mirror of
https://code.forgejo.org/infrastructure/documentation
synced 2024-11-22 03:21:10 +00:00
helpers to prepare a k8s node on Hetzner
This commit is contained in:
parent
4f90ea7af5
commit
8947b16ce6
3
.gitignore
vendored
Normal file
3
.gitignore
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
||||||
|
*~
|
||||||
|
k3s-host/secrets.sh
|
||||||
|
k3s-host/variables.sh
|
||||||
286
README.md
286
README.md
|
|
@ -790,33 +790,19 @@ stream {
|
||||||
https://hetzner05.forgejo.org & https://hetzner06.forgejo.org run on [EX44](https://www.hetzner.com/dedicated-rootserver/ex44) Hetzner hardware.
|
https://hetzner05.forgejo.org & https://hetzner06.forgejo.org run on [EX44](https://www.hetzner.com/dedicated-rootserver/ex44) Hetzner hardware.
|
||||||
|
|
||||||
|
|
||||||
#### LXC
|
#### Imaging
|
||||||
|
|
||||||
```sh
|
Using installimage from the rescue instance.
|
||||||
lxc-helpers.sh lxc_install_lxc_inside 10.47.3 fc11
|
|
||||||
```
|
|
||||||
|
|
||||||
#### NFS
|
- `wipefs -fa /dev/nvme*n1`
|
||||||
|
- `installimage -r no -n hetzner0?`
|
||||||
|
- Debian bookworm
|
||||||
|
- `PART / ext4 100G`
|
||||||
|
- `PART /srv ext4 all`
|
||||||
|
- ESC 0 + yes
|
||||||
|
- reboot
|
||||||
|
|
||||||
[server](https://wiki.archlinux.org/title/NFS).
|
Partitioning.
|
||||||
|
|
||||||
```sh
|
|
||||||
sudo apt install nfs-kernel-server nfs-common
|
|
||||||
cat <<EOF | sudo tee -a /etc/exports
|
|
||||||
/precious 10.53.101.0/24(rw,fsid=0,no_root_squash,no_subtree_check)
|
|
||||||
/precious/k8s 10.53.101.0/24(rw,nohide,insecure,no_subtree_check)
|
|
||||||
EOF
|
|
||||||
sudo exportfs -av
|
|
||||||
sudo exportfs -s
|
|
||||||
```
|
|
||||||
|
|
||||||
[client](https://wiki.archlinux.org/title/NFS).
|
|
||||||
|
|
||||||
```sh
|
|
||||||
sudo apt install nfs-common
|
|
||||||
```
|
|
||||||
|
|
||||||
#### Disk partitioning
|
|
||||||
|
|
||||||
- First disk
|
- First disk
|
||||||
- OS
|
- OS
|
||||||
|
|
@ -824,149 +810,83 @@ sudo apt install nfs-common
|
||||||
- Second disk
|
- Second disk
|
||||||
- a partition configured with DRBD
|
- a partition configured with DRBD
|
||||||
|
|
||||||
#### Root filesystem backups
|
Debian user.
|
||||||
|
|
||||||
- `hetzner05:/etc/cron.daily/backup-hetzner06`
|
- `ssh root@hetzner0?.forgejo.org`
|
||||||
`rsync -aHSv --delete-excluded --delete --numeric-ids --exclude /proc --exclude /dev --exclude /sys --exclude /srv --exclude /var/lib/lxc 10.53.100.6:/ /srv/backups/hetzner06/`
|
- `useradd --shell /bin/bash --create-home --groups sudo debian`
|
||||||
- `hetzner06:/etc/cron.daily/backup-hetzner05`
|
- `mkdir -p /home/debian/.ssh ; cp -a .ssh/authorized_keys /home/debian/.ssh ; chown -R debian /home/debian/.ssh`
|
||||||
`rsync -aHSv --delete-excluded --delete --numeric-ids --exclude /proc --exclude /dev --exclude /sys --exclude /srv --exclude /var/lib/lxc 10.53.100.5:/ /srv/backups/hetzner05/`
|
- in `/etc/sudoers` edit `%sudo ALL=(ALL:ALL) NOPASSWD:ALL`
|
||||||
|
|
||||||
#### Failover IP addresses
|
#### Install helpers
|
||||||
|
|
||||||
The failover IP addresses are configured on all hosts.
|
Each node is identifed by the last digit of the hostname.
|
||||||
|
|
||||||
```
|
|
||||||
auto enp5s0
|
|
||||||
iface enp5s0 inet static
|
|
||||||
...
|
|
||||||
up ip addr add 188.40.16.47/32 dev enp5s0
|
|
||||||
|
|
||||||
iface enp5s0 inet6 static
|
|
||||||
...
|
|
||||||
up ip addr add 2a01:4f8:fff2:48::2/64 dev enp5s0
|
|
||||||
```
|
|
||||||
|
|
||||||
#### k8s node
|
|
||||||
|
|
||||||
The `10.88.1.5` and `fd10::5` IPs are assigned to the interface with VLAN 4002.
