Update docs to mention components

* With the new component system, these components can be managed
independent from the cluster and rolled or edited in advanced
ways

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,10 +0,0 @@
-High level description of the change.
-
-* Specific change
-* Specific change
-
-## Testing
-
-Describe your work to validate the change works.
-
-rel: issue number (if applicable)

.github/dependabot.yaml

@@ -4,6 +4,3 @@ updates:
   directory: "/"
   schedule:
     interval: weekly
-  pull-request-branch-name:
-    separator: "-"
-  open-pull-requests-limit: 3

.github/release.yaml

@@ -0,0 +1,12 @@
+changelog:
+  categories:
+    - title: Contributions
+      labels:
+        - '*'
+      exclude:
+        labels:
+          - dependencies
+          - no-release-note
+    - title: Dependencies
+      labels:
+        - dependencies

.github/workflows/publish.yaml

@@ -0,0 +1,12 @@
+name: publish
+on:
+  push:
+    branches:
+      - release-docs
+jobs:
+  mkdocs:
+    name: mkdocs
+    uses: poseidon/matchbox/.github/workflows/mkdocs-pages.yaml@main
+    # Add content write for GitHub Pages
+    permissions:
+      contents: write

.gitignore

@@ -0,0 +1,2 @@
+site/
+venv/

CHANGES.md

@@ -4,6 +4,388 @@ Notable changes between versions.
 
