diff --git a/charts/karpenter-crd/Chart.yaml b/charts/karpenter-crd/Chart.yaml index ff410068364c..fe260c88ad1d 100644 --- a/charts/karpenter-crd/Chart.yaml +++ b/charts/karpenter-crd/Chart.yaml @@ -2,8 +2,8 @@ apiVersion: v2 name: karpenter-crd description: A Helm chart for Karpenter Custom Resource Definitions (CRDs). type: application -version: 1.3.0 -appVersion: 1.3.0 +version: 1.3.1 +appVersion: 1.3.1 keywords: - cluster - node diff --git a/charts/karpenter/Chart.yaml b/charts/karpenter/Chart.yaml index fd6fd80261f5..e89f6a953190 100644 --- a/charts/karpenter/Chart.yaml +++ b/charts/karpenter/Chart.yaml @@ -2,8 +2,8 @@ apiVersion: v2 name: karpenter description: A Helm chart for Karpenter, an open-source node provisioning project built for Kubernetes. type: application -version: 1.3.0 -appVersion: 1.3.0 +version: 1.3.1 +appVersion: 1.3.1 keywords: - cluster - node diff --git a/charts/karpenter/README.md b/charts/karpenter/README.md index a62cfa5c625d..3d900e0bdfa4 100644 --- a/charts/karpenter/README.md +++ b/charts/karpenter/README.md @@ -2,7 +2,7 @@ A Helm chart for Karpenter, an open-source node provisioning project built for Kubernetes. -![Version: 1.3.0](https://img.shields.io/badge/Version-1.3.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.3.0](https://img.shields.io/badge/AppVersion-1.3.0-informational?style=flat-square) +![Version: 1.3.1](https://img.shields.io/badge/Version-1.3.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.3.1](https://img.shields.io/badge/AppVersion-1.3.1-informational?style=flat-square) ## Documentation @@ -15,7 +15,7 @@ You can follow the detailed installation instruction in the [documentation](http ```bash helm upgrade --install --namespace karpenter --create-namespace \ karpenter oci://public.ecr.aws/karpenter/karpenter \ - --version 1.3.0 \ + --version 1.3.1 \ --set "serviceAccount.annotations.eks\.amazonaws\.com/role-arn=${KARPENTER_IAM_ROLE_ARN}" \ --set settings.clusterName=${CLUSTER_NAME} \ --set settings.interruptionQueue=${CLUSTER_NAME} \ @@ -27,13 +27,13 @@ helm upgrade --install --namespace karpenter --create-namespace \ As the OCI Helm chart is signed by [Cosign](https://github.com/sigstore/cosign) as part of the release process you can verify the chart before installing it by running the following command. ```shell -cosign verify public.ecr.aws/karpenter/karpenter:1.3.0 \ +cosign verify public.ecr.aws/karpenter/karpenter:1.3.1 \ --certificate-oidc-issuer=https://token.actions.githubusercontent.com \ --certificate-identity-regexp='https://github\.com/aws/karpenter-provider-aws/\.github/workflows/release\.yaml@.+' \ --certificate-github-workflow-repository=aws/karpenter-provider-aws \ --certificate-github-workflow-name=Release \ - --certificate-github-workflow-ref=refs/tags/v1.3.0 \ - --annotations version=1.3.0 + --certificate-github-workflow-ref=refs/tags/v1.3.1 \ + --annotations version=1.3.1 ``` ## Values @@ -49,9 +49,9 @@ cosign verify public.ecr.aws/karpenter/karpenter:1.3.0 \ | controller.envFrom | list | `[]` | | | controller.extraVolumeMounts | list | `[]` | Additional volumeMounts for the controller pod. | | controller.healthProbe.port | int | `8081` | The container port to use for http health probe. | -| controller.image.digest | string | `"sha256:23876d27c39f4b99ad41ee245319fc2a2fa499183131e9cfccb550658d003045"` | SHA256 digest of the controller image. | +| controller.image.digest | string | `"sha256:3fffcbbb6d0b1a2183a07bbe52c902d344fa41f8a8485de43760432ef7e2fd17"` | SHA256 digest of the controller image. | | controller.image.repository | string | `"public.ecr.aws/karpenter/controller"` | Repository path to the controller image. | -| controller.image.tag | string | `"1.3.0"` | Tag of the controller image. | +| controller.image.tag | string | `"1.3.1"` | Tag of the controller image. | | controller.metrics.port | int | `8080` | The container port to use for metrics. | | controller.resources | object | `{}` | Resources for the controller pod. | | controller.sidecarContainer | list | `[]` | Additional sidecarContainer config | diff --git a/charts/karpenter/values.yaml b/charts/karpenter/values.yaml index 1b6995cde0bc..03d351eaa594 100644 --- a/charts/karpenter/values.yaml +++ b/charts/karpenter/values.yaml @@ -108,9 +108,9 @@ controller: # -- Repository path to the controller image. repository: public.ecr.aws/karpenter/controller # -- Tag of the controller image. - tag: 1.3.0 + tag: 1.3.1 # -- SHA256 digest of the controller image. - digest: sha256:23876d27c39f4b99ad41ee245319fc2a2fa499183131e9cfccb550658d003045 + digest: sha256:3fffcbbb6d0b1a2183a07bbe52c902d344fa41f8a8485de43760432ef7e2fd17 # -- Additional environment variables for the controller pod. env: [] # - name: AWS_REGION diff --git a/website/content/en/docs/faq.md b/website/content/en/docs/faq.md index f8c4f2a4c670..0b4a8e964f80 100644 --- a/website/content/en/docs/faq.md +++ b/website/content/en/docs/faq.md @@ -17,7 +17,7 @@ See [Configuring NodePools]({{< ref "./concepts/#configuring-nodepools" >}}) for AWS is the first cloud provider supported by Karpenter, although it is designed to be used with other cloud providers as well. ### Can I write my own cloud provider for Karpenter? -Yes, but there is no documentation yet for it. Start with Karpenter's GitHub [cloudprovider](https://github.com/aws/karpenter-core/tree/v1.3.0/pkg/cloudprovider) documentation to see how the AWS provider is built, but there are other sections of the code that will require changes too. +Yes, but there is no documentation yet for it. Start with Karpenter's GitHub [cloudprovider](https://github.com/aws/karpenter-core/tree/v1.3.1/pkg/cloudprovider) documentation to see how the AWS provider is built, but there are other sections of the code that will require changes too. ### What operating system nodes does Karpenter deploy? Karpenter uses the OS defined by the [AMI Family in your EC2NodeClass]({{< ref "./concepts/nodeclasses#specamifamily" >}}). @@ -29,7 +29,7 @@ Karpenter has multiple mechanisms for configuring the [operating system]({{< ref Karpenter is flexible to multi-architecture configurations using [well known labels]({{< ref "./concepts/scheduling/#supported-labels">}}). ### What RBAC access is required? -All the required RBAC rules can be found in the Helm chart template. See [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole-core.yaml), [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole.yaml), [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/rolebinding.yaml), and [role.