|
|
||||||
|
|
||||||
```
|
|
||||||
auto enp5s0.4002
|
|
||||||
iface enp5s0.4002 inet static
|
|
||||||
address 10.88.1.5
|
|
||||||
netmask 255.255.0.0
|
|
||||||
vlan-raw-device enp5s0
|
|
||||||
mtu 1400
|
|
||||||
up ip addr add fd10::5/48 dev enp5s0.4002
|
|
||||||
```
|
|
||||||
|
|
||||||
### k8s first server node
|
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
sudo apt-get install curl
|
sudo apt-get install git etckeeper
|
||||||
master_node_ip=10.88.1.5,fd10::5
|
git clone https://code.forgejo.org/infrastructure/documentation
|
||||||
curl -fL https://get.k3s.io | sh -s - server --cluster-init --disable=servicelb --write-kubeconfig-mode=644 --node-ip=$master_node_ip --cluster-cidr=10.42.0.0/16,fd01::/48 --service-cidr=10.43.0.0/16,fd02::/112 --flannel-ipv6-masq
|
cd documentation/k3s-host
|
||||||
curl -fsSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash -
|
cp variables.sh.example variables.sh
|
||||||
|
cp secrets.sh.example secrets.sh
|
||||||
```
|
```
|
||||||
|
|
||||||
### k8s second server node
|
Variables that must be set depending on the role of the node.
|
||||||
|
|
||||||
|
- first server node
|
||||||
|
- secrets.sh: node_drbd_shared_secret
|
||||||
|
- other server node
|
||||||
|
- secrets.sh: node_drbd_shared_secret
|
||||||
|
- secrets.sh: node_k8s_token: content of /var/lib/rancher/k3s/server/token on the first node
|
||||||
|
- variables.sh: node_k8s_existing: identifier of the first node (e.g. 5)
|
||||||
|
- etcd node
|
||||||
|
- secrets.sh: node_k8s_token: content of /var/lib/rancher/k3s/server/token on the first node
|
||||||
|
- variables.sh: node_k8s_existing: identifier of the first node (e.g. 5)
|
||||||
|
- variables.sh: node_k8s_etcd: identifier of the node whose role is just etcd (e.g. 3)
|
||||||
|
|
||||||
|
The other variables depend on the setup.
|
||||||
|
|
||||||
|
#### Firewall
|
||||||
|
|
||||||
|
`./setup.sh setup_ufw`
|
||||||
|
|
||||||
|
#### DRBD
|
||||||
|
|
||||||
|
DRBD is [configured](https://linbit.com/drbd-user-guide/drbd-guide-9_0-en/#p-work) with:
|
||||||
|
|
||||||
|
`./setup.sh setup_drbd`
|
||||||
|
|
||||||
|
Once two nodes have DRBD setup for the first time, it can be initialized by [pretending all is in sync](https://linbit.com/drbd-user-guide/drbd-guide-9_0-en/#s-skip-initial-resync) to save the initial bitmap sync since there is actually no data at all.
|
||||||
|
|
||||||
The token is found on the first node in the `/var/lib/rancher/k3s/server/token` file.
|
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
sudo apt-get install curl
|
sudo drbdadm primary r1
|
||||||
token=???
|
sudo drbdadm new-current-uuid --clear-bitmap r1/0
|
||||||
master_ip=10.88.1.5
|
sudo mount /precious
|
||||||
second_node_ip=10.88.1.6,fd10::6
|
|
||||||
curl -fL https://get.k3s.io | sh -s - server --token $token --server https://$master_ip:6443 --cluster-init --disable=servicelb --write-kubeconfig-mode=644 --node-ip=$second_node_ip --cluster-cidr=10.42.0.0/16,fd01::/48 --service-cidr=10.43.0.0/16,fd02::/112 --flannel-ipv6-masq
|
|
||||||
curl -fsSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash -
|
|
||||||
kubectl taint nodes $(hostname) key1=value1:NoSchedule
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### k8s dedicated etcd node
|
#### NFS
|
||||||
|
|
||||||
[dedicated etcd node](https://docs.k3s.io/installation/server-roles#dedicated-etcd-nodes)
|
`./setup.sh setup_nfs`
|
||||||
|
|
||||||
The token is found on one of the master nodes in the `/var/lib/rancher/k3s/server/token` file.
|
On the node that has the DRBD volume `/precious` mounted, set the IP of the NFS server to be used by k8s:
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
master_ip=10.88.1.5
|
sudo ip addr add 10.53.101.100/24 dev enp5s0.4001
|
||||||
etcd_node_ip=10.88.1.3,fd10::3
|
|
||||||
curl -sfL https://get.k3s.io | sh -s - server --token "$token" --server https://$master_ip:6443 --cluster-init --disable=servicelb --disable-apiserver --disable-controller-manager --disable-scheduler --write-kubeconfig-mode=644 --node-ip=$etcd_node_ip --cluster-cidr=10.42.0.0/16,fd01::/48 --service-cidr=10.43.0.0/16,fd02::/112 --flannel-ipv6-masq
|
|
||||||
kubectl taint nodes $(hostname) key1=value1:NoSchedule
|
|
||||||
```
|
```
|
||||||
|
|
||||||
### k8s networking
|
#### K8S
|
||||||
|
|
||||||
[cert-manager](https://cert-manager.io/).