 ## Latest
 
+## v1.30.1
+
+* Kubernetes [v1.30.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.30.md#v1301)
+* Add firewall rules and security group rules for Cilium and Hubble metrics ([#1449](https://github.com/poseidon/typhoon/pull/1449))
+* Update Cilium from v1.15.3 to [v1.15.5](https://github.com/cilium/cilium/releases/tag/v1.15.5)
+* Update flannel from v0.24.4 to [v0.25.1](https://github.com/flannel-io/flannel/releases/tag/v0.25.1)
+* Introduce `components` variabe to enable/disable/configure pre-installed components ([#1453](https://github.com/poseidon/typhoon/pull/1453))
+* Add Terraform modules for `coredns`, `cilium`, and `flannel` components
+
+### Azure
+
+* Add `controller_security_group_name` output for adding custom security rules ([#1450](https://github.com/poseidon/typhoon/pull/1450))
+* Add `controller_address_prefixes` output for adding custom security rules ([#1450](https://github.com/poseidon/typhoon/pull/1450))
+
+## v1.30.0
+
+* Kubernetes [v1.30.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.30.md#v1300)
+* Update etcd from v3.5.12 to [v3.5.13](https://github.com/etcd-io/etcd/releases/tag/v3.5.13)
+* Update Cilium from v1.15.2 to [v1.15.3](https://github.com/cilium/cilium/releases/tag/v1.15.3)
+* Update Calico from v3.27.2 to [v3.27.3](https://github.com/projectcalico/calico/releases/tag/v3.27.3)
+
+## v1.29.3
+
+* Kubernetes [v1.29.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.29.md#v1293)
+* Update Cilium from v1.15.1 to [v1.15.2](https://github.com/cilium/cilium/releases/tag/v1.15.2)
+* Update flannel from v0.24.2 to [v0.24.4](https://github.com/flannel-io/flannel/releases/tag/v0.24.4)
+
+## v1.29.2
+
+* Kubernetes [v1.29.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.29.md#v1292)
+* Update etcd from v3.5.10 to [v3.5.12](https://github.com/etcd-io/etcd/releases/tag/v3.5.12)
+* Update Cilium from v1.14.3 to [v1.15.1](https://github.com/cilium/cilium/releases/tag/v1.15.1)
+* Update Calico from v3.26.3 to [v3.27.2](https://github.com/projectcalico/calico/releases/tag/v3.27.2)
+  * Fix upstream incompatibility with Fedora CoreOS ([calico#8372](https://github.com/projectcalico/calico/issues/8372))
+* Update flannel from v0.22.2 to [v0.24.2](https://github.com/flannel-io/flannel/releases/tag/v0.24.2)
+* Add an `install_container_networking` variable (default `true`) ([#1421](https://github.com/poseidon/typhoon/pull/1421))
+  * When `true`, the chosen container `networking` provider is installed during cluster bootstrap
+  * Set `false` to self-manage the container networking provider. This allows flannel, Calico, or Cilium
+  to be managed via Terraform (like any other Kubernetes resources). Nodes will be NotReady until you
+  apply the self-managed container networking provider. This may become the default in future.
+  * Continue to set `networking` to one of the three supported container networking providers. Most
+  require custom firewall / security policies be present across nodes so they have some infra tie-ins.
+
+## v1.29.1
+
+* Kubernetes [v1.29.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.29.md#v1291)
+
+### AWS
+
+* Continue to support AWS IMDSv1 ([#1412](https://github.com/poseidon/typhoon/pull/1412))
+
+### Known Issues
+
+* Calico and Fedora CoreOS cannot be used together currently ([calico#8372](https://github.com/projectcalico/calico/issues/8372))
+
+## v1.29.0
+
+* Kubernetes [v1.29.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.29.md#v1290)
+
+### Known Issues
+
+* Calico and Fedora CoreOS cannot be used together currently ([calico#8372](https://github.com/projectcalico/calico/issues/8372))
+
+## v1.28.4
+
+* Kubernetes [v1.28.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#v1284)
+
+## v1.28.3
+
+* Kubernetes [v1.28.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#v1283)
+* Update etcd from v3.5.9 to [v3.5.10](https://github.com/etcd-io/etcd/releases/tag/v3.5.10)
+* Update Cilium from v1.14.2 to [v1.14.3](https://github.com/cilium/cilium/releases/tag/v1.14.3)
+* Workaround problems in Cilium v1.14's partial `kube-proxy` implementation ([#365](https://github.com/poseidon/terraform-render-bootstrap/pull/365))
+* Update Calico from v3.26.1 to [v3.26.3](https://github.com/projectcalico/calico/releases/tag/v3.26.3)
+
+### Google Cloud
+
+* Allow upgrading Google Cloud Terraform provider to v5.x
+
+## v1.28.2
+
+* Kubernetes [v1.28.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#v1282)
+* Update Cilium from v1.14.1 to [v1.14.2](https://github.com/cilium/cilium/releases/tag/v1.14.2)
