I read through the karpenter document at https://karpenter.sh/v0.16.1/getting-started/getting-started-with-terraform/#install-karpenter-helm-chart. I followed instructions step by step. I got errors at the end.
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller
DEBUG controller.provisioning Relaxing soft constraints for pod since it previously failed to schedule, removing: spec.topologySpreadConstraints = {"maxSkew":1,"topologyKey":"topology.kubernetes.io/zone","whenUnsatisfiable":"ScheduleAnyway","labelSelector":{"matchLabels":{"app.kubernetes.io/instance":"karpenter","app.kubernetes.io/name":"karpenter"}}} {"commit": "b157d45", "pod": "karpenter/karpenter-5755bb5b54-rh65t"} 2022-09-10T00:13:13.122Z
ERROR controller.provisioning Could not schedule pod, incompatible with provisioner "default", incompatible requirements, key karpenter.sh/provisioner-name, karpenter.sh/provisioner-name DoesNotExist not in karpenter.sh/provisioner-name In [default] {"commit": "b157d45", "pod": "karpenter/karpenter-5755bb5b54-rh65t"}
Below is the source code:
cat main.tf
terraform {
required_version = "~> 1.0"
required_providers {
aws = {
source = "hashicorp/aws"
version = "~> 4.0"
}
helm = {
source = "hashicorp/helm"
version = "~> 2.5"
}
kubectl = {
source = "gavinbunney/kubectl"
version = "~> 1.14"
}
}
}
provider "aws" {
region = "us-east-1"
}
locals {
cluster_name = "karpenter-demo"
# Used to determine correct partition (i.e. - `aws`, `aws-gov`, `aws-cn`, etc.)
partition = data.aws_partition.current.partition
}
data "aws_partition" "current" {}
module "vpc" {
# https://registry.terraform.io/modules/terraform-aws-modules/vpc/aws/latest
source = "terraform-aws-modules/vpc/aws"
version = "3.14.4"
name = local.cluster_name
cidr = "10.0.0.0/16"
azs = ["us-east-1a", "us-east-1b", "us-east-1c"]
private_subnets = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
public_subnets = ["10.0.101.0/24", "10.0.102.0/24", "10.0.103.0/24"]
enable_nat_gateway = true
single_nat_gateway = true
one_nat_gateway_per_az = false
public_subnet_tags = {
"kubernetes.io/cluster/${local.cluster_name}" = "shared"
"kubernetes.io/role/elb" = 1
}
private_subnet_tags = {
"kubernetes.io/cluster/${local.cluster_name}" = "shared"
"kubernetes.io/role/internal-elb" = 1
}
}
module "eks" {
# https://registry.terraform.io/modules/terraform-aws-modules/eks/aws/latest
source = "terraform-aws-modules/eks/aws"
version = "18.29.0"
cluster_name = local.cluster_name
cluster_version = "1.22"
vpc_id = module.vpc.vpc_id
subnet_ids = module.vpc.private_subnets
# Required for Karpenter role below
enable_irsa = true
node_security_group_additional_rules = {
ingress_nodes_karpenter_port = {
description = "Cluster API to Node group for Karpenter webhook"
protocol = "tcp"
from_port = 8443
to_port = 8443
type = "ingress"
source_cluster_security_group = true
}
}
node_security_group_tags = {
# NOTE - if creating multiple security groups with this module, only tag the
# security group that Karpenter should utilize with the following tag
# (i.e. - at most, only one security group should have this tag in your account)
"karpenter.sh/discovery/${local.cluster_name}" = local.cluster_name
}
# Only need one node to get Karpenter up and running.
# This ensures core services such as VPC CNI, CoreDNS, etc. are up and running
# so that Karpenter can be deployed and start managing compute capacity as required
eks_managed_node_groups = {
initial = {
instance_types = ["m5.large"]
# Not required nor used - avoid tagging two security groups with same tag as well
create_security_group = false
min_size = 1
max_size = 1
desired_size = 1
iam_role_additional_policies = [
"arn:${local.partition}:iam::aws:policy/AmazonSSMManagedInstanceCore", # Required by Karpenter
"arn:${local.partition}:iam::aws:policy/AmazonEKSWorkerNodePolicy",
"arn:${local.partition}:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly", #for access to ECR images
"arn:${local.partition}:iam::aws:policy/CloudWatchAgentServerPolicy"
]
tags = {
# This will tag the launch template created for use by Karpenter
"karpenter.sh/discovery/${local.cluster_name}" = local.cluster_name
}
}
}
}
#The EKS module creates an IAM role for the EKS managed node group nodes. We’ll use that for Karpenter.
#We need to create an instance profile we can reference.