|
For the first node `./setup.sh setup_k8s`. For nodes joining the cluster `./setup.sh setup_k8s 6` where `hetzner06` is an existing node.
|
||||||
|
|
||||||
```
|
- [metallb](https://metallb.universe.tf) instead of the default load balancer because it does not allow for a public IP different from the `k8s` node IP.
|
||||||
helm install mycertmanager --set installCRDs=true oci://registry-1.docker.io/bitnamicharts/cert-manager
|
`./setup.sh setup_k8s_metallb`
|
||||||
# wait a few seconds
|
- [traefik](https://traefik.io/) requests with [annotations](https://github.com/traefik/traefik-helm-chart/blob/7a13fc8a61a6ad30fcec32eec497dab9d8aea686/traefik/values.yaml#L736) specific IPs from `metalldb`.
|
||||||
cat > clusterissuer.yml <<EOF
|
`./setup.sh setup_k8s_traefik`
|
||||||
apiVersion: cert-manager.io/v1
|
- [cert-manager](https://cert-manager.io/).
|
||||||
kind: ClusterIssuer
|
`./setup.sh setup_k8s_certmanager`
|
||||||
metadata:
|
- NFS storage class
|
||||||
name: letsencrypt-http
|
`./setup.sh setup_k8s_nfs`
|
||||||
spec:
|
|
||||||
acme:
|
|
||||||
email: contact@forgejo.org
|
|
||||||
server: https://acme-v02.api.letsencrypt.org/directory
|
|
||||||
privateKeySecretRef:
|
|
||||||
name: letsencrypt-http
|
|
||||||
solvers:
|
|
||||||
- http01:
|
|
||||||
ingress:
|
|
||||||
class: traefik
|
|
||||||
EOF
|
|
||||||
kubectl apply --server-side=true -f clusterissuer.yml
|
|
||||||
```
|
|
||||||
|
|
||||||
`k3s` is configured to use [metallb](https://metallb.universe.tf) instead of the default load balancer because it does not allow for a public IP different from the `k8s` node IP.
|
#### Forgejo
|
||||||
|
|
||||||
[metallb](https://metallb.universe.tf).
|
|
||||||
|
|
||||||
```
|
|
||||||
helm install metallb --set installCRDs=true metallb/metallb
|
|
||||||
cat > metallb.yaml <<EOF
|
|
||||||
apiVersion: metallb.io/v1beta1
|
|
||||||
kind: IPAddressPool
|
|
||||||
metadata:
|
|
||||||
name: first-pool
|
|
||||||
spec:
|
|
||||||
addresses:
|
|
||||||
- 188.40.16.47/32
|
|
||||||
- 2a01:4f8:fff2:48::0/64
|
|
||||||
EOF
|
|
||||||
sleep 120 ; kubectl apply --server-side=true -f metallb.yml
|
|
||||||
```
|
|
||||||
|
|
||||||
[traefik](https://traefik.io/) requests with [annotations](https://github.com/traefik/traefik-helm-chart/blob/7a13fc8a61a6ad30fcec32eec497dab9d8aea686/traefik/values.yaml#L736) specific IPs from `metalldb`.
|
|
||||||
|
|
||||||
```
|
|
||||||
cat > traefik.yml <<EOF
|
|
||||||
apiVersion: helm.cattle.io/v1
|
|
||||||
kind: HelmChartConfig
|
|
||||||
metadata:
|
|
||||||
name: traefik
|
|
||||||
namespace: kube-system
|
|
||||||
spec:
|
|
||||||
valuesContent: |-
|
|
||||||
ports:
|
|
||||||
web:
|
|
||||||
port: 80
|
|
||||||
redirectTo:
|
|
||||||
port: websecure
|
|
||||||
priority: 1
|
|
||||||
deployment:
|
|
||||||
replicas: 2
|
|
||||||
service:
|
|
||||||
annotations:
|
|
||||||
metallb.universe.tf/allow-shared-ip: "key-to-share-188-40-16-47"
|
|
||||||
metallb.universe.tf/loadBalancerIPs: 188.40.16.47,2a01:4f8:fff2:48::2
|
|
||||||
EOF
|
|
||||||
kubectl apply --server-side=true -f traefik.yml
|
|
||||||
```
|
|
||||||
|
|
||||||
[forgejo](https://code.forgejo.org/forgejo-helm/forgejo-helm) configuration in [ingress](https://code.forgejo.org/forgejo-helm/forgejo-helm#ingress) for the reverse proxy (`traefik`) to route the domain and for the ACME issuer (`cert-manager`) to obtain a certificate. And in [service](https://code.forgejo.org/forgejo-helm/forgejo-helm#service) for the `ssh` port to be bound to the desired IPs of the load balancer (`metallb`).
