In the first part we see how to create an AWS EKS Kubernetes cluster with Terraform.
Now it's time to configure our cluster and deploy Traefik and our services.
EKS cluster configuration
Here several explanations about the AWS EKS cluster configuration and why we configured this way.
- Private Access: Enabled
Private Access allow resources in workers's VPC to access to the api-server. Needed in order to upscale potentially the cluster, nodes need access to api-server.
- We need to add specific NAT GW IPs in Public_access_cidrs var
Why? Because this parameter indicates which CIDR blocks can access the Amazon EKS public API server endpoint when enabled. We need our internal tools to access to this cluster so if you have the same constraint, you now know where to do that.
- Pods per nodes limitation
Warning: In an EKS, the number of pods per nodes, is strongly limited, instead of 110 (the default Kubernetes number).
The pod limit is actually the ENIs and IP addresses limit of the EC2 instance, because the default VPC CNI plugin will assign a secondary IP to each pod.
Our cluster nodes are based in t3.medium instance, so we have a limitation of 17 pods per nodes!
Here the complete map of number of pods max per instance type: https://github.com/awslabs/amazon-eks-ami/blob/master/files/eni-max-pods.txt
Alternative: Install another CNI plugin: https://medium.com/@swazza85/dealing-with-pod-density-limitations-on-eks-worker-nodes-137a12c8b218
Connect to the new cluster locally
At the end of the Terraform step you generates a kubeconfig file so, copy and paste it, save it in your local machine in .kube/config file or if you handle several .kubeconfig files, you can save it in .kube/eks-cluster.conf file and add it in your KUBECONFIG environment variable like this:
KUBECONFIG:/home/toto/.kube/mycluster.conf:/home/toto/.kube/eks-cluster.conf
Then export the variable.
Just one another thing … In kubeconfig file we use aws-iam-authenticator tool in order to get AWS token so you need to install it.
Tips: I recommend you to install kubectx and kubens useful tools which allow you to navigate simply to multiple clusters and multiple namespaces ;-).
$ kubectx
my_other_cluster
eks-scraly-cluster
$ kubectx eks-scraly-cluster
OK, we setted our context to link to the new cluster so we can now navigate to our cluster.
External-DNS deployment
External-DNS is a service, provided by Zalando, which dynamically provisions DNS records, and in our case, manage Route 53 records.
An AWS role have to be configured to work with the eks configuration:
- EKS provide an OIDC that we have to link to IAM through a Provider to enable iam roles for service accounts
- create a policy that allow route53 management: external dns iam policy
- create a role
web identityusing the previous provider and forsts.amazonaws.comaudience. This create a role with atrust relationshipsfrom the eks oidc and allow eks pod to assume role like kube2iam: create service account iam policy and role - attach the previous policy to the new role
All theses required things have been already done with Terraform.
Let’s go back to resources definition and creation. We will create our kubernetes code organization:
$ cd your_git_repo
$ mkdir kubernetes
$ cd kubernetes
$ mkdir external-dns
In this new folder, we will create 3 manifests YAML files:
cluster-role.yaml:
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
name: external-dns
namespace: external-dns
rules:
- apiGroups: [""]
resources: ["services"]
verbs: ["get","watch","list"]
- apiGroups: [""]
resources: ["pods"]
verbs: ["get","watch","list"]
- apiGroups: ["extensions"]
resources: ["ingresses"]
verbs: ["get","watch","list"]
- apiGroups: [""]
resources: ["nodes"]
verbs: ["list","watch"]
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
name: external-dns-viewer
namespace: external-dns
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: external-dns
subjects:
- kind: ServiceAccount
name: external-dns
namespace: external-dns
deployment.yaml:
apiVersion: apps/v1
kind: Deployment
metadata:
name: external-dns
namespace: external-dns
spec:
strategy:
type: Recreate
selector:
matchLabels:
app: external-dns
template:
metadata:
labels:
app: external-dns
spec:
serviceAccountName: external-dns
containers:
- name: external-dns
image: registry.opensource.zalan.do/teapot/external-dns:latest
args:
- --source=service
- --source=ingress
- --domain-filter=scraly.com # will make ExternalDNS see only the hosted zones matching provided domain, omit to process all available hosted zones
- --provider=aws
- --policy=sync # would prevent ExternalDNS from deleting any records, omit to enable full synchronization
- --aws-zone-type=public # only look at public hosted zones (valid values are public, private or no value for both)
- --registry=txt
securityContext:
fsGroup: 65534 # For ExternalDNS to be able to read Kubernetes and AWS token files
As you can see, we specify the AWS provider and ask external-dns to creates/updates/deletes new routes for service and ingress Kubernetes resource type for the domain scraly.com.
