec: + {{- with .Values.image.pullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "aws-node-termination-handler.serviceAccountName" . }} + {{- with .Values.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.daemonsetPriorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.terminationGracePeriodSeconds }} + terminationGracePeriodSeconds: {{ . }} + {{- end }} + hostNetwork: false + dnsPolicy: {{ default .Values.windowsDnsPolicy .Values.dnsPolicy }} + containers: + - name: aws-node-termination-handler + {{- with .Values.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "aws-node-termination-handler.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + - name: ENABLE_PROBES_SERVER + value: {{ .Values.enableProbesServer | quote }} + - name: PROBES_SERVER_PORT + value: {{ .Values.probes.httpGet.port | quote }} + - name: PROBES_SERVER_ENDPOINT + value: {{ .Values.probes.httpGet.path | quote }} + - name: LOG_LEVEL + value: {{ .Values.logLevel | quote }} + - name: JSON_LOGGING + value: {{ .Values.jsonLogging | quote }} + - name: ENABLE_PROMETHEUS_SERVER + value: {{ .Values.enablePrometheusServer | quote }} + - name: PROMETHEUS_SERVER_PORT + value: {{ .Values.prometheusServerPort | quote }} + {{- with .Values.instanceMetadataURL }} + - name: INSTANCE_METADATA_URL + value: {{ . | quote }} + {{- end }} + - name: METADATA_TRIES + value: {{ .Values.metadataTries | quote }} + - name: DRY_RUN + value: {{ .Values.dryRun | quote }} + - name: CORDON_ONLY + value: {{ .Values.cordonOnly | quote }} + - name: TAINT_NODE + value: {{ .Values.taintNode | quote }} + - name: DELETE_LOCAL_DATA + value: {{ .Values.deleteLocalData | quote }} + - name: IGNORE_DAEMON_SETS + value: {{ .Values.ignoreDaemonSets | quote }} + - name: POD_TERMINATION_GRACE_PERIOD + value: {{ .Values.podTerminationGracePeriod | quote }} + - name: NODE_TERMINATION_GRACE_PERIOD + value: {{ .Values.nodeTerminationGracePeriod | quote }} + - name: EMIT_KUBERNETES_EVENTS + value: {{ .Values.emitKubernetesEvents | quote }} + {{- with .Values.kubernetesEventsExtraAnnotations }} + - name: KUBERNETES_EVENTS_EXTRA_ANNOTATIONS + value: {{ . | quote }} + {{- end }} + {{- if or .Values.webhookURL .Values.webhookURLSecretName }} + - name: WEBHOOK_URL + {{- if .Values.webhookURLSecretName }} + valueFrom: + secretKeyRef: + name: {{ .Values.webhookURLSecretName }} + key: webhookurl + {{- else }} + value: {{ .Values.webhookURL | quote }} + {{- end }} + {{- end }} + {{- with .Values.webhookHeaders }} + - name: WEBHOOK_HEADERS + value: {{ . | quote }} + {{- end }} + {{- with .Values.webhookProxy }} + - name: WEBHOOK_PROXY + value: {{ . | quote }} + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + - name: WEBHOOK_TEMPLATE_FILE + value: {{ print "/config/" .Values.webhookTemplateConfigMapKey | quote }} + {{- else if .Values.webhookTemplate }} + - name: WEBHOOK_TEMPLATE + value: {{ .Values.webhookTemplate | quote }} + {{- end }} + - name: ENABLE_SPOT_INTERRUPTION_DRAINING + value: {{ .Values.enableSpotInterruptionDraining | quote }} + - name: ENABLE_SCHEDULED_EVENT_DRAINING + value: {{ .Values.enableScheduledEventDraining | quote }} + - name: ENABLE_REBALANCE_MONITORING + value: {{ .Values.enableRebalanceMonitoring | quote }} + - name: ENABLE_REBALANCE_DRAINING + value: {{ .Values.enableRebalanceDraining | quote }} + - name: ENABLE_SQS_TERMINATION_DRAINING + value: "false" + {{- if or .Values.enablePrometheusServer .Values.enableProbesServer }} + ports: + {{- if .Values.enableProbesServer }} + - name: liveness-probe + protocol: TCP + containerPort: {{ .Values.probes.httpGet.port }} + hostPort: {{ .Values.probes.httpGet.port }} + {{- end }} + {{- if .Values.enablePrometheusServer }} + - name: http-metrics + protocol: TCP + containerPort: {{ .Values.prometheusServerPort }} + hostPort: {{ .Values.prometheusServerPort }} + {{- end }} + {{- end }} + {{- if .Values.enableProbesServer }} + livenessProbe: + {{- toYaml .Values.probes | nindent 12 }} + {{- end }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + volumeMounts: + - name: webhook-template + mountPath: /config/ + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + volumes: + - name: webhook-template + configMap: + name: {{ .Values.webhookTemplateConfigMapName }} + {{- end }} + nodeSelector: + kubernetes.io/os: windows + {{- with default .Values.daemonsetNodeSelector (default .Values.nodeSelector .Values.windowsNodeSelector) }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- if or .Values.daemonsetAffinity (or .Values.affinity .Values.windowsAffinity) }} + affinity: + {{- toYaml (default .Values.daemonsetAffinity (default .Values.affinity .Values.windowsAffinity )) | nindent 8 }} + {{- end }} + {{- if or .Values.daemonsetTolerations (or .Values.tolerations .Values.windowsTolerations) }} + tolerations: + {{- toYaml (default .Values.daemonsetTolerations (default .Values.tolerations .Values.windowsTolerations )) | nindent 8 }} + {{- end }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.yaml deleted file mode 100644 index fb220022..00000000 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/daemonset.yaml +++ /dev/null @@ -1,141 +0,0 @@ -apiVersion: apps/v1 -kind: DaemonSet -metadata: - name: {{ include "aws-node-termination-handler.fullname" . }} - namespace: {{ .Release.Namespace }} - labels: -{{ include "aws-node-termination-handler.labels" . | indent 4 }} -spec: - updateStrategy: -{{ toYaml .Values.updateStrategy | indent 4 }} - selector: - matchLabels: - app.kubernetes.io/name: {{ include "aws-node-termination-handler.name" . }} - app.kubernetes.io/instance: {{ .Release.Name }} - template: - metadata: - {{- if .Values.podAnnotations }} - annotations: - {{- range $key, $value := .Values.podAnnotations }} - {{ $key }}: {{ $value | quote }} - {{- end }} - {{- end }} - labels: - app.kubernetes.io/name: {{ include "aws-node-termination-handler.name" . }} - app.kubernetes.io/instance: {{ .Release.Name }} - k8s-app: aws-node-termination-handler - spec: - volumes: - - name: "uptime" - hostPath: - path: "{{ .Values.procUptimeFile }}" - priorityClassName: "{{ .Values.priorityClassName }}" - affinity: - nodeAffinity: - # NOTE(jaypipes): Change when we complete - # https://github.com/aws/aws-node-termination-handler/issues/8 - requiredDuringSchedulingIgnoredDuringExecution: - nodeSelectorTerms: - - matchExpressions: - - key: {{ .Values.nodeSelectorTermsOs | default "beta.kubernetes.io/os" | quote }} - operator: In - values: - - linux - - key: {{ .Values.nodeSelectorTermsArch | default "beta.kubernetes.io/arch" | quote }} - operator: In - values: - - amd64 - - arm - - arm64 - serviceAccountName: {{ template "aws-node-termination-handler.serviceAccountName" . }} - hostNetwork: true - dnsPolicy: {{ .Values.dnsPolicy }} - containers: - - name: {{ include "aws-node-termination-handler.name" . }} - image: {{ .Values.image.repository}}:{{ .Values.image.tag }} - imagePullPolicy: {{ .Values.image.pullPolicy }} - securityContext: - readOnlyRootFilesystem: true - runAsNonRoot: true - runAsUser: {{ .Values.securityContext.runAsUserID }} - runAsGroup: {{ .Values.securityContext.runAsGroupID }} - allowPrivilegeEscalation: false - volumeMounts: - - name: "uptime" - mountPath: "/proc/uptime" - readOnly: true - env: - - name: NODE_NAME - valueFrom: - fieldRef: - fieldPath: spec.nodeName - - name: POD_NAME - valueFrom: - fieldRef: - fieldPath: metadata.name - - name: NAMESPACE - valueFrom: - fieldRef: - fieldPath: metadata.namespace - - name: SPOT_POD_IP - valueFrom: - fieldRef: - fieldPath: status.podIP - - name: DELETE_LOCAL_DATA - value: {{ .Values.deleteLocalData | quote }} - - name: IGNORE_DAEMON_SETS - value: {{ .Values.ignoreDaemonSets | quote }} - - name: GRACE_PERIOD - value: {{ .Values.gracePeriod | quote }} - - name: POD_TERMINATION_GRACE_PERIOD - value: {{ .Values.podTerminationGracePeriod | quote }} - - name: INSTANCE_METADATA_URL - value: {{ .Values.instanceMetadataURL | quote }} - - name: NODE_TERMINATION_GRACE_PERIOD - value: {{ .Values.nodeTerminationGracePeriod | quote }} - - name: WEBHOOK_URL - value: {{ .Values.webhookURL | quote }} - - name: WEBHOOK_HEADERS - value: {{ .Values.webhookHeaders | quote }} - - name: WEBHOOK_TEMPLATE - value: {{ .Values.webhookTemplate | quote }} - - name: DRY_RUN - value: {{ .Values.dryRun | quote }} - - name: ENABLE_SPOT_INTERRUPTION_DRAINING - value: {{ .Values.enableSpotInterruptionDraining | quote }} - - name: ENABLE_SCHEDULED_EVENT_DRAINING - value: {{ .Values.enableScheduledEventDraining | quote }} - - name: METADATA_TRIES - value: {{ .Values.metadataTries | quote }} - - name: CORDON_ONLY - value: {{ .Values.cordonOnly | quote }} - - name: TAINT_NODE - value: {{ .Values.taintNode | quote }} - - name: JSON_LOGGING - value: {{ .Values.jsonLogging | quote }} - - name: WEBHOOK_PROXY - value: {{ .Values.webhookProxy | quote }} - - name: ENABLE_PROMETHEUS_SERVER - value: {{ .Values.enablePrometheusServer | quote }} - - name: PROMETHEUS_SERVER_PORT - value: {{ .Values.prometheusServerPort | quote }} - resources: - {{- toYaml .Values.resources | nindent 12 }} - {{- with .Values.nodeSelector }} - nodeSelector: - {{- toYaml . | nindent 8 }} - {{- end }} - {{- if .Values.image.pullSecrets }} - imagePullSecrets: - {{- range .Values.image.pullSecrets }} - - name: {{ . }} - {{- end }} - {{- end }} - {{- with .Values.affinity }} - affinity: - {{- toYaml . | nindent 8 }} - {{- end }} - {{- with .Values.tolerations }} - tolerations: - {{- toYaml . | nindent 8 }} - {{- end }} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/deployment.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/deployment.yaml new file mode 100644 index 00000000..38c10e98 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/deployment.yaml @@ -0,0 +1,202 @@ +{{- if .Values.enableSqsTerminationDraining }} +apiVersion: apps/v1 +kind: Deployment +metadata: + name: {{ include "aws-node-termination-handler.fullname" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} +spec: + replicas: {{ .Values.replicas }} + {{- with .Values.strategy }} + strategy: + {{- toYaml . | nindent 4 }} + {{- end }} + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDeployment" . | nindent 6 }} + template: + metadata: + labels: + {{- include "aws-node-termination-handler.selectorLabelsDeployment" . | nindent 8 }} + k8s-app: aws-node-termination-handler + {{- with .Values.podLabels }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.podAnnotations }} + annotations: + {{- toYaml . | nindent 8 }} + {{- end }} + spec: + {{- with .Values.image.pullSecrets }} + imagePullSecrets: + {{- toYaml . | nindent 8 }} + {{- end }} + serviceAccountName: {{ include "aws-node-termination-handler.serviceAccountName" . }} + {{- with .Values.podSecurityContext }} + securityContext: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.priorityClassName }} + priorityClassName: {{ . }} + {{- end }} + {{- with .Values.terminationGracePeriodSeconds }} + terminationGracePeriodSeconds: {{ . }} + {{- end }} + containers: + - name: aws-node-termination-handler + {{- with .Values.securityContext }} + securityContext: + {{- toYaml . | nindent 12 }} + {{- end }} + image: {{ include "aws-node-termination-handler.image" . }} + imagePullPolicy: {{ .Values.image.pullPolicy }} + env: + - name: NODE_NAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + - name: POD_NAME + valueFrom: + fieldRef: + fieldPath: metadata.name + - name: NAMESPACE + valueFrom: + fieldRef: + fieldPath: metadata.namespace + - name: ENABLE_PROBES_SERVER + value: "true" + - name: PROBES_SERVER_PORT + value: {{ .Values.probes.httpGet.port | quote }} + - name: PROBES_SERVER_ENDPOINT + value: {{ .Values.probes.httpGet.path | quote }} + - name: LOG_LEVEL + value: {{ .Values.logLevel | quote }} + - name: JSON_LOGGING + value: {{ .Values.jsonLogging | quote }} + - name: ENABLE_PROMETHEUS_SERVER + value: {{ .Values.enablePrometheusServer | quote }} + - name: PROMETHEUS_SERVER_PORT + value: {{ .Values.prometheusServerPort | quote }} + - name: CHECK_ASG_TAG_BEFORE_DRAINING + value: {{ .Values.checkASGTagBeforeDraining | quote }} + - name: MANAGED_ASG_TAG + value: {{ .Values.managedAsgTag | quote }} + - name: ASSUME_ASG_TAG_PROPAGATION + value: {{ .Values.assumeAsgTagPropagation | quote }} + - name: DRY_RUN + value: {{ .Values.dryRun | quote }} + - name: CORDON_ONLY + value: {{ .Values.cordonOnly | quote }} + - name: TAINT_NODE + value: {{ .Values.taintNode | quote }} + - name: DELETE_LOCAL_DATA + value: {{ .Values.deleteLocalData | quote }} + - name: IGNORE_DAEMON_SETS + value: {{ .Values.ignoreDaemonSets | quote }} + - name: POD_TERMINATION_GRACE_PERIOD + value: {{ .Values.podTerminationGracePeriod | quote }} + - name: NODE_TERMINATION_GRACE_PERIOD + value: {{ .Values.nodeTerminationGracePeriod | quote }} + - name: EMIT_KUBERNETES_EVENTS + value: {{ .Values.emitKubernetesEvents | quote }} + {{- with .Values.kubernetesEventsExtraAnnotations }} + - name: KUBERNETES_EVENTS_EXTRA_ANNOTATIONS + value: {{ . | quote }} + {{- end }} + {{- if or .Values.webhookURL .Values.webhookURLSecretName }} + - name: WEBHOOK_URL + {{- if .Values.webhookURLSecretName }} + valueFrom: + secretKeyRef: + name: {{ .Values.webhookURLSecretName }} + key: webhookurl + {{- else }} + value: {{ .Values.webhookURL | quote }} + {{- end }} + {{- end }} + {{- with .Values.webhookHeaders }} + - name: WEBHOOK_HEADERS + value: {{ . | quote }} + {{- end }} + {{- with .Values.webhookProxy }} + - name: WEBHOOK_PROXY + value: {{ . | quote }} + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + - name: WEBHOOK_TEMPLATE_FILE + value: {{ print "/config/" .Values.webhookTemplateConfigMapKey | quote }} + {{- else if .Values.webhookTemplate }} + - name: WEBHOOK_TEMPLATE + value: {{ .Values.webhookTemplate | quote }} + {{- end }} + - name: ENABLE_SPOT_INTERRUPTION_DRAINING + value: "false" + - name: ENABLE_SCHEDULED_EVENT_DRAINING + value: "false" + - name: ENABLE_REBALANCE_MONITORING + value: "false" + - name: ENABLE_REBALANCE_DRAINING + value: "false" + - name: ENABLE_SQS_TERMINATION_DRAINING + value: "true" + {{- with .Values.awsRegion }} + - name: AWS_REGION + value: {{ . | quote }} + {{- end }} + {{- with .Values.awsEndpoint }} + - name: AWS_ENDPOINT + value: {{ . | quote }} + {{- end }} + {{- if and .Values.awsAccessKeyID .Values.awsSecretAccessKey }} + - name: AWS_ACCESS_KEY_ID + value: {{ .Values.awsAccessKeyID | quote }} + - name: AWS_SECRET_ACCESS_KEY + value: {{ .Values.awsSecretAccessKey | quote }} + {{- end }} + - name: QUEUE_URL + value: {{ .Values.queueURL | quote }} + - name: WORKERS + value: {{ .Values.workers | quote }} + {{- with .Values.extraEnv }} + {{- toYaml . | nindent 12 }} + {{- end }} + ports: + - name: liveness-probe + protocol: TCP + containerPort: {{ .Values.probes.httpGet.port }} + {{- if .Values.enablePrometheusServer }} + - name: http-metrics + protocol: TCP + containerPort: {{ .Values.prometheusServerPort }} + {{- end }} + livenessProbe: + {{- toYaml .Values.probes | nindent 12 }} + {{- with .Values.resources }} + resources: + {{- toYaml . | nindent 12 }} + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + volumeMounts: + - name: webhook-template + mountPath: /config/ + {{- end }} + {{- if and .Values.webhookTemplateConfigMapName .Values.webhookTemplateConfigMapKey }} + volumes: + - name: webhook-template + configMap: + name: {{ .Values.webhookTemplateConfigMapName }} + {{- end }} + nodeSelector: + kubernetes.io/os: linux + {{- with .Values.nodeSelector }} + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.affinity }} + affinity: + {{- toYaml . | nindent 8 }} + {{- end }} + {{- with .Values.tolerations }} + tolerations: + {{- toYaml . | nindent 8 }} + {{- end }} +{{- end }} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/pdb.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/pdb.yaml new file mode 100644 index 00000000..a2564fc5 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/pdb.yaml @@ -0,0 +1,13 @@ +{{- if and .Values.enableSqsTerminationDraining (and .Values.podDisruptionBudget (gt (int .Values.replicas) 1)) }} +apiVersion: {{ include "aws-node-termination-handler.pdb.apiVersion" . }} +kind: PodDisruptionBudget +metadata: + name: {{ include "aws-node-termination-handler.fullname" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} +spec: + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDeployment" . | nindent 6 }} + {{- toYaml .Values.podDisruptionBudget | nindent 2 }} +{{- end }} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/podmonitor.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/podmonitor.yaml new file mode 100644 index 00000000..bbcbd9b4 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/podmonitor.yaml @@ -0,0 +1,31 @@ +{{- if and (not .Values.enableSqsTerminationDraining) (and .Values.enablePrometheusServer .Values.podMonitor.create) -}} +apiVersion: monitoring.coreos.com/v1 +kind: PodMonitor +metadata: + name: {{ template "aws-node-termination-handler.fullname" . }} + {{- if .Values.podMonitor.namespace }} + namespace: {{ .Values.podMonitor.namespace }} + {{- end }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} + {{- with .Values.podMonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} + podMetricsEndpoints: + - port: http-metrics + path: /metrics + {{- with .Values.podMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.podMonitor.sampleLimit }} + sampleLimit: {{ . }} + {{- end }} + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDaemonset" . | nindent 6 }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/psp.