# Karpenter 설치를 위한 변수 설정 및 확인
export CLUSTER_ENDPOINT="$(aws eks describe-cluster --name "${CLUSTER_NAME}" --query "cluster.endpoint" --output text)"
export KARPENTER_IAM_ROLE_ARN="arn:${AWS_PARTITION}:iam::${AWS_ACCOUNT_ID}:role/${CLUSTER_NAME}-karpenter"
echo "${CLUSTER_ENDPOINT} ${KARPENTER_IAM_ROLE_ARN}"
# EC2 Spot Fleet의 service-linked-role 생성 확인 : 만들어있는것을 확인하는 거라 아래 에러 출력이 정상!
# If the role has already been successfully created, you will see:
# An error occurred (InvalidInput) when calling the CreateServiceLinkedRole operation: Service role name AWSServiceRoleForEC2Spot has been taken in this account, please try a different suffix.
aws iam create-service-linked-role --aws-service-name spot.amazonaws.com || true
# docker logout : Logout of docker to perform an unauthenticated pull against the public ECR
docker logout public.ecr.aws
# helm registry logout
helm registry logout public.ecr.aws
# karpenter 설치
helm install karpenter oci://public.ecr.aws/karpenter/karpenter --version "${KARPENTER_VERSION}" --namespace "${KARPENTER_NAMESPACE}" --create-namespace \
--set "serviceAccount.annotations.eks\.amazonaws\.com/role-arn=${KARPENTER_IAM_ROLE_ARN}" \
--set "settings.clusterName=${CLUSTER_NAME}" \
--set "settings.interruptionQueue=${CLUSTER_NAME}" \
--set controller.resources.requests.cpu=1 \
--set controller.resources.requests.memory=1Gi \
--set controller.resources.limits.cpu=1 \
--set controller.resources.limits.memory=1Gi \
--wait
NodePool 생성
cat <<EOF | envsubst | kubectl apply -f -
apiVersion: karpenter.sh/v1beta1
kind: NodePool
metadata:
name: default
spec:
template:
spec:
requirements:
- key: kubernetes.io/arch
operator: In
values: ["amd64"]
- key: kubernetes.io/os
operator: In
values: ["linux"]
- key: karpenter.sh/capacity-type
operator: In
values: ["spot"]
- key: karpenter.k8s.aws/instance-category
operator: In
values: ["c", "m", "r"]
- key: karpenter.k8s.aws/instance-generation
operator: Gt
values: ["2"]
nodeClassRef:
apiVersion: karpenter.k8s.aws/v1beta1
kind: EC2NodeClass
name: default
limits:
cpu: 1000
disruption:
consolidationPolicy: WhenUnderutilized
expireAfter: 720h # 30 * 24h = 720h
---
apiVersion: karpenter.k8s.aws/v1beta1
kind: EC2NodeClass
metadata:
name: default
spec:
amiFamily: AL2 # Amazon Linux 2
role: "KarpenterNodeRole-${CLUSTER_NAME}" # replace with your cluster name
subnetSelectorTerms:
- tags:
karpenter.sh/discovery: "${CLUSTER_NAME}" # replace with your cluster name
securityGroupSelectorTerms:
- tags:
karpenter.sh/discovery: "${CLUSTER_NAME}" # replace with your cluster name
amiSelectorTerms:
- id: "${ARM_AMI_ID}"
- id: "${AMD_AMI_ID}"
# - id: "${GPU_AMI_ID}" # <- GPU Optimized AMD AMI
# - name: "amazon-eks-node-${K8S_VERSION}-*" # <- automatically upgrade when a new AL2 EKS Optimized AMI is released. This is unsafe for production workloads. Validate AMIs in lower environments before deploying them to production.
EOF
# Now, delete the deployment. After a short amount of time, Karpenter should terminate the empty nodes due to consolidation.
kubectl delete deployment inflate && date
kubectl logs -f -n "${KARPENTER_NAMESPACE}" -l app.kubernetes.io/name=karpenter -c controller
Expiration 만료 : 기본 720시간(30일) 후 인스턴스를 자동으로 만료하여 강제로 노드를 최신 상태로 유지
Drift 드리프트 : 구성 변경 사항(NodePool, EC2NodeClass)를 감지하여 필요한 변경 사항을 적용
Consolidation 통합 : 비용 효율적인 컴퓨팅 최적화
카펜터가 스팟 인스턴스를 시작할 때, AWS EC2 Fleet Instance API를 호출하여 NodePool 구성에 기반하여 선택한 인스턴스 유형을 전달합니다.
이 API는 시작된 인스턴스 목록과 시작할 수 없는 인스턴스 목록을 즉시 반환합니다. 시작할 수 없는 경우, 카펜터는 대체 용량을 요청하거나 워크로드에 대한 soft 일정 제약 조건을 제거할 수 있습니다. 이를 통해 클러스터는 필요한 인스턴스를 효율적으로 확보하고 작업을 지속할 수 있습니다.
기존 NodePool 삭제 & 신규 NodePool 생성
# 기존 nodepool 삭제
kubectl delete nodepool,ec2nodeclass default
# v0.34.0 부터 featureGates 에 spotToSpotConsolidation 활성화로 사용 가능
helm upgrade karpenter -n kube-system oci://public.ecr.aws/karpenter/karpenter --reuse-values --set settings.featureGates.spotToSpotConsolidation=true
# Create a Karpenter NodePool and EC2NodeClass
cat <<EOF > nodepool.yaml
apiVersion: karpenter.sh/v1beta1
kind: NodePool
metadata:
name: default
spec:
template:
metadata:
labels:
intent: apps
spec:
nodeClassRef:
name: default
requirements:
- key: karpenter.sh/capacity-type
operator: In
values: ["spot"]
- key: karpenter.k8s.aws/instance-category
operator: In
values: ["c","m","r"]
- key: karpenter.k8s.aws/instance-size
operator: NotIn
values: ["nano","micro","small","medium"]
- key: karpenter.k8s.aws/instance-hypervisor
operator: In
values: ["nitro"]
limits:
cpu: 100
memory: 100Gi
disruption:
consolidationPolicy: WhenUnderutilized
---
apiVersion: karpenter.k8s.aws/v1beta1
kind: EC2NodeClass
metadata:
name: default
spec:
amiFamily: Bottlerocket
subnetSelectorTerms:
- tags:
karpenter.sh/discovery: "${CLUSTER_NAME}" # replace with your cluster name
securityGroupSelectorTerms:
- tags:
karpenter.sh/discovery: "${CLUSTER_NAME}" # replace with your cluster name
role: "KarpenterNodeRole-${CLUSTER_NAME}" # replace with your cluster name
tags:
Name: karpenter.sh/nodepool/default
IntentLabel: "apps"
EOF
kubectl apply -f nodepool.yaml
# Scale in a sample workload to observe consolidation
# To invoke a Karpenter consolidation event scale, inflate the deployment to 1. Run the following command:
kubectl scale --replicas=1 deployment/inflate