serviceaccount.yaml:
apiVersion: v1
kind: ServiceAccount
metadata:
name: external-dns
namespace: external-dns
# If you're using Amazon EKS with IAM Roles for Service Accounts, specify the following annotation.
# Otherwise, you may safely omit it.
annotations:
# Substitute your ARN external dns role below.
eks.amazonaws.com/role-arn: ARN_EXTERNAL_DNS_ROLE
Through Terraform output we retrieved an ARN, so now you need to retrieve it and then to pass it to manifest file:
$ sed -i -e "s|ARN_EXTERNAL_DNS_ROLE|${ARN_EXTERNAL_DNS_ROLE}|g" service-account.yaml
Great, you gave the ARN to the external-dns serviceaccount file.
Of course, AWS IAM Role we use needs appropriate Route 53 permissions.
Let’s deploy this new service (and before, create a external-dns namespace):
$ kubectl create namespace external-dns
$ kubectl apply -f external-dns -n external-dns
In order to check if external-dns is running, please watch the logs:
kubectl get po -n external-dns
kubectl logs external-dns-<pod_id> -n external-dns
External-DNS is ready, let’s deploy our reverse-proxy.
Deploy an API Gateway with Traefik
Traefik is an open source reverse proxy and load balancer for HTTP and TCP-based applications that is easy, dynamic, automatic, fast, full-featured, production proven, provides metrics, and integrates with every major cluster technology.
We will install Traefik (v2.0) as an Ingress controller for a Kubernetes cluster (https://docs.traefik.io/v2.0/user-guide/kubernetes/).
Role Based Access Control configuration
We need to authorize Traefik to use the Kubernetes API.
There are two ways to set up the proper permission: Via namespace-specific RoleBindings or a single, global ClusterRoleBinding.
Deployment
We create a traefik folder:
$ cd your_git_repo
$ cd kubernetes/
$ mkdir traefik
$ cd traefik
Creates a 1.crd.yaml file which will contains new CRDs for Traefik:
apiVersion: apiextensions.k8s.io/v1beta1
kind: CustomResourceDefinition
metadata:
name: ingressroutes.traefik.containo.us
spec:
group: traefik.containo.us
version: v1alpha1
names:
kind: IngressRoute
plural: ingressroutes
singular: ingressroute
scope: Namespaced
---
apiVersion: apiextensions.k8s.io/v1beta1
kind: CustomResourceDefinition
metadata:
name: ingressroutetcps.traefik.containo.us
spec:
group: traefik.containo.us
version: v1alpha1
names:
kind: IngressRouteTCP
plural: ingressroutetcps
singular: ingressroutetcp
scope: Namespaced
---
apiVersion: apiextensions.k8s.io/v1beta1
kind: CustomResourceDefinition
metadata:
name: middlewares.traefik.containo.us
spec:
group: traefik.containo.us
version: v1alpha1
names:
kind: Middleware
plural: middlewares
singular: middleware
scope: Namespaced
---
apiVersion: apiextensions.k8s.io/v1beta1
kind: CustomResourceDefinition
metadata:
name: tlsoptions.traefik.containo.us
spec:
group: traefik.containo.us
version: v1alpha1
names:
kind: TLSOption
plural: tlsoptions
singular: tlsoption
scope: Namespaced
---
apiVersion: apiextensions.k8s.io/v1beta1
kind: CustomResourceDefinition
metadata:
name: traefikservices.traefik.containo.us
spec:
group: traefik.containo.us
version: v1alpha1
names:
kind: TraefikService
plural: traefikservices
singular: traefikservice
scope: Namespaced
Now, we creates 2.rbac.yaml file which contains ClusterRole and ClusterRoleBinding for RBAC.