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/psp.yaml index 0eda5002..e0034c1f 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/psp.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/psp.yaml @@ -4,14 +4,25 @@ kind: PodSecurityPolicy metadata: name: {{ template "aws-node-termination-handler.fullname" . }} labels: -{{ include "aws-node-termination-handler.labels" . | indent 4 }} + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} annotations: seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*' spec: privileged: false hostIPC: false - hostNetwork: true + hostNetwork: {{ .Values.useHostNetwork }} hostPID: false +{{- if and (and (not .Values.enableSqsTerminationDraining) .Values.useHostNetwork ) (or .Values.enablePrometheusServer .Values.enableProbesServer) }} + hostPorts: +{{- if .Values.enablePrometheusServer }} + - min: {{ .Values.prometheusServerPort }} + max: {{ .Values.prometheusServerPort }} +{{- end }} +{{- if .Values.enableProbesServer }} + - min: {{ .Values.probesServerPort }} + max: {{ .Values.probesServerPort }} +{{- end }} +{{- end }} readOnlyRootFilesystem: false allowPrivilegeEscalation: false allowedCapabilities: @@ -27,12 +38,13 @@ spec: volumes: - '*' --- -kind: ClusterRole apiVersion: rbac.authorization.k8s.io/v1 +kind: Role metadata: name: {{ template "aws-node-termination-handler.fullname" . }}-psp + namespace: {{ .Release.Namespace }} labels: -{{ include "aws-node-termination-handler.labels" . | indent 4 }} + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} rules: - apiGroups: ['policy'] resources: ['podsecuritypolicies'] @@ -44,11 +56,12 @@ apiVersion: rbac.authorization.k8s.io/v1 kind: RoleBinding metadata: name: {{ template "aws-node-termination-handler.fullname" . }}-psp + namespace: {{ .Release.Namespace }} labels: -{{ include "aws-node-termination-handler.labels" . | indent 4 }} + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} roleRef: apiGroup: rbac.authorization.k8s.io - kind: ClusterRole + kind: Role name: {{ template "aws-node-termination-handler.fullname" . }}-psp subjects: - kind: ServiceAccount diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/service.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/service.yaml new file mode 100644 index 00000000..869e2606 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/service.yaml @@ -0,0 +1,17 @@ +{{- if and .Values.enableSqsTerminationDraining .Values.enablePrometheusServer -}} +apiVersion: v1 +kind: Service +metadata: + name: {{ include "aws-node-termination-handler.fullname" . }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} +spec: + type: ClusterIP + selector: + {{- include "aws-node-termination-handler.selectorLabelsDeployment" . | nindent 4 }} + ports: + - name: http-metrics + port: {{ .Values.prometheusServerPort }} + targetPort: http-metrics + protocol: TCP +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/serviceaccount.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/serviceaccount.yaml index 55f2d766..a83276d6 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/serviceaccount.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/serviceaccount.yaml @@ -3,11 +3,10 @@ apiVersion: v1 kind: ServiceAccount metadata: name: {{ template "aws-node-termination-handler.serviceAccountName" . }} - namespace: {{ .Release.Namespace }} -{{- with .Values.serviceAccount.annotations }} - annotations: -{{ toYaml . | indent 4 }} -{{- end }} labels: -{{ include "aws-node-termination-handler.labels" . | indent 4 }} + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} + {{- with .Values.serviceAccount.annotations }} + annotations: + {{- toYaml . | nindent 4 }} + {{- end }} {{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/servicemonitor.