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/role.yaml) files for details. +All the required RBAC rules can be found in the Helm chart template. See [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole-core.yaml), [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole.yaml), [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/rolebinding.yaml), and [role.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/role.yaml) files for details. ### Can I run Karpenter outside of a Kubernetes cluster? Yes, as long as the controller has network and IAM/RBAC access to the Kubernetes API and your provider API. diff --git a/website/content/en/docs/getting-started/getting-started-with-karpenter/_index.md b/website/content/en/docs/getting-started/getting-started-with-karpenter/_index.md index 3ff84c20911d..6c4e0a59b07f 100644 --- a/website/content/en/docs/getting-started/getting-started-with-karpenter/_index.md +++ b/website/content/en/docs/getting-started/getting-started-with-karpenter/_index.md @@ -48,7 +48,7 @@ After setting up the tools, set the Karpenter and Kubernetes version: ```bash export KARPENTER_NAMESPACE="kube-system" -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" export K8S_VERSION="1.32" ``` @@ -115,13 +115,13 @@ See [Enabling Windows support](https://docs.aws.amazon.com/eks/latest/userguide/ As the OCI Helm chart is signed by [Cosign](https://github.com/sigstore/cosign) as part of the release process you can verify the chart before installing it by running the following command. ```bash -cosign verify public.ecr.aws/karpenter/karpenter:1.3.0 \ +cosign verify public.ecr.aws/karpenter/karpenter:1.3.1 \ --certificate-oidc-issuer=https://token.actions.githubusercontent.com \ --certificate-identity-regexp='https://github\.com/aws/karpenter-provider-aws/\.github/workflows/release\.yaml@.+' \ --certificate-github-workflow-repository=aws/karpenter-provider-aws \ --certificate-github-workflow-name=Release \ - --certificate-github-workflow-ref=refs/tags/v1.3.0 \ - --annotations version=1.3.0 + --certificate-github-workflow-ref=refs/tags/v1.3.1 \ + --annotations version=1.3.1 ``` {{% alert title="DNS Policy Notice" color="warning" %}} diff --git a/website/content/en/docs/getting-started/migrating-from-cas/_index.md b/website/content/en/docs/getting-started/migrating-from-cas/_index.md index 4b9514d71de3..4e263c972627 100644 --- a/website/content/en/docs/getting-started/migrating-from-cas/_index.md +++ b/website/content/en/docs/getting-started/migrating-from-cas/_index.md @@ -92,7 +92,7 @@ One for your Karpenter node role and one for your existing node group. First set the Karpenter release you want to deploy. ```bash -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" ``` We can now generate a full Karpenter deployment yaml from the Helm chart. @@ -132,7 +132,7 @@ Now that our deployment is ready we can create the karpenter namespace, create t ## Create default NodePool -We need to create a default NodePool so Karpenter knows what types of nodes we want for unscheduled workloads. You can refer to some of the [example NodePool](https://github.com/aws/karpenter/tree/v1.3.0/examples/v1) for specific needs. +We need to create a default NodePool so Karpenter knows what types of nodes we want for unscheduled workloads. You can refer to some of the [example NodePool](https://github.com/aws/karpenter/tree/v1.3.1/examples/v1) for specific needs. {{% script file="./content/en/{VERSION}/getting-started/migrating-from-cas/scripts/step10-create-nodepool.sh" language="bash" %}} diff --git a/website/content/en/docs/reference/cloudformation.md b/website/content/en/docs/reference/cloudformation.md index c5e5f0722e47..2c2958821d40 100644 --- a/website/content/en/docs/reference/cloudformation.md +++ b/website/content/en/docs/reference/cloudformation.md @@ -17,7 +17,7 @@ These descriptions should allow you to understand: To download a particular version of `cloudformation.yaml`, set the version and use `curl` to pull the file to your local system: ```bash -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" curl https://raw.githubusercontent.com/aws/karpenter-provider-aws/v"${KARPENTER_VERSION}"/website/content/en/preview/getting-started/getting-started-with-karpenter/cloudformation.yaml > cloudformation.yaml ``` diff --git a/website/content/en/docs/reference/instance-types.md b/website/content/en/docs/reference/instance-types.md index cf3411a2344e..91eb8076683f 100644 --- a/website/content/en/docs/reference/instance-types.md +++ b/website/content/en/docs/reference/instance-types.md @@ -22564,6 +22564,7 @@ below are the resources available with some assumptions and after the instance o |ephemeral-storage|17Gi| |memory|7751000Mi| |pods|737| + |vpc.amazonaws.com/efa|1| ## u7in-16tb Family ### `u7in-16tb.224xlarge` #### Labels diff --git a/website/content/en/docs/reference/threat-model.md b/website/content/en/docs/reference/threat-model.md index 384f093f7fc9..85b4a947f646 100644 --- a/website/content/en/docs/reference/threat-model.md +++ b/website/content/en/docs/reference/threat-model.md @@ -31,11 +31,11 @@ A Cluster Developer has the ability to create pods via `Deployments`, `ReplicaSe Karpenter has permissions to create and manage cloud instances. Karpenter has Kubernetes API permissions to create, update, and remove nodes, as well as evict pods. For a full list of the permissions, see the RBAC rules in the helm chart template. Karpenter also has AWS IAM permissions to create instances with IAM roles. -* [aggregate-clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/aggregate-clusterrole.yaml) -* [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole-core.yaml) -* [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole.yaml) -* [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/rolebinding.yaml) -* [role.