+
+### Azure
+
+* Add optional `azure_authorized_key` variable
+  * Azure obtusely inspects public keys, requires RSA keys, and forbids more secure key formats (e.g. ed25519)
+  * Allow passing a dummy RSA key via `azure_authorized_key` (delete the private key) to satisfy Azure validations, then the usual `ssh_authorized_key` variable can new newer formats (e.g. ed25519)
+
+## v1.28.1
+
+* Kubernetes [v1.28.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#v1281)
+
+## v1.28.0
+
+* Kubernetes [v1.28.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.28.md#v1280)
+* Update Cilium from v1.13.4 to [v1.14.1](https://github.com/cilium/cilium/releases/tag/v1.14.1)
+* Update flannel from v0.22.0 to [v0.22.2](https://github.com/flannel-io/flannel/releases/tag/v0.22.2)
+
+## v1.27.4
+
+* Kubernetes [v1.27.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.27.md#v1274)
+
+## v1.27.3
+
+* Kubernetes [v1.27.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.27.md#v1273)
+* Update etcd from v3.5.7 to [v3.5.9](https://github.com/etcd-io/etcd/releases/tag/v3.5.9)
+* Update Cilium from v1.13.2 to [v1.13.4](https://github.com/cilium/cilium/releases/tag/v1.13.4)
+* Update Calico from v3.25.1 to [v3.26.1](https://github.com/projectcalico/calico/releases/tag/v3.26.1)
+* Update flannel from v0.21.2 to [v0.22.0](https://github.com/flannel-io/flannel/releases/tag/v0.22.0)
+
+### AWS
+
+* Allow upgrading AWS Terraform provider to v5.x ([#1353](https://github.com/poseidon/typhoon/pull/1353))
+
+### Azure
+
+* Enable boot diagnostics for controller and worker VMs ([#1351](https://github.com/poseidon/typhoon/pull/1351))
+
+## v1.27.2
+
+* Kubernetes [v1.27.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.27.md#v1272)
+
+### Fedora CoreOS
+
+* Update Butane Config version from v1.4.0 to v1.5.0
+  * Require any custom Butane [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) update to v1.5.0
+* Require Fedora CoreOS `37.20230303.3.0` or newer (with ignition v2.15)
+* Require poseidon/ct v0.13+ (**action required**)
+
+## v1.27.1
+
+* Kubernetes [v1.27.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.27.md#v1271)
+* Update etcd from v3.5.7 to [v3.5.8](https://github.com/etcd-io/etcd/releases/tag/v3.5.8)
+* Update Cilium from v1.13.1 to [v1.13.2](https://github.com/cilium/cilium/releases/tag/v1.13.2)
+* Update Calico from v3.25.0 to [v3.25.1](https://github.com/projectcalico/calico/releases/tag/v3.25.1)
+
+## v1.26.3
+
+* Kubernetes [v1.26.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1263)
+* Update Cilium from v1.12.6 to [v1.13.1](https://github.com/cilium/cilium/releases/tag/v1.13.1)
+
+### Bare-Metal
+
+* Add `oem_type` variable for Flatcar Linux ([#1302](https://github.com/poseidon/typhoon/pull/1302))
+
+## v1.26.2
+
+* Kubernetes [v1.26.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1262)
+* Update Cilium from v1.12.5 to [v1.12.6](https://github.com/cilium/cilium/releases/tag/v1.12.6)
+* Update flannel from v0.20.2 to [v0.21.2](https://github.com/flannel-io/flannel/releases/tag/v0.21.2)
+
+### Bare-Metal
+
+* Add a `worker` module to allow customizing individual worker nodes ([#1295](https://github.com/poseidon/typhoon/pull/1295))
+
+### Known Issues
+
+* Fedora CoreOS [issue](https://github.com/coreos/fedora-coreos-tracker/issues/1423) fix is progressing through channels
+
+## v1.26.1
+
+* Kubernetes [v1.26.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1261)
+* Update etcd from v3.5.6 to [v3.5.7](https://github.com/etcd-io/etcd/releases/tag/v3.5.7)
+* Update Cilium from v1.12.4 to [v1.12.5](https://github.com/cilium/cilium/releases/tag/v1.12.5)
+* Update Calico from v3.24.5 to [v3.25.0](https://github.com/projectcalico/calico/releases/tag/v3.25.0)
+* Update CoreDNS from v1.9.3 to [v1.9.4](https://github.com/poseidon/terraform-render-bootstrap/pull/341)
+
+## v1.26.0
+
+* Kubernetes [v1.26.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1260)
+* Update etcd from v3.5.5 to [v3.5.6](https://github.com/etcd-io/etcd/releases/tag/v3.5.6)
+* Update Cilium from v1.12.3 to [v1.12.4](https://github.com/cilium/cilium/releases/tag/v1.12.4)
+* Update flannel from v0.15.1 to [v0.20.2](https://github.com/flannel-io/flannel/releases/tag/v0.20.2)
+* Reminder: Modules are no longer published to the [Terraform Module Registry](https://registry.terraform.io/search/modules?q=poseidon) ([#1282](https://github.com/poseidon/typhoon/pull/1282))