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/servicemonitor.yaml new file mode 100644 index 00000000..caee5051 --- /dev/null +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/templates/servicemonitor.yaml @@ -0,0 +1,31 @@ +{{- if and .Values.enableSqsTerminationDraining (and .Values.enablePrometheusServer .Values.serviceMonitor.create) -}} +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: {{ include "aws-node-termination-handler.fullname" . }} + {{- if .Values.serviceMonitor.namespace }} + namespace: {{ .Values.serviceMonitor.namespace }} + {{- end }} + labels: + {{- include "aws-node-termination-handler.labels" . | nindent 4 }} + {{- with .Values.serviceMonitor.labels }} + {{- toYaml . | nindent 4 }} + {{- end }} +spec: + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - {{ .Release.Namespace }} + endpoints: + - port: http-metrics + path: /metrics + {{- with .Values.serviceMonitor.interval }} + interval: {{ . }} + {{- end }} + {{- with .Values.serviceMonitor.sampleLimit }} + sampleLimit: {{ . }} + {{- end }} + selector: + matchLabels: + {{- include "aws-node-termination-handler.selectorLabelsDeployment" . | nindent 6 }} +{{- end -}} diff --git a/lib/aws/bootstrap/charts/aws-node-termination-handler/values.yaml b/lib/aws/bootstrap/charts/aws-node-termination-handler/values.yaml index 469a51e4..a49c7d62 100644 --- a/lib/aws/bootstrap/charts/aws-node-termination-handler/values.yaml +++ b/lib/aws/bootstrap/charts/aws-node-termination-handler/values.yaml @@ -3,100 +3,277 @@ # Declare variables to be passed into your templates. image: - repository: amazon/aws-node-termination-handler - tag: v1.5.0 + repository: public.ecr.aws/aws-ec2/aws-node-termination-handler + # Overrides the image tag whose default is {{ printf "v%s" .Chart.AppVersion }} + tag: "" pullPolicy: IfNotPresent pullSecrets: [] -securityContext: - runAsUserID: 1000 - runAsGroupID: 1000 - nameOverride: "" fullnameOverride: "" -priorityClassName: system-node-critical +serviceAccount: + # Specifies whether a service account should be created + create: true + # The name of the service account to use. If namenot set and create is true, a name is generated using fullname template + name: + annotations: {} + # eks.amazonaws.com/role-arn: arn:aws:iam::AWS_ACCOUNT_ID:role/IAM_ROLE_NAME + +rbac: + # Specifies whether RBAC resources should be created + create: true + # Specifies if PodSecurityPolicy resources should be created + pspEnabled: true + +customLabels: {} + +podLabels: {} podAnnotations: {} -resources: - requests: - memory: "64Mi" - cpu: "50m" - limits: - memory: "128Mi" - cpu: "100m" +podSecurityContext: + fsGroup: 1000 -## enableSpotInterruptionDraining If true, drain nodes when the spot interruption termination notice is receieved -enableSpotInterruptionDraining: "" +securityContext: + readOnlyRootFilesystem: true + runAsNonRoot: true + allowPrivilegeEscalation: false + runAsUser: 1000 + runAsGroup: 1000 -## enableScheduledEventDraining [EXPERIMENTAL] If true, drain nodes before the maintenance window starts for an EC2 instance scheduled event -enableScheduledEventDraining: "" +terminationGracePeriodSeconds: -taintNode: false +resources: {} -## dryRun tells node-termination-handler to only log calls to kubernetes control plane +nodeSelector: {} + +affinity: {} + +tolerations: [] + +# Extra environment variables +extraEnv: [] + +# Liveness probe settings +probes: + httpGet: + path: /healthz + port: 8080 + initialDelaySeconds: 5 + periodSeconds: 5 + +# Set the log level +logLevel: info + +# Log messages in JSON format +jsonLogging: false + +enablePrometheusServer: false +prometheusServerPort: 9092 + +# dryRun tells node-termination-handler to only log calls to kubernetes control plane dryRun: false +# Cordon but do not drain nodes upon spot interruption termination notice. +cordonOnly: false + +# Taint node upon spot interruption termination notice. +taintNode: false + # deleteLocalData tells kubectl to continue even if there are pods using # emptyDir (local data that will be deleted when the node is drained). -deleteLocalData: "" +deleteLocalData: true # ignoreDaemonSets causes kubectl to skip Daemon Set managed pods. -ignoreDaemonSets: "" +ignoreDaemonSets: true -# gracePeriod (DEPRECATED - use podTerminationGracePeriod instead) is time in seconds given to each pod to terminate gracefully. -# If negative, the default value specified in the pod will be used. -gracePeriod: "" -podTerminationGracePeriod: "" +# podTerminationGracePeriod is time in seconds given to each pod to terminate gracefully. If negative, the default value specified in the pod will be used. +podTerminationGracePeriod: -1 # nodeTerminationGracePeriod specifies the period of time in seconds given to each NODE to terminate gracefully. Node draining will be scheduled based on this value to optimize the amount of compute time, but still safely drain the node before an event. -nodeTerminationGracePeriod: "" +nodeTerminationGracePeriod: 120 + +# emitKubernetesEvents If