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/role.yaml) +* [aggregate-clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/aggregate-clusterrole.yaml) +* [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole-core.yaml) +* [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole.yaml) +* [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/rolebinding.yaml) +* [role.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/role.yaml) ## Assumptions diff --git a/website/content/en/preview/reference/instance-types.md b/website/content/en/preview/reference/instance-types.md index cf3411a2344e..91eb8076683f 100644 --- a/website/content/en/preview/reference/instance-types.md +++ b/website/content/en/preview/reference/instance-types.md @@ -22564,6 +22564,7 @@ below are the resources available with some assumptions and after the instance o |ephemeral-storage|17Gi| |memory|7751000Mi| |pods|737| + |vpc.amazonaws.com/efa|1| ## u7in-16tb Family ### `u7in-16tb.224xlarge` #### Labels diff --git a/website/content/en/preview/reference/metrics.md b/website/content/en/preview/reference/metrics.md index 33a0170791d3..732b3bb97fe6 100644 --- a/website/content/en/preview/reference/metrics.md +++ b/website/content/en/preview/reference/metrics.md @@ -8,329 +8,6 @@ description: > --- Karpenter makes several metrics available in Prometheus format to allow monitoring cluster provisioning status. These metrics are available by default at `karpenter.kube-system.svc.cluster.local:8080/metrics` configurable via the `METRICS_PORT` environment variable documented [here](../settings) - -### `karpenter_ignored_pod_count` -Number of pods ignored during scheduling by Karpenter -- Stability Level: ALPHA - -### `karpenter_build_info` -A metric with a constant '1' value labeled by version from which karpenter was built. -- Stability Level: STABLE - -## Nodeclaims Metrics - -### `karpenter_nodeclaims_termination_duration_seconds` -Duration of NodeClaim termination in seconds. -- Stability Level: BETA - -### `karpenter_nodeclaims_terminated_total` -Number of nodeclaims terminated in total by Karpenter. Labeled by the owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodeclaims_instance_termination_duration_seconds` -Duration of CloudProvider Instance termination in seconds. -- Stability Level: BETA - -### `karpenter_nodeclaims_disrupted_total` -Number of nodeclaims disrupted in total by Karpenter. Labeled by reason the nodeclaim was disrupted and the owning nodepool. -- Stability Level: ALPHA - -### `karpenter_nodeclaims_created_total` -Number of nodeclaims created in total by Karpenter. Labeled by reason the nodeclaim was created and the owning nodepool. -- Stability Level: STABLE - -### `operator_nodeclaim_status_condition_transitions_total` -The count of transitions of a nodeclaim, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_count` -The number of a condition for a nodeclaim, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodeclaim_termination_current_time_seconds` -The current amount of time in seconds that a nodeclaim has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_nodeclaim_termination_duration_seconds` -The amount of time taken by a nodeclaim to terminate completely. -- Stability Level: BETA - -## Nodes Metrics - -### `karpenter_nodes_total_pod_requests` -Node total pod requests are the resources requested by pods bound to nodes, including the DaemonSet pods. -- Stability Level: BETA - -### `karpenter_nodes_total_pod_limits` -Node total pod limits are the resources specified by pod limits, including the DaemonSet pods. -- Stability Level: BETA - -### `karpenter_nodes_total_daemon_requests` -Node total daemon requests are the resource requested by DaemonSet pods bound to nodes. -- Stability Level: BETA - -### `karpenter_nodes_total_daemon_limits` -Node total daemon limits are the resources specified by DaemonSet pod limits. -- Stability Level: BETA - -### `karpenter_nodes_termination_duration_seconds` -The time taken between a node's deletion request and the removal of its finalizer -- Stability Level: BETA - -### `karpenter_nodes_terminated_total` -Number of nodes terminated in total by Karpenter. Labeled by owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodes_system_overhead` -Node system daemon overhead are the resources reserved for system overhead, the difference between the node's capacity and allocatable values are reported by the status. -- Stability Level: BETA - -### `karpenter_nodes_lifetime_duration_seconds` -The lifetime duration of the nodes since creation. -- Stability Level: ALPHA - -### `karpenter_nodes_eviction_requests_total` -The total number of eviction requests made by Karpenter -- Stability Level: ALPHA - -### `karpenter_nodes_drained_total` -The total number of nodes drained by Karpenter -- Stability Level: ALPHA - -### `karpenter_nodes_current_lifetime_seconds` -Node age in seconds -- Stability Level: ALPHA - -### `karpenter_nodes_created_total` -Number of nodes created in total by Karpenter. Labeled by owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodes_allocatable` -Node allocatable are the resources allocatable by nodes. -- Stability Level: BETA - -### `operator_node_status_condition_transitions_total` -The count of transitions of a node, type and status. -- Stability Level: BETA - -### `operator_node_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_node_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_node_status_condition_count` -The number of a condition for a node, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_node_termination_current_time_seconds` -The current amount of time in seconds that a node has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_node_termination_duration_seconds` -The amount of time taken by a node to terminate completely. -- Stability Level: BETA - -### `operator_node_event_count` -The number of a events for