RBAC will allow Traefik to do self-discovery on Kubernetes, it will use read-only rights on several objects.
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
name: traefik-ingress-controller
rules:
- apiGroups:
- ""
resources:
- services
- endpoints
- secrets
verbs:
- get
- list
- watch
- apiGroups:
- extensions
resources:
- ingresses
verbs:
- get
- list
- watch
- apiGroups:
- extensions
resources:
- ingresses/status
verbs:
- update
- apiGroups:
- traefik.containo.us
resources:
- middlewares
verbs:
- get
- list
- watch
- apiGroups:
- traefik.containo.us
resources:
- ingressroutes
verbs:
- get
- list
- watch
- apiGroups:
- traefik.containo.us
resources:
- ingressroutetcps
verbs:
- get
- list
- watch
- apiGroups:
- traefik.containo.us
resources:
- tlsoptions
verbs:
- get
- list
- watch
- apiGroups:
- traefik.containo.us
resources:
- traefikservices
verbs:
- get
- list
- watch
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1beta1
metadata:
name: traefik-ingress-controller
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: traefik-ingress-controller
subjects:
- kind: ServiceAccount
name: traefik-ingress-controller
namespace: traefik
Now we create the deployment file in 3.traefik.deploy.yaml file which contains the deployment of traefik pods and services and enabling the tracing:
apiVersion: v1
kind: ServiceAccount
metadata:
name: traefik-ingress-controller
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: traefik
labels:
app: traefik
spec:
replicas: 1
selector:
matchLabels:
app: traefik
template:
metadata:
labels:
app: traefik
spec:
serviceAccountName: traefik-ingress-controller
containers:
- name: traefik
image: traefik:v2.0
args:
- --api.insecure
- --accesslog
- --entrypoints.web.Address=:8000
- --entrypoints.websecure.Address=:4443
- --providers.kubernetescrd
- --certificatesresolvers.default.acme.tlschallenge
- --certificatesresolvers.default.acme.email=scraly@myemail.com
- --certificatesresolvers.default.acme.storage=acme.json
# Please note that this is the staging Let's Encrypt server.
# Once you get things working, you should remove that whole line altogether.
- --certificatesresolvers.default.acme.caserver=https://acme-staging-v02.api.letsencrypt.org/directory
- --tracing.jaeger=true
- --tracing.jaeger.gen128Bit
- --tracing.jaeger.propagation=b3
- --tracing.jaeger.localAgentHostPort=jaeger-agent:6831
- --tracing.jaeger.collector.endpoint=http://jaeger-collector:14268/api/traces?format=jaeger.thrift
- --metrics.prometheus=true
ports:
- name: web
containerPort: 8000
- name: websecure
containerPort: 4443
---
apiVersion: v1
kind: Service
metadata:
name: traefik
annotations:
service.beta.kubernetes.io/aws-load-balancer-type: nlb
external-dns.alpha.kubernetes.io/hostname: "*.traefik.scraly.com"
spec:
type: LoadBalancer
ports:
- protocol: TCP
name: web
port: 80
targetPort: web
- protocol: TCP
name: admin
port: 8080
- protocol: TCP
name: websecure
port: 443
targetPort: websecure
selector:
app: traefik
And then we can create IngressRoute for http and https routes in 5.ingressroutes.yaml file.