|
[forgejo](https://code.forgejo.org/forgejo-helm/forgejo-helm) configuration in [ingress](https://code.forgejo.org/forgejo-helm/forgejo-helm#ingress) for the reverse proxy (`traefik`) to route the domain and for the ACME issuer (`cert-manager`) to obtain a certificate. And in [service](https://code.forgejo.org/forgejo-helm/forgejo-helm#service) for the `ssh` port to be bound to the desired IPs of the load balancer (`metallb`).
|
||||||
|
|
||||||
|
|
@ -1000,79 +920,17 @@ service:
|
||||||
type: LoadBalancer
|
type: LoadBalancer
|
||||||
annotations:
|
annotations:
|
||||||
metallb.universe.tf/loadBalancerIPs: 188.40.16.47,2a01:4f8:fff2:48::2
|
metallb.universe.tf/loadBalancerIPs: 188.40.16.47,2a01:4f8:fff2:48::2
|
||||||
metallb.universe.tf/allow-shared-ip: "key-to-share-188-40-16-47"
|
metallb.universe.tf/allow-shared-ip: "key-to-share-failover"
|
||||||
ipFamilyPolicy: PreferDualStack
|
ipFamilyPolicy: PreferDualStack
|
||||||
port: 2222
|
port: 2222
|
||||||
```
|
```
|
||||||
|
|
||||||
Define the nfs storage class.
|
### K8S NFS storage creation
|
||||||
|
|
||||||
|
Define the 20GB `forgejo-data` pvc owned by user id 1000.
|
||||||
|
|
||||||
```sh
|
```sh
|
||||||
$ cat nfs.yml
|
./setup.sh setup_k8s_pvc forgejo-data 20Gi 1000
|
||||||
apiVersion: helm.cattle.io/v1
|
|
||||||
kind: HelmChart
|
|
||||||
metadata:
|
|
||||||
name: nfs
|
|
||||||
namespace: default
|
|
||||||
spec:
|
|
||||||
chart: nfs-subdir-external-provisioner
|
|
||||||
repo: https://kubernetes-sigs.github.io/nfs-subdir-external-provisioner
|
|
||||||
targetNamespace: default
|
|
||||||
set:
|
|
||||||
nfs.server: 10.53.101.100
|
|
||||||
nfs.path: /k8s
|
|
||||||
storageClass.name: nfs
|
|
||||||
$ kubectl apply --server-side=true -f nfs.yml
|
|
||||||
$ sleep 120 ; kubectl get storageclass nfs
|
|
||||||
```
|
|
||||||
|
|
||||||
### k8s NFS storage creation
|
|
||||||
|
|
||||||
Create the directory to be used, with the expected permissions (assuing `/k8s` is the directory exported via NFS).
|
|
||||||
|
|
||||||
```sh
|
|
||||||
sudo mkdir /precious/k8s/forgejo-data
|
|
||||||
sudo chmod 1000:1000 /precious/k8s/forgejo-data
|
|
||||||
```
|
|
||||||
|
|
||||||
Define the `forgejo-data` pvc.
|
|
||||||
|
|
||||||
```sh
|
|
||||||
$ cat pv.yml
|
|
||||||
---
|
|
||||||
apiVersion: v1
|
|
||||||
kind: PersistentVolume
|
|
||||||
metadata:
|
|
||||||
name: forgejo-data
|
|
||||||
spec:
|
|
||||||
capacity:
|
|
||||||
storage: 20Gi
|
|
||||||
nfs:
|
|
||||||
server: 10.53.101.100
|
|
||||||
path: /k8s/forgejo-data
|
|
||||||
accessModes:
|
|
||||||
- ReadWriteMany
|
|
||||||
persistentVolumeReclaimPolicy: Retain
|
|
||||||
storageClassName: nfs
|
|
||||||
mountOptions:
|
|
||||||
- noatime
|
|
||||||
- nfsvers=4.2
|
|
||||||
volumeMode: Filesystem
|
|
||||||
---
|
|
||||||
apiVersion: v1
|
|
||||||
kind: PersistentVolumeClaim
|
|
||||||
metadata:
|
|
||||||
name: forgejo-data
|
|
||||||
spec:
|
|
||||||
accessModes:
|
|
||||||
- ReadWriteMany
|
|
||||||
resources:
|
|
||||||
requests:
|
|
||||||
storage: 20Gi
|
|
||||||
volumeName: forgejo-data
|
|
||||||
storageClassName: nfs
|
|
||||||
volumeMode: Filesystem
|
|
||||||
$ kubectl apply --server-side=true -f pv.yml
|
|
||||||
```
|
```
|
||||||
|
|
||||||
[Instruct the forgejo pod](https://code.forgejo.org/forgejo-helm/forgejo-helm#persistence) to use the `forgejo-data` pvc.
|
[Instruct the forgejo pod](https://code.forgejo.org/forgejo-helm/forgejo-helm#persistence) to use the `forgejo-data` pvc.