+  * See [#1282](https://github.com/poseidon/typhoon/pull/1282) and [v1.25.4](https://github.com/poseidon/typhoon/releases/tag/v1.25.4) for details
+
+### AWS
+
+* Migrate AWS launch configurations to launch templates ([#1275](https://github.com/poseidon/typhoon/pull/1275))
+  * Starting Dec 31, 2022 AWS won't add new instance types/families to launch configurations
+
+### Addons
+
+* Update ingress-nginx from v1.3.1 to [v1.5.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.5.1)
+* Update Prometheus from v2.40.1 to [v2.40.5](https://github.com/prometheus/prometheus/releases/tag/v2.40.5)
+* Update node-exporter from v1.3.1 to [v1.5.0](https://github.com/prometheus/node_exporter/releases/tag/v1.5.0)
+* Update kube-state-metrics from v2.6.0 to [v2.7.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.7.0)
+* Update Grafana from v9.2.4 to [v9.3.1](https://github.com/grafana/grafana/releases/tag/v9.3.1)
+
+## v1.25.4
+
+* Kubernetes [v1.25.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1254)
+* Update Calico from v3.24.1 to [v3.24.5](https://github.com/projectcalico/calico/releases/tag/v3.24.5)
+* Allow Kubelet kubeconfig to drain nodes, if desired ([#330](https://github.com/poseidon/terraform-render-bootstrap/pull/330))
+* Re-enable Kubelet Graceful Node Shutdown ([#1261](https://github.com/poseidon/typhoon/pull/1261))
+  * Introduce companion project [poseidon/scuttle](https://github.com/poseidon/scuttle)
+* Link to new Mastodon account for release announcements
+  * [@typhoon@fosstodon.org](https://fosstodon.org/@typhoon)
+  * [@poseidon@fosstodon.org](https://fosstodon.org/@poseidon)
+* Deprecate publishing to the [Terraform Module Registry](https://registry.terraform.io/search/modules?q=poseidon)
+  * Typhoon docs have always shown using Git-based module sources, not the Terraform Module Registry
+  * Module usage should be `source = "git::https://github.com/poseidon/typhoon/...` not `source = poseidon/kubernetes/...`
+  * Terraform's Module Registry requires subtree mirroring typhoon to special terraform-platform-kubernetes repos, only supports release versions (no commit SHAs or forks), only ever contained Flatcar Linux modules (not Fedora CoreOS) for historical reasons
+  * Note, this does not affect Terraform Providers like `poseidon/matchbox` or `poseidon/ct`, the registry works well for providers
+
+### Fedora CoreOS
+
+* Remove unused `Wants=network.target` from `etcd-member.service` ([#1254](https://github.com/poseidon/typhoon/pull/1254))
+
+### Cloud
+
+* Remove defunct `delete-node.service` from worker node configurations ([#1256](https://github.com/poseidon/typhoon/pull/1256))
+
+### Addons
+
+* Update Prometheus from v2.39.1 to [v2.40.1](https://github.com/prometheus/prometheus/releases/tag/v2.40.1)
+* Update Grafana from v9.1.7 to [v9.2.4](https://github.com/grafana/grafana/releases/tag/v9.2.4)
+
+## v1.25.3
+
+* Kubernetes [v1.25.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1253)
+* Switch Kubernetes registry from `k8s.gcr.io` to `registry.k8s.io` for addons ([#1246](https://github.com/poseidon/typhoon/pull/1246))
+* Update Cilium from v1.12.2 to [v1.12.3](https://github.com/cilium/cilium/releases/tag/v1.12.3) ([#1253](https://github.com/poseidon/typhoon/pull/1253))
+
+### Azure
+
+* Change default Azure `worker_type` from [`Standard_DS1_v2`](https://learn.microsoft.com/en-us/azure/virtual-machines/dv2-dsv2-series#dsv2-series) to [`Standard_D2as_v5`](https://learn.microsoft.com/en-us/azure/virtual-machines/dasv5-dadsv5-series#dasv5-series) ([#1248](https://github.com/poseidon/typhoon/pull/1248))
+  * Get 2 VCPU, 7 GiB, 12500Mbps (vs 1 VCPU, 3.5GiB, 750 Mbps)
+  * Small increase in pay-as-you-go price ($53.29 -> $62.78)
+  * Small increase in spot price ($5.64/mo -> $7.37/mo)
+  * Change from Intel to AMD EPYC (`D2as_v5` cheaper than `D2s_v5`)
+
+### Flatcar Linux
+
+* Add Flatcar Linux ARM64 support on Azure ([docs](https://typhoon.psdn.io/advanced/arm64/), [#1251](https://github.com/poseidon/typhoon/pull/1251))
+* Switch from Azure Hypervisor gen1 to gen2 (**action required**) ([#1248](https://github.com/poseidon/typhoon/pull/1248))
+  * Run `az vm image terms accept --publish kinvolk --offer flatcar-container-linux-free --plan stable-gen2`
+
+### Docs
+
+* Remove old docs note about not supporting ARM64 with Calico
+  * Typhoon supports ARM64 with `cilium`, `calico`, and `flannel`
+
+### Addons
+
+* Update Prometheus from v2.38.0 to [v2.39.1](https://github.com/prometheus/prometheus/releases/tag/v2.39.1)
+* Update Grafana from v9.1.6 to [v9.1.7](https://github.com/grafana/grafana/releases/tag/v9.1.7)