We will secured Jaeger with basic auth with an user and a password, in order to generate it here the command line:
$ htpasswd -nb admin admin | base64
YWRtaW46JGFwcjEkdWllZko3UkskaHhOc1ZUZzFjSVBWZlp6VEJ6Uk9wLgoK
5.ingressroutes.yaml:
apiVersion: v1
kind: Secret
metadata:
name: authsecret
data:
# admin / admin
users: YWRtaW46JGFwcjEkdWllZko3UkskaHhOc1ZUZzFjSVBWZlp6VEJ6Uk9wLgoK
---
# Declaring the user list
apiVersion: traefik.containo.us/v1alpha1
kind: Middleware
metadata:
name: jaeger-ingress-auth
spec:
basicAuth:
secret: authsecret
---
apiVersion: traefik.containo.us/v1alpha1
kind: Middleware
metadata:
name: striptlsprefix
spec:
stripPrefix:
prefixes:
- /tls
- /notls
---
apiVersion: traefik.containo.us/v1alpha1
kind: IngressRoute
metadata:
name: simpleingressroute
spec:
entryPoints:
- web
routes:
- match: Host(`apigw.traefik.scraly.com`)
kind: Rule
services:
- name: httpbin
port: 80
middlewares:
- name: striptlsprefix
---
apiVersion: traefik.containo.us/v1alpha1
kind: IngressRoute
metadata:
name: ingressroutetls
spec:
entryPoints:
- websecure
routes:
- match: Host(`apigw.traefik.scraly.com`)
kind: Rule
services:
- name: httpbin
port: 80
middlewares:
- name: striptlsprefix
- name: tlssubjectheader
tls:
certResolver: default
options:
name: scraly-mtls
---
apiVersion: traefik.containo.us/v1alpha1
kind: IngressRoute
metadata:
name: jaeger-ingress-tls
spec:
entryPoints:
- websecure
routes:
- match: Host(`jaeger.traefik.scraly.com`)
kind: Rule
services:
- name: jaeger-query
port: 16686
middlewares:
- name: jaeger-ingress-auth
tls:
certResolver: default
As you can see in Deployment resource, we let Let's encrypt handle Server certificate for TLS. If you keep let’s encrypt staging URL, you will have a warning/issue in your browser, in order to remote this warning, you need to use Let’s Encrypt production URL:
https://acme-v02.api.letsencrypt.org/directory
Our manifests files are ready so let’s deploy them in the cluster:
$ cd kubernetes
$ kubectl apply -f traefik
$ kubectl get po,svc,deploy,ingressroute,secret
NAME READY STATUS RESTARTS AGE
pod/httpbin-c134bc87b-4c9qt 1/1 Running 0 17m
pod/jaeger-6765759cb5-9ljwb 1/1 Running 0 17m
pod/jaeger-agent-daemonset-dgdls 1/1 Running 0 17m
pod/jaeger-operator-75f9699896-fl9zv 1/1 Running 0 17m
pod/traefik-71234cd8cfc-k78b 1/1 Running 0 47m
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE
service/httpbin ClusterIP 1xx.xx.xxx.x <none> 80/TCP 17m
service/jaeger-agent ClusterIP None <none> 5775/UDP,5778/TCP,6831/UDP,6832/UDP 17m
service/jaeger-collector ClusterIP 1xx.xx.xx.xxx <none> 9411/TCP,14250/TCP,14267/TCP,14268/TCP 17m
service/jaeger-collector-headless ClusterIP None <none> 9411/TCP,14250/TCP,14267/TCP,14268/TCP 17m
service/jaeger-operator-metrics ClusterIP 1xx.20.122.97 <none> 8383/TCP,8686/TCP 17m
service/jaeger-query ClusterIP 1xx.xx.xxx.xxx <none> 16686/TCP 17m
service/traefik LoadBalancer 1xx.xx.xxx.xxx a012436577463524f84547656459c1f-126543650.eu-central-1.elb.amazonaws.com 80:30123/TCP,443:30980/TCP 17m
NAME READY UP-TO-DATE AVAILABLE AGE
deployment.extensions/httpbin 1/1 1 1 17m
deployment.extensions/jaeger 1/1 1 1 17m
deployment.extensions/jaeger-operator 1/1 1 1 17m
deployment.extensions/traefik 1/1 1 1 17m
NAME AGE
ingressroute.traefik.containo.us/ingressroutetls 17m
ingressroute.traefik.containo.us/jaeger-ingress-tls 14m
ingressroute.traefik.containo.us/simpleingressroute 14m
Cool, we know have a reverse-proxy which in HTTP and HTTPS, nice but we need to go further and deploy it in mTLS in order to be more secure.