|
||||||
|
|
@ -1089,6 +947,8 @@ persistence:
|
||||||
### When a machine or disk is scheduled for replacement.
|
### When a machine or disk is scheduled for replacement.
|
||||||
|
|
||||||
* `kubectl drain hetzner05` # evacuate all the pods out of the node to be shutdown
|
* `kubectl drain hetzner05` # evacuate all the pods out of the node to be shutdown
|
||||||
|
* `kubectl taint nodes hetzner05 key1=value1:NoSchedule` # prevent any pod from being created there (metallb speaker won't be drained, for instance)
|
||||||
|
* `kubectl delete node hetzner05` # let the cluster know it no longer exists so a new one by the same name can replace it
|
||||||
|
|
||||||
### Routing the failover IP
|
### Routing the failover IP
|
||||||
|
|
||||||
|
|
|
||||||
14
k3s-host/certmanager.yml
Normal file
14
k3s-host/certmanager.yml
Normal file
|
|
@ -0,0 +1,14 @@
|
||||||
|
apiVersion: cert-manager.io/v1
|
||||||
|
kind: ClusterIssuer
|
||||||
|
metadata:
|
||||||
|
name: letsencrypt-http
|
||||||
|
spec:
|
||||||
|
acme:
|
||||||
|
email: contact@forgejo.org
|
||||||
|
server: https://acme-v02.api.letsencrypt.org/directory
|
||||||
|
privateKeySecretRef:
|
||||||
|
name: letsencrypt-http
|
||||||
|
solvers:
|
||||||
|
- http01:
|
||||||
|
ingress:
|
||||||
|
class: traefik
|
||||||
8
k3s-host/metallb.yml
Normal file
8
k3s-host/metallb.yml
Normal file
|
|
@ -0,0 +1,8 @@
|
||||||
|
apiVersion: metallb.io/v1beta1
|
||||||
|
kind: IPAddressPool
|
||||||
|
metadata:
|
||||||
|
name: first-pool
|
||||||
|
spec:
|
||||||
|
addresses:
|
||||||
|
- $failover_ipv4/$failover_ipv4_range
|
||||||
|
- $failover_ipv6/$failover_ipv6_range
|
||||||
13
k3s-host/nfs.yml
Normal file
13
k3s-host/nfs.yml
Normal file
|
|
@ -0,0 +1,13 @@
|
||||||
|
apiVersion: helm.cattle.io/v1
|
||||||
|
kind: HelmChart
|
||||||
|
metadata:
|
||||||
|
name: nfs
|
||||||
|
namespace: default
|
||||||
|
spec:
|
||||||
|
chart: nfs-subdir-external-provisioner
|
||||||
|
repo: https://kubernetes-sigs.github.io/nfs-subdir-external-provisioner
|
||||||
|
targetNamespace: default
|
||||||
|
set:
|
||||||
|
nfs.server: $node_nfs_server
|
||||||
|
nfs.path: /k8s
|
||||||
|
storageClass.name: nfs
|
||||||
33
k3s-host/pvc.yml
Normal file
33
k3s-host/pvc.yml
Normal file
|
|
@ -0,0 +1,33 @@
|
||||||
|
---
|
||||||
|
apiVersion: v1
|
||||||
|
kind: PersistentVolume
|
||||||
|
metadata:
|
||||||
|
name: $pvc_name
|
||||||
|
spec:
|
||||||
|
capacity:
|
||||||
|
storage: $pvc_capacity
|
||||||
|
nfs:
|
||||||
|
server: $node_nfs_server
|
||||||
|
path: /k8s/$pvc_name
|
||||||
|
accessModes:
|
||||||
|
- ReadWriteMany
|
||||||
|
persistentVolumeReclaimPolicy: Retain
|
||||||
|
storageClassName: nfs
|
||||||
|
mountOptions:
|
||||||
|
- noatime
|
||||||
|
- nfsvers=4.2
|
||||||
|
volumeMode: Filesystem
|
||||||
|
---
|
||||||
|
apiVersion: v1
|
||||||
|
kind: PersistentVolumeClaim
|
||||||
|
metadata:
|
||||||
|
name: $pvc_name
|
||||||
|
spec:
|
||||||
|
accessModes:
|
||||||
|
- ReadWriteMany
|
||||||
|
resources:
|
||||||
|
requests:
|
||||||
|
storage: $pvc_capacity
|
||||||
|
volumeName: $pvc_name
|
||||||
|
storageClassName: nfs
|
||||||
|
volumeMode: Filesystem
|
||||||
4
k3s-host/secrets.sh.example
Normal file
4
k3s-host/secrets.sh.example
Normal file
|
|
@ -0,0 +1,4 @@
|
||||||
|
node_drbd_shared_secret=***
|
||||||
|
node_k8s_token=none
|
||||||
|
|
||||||
|
|
||||||
224
k3s-host/setup.sh
Executable file
224
k3s-host/setup.sh
Executable file
|
|
@ -0,0 +1,224 @@
|
||||||
|
#!/bin/bash
|
||||||
|
|
||||||
|
SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
|
||||||
|
if ${VERBOSE:-false}; then