a node. -- Stability Level: BETA - -## Pods Metrics - -### `karpenter_pods_state` -Pod state is the current state of pods. This metric can be used several ways as it is labeled by the pod name, namespace, owner, node, nodepool name, zone, architecture, capacity type, instance type and pod phase. -- Stability Level: BETA - -### `karpenter_pods_startup_duration_seconds` -The time from pod creation until the pod is running. -- Stability Level: STABLE - -## Termination Metrics - -### `operator_termination_duration_seconds` -The amount of time taken by an object to terminate completely. -- Stability Level: DEPRECATED - -### `operator_termination_current_time_seconds` -The current amount of time in seconds that an object has been in terminating state. -- Stability Level: DEPRECATED - -## Voluntary Disruption Metrics - -### `karpenter_voluntary_disruption_queue_failures_total` -The number of times that an enqueued disruption decision failed. Labeled by disruption method. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_eligible_nodes` -Number of nodes eligible for disruption by Karpenter. Labeled by disruption reason. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_decisions_total` -Number of disruption decisions performed. Labeled by disruption decision, reason, and consolidation type. -- Stability Level: STABLE - -### `karpenter_voluntary_disruption_decision_evaluation_duration_seconds` -Duration of the disruption decision evaluation process in seconds. Labeled by method and consolidation type. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_consolidation_timeouts_total` -Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type. -- Stability Level: BETA - -## Scheduler Metrics - -### `karpenter_scheduler_scheduling_duration_seconds` -Duration of scheduling simulations used for deprovisioning and provisioning in seconds. -- Stability Level: STABLE - -### `karpenter_scheduler_queue_depth` -The number of pods currently waiting to be scheduled. -- Stability Level: BETA - -## Nodepools Metrics - -### `karpenter_nodepools_usage` -The amount of resources that have been provisioned for a nodepool. Labeled by nodepool name and resource type. -- Stability Level: ALPHA - -### `karpenter_nodepools_limit` -Limits specified on the nodepool that restrict the quantity of resources provisioned. Labeled by nodepool name and resource type. -- Stability Level: ALPHA - -### `karpenter_nodepools_allowed_disruptions` -The number of nodes for a given NodePool that can be concurrently disrupting at a point in time. Labeled by NodePool. Note that allowed disruptions can change very rapidly, as new nodes may be created and others may be deleted at any point. -- Stability Level: ALPHA - -### `operator_nodepool_status_condition_transitions_total` -The count of transitions of a nodepool, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_nodepool_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_nodepool_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodepool_status_condition_count` -The number of an condition for a nodepool, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodepool_termination_current_time_seconds` -The current amount of time in seconds that a nodepool has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_nodepool_termination_duration_seconds` -Duration of NodePool termination in seconds. -- Stability Level: BETA - -## EC2NodeClass Metrics - -### `operator_ec2nodeclass_status_condition_transitions_total` -The count of transitions of a ec2nodeclass, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_count` -The number of an condition for an ec2nodeclass, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_ec2nodeclass_termination_current_time_seconds` -The current amount of time in seconds that an ec2nodeclass has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_ec2nodeclass_termination_duration_seconds` -Duration of ec2nodeclass termination in seconds. -- Stability Level: BETA - -## Interruption Metrics - -### `karpenter_interruption_received_messages_total` -Count of messages received from the SQS queue. Broken down by message type and whether the message was actionable. -- Stability Level: STABLE - -### `karpenter_interruption_message_queue_duration_seconds` -Amount of time an interruption message is on the queue before it is processed by karpenter. -- Stability Level: STABLE - -### `karpenter_interruption_deleted_messages_total` -Count of messages deleted from the SQS queue. -- Stability Level: STABLE - -## Cluster Metrics - -### `karpenter_cluster_utilization_percent` -Utilization of allocatable resources by pod requests -- Stability Level: ALPHA - -## Cluster State Metrics - -### `karpenter_cluster_state_unsynced_time_seconds` -The time for which cluster state is not synced -- Stability Level: ALPHA - -### `karpenter_cluster_state_synced` -Returns 1 if cluster state is synced and 0 otherwise. Synced checks that nodeclaims and nodes that are stored in the APIServer have the same representation as Karpenter's cluster state -- Stability Level: STABLE - -### `karpenter_cluster_state_node_count` -Current count of nodes in cluster state -- Stability Level: STABLE - -## Cloudprovider Metrics - -### `karpenter_cloudprovider_instance_type_offering_price_estimate` -Instance type offering estimated hourly price used when making informed decisions on node cost calculation, based on instance type, capacity type, and zone. -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_offering_available` -Instance type offering availability, based on instance type, capacity type, and zone -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_memory_bytes` -Memory, in bytes, for a given instance type. -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_cpu_cores` -VCPUs cores for a given instance type. -- Stability Level: BETA - -### `karpenter_cloudprovider_errors_total` -Total number of errors returned from CloudProvider calls. -- Stability Level: BETA - -### `karpenter_cloudprovider_duration_seconds` -Duration of cloud provider method calls. Labeled by the