Secure our reverse-proxy with mTLS
Mutual TLS (mTLS) authentication ensures that traffic is both secure and trusted in both directions between a client and server. Client certificate authentication is a second layer of security.
With a root certificate authority (CA) in place, the server only allows requests from devices with a corresponding client certificate. When a request reaches the application, server responds with a request for the client to present a certificate. If the device fails to present the certificate, the request is not allowed to proceed. If the client does have a certificate, the certificate is verified.
For this POC purpose & scope, we generates a root CA that we used to sign client certificate (for testing/access purpose). Server accepts exclusively requests signed with such certificates.
Server certificate being generated by Let's Encrypt.
Root CA:
First of all, we generate a key pair for CA root:
$ openssl genrsa -out ca.key 2048
Then, we generates Root CA certificate:
$ openssl req -days 3600 -new -x509 -key ca.key -out ca.pem
In this step, you are about to be asked to enter information that will be incorporated into your certificate request.
What you are about to enter is what is called a Distinguished Name or a DN.
There are quite a few fields but you can leave some blank
For some fields there will be a default value,
If you enter '.', the field will be left blank.
Country Name (2 letter code) [AU]:FR
State or Province Name (full name) [Some-State]:Your_city
Locality Name (eg, city) []:
Organization Name (eg, company) [Internet Widgits Pty Ltd]:Your_Company
Organizational Unit Name (eg, section) []:Your_Orga_Unit_Name
Common Name (e.g. server FQDN or YOUR name) []:Root CA Test
Email Address []:
Server certificate:
Then, you can create the certificate server.
Key pair generation for CA root:
$ openssl genrsa -out server.key 2048
CSR creation:
$ openssl req -new -key server.key -out server.csr -subj "/C=FR/ST=Your_city/O=Your-Company/OU=Your_Unit_Name/CN=###your_domain_name###"
Certificate creation:
$ openssl x509 -req -days 360 -in server.csr -CA ca.pem -CAkey ca.key -CAcreateserial -out server.pem -sha256
Client certificate:
Key pair generation for CA root:
$ openssl genrsa -out client.key 2048
CSR creation:
$ openssl req -new -key client.key -out client.csr -subj "/C=FR/ST=Your_city/O=Test"
Certificate creation:
$ openssl x509 -req -days 360 -in client.csr -CA ca.pem -CAkey ca.key -CAcreateserial -out client.pem -sha256
A tips is you can visualize your certificate directly in command line:
$ openssl x509 -noout -text -in file.pem
Ok, you have plenty of certificates now ^^.
We will uses and store this CA certificate, base64 encoded, in mtls-ca kubernetes secret, use it in ingressroutetls and specify TLSOption RequireAndVerifyClientCert.