+
+## v1.25.2
+
+Kubernetes v1.25.2 was skipped since there were minimal changes upstream.
+
+## v1.25.1
+
+* Kubernetes [v1.25.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1251)
+* Update etcd from v3.5.4 to [v3.5.5](https://github.com/etcd-io/etcd/releases/tag/v3.5.5)
+* Update Cilium from v1.12.1 to [v1.12.2](https://github.com/cilium/cilium/releases/tag/v1.12.2)
+* Update Calico from v3.23.3 to [v3.24.1](https://github.com/projectcalico/calico/releases/tag/v3.24.1)
+* Revert Kubelet Graceful Node Shutdown on worker nodes ([#1227](https://github.com/poseidon/typhoon/pull/1227))
+  * Fix issue where non-critical pods are left in Error/Completed state on node shutdown
+* Remove feature flag disable workaround for [kubernetes/kubernetes#112081](https://github.com/kubernetes/kubernetes/issues/112081)
+  * Kubernetes [reverted](https://github.com/kubernetes/kubernetes/pull/112078) `LocalStorageCapacityIsolationFSQuotaMonitoring` back to alpha
+* Remove workaround for preventing `search .` propagation in [kubernetes/kubernetes#112135](https://github.com/kubernetes/kubernetes/issues/112135)
+  * Upstream Kubernetes [fix](https://github.com/kubernetes/kubernetes/pull/112157)
+
+### Addons
+
+* Update kube-state-metrics from v2.5.0 to [v2.6.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.6.0)
+* Update ingress-nginx from v1.3.0 to [v1.3.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.3.1)
+* Update Grafana from v9.1.0 to [v9.1.6](https://github.com/grafana/grafana/releases/tag/v9.1.6)
+
+## v1.25.0
+
+* Kubernetes [v1.25.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1250)
+  * Disable LocalStorageCapacityIsolationFSQuotaMonitoring feature gate ([#1220](https://github.com/poseidon/typhoon/pull/1220), fixes [kubernetes#112081](https://github.com/kubernetes/kubernetes/issues/112081))
+  * Add workaround to revert adding "search ." to containers' `/etc/resolv.conf` ([#1224](https://github.com/poseidon/typhoon/pull/1224), fixes [kubernetes#112135](https://github.com/kubernetes/kubernetes/issues/112135))
+* Migrate most Kubelet flags to KubeletConfiguration file ([#1219](https://github.com/poseidon/typhoon/pull/1219))
+* Configure Kubelet Graceful Node Shutdown ([#1222](https://github.com/poseidon/typhoon/pull/1222))
+  * Allow up to 30s for critical pods to gracefully shutdown on node shutdown
+  * Allow up to 15s for regular pods to gracefully shutdown on node shutdown
+  * Mark node NotReady promptly on node shutdown
+  * Lengthen systemd inhibitor lock max delay from 5s to 45s
+
+### Fedora CoreOS
+
+* Change Podman `log-driver` from `journald` to `k8s-file` ([#1221](https://github.com/poseidon/typhoon/pull/1221))
+  * Fix `etcd-member` and Kubelet systemd service log lines appearing twice in journal logs
+
+## v1.24.4
+
+* Kubernetes [v1.24.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1244)
+* Update CoreDNS from v1.8.6 to [v1.9.3](https://github.com/poseidon/terraform-render-bootstrap/pull/318)
+* Update Cilium from v1.11.7 to [v1.12.1](https://github.com/cilium/cilium/releases/tag/v1.12.1)
+* Update Calico from v3.23.1 to [v3.23.3](https://github.com/projectcalico/calico/releases/tag/v3.23.3)
+* Switch Kubernetes registry from `k8s.gcr.io` to `registry.k8s.io` ([#1206](https://github.com/poseidon/typhoon/pull/1206))
+* Remove use of deprecated Terraform [template](https://registry.terraform.io/providers/hashicorp/template) provider ([#1194](https://github.com/poseidon/typhoon/pull/1194))
+
+### Fedora CoreOS
+
+* Remove ineffective `/etc/fedora-coreos/iptables-legacy.stamp` ([#1201](https://github.com/poseidon/typhoon/pull/1201))
+  * Typhoon already uses iptables v1.8.7 (nf_tables) since FCOS 36
+  * Staying on legacy iptables required a file in `/etc/coreos` instead
+
+### Flatcar Linux
+
+* Migrate Flatcar Linux from Ignition spec v2.3.0 to v3.3.0 ([#1196](https://github.com/poseidon/typhoon/pull/1196)) (**action required**)
+  * Flatcar Linux 3185.0.0+ [supports](https://flatcar-linux.org/docs/latest/provisioning/ignition/specification/#ignition-v3) Ignition v3.x specs (which are rendered from Butane Configs, like Fedora CoreOS)
+  * `poseidon/ct` v0.11.0 [supports](https://github.com/poseidon/terraform-provider-ct/pull/131) the `flatcar` Butane Config variant
+  * Require poseidon/ct v0.11+ and Flatcar Linux 3185.0.0+
+* Please modify any Flatcar Linux snippets to use the [Butane Config](https://coreos.github.io/butane/config-flatcar-v1_0/) format (**action required**)
+