true, Kubernetes events will be emitted when interruption events are received and when actions are taken on Kubernetes nodes. In IMDS Processor mode a default set of annotations with all the node metadata gathered from IMDS will be attached to each event +emitKubernetesEvents: false + +# kubernetesEventsExtraAnnotations A comma-separated list of key=value extra annotations to attach to all emitted Kubernetes events +# Example: "first=annotation,sample.annotation/number=two" +kubernetesEventsExtraAnnotations: "" # webhookURL if specified, posts event data to URL upon instance interruption action. webhookURL: "" -# webhookProxy if specified, uses this HTTP(S) proxy configuration. -webhookProxy: "" +# Webhook URL will be fetched from the secret store using the given name. +webhookURLSecretName: "" # webhookHeaders if specified, replaces the default webhook headers. webhookHeaders: "" +# webhookProxy if specified, uses this HTTP(S) proxy configuration. +webhookProxy: "" + # webhookTemplate if specified, replaces the default webhook message template. webhookTemplate: "" -# instanceMetadataURL is used to override the default metadata URL (default: http://169.254.169.254:80) +# webhook template file will be fetched from given config map name +# if specified, replaces the default webhook message with the content of the template file +webhookTemplateConfigMapName: "" + +# template file name stored in configmap +webhookTemplateConfigMapKey: "" + +# enableSqsTerminationDraining If true, this turns on queue-processor mode which drains nodes when an SQS termination event is received +enableSqsTerminationDraining: false + +# --------------------------------------------------------------------------------------------------------------------- +# Queue Processor Mode +# --------------------------------------------------------------------------------------------------------------------- + +# The number of replicas in the NTH deployment when using queue-processor mode (NOTE: increasing this may cause duplicate webhooks since NTH pods are stateless) +replicas: 1 + +# Specify the update strategy for the deployment +strategy: {} + +# podDisruptionBudget specifies the disruption budget for the controller pods. +# Disruption budget will be configured only when the replicaCount is greater than 1 +podDisruptionBudget: {} +# maxUnavailable: 1 + +serviceMonitor: + # Specifies whether ServiceMonitor should be created + # this needs enableSqsTerminationDraining: true + # and enablePrometheusServer: true + create: false + # Specifies whether the ServiceMonitor should be created in a different namespace than + # the Helm release + namespace: + # Additional labels to add to the metadata + labels: {} + # The Prometheus scrape interval + interval: 30s + # The number of scraped samples that will be accepted + sampleLimit: 5000 + +priorityClassName: system-cluster-critical + +# If specified, use the AWS region for AWS API calls +awsRegion: "" + +# Listens for messages on the specified SQS queue URL +queueURL: "" + +# The maximum amount of parallel event processors to handle concurrent events +workers: 10 + +# If true, check that the instance is tagged with "aws-node-termination-handler/managed" as the key before draining the node +checkASGTagBeforeDraining: true + +# The tag to ensure is on a node if checkASGTagBeforeDraining is true +managedAsgTag: "aws-node-termination-handler/managed" + +# If true, assume that ASG tags will be appear on the ASG's instances +assumeAsgTagPropagation: false + +# --------------------------------------------------------------------------------------------------------------------- +# IMDS Mode +# --------------------------------------------------------------------------------------------------------------------- + +# Create node OS specific daemonset(s). (e.g. "linux", "windows", "linux windows") +targetNodeOs: linux + +linuxPodLabels: {} +windowsPodLabels: {} + +linuxPodAnnotations: {} +windowsPodAnnotations: {} + +# K8s DaemonSet update strategy. +updateStrategy: + type: RollingUpdate + rollingUpdate: + maxUnavailable: 25% + +daemonsetPriorityClassName: system-node-critical + +podMonitor: + # Specifies whether PodMonitor should be created + # this needs enableSqsTerminationDraining: false + # and enablePrometheusServer: true + create: false + # Specifies whether the PodMonitor should be created in a