|
||||||
|
set -ex
|
||||||
|
PS4='${BASH_SOURCE[0]}:$LINENO: ${FUNCNAME[0]}: '
|
||||||
|
else
|
||||||
|
set -e
|
||||||
|
fi
|
||||||
|
|
||||||
|
source $SELF_DIR/variables.sh
|
||||||
|
source $SELF_DIR/secrets.sh
|
||||||
|
|
||||||
|
set -o pipefail
|
||||||
|
|
||||||
|
self_node=$(hostname | sed -e 's/hetzner0//')
|
||||||
|
interface=${node_interface[$self_node]}
|
||||||
|
|
||||||
|
dependencies="retry etckeeper"
|
||||||
|
|
||||||
|
if ! which $dependencies >&/dev/null; then
|
||||||
|
sudo apt-get -q install -qq -y $dependencies
|
||||||
|
fi
|
||||||
|
|
||||||
|
function setup_ufw() {
|
||||||
|
sudo apt-get -q install -qq -y ufw
|
||||||
|
|
||||||
|
sudo ufw --force reset
|
||||||
|
|
||||||
|
sudo ufw default allow incoming
|
||||||
|
sudo ufw default allow outgoing
|
||||||
|
sudo ufw default allow routed
|
||||||
|
|
||||||
|
for from in $nodes; do
|
||||||
|
for to in $nodes; do
|
||||||
|
if test $from != $to; then
|
||||||
|
for v in ipv4 ipv6; do
|
||||||
|
eval from_ip=\${node_$v[$from]}
|
||||||
|
eval to_ip=\${node_$v[$to]}
|
||||||
|
sudo ufw allow in on $interface from $from_ip to $to_ip
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
done
|
||||||
|
|
||||||
|
for host_ip in ${node_ipv4[$self_node]} ${node_ipv6[$self_node]}; do
|
||||||
|
sudo ufw allow in on $interface to $host_ip port 22 proto tcp
|
||||||
|
sudo ufw deny in on $interface log-all to $host_ip
|
||||||
|
done
|
||||||
|
|
||||||
|
for public_ip in $failover_ipv4 $failover_ipv6; do
|
||||||
|
sudo ufw allow in on $interface to $public_ip port 22,80,443,2000:3000 proto tcp
|
||||||
|
sudo ufw deny in on $interface log-all to $public_ip
|
||||||
|
done
|
||||||
|
|
||||||
|
sudo ufw enable
|
||||||
|
sudo systemctl start ufw
|
||||||
|
sudo systemctl enable ufw
|
||||||
|
sudo ufw status verbose
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_drbd() {
|
||||||
|
if ! test -f /etc/network/interfaces.d/drbd; then
|
||||||
|
cat <<EOF | sudo tee /etc/network/interfaces.d/drbd
|
||||||
|
auto $interface.$node_drbd_vlan
|
||||||
|
iface $interface.$node_drbd_vlan inet static
|
||||||
|
address $node_drbd_ipv4_prefix.$self_node
|
||||||
|
netmask 255.255.255.0
|
||||||
|
vlan-raw-device $interface
|
||||||
|
mtu 1400
|
||||||
|
EOF
|
||||||
|
sudo ifup $interface.$node_drbd_vlan
|
||||||
|
fi
|
||||||
|
sudo apt-get install -y drbd-utils
|
||||||
|
res_file=/etc/drbd.d/$node_drbd_resource.res
|
||||||
|
if ! sudo test -f $res_file; then
|
||||||
|
(
|
||||||
|
cat <<EOF
|
||||||
|
resource $node_drbd_resource {
|
||||||
|
net {
|
||||||
|
# A : write completion is determined when data is written to the local disk and the local TCP transmission buffer
|
||||||
|
# B : write completion is determined when data is written to the local disk and remote buffer cache
|
||||||
|
# C : write completion is determined when data is written to both the local disk and the remote disk
|
||||||
|
protocol C;
|
||||||
|
cram-hmac-alg sha1;
|
||||||
|
# any secret key for authentication among nodes
|
||||||
|
shared-secret "$node_drbd_shared_secret";
|
||||||
|
}
|
||||||
|
disk {
|
||||||
|
resync-rate 100M;
|
||||||
|
}
|
||||||
|
EOF
|
||||||
|
for node in $nodes; do
|
||||||
|
cat <<EOF
|
||||||
|
on hetzner0$node {
|
||||||
|
address $node_drbd_ipv4_prefix.$node:7788;
|
||||||
|
volume 0 {
|
||||||
|
device /dev/drbd0;
|
||||||
|
disk ${node_drbd_device[$node]};
|
||||||
|
meta-disk internal;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
EOF
|
||||||
|
done
|
||||||
|
cat <<EOF
|
||||||
|
}
|
||||||
|
EOF
|
||||||
|