+```tf
+variant: flatcar
+version: 1.0.0
+...
+```
+
+### AWS
+
+* [Refresh](https://docs.aws.amazon.com/autoscaling/ec2/userguide/asg-instance-refresh.html) instances in autoscaling group when launch configuration changes ([#1208](https://github.com/poseidon/typhoon/pull/1208)) ([docs](https://typhoon.psdn.io/topics/maintenance/#node-configuration-updates), **important**)
+  * Worker launch configuration changes start an autoscaling group instance refresh to replace instances
+  * Instance refresh creates surge instances, waits for a warm-up period, then deletes old instances
+  * Changing `worker_type`, `disk_*`, `worker_price`, `worker_target_groups`, or Butane `worker_snippets` on existing worker nodes will replace instances
+  * New AMIs or changing `os_stream` will be ignored, to allow Fedora CoreOS or Flatcar Linux to keep themselves updated
+  * Previously, new launch configurations were made in the same way, but not applied to instances unless manually replaced
+* Rename worker autoscaling group `${cluster_name}-worker` ([#1202](https://github.com/poseidon/typhoon/pull/1202))
+  * Rename launch configuration `${cluster_name}-worker` instead of a random id
+
+### Google
+
+* [Roll](https://cloud.google.com/compute/docs/instance-groups/rolling-out-updates-to-managed-instance-groups) instance template changes to worker managed instance groups ([#1207](https://github.com/poseidon/typhoon/pull/1207)) ([docs](https://typhoon.psdn.io/topics/maintenance/#node-configuration-updates), **important**)
+  * Worker instance template changes roll out by gradually replacing instances
+  * Automatic rollouts create surge instances, wait for health checks, then delete old instances (0 unavailable instances)
+  * Changing `worker_type`, `disk_size`, `worker_preemptible`, or Butane `worker_snippets` on existing worker nodes will replace instances
+  * New compute images or changing `os_stream` will be ignored, to allow Fedora CoreOS or Flatcar Linux to keep themselves updated
+  * Previously, new instance templates were made in the same way, but not applied to instances unless manually replaced
+* Add health checks to worker managed instance groups (i.e. "autohealing") ([#1207](https://github.com/poseidon/typhoon/pull/1207))
+  * Use health checks to probe kube-proxy every 30s
+  * Replace worker nodes that fail the health check 6 times (3min)
+* Name `kube-apiserver` and `worker` health checks consistently ([#1207](https://github.com/poseidon/typhoon/pull/1207))
+  * Use name `${cluster_name}-apiserver-health` and `${cluster_name}-worker-health`
+* Rename managed instance group from `${cluster_name}-worker-group` to `${cluster_name}-worker` ([#1207](https://github.com/poseidon/typhoon/pull/1207))
+* Fix bug provisioning clusters with multiple controller nodes ([#1195](https://github.com/poseidon/typhoon/pull/1195))
+
+### Addons
+
+* Update Prometheus from v2.37.0 to [v2.38.0](https://github.com/prometheus/prometheus/releases/tag/v2.38.0)
+* Update Grafana from v9.0.3 to [v9.1.0](https://github.com/grafana/grafana/releases/tag/v9.1.0)
+
+## v1.24.3
+
+* Kubernetes [v1.24.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1243)
+* Update Cilium from v1.11.6 to [v1.11.7](https://github.com/cilium/cilium/releases/tag/v1.11.7)
+
+### Addons
+
+* Update ingress-nginx from v1.2.1 to [v1.3.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.3.0)
+* Update Prometheus from v2.36.1 to [v2.37.0](https://github.com/prometheus/prometheus/releases/tag/v2.37.0)
+* Update Grafana from v8.5.6 to [v9.0.3](https://github.com/grafana/grafana/releases/tag/v9.0.3)
+
+### Notes
+
+* Poseidon repos will soon change their default branch from `master` to `main`
+
+## v1.24.2
+
+* Kubernetes [v1.24.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1242)
+* Update Cilium from v1.11.5 to [v1.11.6](https://github.com/cilium/cilium/releases/tag/v1.11.6)
+* Update Calico from v3.22.2 to [v3.23.1](https://github.com/projectcalico/calico/releases/tag/v3.23.1)
+
+### Addons
+
+* Update Prometheus from v2.36.0 to [v2.36.1](https://github.com/prometheus/prometheus/releases/tag/v2.36.1)
+* Update Grafana from v8.5.3 to [v8.5.6](https://github.com/grafana/grafana/releases/tag/v8.5.6)
+* Update kube-state-metrics from v2.4.2 to [v2.5.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.5.0)
+
+## Known Issues
+
+* Skip AWS Terraform provider v4.17.0 to v4.19.0, which had a regression affecting workers joining ([#1173](https://github.com/poseidon/typhoon/issues/1173))
+
 ## v1.24.1
 