#Karpenter can use this instance profile to launch new EC2 instances and those instances will be able to connect to your cluster.
resource "aws_iam_instance_profile" "karpenter" {
name = "KarpenterNodeInstanceProfile-${local.cluster_name}"
role = module.eks.eks_managed_node_groups["initial"].iam_role_name
}
#Create the KarpenterController IAM Role
#Karpenter requires permissions like launching instances, which means it needs an IAM role that grants it access. The config
#below will create an AWS IAM Role, attach a policy, and authorize the Service Account to assume the role using IRSA. We will
#create the ServiceAccount and connect it to this role during the Helm chart install.
module "karpenter_irsa" {
source = "terraform-aws-modules/iam/aws//modules/iam-role-for-service-accounts-eks"
version = "5.3.3"
role_name = "karpenter-controller-${local.cluster_name}"
attach_karpenter_controller_policy = true
karpenter_tag_key = "karpenter.sh/discovery/${local.cluster_name}"
karpenter_controller_cluster_id = module.eks.cluster_id
karpenter_controller_node_iam_role_arns = [
module.eks.eks_managed_node_groups["initial"].iam_role_arn
]
oidc_providers = {
ex = {
provider_arn = module.eks.oidc_provider_arn
namespace_service_accounts = ["karpenter:karpenter"]
}
}
}
#Install Karpenter Helm Chart
#Use helm to deploy Karpenter to the cluster. We are going to use the helm_release Terraform resource to do the deploy and pass in the
#cluster details and IAM role Karpenter needs to assume.
provider "helm" {
kubernetes {
host = module.eks.cluster_endpoint
cluster_ca_certificate = base64decode(module.eks.cluster_certificate_authority_data)
exec {
api_version = "client.authentication.k8s.io/v1beta1"
command = "aws"
args = ["eks", "get-token", "--cluster-name", local.cluster_name]
}
}
}
resource "helm_release" "karpenter" {
namespace = "karpenter"
create_namespace = true
name = "karpenter"
repository = "https://charts.karpenter.sh"
chart = "karpenter"
version = "v0.16.1"
set {
name = "serviceAccount.annotations.eks\\.amazonaws\\.com/role-arn"
value = module.karpenter_irsa.iam_role_arn
}
set {
name = "clusterName"
value = module.eks.cluster_id
}
set {
name = "clusterEndpoint"
value = module.eks.cluster_endpoint
}
set {
name = "aws.defaultInstanceProfile"
value = aws_iam_instance_profile.karpenter.name
}
}
#Provisioner
#Create a default provisioner using the command below. This provisioner configures instances to connect to your cluster’s endpoint and
#discovers resources like subnets and security groups using the cluster’s name.
#This provisioner will create capacity as long as the sum of all created capacity is less than the specified limit.
provider "kubectl" {
apply_retry_count = 5
host = module.eks.cluster_endpoint
cluster_ca_certificate = base64decode(module.eks.cluster_certificate_authority_data)
load_config_file = false
exec {
api_version = "client.authentication.k8s.io/v1beta1"
command = "aws"
args = ["eks", "get-token", "--cluster-name", module.eks.cluster_id]
}
}
resource "kubectl_manifest" "karpenter_provisioner" {
yaml_body = <<-YAML
apiVersion: karpenter.sh/v1alpha5
kind: Provisioner
metadata:
name: default
spec:
requirements:
- key: karpenter.sh/capacity-type
operator: In
values: ["spot"]
limits:
resources:
cpu: 1000
provider:
subnetSelector:
Name: "*private*"
securityGroupSelector:
karpenter.sh/discovery/${module.eks.cluster_id}: ${module.eks.cluster_id}
tags:
karpenter.sh/discovery/${module.eks.cluster_id}: ${module.eks.cluster_id}
ttlSecondsAfterEmpty: 30
YAML
depends_on = [
helm_release.karpenter
]
}
cat <<EOF | kubectl apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
name: inflate
spec:
replicas: 0
selector:
matchLabels:
app: inflate
template:
metadata:
labels:
app: inflate
spec:
terminationGracePeriodSeconds: 0
containers:
- name: inflate
image: public.ecr.aws/eks-distro/kubernetes/pause:3.2
resources:
requests:
cpu: 1
EOF
kubectl scale deployment inflate --replicas 5
kubectl logs -f -n karpenter -l app.kubernetes.io/name=karpenter -c controller
DEBUG controller.provisioning Relaxing soft constraints for pod since it previously failed to schedule, removing: spec.topologySpreadConstraints = {"maxSkew":1,"topologyKey":"topology.kubernetes.io/zone","whenUnsatisfiable":"ScheduleAnyway","labelSelector":{"matchLabels":{"app.kubernetes.io/instance":"karpenter","app.kubernetes.io/name":"karpenter"}}} {"commit": "b157d45", "pod": "karpenter/karpenter-5755bb5b54-rh65t"} 2022-09-10T00:13:13.122Z
ERROR controller.provisioning Could not schedule pod, incompatible with provisioner "default", incompatible requirements, key karpenter.sh/provisioner-name, karpenter.sh/provisioner-name DoesNotExist not in karpenter.sh/provisioner-name In [default] {"commit": "b157d45", "pod": "karpenter/karpenter-5755bb5b54-rh65t"}
I belive this is due to the pod topology defined in the Karpenter deployment here:
https://github.com/aws/karpenter/blob/main/charts/karpenter/values.yaml#L73-L77
, you can read further on what pod topologySpreadConstraints does here:
https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/
If you increase the desired_size to 2 which matches the default deployment replicas above, that should resove the error.