different namespace than + # the Helm release + namespace: + # Additional labels to add to the metadata + labels: {} + # The Prometheus scrape interval + interval: 30s + # The number of scraped samples that will be accepted + sampleLimit: 5000 + +# Determines if NTH uses host networking for Linux when running the DaemonSet (only IMDS mode; queue-processor never runs with host networking) +# If you have disabled IMDSv1 and are relying on IMDSv2, you'll need to increase the IP hop count to 2 before switching this to false +# https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/configuring-instance-metadata-service.html +useHostNetwork: true + +# Daemonset DNS policy +dnsPolicy: "" +linuxDnsPolicy: ClusterFirstWithHostNet +windowsDnsPolicy: ClusterFirst + +daemonsetNodeSelector: {} +linuxNodeSelector: {} +windowsNodeSelector: {} + +daemonsetAffinity: + nodeAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + nodeSelectorTerms: + - matchExpressions: + - key: "eks.amazonaws.com/compute-type" + operator: NotIn + values: + - fargate +linuxAffinity: {} +windowsAffinity: {} + +daemonsetTolerations: + - operator: Exists +linuxTolerations: [] +windowsTolerations: [] + +# If the probes server is running for the Daemonset +enableProbesServer: false + +# Total number of times to try making the metadata request before failing. +metadataTries: 3 + +# enableSpotInterruptionDraining If false, do not drain nodes when the spot interruption termination notice is received +enableSpotInterruptionDraining: true + +# enableScheduledEventDraining [EXPERIMENTAL] If true, drain nodes before the maintenance window starts for an EC2 instance scheduled event +enableScheduledEventDraining: false + +# enableRebalanceMonitoring If true, cordon nodes when the rebalance recommendation notice is received +enableRebalanceMonitoring: false + +# enableRebalanceDraining If true, drain nodes when the rebalance recommendation notice is received +enableRebalanceDraining: false + +# --------------------------------------------------------------------------------------------------------------------- +# Testing +# --------------------------------------------------------------------------------------------------------------------- + +# (TESTING USE): If specified, use the provided AWS endpoint to make API calls. +awsEndpoint: "" + +# (TESTING USE): These should only be used for testing w/ localstack! +awsAccessKeyID: +awsSecretAccessKey: + +# (TESTING USE): Override the default metadata URL (default: http://169.254.169.254:80) instanceMetadataURL: "" # (TESTING USE): Mount path for uptime file -procUptimeFile: "/proc/uptime" - -# nodeSelector tells the daemonset where to place the node-termination-handler -# pods. By default, this value is empty and every node will receive a pod. -nodeSelector: {} - -nodeSelectorTermsOs: "" -nodeSelectorTermsArch: "" - -enablePrometheusServer: false -prometheusServerPort: "9092" - -tolerations: - - operator: "Exists" - -affinity: {} - -serviceAccount: - # Specifies whether a service account should be created - create: true - # The name of the service account to use. If namenot set and create is true, - # a name is generated using fullname template - name: - annotations: {} - # eks.amazonaws.com/role-arn: arn:aws:iam::AWS_ACCOUNT_ID:role/IAM_ROLE_NAME - -rbac: - # rbac.pspEnabled: `true` if PodSecurityPolicy resources should be created - pspEnabled: true - -dnsPolicy: "ClusterFirstWithHostNet" +procUptimeFile: /proc/uptime diff --git a/lib/helm-freeze.yaml b/lib/helm-freeze.yaml index 1babc180..c55f287e 100644 --- a/lib/helm-freeze.yaml +++ b/lib/helm-freeze.yaml @@ -21,7 +21,7 @@ charts: - name: aws-node-termination-handler repo_name: aws dest: aws-bootstrap - version: 0.8.0 + version: 0.16.1 - name: aws-vpc-cni repo_name: aws dest: aws-bootstrap diff --git a/src/cloud_provider/aws/kubernetes/helm_charts.rs b/src/cloud_provider/aws/kubernetes/helm_charts.rs index 4908df10..59d919a5 100644 --- a/src/cloud_provider/aws/kubernetes/helm_charts.rs +++ b/src/cloud_provider/aws/kubernetes/helm_charts.rs @@ -205,6 +205,7 @@ pub fn aws_helm_charts( let aws_node_term_handler = CommonChart { chart_info: ChartInfo { name: "aws-node-term-handler".to_string(), + last_breaking_version_requiring_restart: Some(Version::new(0, 16, 1)), path: chart_path("charts/aws-node-termination-handler"), values: vec![ ChartSetValue {