controller, method name and provider. -- Stability Level: BETA - -## Cloudprovider Batcher Metrics - -### `karpenter_cloudprovider_batcher_batch_time_seconds` -Duration of the batching window per batcher -- Stability Level: BETA - -### `karpenter_cloudprovider_batcher_batch_size` -Size of the request batch per batcher -- Stability Level: BETA - ## Controller Runtime Metrics ### `controller_runtime_terminal_reconcile_errors_total` @@ -391,34 +68,6 @@ Current depth of workqueue Total number of adds handled by workqueue - Stability Level: STABLE -## Status Condition Metrics - -### `operator_status_condition_transitions_total` -The count of transitions of a given object, type and status. -- Stability Level: DEPRECATED - -### `operator_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. e.g. Alarm := P99(Updated=False) > 5 minutes -- Stability Level: DEPRECATED - -### `operator_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Alarm := P99(Updated=Unknown) > 5 minutes -- Stability Level: DEPRECATED - -### `operator_status_condition_count` -The number of an condition for a given object, type and status. e.g. Alarm := Available=False > 0 -- Stability Level: DEPRECATED - -## Client Go Metrics - -### `client_go_request_total` -Number of HTTP requests, partitioned by status code and method. -- Stability Level: STABLE - -### `client_go_request_duration_seconds` -Request latency in seconds. Broken down by verb, group, version, kind, and subresource. -- Stability Level: STABLE - ## AWS SDK Go Metrics ### `aws_sdk_go_request_total` diff --git a/website/content/en/v1.3/concepts/disruption.md b/website/content/en/v1.3/concepts/disruption.md index 69537284d3f0..81759b29ff3a 100644 --- a/website/content/en/v1.3/concepts/disruption.md +++ b/website/content/en/v1.3/concepts/disruption.md @@ -249,7 +249,7 @@ Changes to the [`spec.template.spec.terminationGracePeriod`]({{}}) for AWS is the first cloud provider supported by Karpenter, although it is designed to be used with other cloud providers as well. ### Can I write my own cloud provider for Karpenter? -Yes, but there is no documentation yet for it. Start with Karpenter's GitHub [cloudprovider](https://github.com/aws/karpenter-core/tree/v1.3.0/pkg/cloudprovider) documentation to see how the AWS provider is built, but there are other sections of the code that will require changes too. +Yes, but there is no documentation yet for it. Start with Karpenter's GitHub [cloudprovider](https://github.com/aws/karpenter-core/tree/v1.3.1/pkg/cloudprovider) documentation to see how the AWS provider is built, but there are other sections of the code that will require changes too. ### What operating system nodes does Karpenter deploy? Karpenter uses the OS defined by the [AMI Family in your EC2NodeClass]({{< ref "./concepts/nodeclasses#specamifamily" >}}). @@ -29,7 +29,7 @@ Karpenter has multiple mechanisms for configuring the [operating system]({{< ref Karpenter is flexible to multi-architecture configurations using [well known labels]({{< ref "./concepts/scheduling/#supported-labels">}}). ### What RBAC access is required? -All the required RBAC rules can be found in the Helm chart template. See [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole-core.yaml), [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole.yaml), [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/rolebinding.yaml), and [role.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/role.yaml) files for details. +All the required RBAC rules can be found in the Helm chart template. See [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole-core.yaml), [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole.yaml), [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/rolebinding.yaml), and [role.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/role.yaml) files for details. ### Can I run Karpenter outside of a Kubernetes cluster? Yes, as long as the controller has network and IAM/RBAC access to the Kubernetes API and your provider API. diff --git a/website/content/en/v1.3/getting-started/getting-started-with-karpenter/_index.md b/website/content/en/v1.3/getting-started/getting-started-with-karpenter/_index.md index 3ff84c20911d..6c4e0a59b07f 100644 --- a/website/content/en/v1.3/getting-started/getting-started-with-karpenter/_index.md +++ b/website/content/en/v1.3/getting-started/getting-started-with-karpenter/_index.md @@ -48,7 +48,7 @@ After setting up the tools, set the Karpenter and Kubernetes version: ```bash export KARPENTER_NAMESPACE="kube-system" -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" export K8S_VERSION="1.32" ``` @@ -115,13 +115,13 @@ See [Enabling Windows support](https://docs.aws.amazon.com/eks/latest/userguide/ As the OCI Helm chart is signed by [Cosign](https://github.com/sigstore/cosign) as part of the release process you can verify the chart before installing it by running the following command. ```bash -cosign verify public.ecr.aws/karpenter/karpenter:1.3.0 \ +cosign verify public.ecr.aws/karpenter/karpenter:1.3.1 \ --certificate-oidc-issuer=https://token.actions.githubusercontent.com \ --certificate-identity-regexp='https://github\.com/aws/karpenter-provider-aws/\.github/workflows/release\.yaml@.