In order to store the CA root in a Kubernetes secret, you need to encode it in base64:
$ cat ca.pem | base64
In traefik folder, create a 4.mtls.yaml file:
apiVersion: v1
kind: Secret
metadata:
name: mtls-ca
data:
tls.ca: <base64_result>
---
apiVersion: traefik.containo.us/v1alpha1
kind: TLSOption
metadata:
name: scraly-mtls
spec:
clientAuth:
secretNames:
- mtls-ca
clientAuthType: RequireAndVerifyClientCert
---
apiVersion: traefik.containo.us/v1alpha1
kind: Middleware
metadata:
name: tlssubjectheader
spec:
passTLSClientCert:
info:
subject:
commonName: true
$ kubectl apply -f traefik/4.mtls.yaml
And now we can edit our 5.ingressroutes.yaml file in order to use the mTLS and comment HTTP route:
apiVersion: v1
kind: Secret
metadata:
name: authsecret
data:
# admin / admin
users: YWRtaW46JGFwcjEkdWllZko3UkskaHhOc1ZUZzFjSVBWZlp6VEJ6Uk9wLgoK
---
# Declaring the user list
apiVersion: traefik.containo.us/v1alpha1
kind: Middleware
metadata:
name: jaeger-ingress-auth
spec:
basicAuth:
secret: authsecret
---
apiVersion: traefik.containo.us/v1alpha1
kind: Middleware
metadata:
name: striptlsprefix
spec:
stripPrefix:
prefixes:
- /tls
- /notls
# ---
# apiVersion: traefik.containo.us/v1alpha1
# kind: IngressRoute
# metadata:
# name: simpleingressroute
# spec:
# entryPoints:
# - web
# routes:
# - match: Host(`apigw.traefik.scraly.com`)
# kind: Rule
# services:
# - name: httpbin
# port: 80
# middlewares:
# - name: striptlsprefix
---
apiVersion: traefik.containo.us/v1alpha1
kind: IngressRoute
metadata:
name: ingressroutetls
spec:
entryPoints:
- websecure
routes:
- match: Host(`apigw.traefik.scraly.com`)
kind: Rule
services:
- name: httpbin
port: 80
middlewares:
- name: striptlsprefix
- name: tlssubjectheader
tls:
certResolver: default
options:
name: scraly-mtls
---
apiVersion: traefik.containo.us/v1alpha1
kind: IngressRoute
metadata:
name: jaeger-ingress-tls
spec:
entryPoints:
- websecure
routes:
- match: Host(`jaeger.traefik.scraly.com`)
kind: Rule
services:
- name: jaeger-query
port: 16686
middlewares:
- name: jaeger-ingress-auth
tls:
certResolver: default
$ kubectl apply -f traefik/5.ingressroutes.yaml
Deploy HTTPBin
In order to validate the infrastructure, we will deploy an httpbin service in the cluster (which will be exposed via the API Gateway, Traefik).
httpbin is a simple Rest API for network and implementation testing. We will deploy a httpbin deployment for testing purpose.
$ cd kubernetes
$ mkdir httpbin
$ cd httpbin
deployment.yaml:
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
labels:
app: httpbin
name: httpbin
spec:
replicas: 1
selector:
matchLabels:
app: httpbin
template:
metadata:
labels:
app: httpbin
spec:
containers:
- image: kennethreitz/httpbin
imagePullPolicy: Always
name: httpbin
ports:
- containerPort: 80
name: http
protocol: TCP
resources:
requests:
cpu: 5m
memory: 70Mi
service.yaml
apiVersion: v1
kind: Service
metadata:
labels:
app: httpbin
name: httpbin
spec:
ports:
- name: http
port: 80
protocol: TCP
targetPort: 80
selector:
app: httpbin
type: ClusterIP
$ cd ..
$ kubectl apply -f httpbin
As usual, we check if the resources we deployed are running:
$ kubectl get po -n traefik
…
pod/httpbin-c123bc45b-6c7qt 1/1 Running 0 1m
…
Test with Postman
All our infrastructure is deployed so now it’s time to test it.
HTTPBin is secured with mTLS so we can test our service through cURL or for example with Postman.
