added kustomization backup

.gitignore

@@ -7,3 +7,5 @@ terraform.tfvars
 plans-custom.yaml
 traefik-custom.yaml
 kured-custom.yaml
+kustomization.yaml
+kustomization_backup.yaml

README.md

@@ -114,25 +114,38 @@ Otherwise, it's essential to turn off automatic OS upgrades (k3s can continue to
 
 ## Automatic Upgrade
 
+### The Default Setting
+
 By default, MicroOS gets upgraded automatically on each node and reboot safely via [Kured](https://github.com/weaveworks/kured) installed in the cluster.
 
 As for k3s, it also automatically upgrades thanks to Rancher's [system upgrade controller](https://github.com/rancher/system-upgrade-controller). By default, it follows the k3s `stable` channel, but you can also change to the `latest` one if needed or specify a target version to upgrade to via the upgrade plan.
 
 You can copy and modify the [one in the templates](https://github.com/kube-hetzner/kube-hetzner/blob/master/templates/plans.yaml.tpl) for that! More on the subject in [k3s upgrades](https://rancher.com/docs/k3s/latest/en/upgrades/basic/).
 
-_If you wish to turn off automatic MicroOS upgrades on a specific node, you need to ssh into it and issue the following command:_
+### Turning Off Automatic Upgrade
+
+_If you wish to turn off automatic MicroOS upgrades (Important if you are not launching an HA setup which requires at least 3 control-plane nodes), you need to ssh into each node and issue the following command:_
 
 ```sh
 systemctl --now disable transactional-update.timer
 
 ```
 
-_To turn off k3s upgrades, you can either set the `k3s_upgrade=true` label in the node you want or set it to `false`. To remove it, apply:_
+_To turn off k3s upgrades, you can either remove the `k3s_upgrade=true` label or set it to `false`. This needs to happen for all the nodes too! To remove it, apply:_
 
 ```sh
 kubectl -n system-upgrade label node <node-name> k3s_upgrade-
 ```
 
+### Individual Components Upgrade
+
+Rarely needed, but can be handy in the long run. During the installation, we automatically download a backup of the kustomization to a `kustomization_backup.yaml` file. You will find it next to your `kubeconfig.yaml` at the root of your project.
+
+1. First create a duplicate of that file and name it `kustomization.yaml`, keeping the original file intact, in case you need to restore the old config.
+2. Edit the `kustomization.yaml` file; you want to go to the very bottom where you have the links to the different source files; grab the latest versions for each on Github, and replace.
+3. If present, remove any local reference to `traefik_config.yaml`, as Traefik is updated automatically by the system upgrade controller.
+4. Apply the the updated `kustomization.yaml` with `kubectl apply -k ./`.
+
 ## Examples
 
 <details>

init.tf

@@ -40,7 +40,7 @@ resource "null_resource" "first_control_plane" {
     inline = [
       "systemctl start k3s",
       # prepare the post_install directory
-      "mkdir -p /tmp/post_install",
+      "mkdir -p /var/post_install",
       # wait for k3s to become ready
       <<-EOT
       timeout 120 bash <<EOF
@@ -85,7 +85,7 @@ resource "null_resource" "kustomization" {
         "https://raw.githubusercontent.com/hetznercloud/csi-driver/${local.csi_version}/deploy/kubernetes/hcloud-csi.yml",
         "https://github.com/weaveworks/kured/releases/download/${local.kured_version}/kured-${local.kured_version}-dockerhub.yaml",
         "https://raw.githubusercontent.com/rancher/system-upgrade-controller/master/manifests/system-upgrade-controller.yaml",
-        ], local.is_single_node_cluster ? [] : var.traefik_enabled ? ["traefik.yaml"] : []
+        ], local.is_single_node_cluster ? [] : var.traefik_enabled ? ["traefik_config.yaml"] : []
       , var.cni_plugin == "calico" ? ["https://projectcalico.docs.tigera.io/manifests/calico.yaml"] : []),
       patchesStrategicMerge = concat([
         file("${path.module}/kustomize/kured.yaml"),
@@ -93,7 +93,7 @@ resource "null_resource" "kustomization" {
         file("${path.module}/kustomize/system-upgrade-controller.yaml")
       ], var.cni_plugin == "calico" ? [file("${path.module}/kustomize/calico.yaml")] : [])
     })
-    destination = "/tmp/post_install/kustomization.yaml"
+    destination = "/var/post_install/kustomization.yaml"
   }
 