+' \ --certificate-github-workflow-repository=aws/karpenter-provider-aws \ --certificate-github-workflow-name=Release \ - --certificate-github-workflow-ref=refs/tags/v1.3.0 \ - --annotations version=1.3.0 + --certificate-github-workflow-ref=refs/tags/v1.3.1 \ + --annotations version=1.3.1 ``` {{% alert title="DNS Policy Notice" color="warning" %}} diff --git a/website/content/en/v1.3/getting-started/getting-started-with-karpenter/scripts/step02-create-cluster.sh b/website/content/en/v1.3/getting-started/getting-started-with-karpenter/scripts/step02-create-cluster.sh index 65c6dc07b5de..648802188de2 100755 --- a/website/content/en/v1.3/getting-started/getting-started-with-karpenter/scripts/step02-create-cluster.sh +++ b/website/content/en/v1.3/getting-started/getting-started-with-karpenter/scripts/step02-create-cluster.sh @@ -1,4 +1,4 @@ -curl -fsSL https://raw.githubusercontent.com/aws/karpenter-provider-aws/v1.3.0/website/content/en/preview/getting-started/getting-started-with-karpenter/cloudformation.yaml > "${TEMPOUT}" \ +curl -fsSL https://raw.githubusercontent.com/aws/karpenter-provider-aws/v"${KARPENTER_VERSION}"/website/content/en/preview/getting-started/getting-started-with-karpenter/cloudformation.yaml > "${TEMPOUT}" \ && aws cloudformation deploy \ --stack-name "Karpenter-${CLUSTER_NAME}" \ --template-file "${TEMPOUT}" \ diff --git a/website/content/en/v1.3/getting-started/migrating-from-cas/_index.md b/website/content/en/v1.3/getting-started/migrating-from-cas/_index.md index 4b9514d71de3..4e263c972627 100644 --- a/website/content/en/v1.3/getting-started/migrating-from-cas/_index.md +++ b/website/content/en/v1.3/getting-started/migrating-from-cas/_index.md @@ -92,7 +92,7 @@ One for your Karpenter node role and one for your existing node group. First set the Karpenter release you want to deploy. ```bash -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" ``` We can now generate a full Karpenter deployment yaml from the Helm chart. @@ -132,7 +132,7 @@ Now that our deployment is ready we can create the karpenter namespace, create t ## Create default NodePool -We need to create a default NodePool so Karpenter knows what types of nodes we want for unscheduled workloads. You can refer to some of the [example NodePool](https://github.com/aws/karpenter/tree/v1.3.0/examples/v1) for specific needs. +We need to create a default NodePool so Karpenter knows what types of nodes we want for unscheduled workloads. You can refer to some of the [example NodePool](https://github.com/aws/karpenter/tree/v1.3.1/examples/v1) for specific needs. {{% script file="./content/en/{VERSION}/getting-started/migrating-from-cas/scripts/step10-create-nodepool.sh" language="bash" %}} diff --git a/website/content/en/v1.3/reference/cloudformation.md b/website/content/en/v1.3/reference/cloudformation.md index c5e5f0722e47..2c2958821d40 100644 --- a/website/content/en/v1.3/reference/cloudformation.md +++ b/website/content/en/v1.3/reference/cloudformation.md @@ -17,7 +17,7 @@ These descriptions should allow you to understand: To download a particular version of `cloudformation.yaml`, set the version and use `curl` to pull the file to your local system: ```bash -export KARPENTER_VERSION="1.3.0" +export KARPENTER_VERSION="1.3.1" curl https://raw.githubusercontent.com/aws/karpenter-provider-aws/v"${KARPENTER_VERSION}"/website/content/en/preview/getting-started/getting-started-with-karpenter/cloudformation.yaml > cloudformation.yaml ``` diff --git a/website/content/en/v1.3/reference/instance-types.md b/website/content/en/v1.3/reference/instance-types.md index cf3411a2344e..91eb8076683f 100644 --- a/website/content/en/v1.3/reference/instance-types.md +++ b/website/content/en/v1.3/reference/instance-types.md @@ -22564,6 +22564,7 @@ below are the resources available with some assumptions and after the instance o |ephemeral-storage|17Gi| |memory|7751000Mi| |pods|737| + |vpc.amazonaws.com/efa|1| ## u7in-16tb Family ### `u7in-16tb.224xlarge` #### Labels diff --git a/website/content/en/v1.3/reference/metrics.md b/website/content/en/v1.3/reference/metrics.md index 33a0170791d3..732b3bb97fe6 100644 --- a/website/content/en/v1.3/reference/metrics.md +++ b/website/content/en/v1.3/reference/metrics.md @@ -8,329 +8,6 @@ description: > --- Karpenter makes several metrics available in Prometheus format to allow monitoring cluster provisioning status. These metrics are available by default at `karpenter.kube-system.svc.cluster.local:8080/metrics` configurable via the `METRICS_PORT` environment variable documented [here](../settings) - -### `karpenter_ignored_pod_count` -Number of pods ignored during scheduling by Karpenter -- Stability Level: ALPHA - -### `karpenter_build_info` -A metric with a constant '1' value labeled by version from which karpenter was built. -- Stability Level: STABLE - -## Nodeclaims Metrics - -### `karpenter_nodeclaims_termination_duration_seconds` -Duration of NodeClaim termination in seconds. -- Stability Level: BETA - -### `karpenter_nodeclaims_terminated_total` -Number of nodeclaims terminated in total by Karpenter. Labeled by the owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodeclaims_instance_termination_duration_seconds` -Duration of CloudProvider Instance termination in seconds. -- Stability Level: BETA - -### `karpenter_nodeclaims_disrupted_total` -Number of nodeclaims disrupted in total by Karpenter. Labeled by reason the nodeclaim was disrupted and the owning nodepool. -- Stability Level: ALPHA - -### `karpenter_nodeclaims_created_total` -Number of nodeclaims created in total by Karpenter. Labeled by reason the nodeclaim was created and the owning nodepool. -- Stability Level: STABLE - -### `operator_nodeclaim_status_condition_transitions_total` -The count of transitions of a nodeclaim, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodeclaim_status_condition_count` -The number of a condition for a nodeclaim, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodeclaim_termination_current_time_seconds` -The current amount of time in seconds that a nodeclaim has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_nodeclaim_termination_duration_seconds` -The amount of time taken by a nodeclaim to terminate completely. -- Stability Level: BETA - -## Nodes Metrics - -### `karpenter_nodes_total_pod_requests` -Node total pod requests are the resources requested by pods bound to nodes, including the DaemonSet pods. -- Stability Level: BETA - -### `karpenter_nodes_total_pod_limits` -Node total pod limits are the resources specified by pod limits, including the DaemonSet pods. -- Stability Level: BETA - -### `karpenter_nodes_total_daemon_requests` -Node total daemon requests are the resource requested by DaemonSet pods bound to nodes. -- Stability Level: BETA - -### `karpenter_nodes_total_daemon_limits` -Node total daemon limits are the resources specified by DaemonSet pod limits. -- Stability Level: BETA - -### `karpenter_nodes_termination_duration_seconds` -The time taken between a node's deletion request and the removal of its finalizer -- Stability Level: BETA - -### `karpenter_nodes_terminated_total` -Number of nodes terminated in total by Karpenter. Labeled by owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodes_system_overhead` -Node system daemon overhead are the resources reserved for system overhead, the difference between the node's capacity and allocatable values are reported by the status. -- Stability Level: BETA - -### `karpenter_nodes_lifetime_duration_seconds` -The lifetime duration of the nodes since creation. -- Stability Level: ALPHA - -### `karpenter_nodes_eviction_requests_total` -The total number of eviction requests made by Karpenter -- Stability Level: ALPHA - -### `karpenter_nodes_drained_total` -The total number of nodes drained by Karpenter -- Stability Level: ALPHA - -### `karpenter_nodes_current_lifetime_seconds` -Node age in seconds -- Stability Level: ALPHA - -### `karpenter_nodes_created_total` -Number of nodes created in total by Karpenter. Labeled by owning nodepool. -- Stability Level: STABLE - -### `karpenter_nodes_allocatable` -Node allocatable are the resources allocatable by nodes. -- Stability Level: BETA - -### `operator_node_status_condition_transitions_total` -The count of transitions of a node, type and status. -- Stability Level: BETA - -### `operator_node_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_node_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_node_status_condition_count` -The number of a condition for a node, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_node_termination_current_time_seconds` -The current amount of time in seconds that a node has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_node_termination_duration_seconds` -The amount of time taken by a node to terminate completely. -- Stability Level: BETA - -### `operator_node_event_count` -The number of a events for a node. -- Stability Level: BETA - -## Pods Metrics - -### `karpenter_pods_state` -Pod state is the current state of pods. This metric can be used several ways as it is labeled by the pod name, namespace, owner, node, nodepool name, zone, architecture, capacity type, instance type and pod phase. -- Stability Level: BETA - -### `karpenter_pods_startup_duration_seconds` -The time from pod creation until the pod is running. -- Stability Level: STABLE - -## Termination Metrics - -### `operator_termination_duration_seconds` -The amount of time taken by an object to terminate completely. -- Stability Level: DEPRECATED - -### `operator_termination_current_time_seconds` -The current amount of time in seconds that an object has been in terminating state. -- Stability Level: DEPRECATED - -## Voluntary Disruption Metrics - -### `karpenter_voluntary_disruption_queue_failures_total` -The number of times that an enqueued disruption decision failed. Labeled by disruption method. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_eligible_nodes` -Number of nodes eligible for disruption by Karpenter. Labeled by disruption reason. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_decisions_total` -Number of disruption decisions performed. Labeled by disruption decision, reason, and consolidation type. -- Stability Level: STABLE - -### `karpenter_voluntary_disruption_decision_evaluation_duration_seconds` -Duration of the disruption decision evaluation process in seconds. Labeled by method and consolidation type. -- Stability Level: BETA - -### `karpenter_voluntary_disruption_consolidation_timeouts_total` -Number of times the Consolidation algorithm has reached a timeout. Labeled by consolidation type. -- Stability Level: BETA - -## Scheduler Metrics - -### `karpenter_scheduler_scheduling_duration_seconds` -Duration of scheduling simulations used for deprovisioning and provisioning in seconds. -- Stability Level: STABLE - -### `karpenter_scheduler_queue_depth` -The number of pods currently waiting to be scheduled. -- Stability Level: BETA - -## Nodepools Metrics - -### `karpenter_nodepools_usage` -The amount of resources that have been provisioned for a nodepool. Labeled by nodepool name and resource type. -- Stability Level: ALPHA - -### `karpenter_nodepools_limit` -Limits specified on the nodepool that restrict the quantity of resources provisioned. Labeled by nodepool name and resource type. -- Stability Level: ALPHA - -### `karpenter_nodepools_allowed_disruptions` -The number of nodes for a given NodePool that can be concurrently disrupting at a point in time. Labeled by NodePool. Note that allowed disruptions can change very rapidly, as new nodes may be created and others may be deleted at any point. -- Stability Level: ALPHA - -### `operator_nodepool_status_condition_transitions_total` -The count of transitions of a nodepool, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_nodepool_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_nodepool_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodepool_status_condition_count` -The number of an condition for a nodepool, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_nodepool_termination_current_time_seconds` -The current amount of time in seconds that a nodepool has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_nodepool_termination_duration_seconds` -Duration of NodePool termination in seconds. -- Stability Level: BETA - -## EC2NodeClass Metrics - -### `operator_ec2nodeclass_status_condition_transitions_total` -The count of transitions of a ec2nodeclass, type and status. Labeled by the type, reason, and status. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. Labeled by the name of the nodeclaim, and the namespace. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Labeled by the name of the nodelcaim, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_ec2nodeclass_status_condition_count` -The number of an condition for an ec2nodeclass, type and status. Labeled by the name, namespace, type, status, and reason. -- Stability Level: BETA - -### `operator_ec2nodeclass_termination_current_time_seconds` -The current amount of time in seconds that an ec2nodeclass has been in terminating state. Labeled by name, and namespace. -- Stability Level: BETA - -### `operator_ec2nodeclass_termination_duration_seconds` -Duration of ec2nodeclass termination in seconds. -- Stability Level: BETA - -## Interruption Metrics - -### `karpenter_interruption_received_messages_total` -Count of messages received from the SQS queue. Broken down by message type and whether the message was actionable. -- Stability Level: STABLE - -### `karpenter_interruption_message_queue_duration_seconds` -Amount of time an interruption message is on the queue before it is processed by karpenter. -- Stability Level: STABLE - -### `karpenter_interruption_deleted_messages_total` -Count of messages deleted from the SQS queue. -- Stability Level: STABLE - -## Cluster Metrics - -### `karpenter_cluster_utilization_percent` -Utilization of allocatable resources by pod requests -- Stability Level: ALPHA - -## Cluster State Metrics - -### `karpenter_cluster_state_unsynced_time_seconds` -The time for which cluster state is not synced -- Stability Level: ALPHA - -### `karpenter_cluster_state_synced` -Returns 1 if cluster state is synced and 0 otherwise. Synced checks that nodeclaims and nodes that are stored in the APIServer have the same representation as Karpenter's cluster state -- Stability Level: STABLE - -### `karpenter_cluster_state_node_count` -Current count of nodes in cluster state -- Stability Level: STABLE - -## Cloudprovider Metrics - -### `karpenter_cloudprovider_instance_type_offering_price_estimate` -Instance type offering estimated hourly price used when making informed decisions on node cost calculation, based on instance type, capacity type, and zone. -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_offering_available` -Instance type offering availability, based on instance type, capacity type, and zone -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_memory_bytes` -Memory, in bytes, for a given instance type. -- Stability Level: BETA - -### `karpenter_cloudprovider_instance_type_cpu_cores` -VCPUs cores for a given instance type. -- Stability Level: BETA - -### `karpenter_cloudprovider_errors_total` -Total number of errors returned from CloudProvider calls. -- Stability Level: BETA - -### `karpenter_cloudprovider_duration_seconds` -Duration of cloud provider method calls. Labeled by the controller, method name and provider. -- Stability Level: BETA - -## Cloudprovider Batcher Metrics - -### `karpenter_cloudprovider_batcher_batch_time_seconds` -Duration of the batching window per batcher -- Stability Level: BETA - -### `karpenter_cloudprovider_batcher_batch_size` -Size of the request batch per batcher -- Stability Level: BETA - ## Controller Runtime Metrics ### `controller_runtime_terminal_reconcile_errors_total` @@ -391,34 +68,6 @@ Current depth of workqueue Total number of adds handled by workqueue - Stability Level: STABLE -## Status Condition Metrics - -### `operator_status_condition_transitions_total` -The count of transitions of a given object, type and status. -- Stability Level: DEPRECATED - -### `operator_status_condition_transition_seconds` -The amount of time a condition was in a given state before transitioning. e.g. Alarm := P99(Updated=False) > 5 minutes -- Stability Level: DEPRECATED - -### `operator_status_condition_current_status_seconds` -The current amount of time in seconds that a status condition has been in a specific state. Alarm := P99(Updated=Unknown) > 5 minutes -- Stability Level: DEPRECATED - -### `operator_status_condition_count` -The number of an condition for a given object, type and status. e.g. Alarm := Available=False > 0 -- Stability Level: DEPRECATED - -## Client Go Metrics - -### `client_go_request_total` -Number of HTTP requests, partitioned by status code and method. -- Stability Level: STABLE - -### `client_go_request_duration_seconds` -Request latency in seconds. Broken down by verb, group, version, kind, and subresource. -- Stability Level: STABLE - ## AWS SDK Go Metrics ### `aws_sdk_go_request_total` diff --git a/website/content/en/v1.3/reference/threat-model.md b/website/content/en/v1.3/reference/threat-model.md index 384f093f7fc9..85b4a947f646 100644 --- a/website/content/en/v1.3/reference/threat-model.md +++ b/website/content/en/v1.3/reference/threat-model.md @@ -31,11 +31,11 @@ A Cluster Developer has the ability to create pods via `Deployments`, `ReplicaSe Karpenter has permissions to create and manage cloud instances. Karpenter has Kubernetes API permissions to create, update, and remove nodes, as well as evict pods. For a full list of the permissions, see the RBAC rules in the helm chart template. Karpenter also has AWS IAM permissions to create instances with IAM roles. -* [aggregate-clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/aggregate-clusterrole.yaml) -* [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole-core.yaml) -* [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/clusterrole.yaml) -* [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/rolebinding.yaml) -* [role.yaml](https://github.com/aws/karpenter/blob/v1.3.0/charts/karpenter/templates/role.yaml) +* [aggregate-clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/aggregate-clusterrole.yaml) +* [clusterrole-core.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole-core.yaml) +* [clusterrole.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/clusterrole.yaml) +* [rolebinding.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/rolebinding.yaml) +* [role.yaml](https://github.com/aws/karpenter/blob/v1.3.1/charts/karpenter/templates/role.yaml) ## Assumptions diff --git a/website/hugo.yaml b/website/hugo.yaml index 17b8f1150b15..5d97bc1beb8b 100644 --- a/website/hugo.yaml +++ b/website/hugo.yaml @@ -76,7 +76,7 @@ params: url: "https://slack.k8s.io/" icon: fab fa-slack desc: "Chat with us on Slack in the #aws-provider channel" - latest_release_version: "1.3.0" + latest_release_version: "1.3.1" latest_k8s_version: "1.32" versions: - v1.3