Postman is one of the famous tool for API testing. Very useful for day-to-day tests during development.
You need to edit the settings of Postman to set the client key and pem in Settings>Certificates>Client Certificates like this:
Create a new collection in Postman and create a new request like this:
Issues we faced
During this story, we faced multiple issues caused by solutions we made.
Through this ReX (Return of eXperience) I will explain you the problem we faced, the analysis and the solution to fixed them.
LoadBalancer can’t be created / External-DNS can’t create Route53 records
First time we deployed our stack we faced in a problem: our service couldn't have external IP:
service/traefik LoadBalancer 1xx.xx.xxx.xx <pending> 80:32666/TCP,443:32088/TCP 33m
<pending>
$ kubectl describe svc/traefik
Name: traefik
Namespace: traefik
Labels: <none>
...
Session Affinity: None
External Traffic Policy: Cluster
Events:
Type Reason Age From Message
---- ------ ---- ---- -------
Normal EnsuringLoadBalancer 3m23s (x12 over 33m) service-controller Ensuring load balancer
Warning SyncLoadBalancerFailed 3m22s (x12 over 33m) service-controller Error syncing load balancer: failed to ensure load balancer: could not find any suitable subnets for creating the ELB
Solution:
Public subnets in the VPC may be tagged accordingly so that Kubernetes knows to use only those subnets for external load balancers, so added one tag:
"kubernetes.io/role/elb" = "1"
c.f https://docs.aws.amazon.com/eks/latest/userguide/load-balancing.html
Issues while deployment through Terraform
If you create OIDC connect provider through Terraform, CA thumbprint list will be empty, the problem is that with OIDC as my service accounts couldn’t get valid credentials so external-dns service will not work :'(.
Here the problem and the solution: https://medium.com/@marcincuber/amazon-eks-with-oidc-provider-iam-roles-for-kubernetes-services-accounts-59015d15cb0c
So the solution is to create a script get_thumbprint.sh:
#!/bin/sh
# https://github.com/terraform-providers/terraform-provider-aws/issues/10104
THUMBPRINT=$(echo | openssl s_client -servername oidc.eks.${1}.amazonaws.com -showcerts -connect oidc.eks.${1}.amazonaws.com:443 2>&- | tac | sed -n '/-----END CERTIFICATE-----/,/-----BEGIN CERTIFICATE-----/p; /-----BEGIN CERTIFICATE-----/q' | tac | openssl x509 -fingerprint -sha1 -noout | sed 's/://g' | awk -F= '{print tolower($2)}')
THUMBPRINT_JSON="{\"thumbprint\": \"${THUMBPRINT}\"}"
echo $THUMBPRINT_JSON
Then we added an external data in order to retrieve the thumbprint and we added this list in our OIDC provider resource definition:
### External cli kubergrunt
data "external" "thumb" {
program = [ "get_thumbprint.sh", var.aws_region ]
}
# Enabling IAM Roles for Service Accounts
resource "aws_iam_openid_connect_provider" "eks-scraly-cluster-oidc" {
client_id_list = ["sts.amazonaws.com"]
thumbprint_list = [data.external.thumb.result.thumbprint]
url = aws_eks_cluster.eks-scraly-cluster.identity.0.oidc.0.issuer
}
Conclusion
I know our solution it’s not a perfect solution but it aims us to deploy a start infrastructure in several days with a Kubernetes cluster, an API Gateway and secured by mTLS. For a POC purpose it’s a good way to start. I hope you’ll like this little ReX ;-).
Top comments (3)
That's a very informative ReX, I will be using some parts (the mTLS) soon ! :)
Beware, the linked traefik documentation is v1.7 and not v2.0. (the traefik website is verry annoying on the version management)
Thank, I will fix this! 😉
Hi @aurelievache ,
it seems you have skipped the part where the jaeger service is set up?
I followed your instructions and traefik is logging "Cannot create service: service not found traefik/jaeger-query"