   # Upload traefik config
@@ -109,7 +109,7 @@ resource "null_resource" "kustomization" {
         traefik_acme_email         = var.traefik_acme_email
         traefik_additional_options = var.traefik_additional_options
     })
-    destination = "/tmp/post_install/traefik.yaml"
+    destination = "/var/post_install/traefik_config.yaml"
   }
 
   # Upload the system upgrade controller plans config
@@ -119,7 +119,7 @@ resource "null_resource" "kustomization" {
       {
         channel = var.initial_k3s_channel
     })
-    destination = "/tmp/post_install/plans.yaml"
+    destination = "/var/post_install/plans.yaml"
   }
 
   # Deploy secrets, logging is automatically disabled due to sensitive variables
@@ -143,11 +143,11 @@ resource "null_resource" "kustomization" {
       # replace lines like "- |3" by "- |" (yaml block syntax).
       # due to indendation this should not changes the embedded
       # manifests themselves
-      "sed -i 's/^- |[0-9]\\+$/- |/g' /tmp/post_install/kustomization.yaml",
+      "sed -i 's/^- |[0-9]\\+$/- |/g' /var/post_install/kustomization.yaml",
-      "kubectl apply -k /tmp/post_install",
+      "kubectl apply -k /var/post_install",
       "echo 'Waiting for the system-upgrade-controller deployment to become available...'",
       "kubectl -n system-upgrade wait --for=condition=available --timeout=120s deployment/system-upgrade-controller",
-      "kubectl -n system-upgrade apply -f /tmp/post_install/plans.yaml"
+      "kubectl -n system-upgrade apply -f /var/post_install/plans.yaml"
       ],
       local.is_single_node_cluster || var.traefik_enabled == false ? [] : [<<-EOT
       timeout 120 bash <<EOF

kustomization_backup.tf

@@ -0,0 +1,18 @@
+data "remote_file" "kustomization_backup" {
+  conn {
+    host        = module.control_planes[keys(module.control_planes)[0]].ipv4_address
+    port        = 22
+    user        = "root"
+    private_key = local.ssh_private_key
+    agent       = var.private_key == null
+  }
+  path = "/var/post_install/kustomization.yaml"
+
+  depends_on = [null_resource.kustomization]
+}
+
+resource "local_file" "kustomization_backup" {
+  content         = data.remote_file.kustomization_backup.content
+  filename        = "kustomization_backup.yaml"
+  file_permission = "600"
+}

locals.tf

@@ -1,9 +1,4 @@
 locals {
-  # if we are in a single cluster config, we use the default klipper lb instead of Hetzner LB
-  total_node_count       = sum(concat([for v in var.control_plane_nodepools : v.count], [0])) + sum(concat([for v in var.agent_nodepools : v.count], [0]))
-  control_plane_count    = sum(concat([for v in var.control_plane_nodepools : v.count], [0]))
-  agent_count            = sum(concat([for v in var.agent_nodepools : v.count], [0]))
-  is_single_node_cluster = local.total_node_count == 1
   ssh_public_key = trimspace(file(var.public_key))
   # ssh_private_key is either the contents of var.private_key or null to use a ssh agent.
   ssh_private_key = var.private_key == null ? null : trimspace(file(var.private_key))
@@ -20,6 +15,73 @@ locals {
   csi_version   = var.hetzner_csi_version != null ? var.hetzner_csi_version : data.github_release.hetzner_csi.release_tag
   kured_version = data.github_release.kured.release_tag
 