) | sudo tee $res_file
|
||||||
|
fi
|
||||||
|
if ! sudo drbdadm status $node_drbd_resource >&/dev/null; then
|
||||||
|
sudo drbdadm create-md $node_drbd_resource
|
||||||
|
sudo systemctl enable drbd
|
||||||
|
sudo systemctl start drbd
|
||||||
|
fi
|
||||||
|
if ! grep --quiet '^/dev/drbd0 /precious' /etc/fstab; then
|
||||||
|
echo /dev/drbd0 /precious ext4 noauto,noatime,defaults 0 0 | sudo tee -a /etc/fstab
|
||||||
|
sudo mkdir -p /precious
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_nfs() {
|
||||||
|
sudo apt-get install -y nfs-kernel-server nfs-common
|
||||||
|
|
||||||
|
if ! test -f /etc/network/interfaces.d/nfs; then
|
||||||
|
cat <<EOF | sudo tee /etc/network/interfaces.d/nfs
|
||||||
|
auto $interface.$node_nfs_vlan
|
||||||
|
iface $interface.$node_nfs_vlan inet static
|
||||||
|
address $node_nfs_ipv4_prefix.$self_node
|
||||||
|
netmask 255.255.255.0
|
||||||
|
vlan-raw-device $interface
|
||||||
|
mtu 1400
|
||||||
|
EOF
|
||||||
|
sudo ifup $interface.$node_nfs_vlan
|
||||||
|
fi
|
||||||
|
if ! grep --quiet '^/precious' /etc/exports; then
|
||||||
|
cat <<EOF | sudo tee -a /etc/exports
|
||||||
|
/precious $node_nfs_ipv4_prefix.0/24(rw,fsid=0,no_root_squash,no_subtree_check)
|
||||||
|
/precious/k8s $node_nfs_ipv4_prefix.0/24(rw,nohide,insecure,no_subtree_check)
|
||||||
|
EOF
|
||||||
|
sudo exportfs -va || true # it does not matter if the expored dirs do not exist, they will
|
||||||
|
sudo exportfs -s
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s() {
|
||||||
|
existing=$1
|
||||||
|
|
||||||
|
if ! test -f /etc/network/interfaces.d/k8s; then
|
||||||
|
cat <<EOF | sudo tee /etc/network/interfaces.d/k8s
|
||||||
|
auto $interface.$node_k8s_vlan
|
||||||
|
iface $interface.$node_k8s_vlan inet static
|
||||||
|
address $node_k8s_ipv4_prefix.$self_node
|
||||||
|
netmask 255.255.0.0
|
||||||
|
vlan-raw-device $interface
|
||||||
|
mtu 1400
|
||||||
|
up ip addr add $node_k8s_ipv6_prefix::$self_node/48 dev $interface.$node_k8s_vlan
|
||||||
|
up ip addr add $failover_ipv4/$failover_ipv4_range dev $interface
|
||||||
|
up ip addr add $failover_ipv6/$failover_ipv6_range dev $interface
|
||||||
|
EOF
|
||||||
|
sudo ifup $interface.$node_k8s_vlan
|
||||||
|
fi
|
||||||
|
if ! grep --quiet 'export KUBECONFIG' ~/.bashrc; then
|
||||||
|
echo "export KUBECONFIG=/etc/rancher/k3s/k3s.yaml" >>~/.bashrc
|
||||||
|
fi
|
||||||
|
if ! sudo systemctl --quiet is-active k3s; then
|
||||||
|
args=""
|
||||||
|
if test "$existing"; then
|
||||||
|
if ! test "$node_k8s_token"; then
|
||||||
|
echo "obtain the token from node $existing with sudo cat /var/lib/rancher/k3s/server/token and set node_k8s_token= in secrets.sh"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
args="$args --token $node_k8s_token --server https://$node_k8s_ipv4_prefix.$existing:6443"
|
||||||
|
fi
|
||||||
|
if test "$self_node" = $node_k8s_etcd; then
|
||||||
|
args="$args --disable-apiserver --disable-controller-manager --disable-scheduler"
|
||||||
|
fi
|
||||||
|
curl -fL https://get.k3s.io | sh -s - server $args --cluster-init --disable=servicelb --write-kubeconfig-mode=644 --node-ip=$node_k8s_ipv4_prefix.$self_node,$node_k8s_ipv6_prefix::$self_node $node_k8s_cidr --flannel-ipv6-masq
|
||||||
|
if test "$self_node" = $node_k8s_etcd; then
|
||||||
|
retry --times 20 -- kubectl taint nodes $(hostname) key1=value1:NoSchedule
|
||||||
|
fi
|
||||||
|
if test "$self_node" != $node_k8s_etcd; then
|
||||||
|
curl -fsSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash -
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_apply() {