+  common_commands_install_k3s = [
+    "set -ex",
+    # prepare the k3s config directory
+    "mkdir -p /etc/rancher/k3s",
+    # move the config file into place
+    "mv /tmp/config.yaml /etc/rancher/k3s/config.yaml",
+    # if the server has already been initialized just stop here
+    "[ -e /etc/rancher/k3s/k3s.yaml ] && exit 0",
+  ]
+
+  apply_k3s_selinux = ["/sbin/semodule -v -i /usr/share/selinux/packages/k3s.pp"]
+
+  install_k3s_server = concat(local.common_commands_install_k3s, ["curl -sfL https://get.k3s.io | INSTALL_K3S_SKIP_START=true INSTALL_K3S_SKIP_SELINUX_RPM=true INSTALL_K3S_CHANNEL=${var.initial_k3s_channel} INSTALL_K3S_EXEC=server sh -"], local.apply_k3s_selinux)
+  install_k3s_agent  = concat(local.common_commands_install_k3s, ["curl -sfL https://get.k3s.io | INSTALL_K3S_SKIP_START=true INSTALL_K3S_SKIP_SELINUX_RPM=true INSTALL_K3S_CHANNEL=${var.initial_k3s_channel} INSTALL_K3S_EXEC=agent sh -"], local.apply_k3s_selinux)
+
+  control_plane_nodes = merge([
+    for pool_index, nodepool_obj in var.control_plane_nodepools : {
+      for node_index in range(nodepool_obj.count) :
+      format("%s-%s-%s", pool_index, node_index, nodepool_obj.name) => {
+        nodepool_name : nodepool_obj.name,
+        server_type : nodepool_obj.server_type,
+        location : nodepool_obj.location,
+        labels : concat(local.default_control_plane_labels, nodepool_obj.labels),
+        taints : concat(local.default_control_plane_taints, nodepool_obj.taints),
+        index : node_index
+      }
+    }
+  ]...)
+
+  agent_nodes = merge([
+    for pool_index, nodepool_obj in var.agent_nodepools : {
+      for node_index in range(nodepool_obj.count) :
+      format("%s-%s-%s", pool_index, node_index, nodepool_obj.name) => {
+        nodepool_name : nodepool_obj.name,
+        server_type : nodepool_obj.server_type,
+        location : nodepool_obj.location,
+        labels : concat(local.default_agent_labels, nodepool_obj.labels),
+        taints : nodepool_obj.taints,
+        index : node_index
+      }
+    }
+  ]...)
+
+  # The main network cidr that all subnets will be created upon
+  network_ipv4_cidr = "10.0.0.0/8"
+
+  # The first two subnets are respectively the default subnet 10.0.0.0/16 use for potientially anything and 10.1.0.0/16 used for control plane nodes.
+  # the rest of the subnets are for agent nodes in each nodepools.
+  network_ipv4_subnets = [for index in range(256) : cidrsubnet(local.network_ipv4_cidr, 8, index)]
+
+  # if we are in a single cluster config, we use the default klipper lb instead of Hetzner LB
+  control_plane_count    = sum([for v in var.control_plane_nodepools : v.count])
+  agent_count            = sum([for v in var.agent_nodepools : v.count])
+  is_single_node_cluster = local.control_plane_count + local.agent_count == 1
+
+  # disable k3s extras
+  disable_extras = concat(["local-storage"], local.is_single_node_cluster ? [] : ["servicelb"], var.traefik_enabled ? [] : ["traefik"], var.metrics_server_enabled ? [] : ["metrics-server"])
+
+  # Default k3s node labels
+  default_agent_labels         = concat([], var.automatically_upgrade_k3s ? ["k3s_upgrade=true"] : [])
+  default_control_plane_labels = concat([], var.automatically_upgrade_k3s ? ["k3s_upgrade=true"] : [])
+
+  allow_scheduling_on_control_plane = local.is_single_node_cluster ? true : var.allow_scheduling_on_control_plane
+
+  # Default k3s node taints
+  default_control_plane_taints = concat([], local.allow_scheduling_on_control_plane ? [] : ["node-role.kubernetes.io/master:NoSchedule"])
+
   # The following IPs are important to be whitelisted because they communicate with Hetzner services and enable the CCM and CSI to work properly.
   # Source https://github.com/hetznercloud/csi-driver/issues/204#issuecomment-848625566
   hetzner_metadata_service_ipv4 = "169.254.169.254/32"
@@ -156,66 +218,4 @@ locals {
       ]
     }
   ])
-
-  common_commands_install_k3s = [
-    "set -ex",
-    # prepare the k3s config directory
-    "mkdir -p /etc/rancher/k3s",
-    # move the config file into place
-    "mv /tmp/config.yaml /etc/rancher/k3s/config.yaml",
-    # if the server has already been initialized just stop here
-    "[ -e /etc/rancher/k3s/k3s.yaml ] && exit 0",
-  ]
-
-  apply_k3s_selinux = ["/sbin/semodule -v -i /usr/share/selinux/packages/k3s.pp"]
-
-  install_k3s_server = concat(local.common_commands_install_k3s, ["curl -sfL https://get.k3s.io | INSTALL_K3S_SKIP_START=true INSTALL_K3S_SKIP_SELINUX_RPM=true INSTALL_K3S_CHANNEL=${var.initial_k3s_channel} INSTALL_K3S_EXEC=server sh -"], local.apply_k3s_selinux)
-  install_k3s_agent  = concat(local.common_commands_install_k3s, ["curl -sfL https://get.k3s.io | INSTALL_K3S_SKIP_START=true INSTALL_K3S_SKIP_SELINUX_RPM=true INSTALL_K3S_CHANNEL=${var.initial_k3s_channel} INSTALL_K3S_EXEC=agent sh -"], local.apply_k3s_selinux)
-
-  control_plane_nodes = merge([
-    for pool_index, nodepool_obj in var.control_plane_nodepools : {
-      for node_index in range(nodepool_obj.count) :
-      format("%s-%s-%s", pool_index, node_index, nodepool_obj.name) => {
-        nodepool_name : nodepool_obj.name,
-        server_type : nodepool_obj.server_type,
-        location : nodepool_obj.location,
-        labels : concat(local.default_control_plane_labels, nodepool_obj.labels),
-        taints : concat(local.default_control_plane_taints, nodepool_obj.taints),
-        index : node_index
-      }
-    }
-  ]...)
-
-  agent_nodes = merge([
-    for pool_index, nodepool_obj in var.agent_nodepools : {
-      for node_index in range(nodepool_obj.count) :
-      format("%s-%s-%s", pool_index, node_index, nodepool_obj.name) => {
-        nodepool_name : nodepool_obj.name,
-        server_type : nodepool_obj.server_type,
-        location : nodepool_obj.location,
-        labels : concat(local.default_agent_labels, nodepool_obj.labels),
-        taints : nodepool_obj.taints,
-        index : node_index
-      }
-    }
-  ]...)
-
-  # The main network cidr that all subnets will be created upon
-  network_ipv4_cidr = "10.0.0.0/8"
-
-  # The first two subnets are respectively the default subnet 10.0.0.0/16 use for potientially anything and 10.1.0.0/16 used for control plane nodes.
-  # the rest of the subnets are for agent nodes in each nodepools.
-  network_ipv4_subnets = [for index in range(256) : cidrsubnet(local.network_ipv4_cidr, 8, index)]
-
-  # disable k3s extras
-  disable_extras = concat(["local-storage"], local.is_single_node_cluster ? [] : ["servicelb"], var.traefik_enabled ? [] : ["traefik"], var.metrics_server_enabled ? [] : ["metrics-server"])
-
-  # Default k3s node labels
-  default_agent_labels         = concat([], var.automatically_upgrade_k3s ? ["k3s_upgrade=true"] : [])
-  default_control_plane_labels = concat([], var.automatically_upgrade_k3s ? ["k3s_upgrade=true"] : [])
-
-  allow_scheduling_on_control_plane = local.is_single_node_cluster ? true : var.allow_scheduling_on_control_plane
-
-  # Default k3s node taints
-  default_control_plane_taints = concat([], local.allow_scheduling_on_control_plane ? [] : ["node-role.kubernetes.io/master:NoSchedule"])
 }

terraform.tfvars.example

@@ -33,7 +33,7 @@ network_region   = "eu-central" # change to `us-east` if location is ash
 # Also, before decreasing the count of any nodepools to 0, it's essential to drain and cordon the nodes in question. Otherwise, it will leave your cluster in a bad state.
 
 # Before initializing the cluster, you can change all parameters and add or remove any nodepools. You need at least one nodepool of each kind, control plane, and agent.
-# The nodepool names are entirely arbitrary, you can choose whatever you want, but no special characters or underscore; only alphanumeric characters and dashes are allowed.
+# The nodepool names are entirely arbitrary, you can choose whatever you want, but no special characters or underscore, and they must be unique; only alphanumeric characters and dashes are allowed.
 
 # If you want to have a single node cluster, have one control plane nodepools with a count of 1, and one agent nodepool with a count of 0.
 
@@ -108,11 +108,13 @@ load_balancer_location = "fsn1"
 # hetzner_csi_version = ""
 
 
-# If you want to use letsencrypt with tls Challenge, the email address is used to send you certificates expiration notices
+# We give you the possibility to use letsencrypt directly with Traefik because it's an easy setup, however it's not optimal,
+# as the free version of Traefik causes a little bit of downtime when when the certificates get renewed. For proper SSL management,
+# we instead recommend you to use cert-manager, that you can easily deploy with helm; see https://cert-manager.io/.
 # traefik_acme_tls = true
 # traefik_acme_email = "mail@example.com"
 
-# If you want to disable the Traefik ingress controller, you can. Default is "true".
+# If you want to disable the Traefik ingress controller, you can can set this to "false". Default is "true".
 # traefik_enabled = false
 
 # If you want to disable the metric server, you can! Default is "true".
@@ -162,6 +164,8 @@ load_balancer_location = "fsn1"
 
 # If you want to configure a different CNI for k3s, use this flag
 # possible values: flannel (Default), calico
+# Cilium or other would be easy to add, you can mirror how Calico was added. PRs are welcome!
+# CAVEATS: Calico is not supported for single node setups, because of the following issue https://github.com/k3s-io/klipper-lb/issues/6.
 # cni_plugin = "calico"
 
 # If you want to disable the k3s default network policy controller, use this flag