|
||||||
|
retry --delay 30 --times 10 -- bash -c "$SELF_DIR/subst.sh $1 | kubectl apply --server-side=true -f -"
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_traefik() {
|
||||||
|
setup_k8s_apply traefik.yml
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_nfs() {
|
||||||
|
setup_k8s_apply nfs.yml
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_metallb() {
|
||||||
|
helm repo add metallb https://metallb.github.io/metallb
|
||||||
|
helm upgrade --install metallb --set installCRDs=true metallb/metallb
|
||||||
|
setup_k8s_apply metallb.yml
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_certmanager() {
|
||||||
|
helm upgrade --install mycertmanager --set installCRDs=true oci://registry-1.docker.io/bitnamicharts/cert-manager
|
||||||
|
setup_k8s_apply certmanager.yml
|
||||||
|
}
|
||||||
|
|
||||||
|
function setup_k8s_pvc() {
|
||||||
|
export pvc_name=$1
|
||||||
|
export pvc_capacity=$2
|
||||||
|
export pvc_owner=$3
|
||||||
|
|
||||||
|
sudo mount -o nfsvers=4.2 $node_nfs_server:/k8s /opt
|
||||||
|
sudo mkdir -p /opt/$pvc_name
|
||||||
|
sudo chown $pvc_owner:$pvc_owner /opt/$pvc_name
|
||||||
|
sudo umount /opt
|
||||||
|
|
||||||
|
setup_k8s_apply pvc.yml
|
||||||
|
}
|
||||||
|
|
||||||
|
"$@"
|
||||||
10
k3s-host/subst.sh
Executable file
10
k3s-host/subst.sh
Executable file
|
|
@ -0,0 +1,10 @@
|
||||||
|
#!/bin/bash
|
||||||
|
|
||||||
|
SELF_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
|
||||||
|
source $SELF_DIR/variables.sh
|
||||||
|
|
||||||
|
eval "cat <<EOF
|
||||||
|
$(<$1)
|
||||||
|
EOF
|
||||||
|
"
|
||||||
19
k3s-host/traefik.yml
Normal file
19
k3s-host/traefik.yml
Normal file
|
|
@ -0,0 +1,19 @@
|
||||||
|
apiVersion: helm.cattle.io/v1
|
||||||
|
kind: HelmChartConfig
|
||||||
|
metadata:
|
||||||
|
name: traefik
|
||||||
|
namespace: kube-system
|
||||||
|
spec:
|
||||||
|
valuesContent: |-
|
||||||
|
ports:
|
||||||
|
web:
|
||||||
|
port: 80
|
||||||
|
redirectTo:
|
||||||
|
port: websecure
|
||||||
|
priority: 1
|
||||||
|
deployment:
|
||||||
|
replicas: 2
|
||||||
|
service:
|
||||||
|
annotations:
|
||||||
|
metallb.universe.tf/allow-shared-ip: "key-to-share-failover"
|
||||||
|
metallb.universe.tf/loadBalancerIPs: $failover_ipv4,$failover_ipv6
|
||||||
42
k3s-host/variables.sh.example
Executable file
42
k3s-host/variables.sh.example
Executable file
|
|
@ -0,0 +1,42 @@
|
||||||
|
#!/bin/bash
|
||||||
|
|
||||||
|
nodes="5 6"
|
||||||
|
|
||||||
|
node_interface=(
|
||||||
|
[3]=enp5s0
|
||||||
|
[5]=enp5s0
|
||||||
|
[6]=enp5s0
|
||||||
|
)
|
||||||
|
|
||||||
|
node_ipv4=(
|
||||||
|
[5]=88.198.58.177
|
||||||
|
[6]=65.108.204.171
|
||||||
|
)
|
||||||
|
|
||||||
|
node_ipv6=(
|
||||||
|
[5]=2a01:4f8:222:507::2
|
||||||
|
[6]=2a01:4f9:1a:a082::2
|
||||||
|
)
|
||||||
|
|
||||||
|
failover_ipv4=188.40.16.47
|
||||||
|
failover_ipv4_range=32
|
||||||
|
failover_ipv6=2a01:4f8:fff2:48::2
|
||||||
|
failover_ipv6_range=48
|
||||||
|
|
||||||
|
node_drbd_vlan=4000
|
||||||
|
node_drbd_resource=r1
|
||||||
|
node_drbd_ipv4_prefix=10.53.100
|
||||||
|
node_drbd_device=(
|
||||||
|
[5]=/dev/nvme0n1
|
||||||
|
[6]=/dev/nvme0n1
|
||||||
|
)
|
||||||
|
|
||||||
|
node_nfs_vlan=4001
|
||||||
|
node_nfs_ipv4_prefix=10.53.101
|
||||||
|
node_nfs_server=$node_nfs_ipv4_prefix.100
|
||||||
|
|
||||||
|
node_k8s_vlan=4002
|
||||||
|
node_k8s_ipv4_prefix=10.88.1
|
||||||
|
node_k8s_ipv6_prefix=fd10
|
||||||
|
node_k8s_cidr="--cluster-cidr=10.42.0.0/16,fd01::/48 --service-cidr=10.43.0.0/16,fd02::/112"
|
||||||
|
node_k8s_etcd=3
|
||||||
Loading…
Reference in a new issue