 * Kubernetes [v1.24.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1241)
@@ -13,7 +395,7 @@ Notable changes between versions.
 
 * Update Prometheus from v2.35.0 to [v2.36.0](https://github.com/prometheus/prometheus/releases/tag/v2.36.0)
 * Update Grafana from v8.5.1 to [v8.5.3](https://github.com/grafana/grafana/releases/tag/v8.5.3)
-* Update nginx-ingress from v1.2.1 to [v1.2.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.2.1)
+* Update nginx-ingress from v1.2.0 to [v1.2.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.2.1)
 
 ## v1.24.0
 

README.md

@@ -1,4 +1,11 @@
-# Typhoon <img align="right" src="https://storage.googleapis.com/poseidon/typhoon-logo.png">
+# Typhoon
+
+[![Release](https://img.shields.io/github/v/release/poseidon/typhoon?style=flat-square)](https://github.com/poseidon/typhoon/releases)
+[![Stars](https://img.shields.io/github/stars/poseidon/typhoon?style=flat-square)](https://github.com/poseidon/typhoon/stargazers)
+[![Sponsors](https://img.shields.io/github/sponsors/poseidon?logo=github&style=flat-square)](https://github.com/sponsors/poseidon)
+[![Mastodon](https://img.shields.io/badge/follow-news-6364ff?logo=mastodon&style=flat-square)](https://fosstodon.org/@typhoon)
+
+<img align="right" src="https://storage.googleapis.com/poseidon/typhoon-logo.png">
 
 Typhoon is a minimal and free Kubernetes distribution.
 
@@ -11,7 +18,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
 * Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/flatcar-linux/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
@@ -19,7 +26,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Modules
 
-Typhoon provides a Terraform Module for each supported operating system and platform.
+Typhoon provides a Terraform Module for defining a Kubernetes cluster on each supported operating system and platform.
 
 Typhoon is available for [Fedora CoreOS](https://getfedora.org/coreos/).
 
@@ -48,6 +55,15 @@ Typhoon is available for [Flatcar Linux](https://www.flatcar-linux.org/releases/
 | Platform      | Operating System | Terraform Module | Status |
 |---------------|------------------|------------------|--------|
 | AWS           | Flatcar Linux (ARM64) | [aws/flatcar-linux/kubernetes](aws/flatcar-linux/kubernetes) | alpha |
+| Azure         | Flatcar Linux (ARM64) | [azure/flatcar-linux/kubernetes](azure/flatcar-linux/kubernetes) | alpha |
+
+Typhoon also provides Terraform Modules for optionally managing individual components applied onto clusters.
+
+| Name    | Terraform Module | Status |
+|---------|------------------|--------|
+| CoreDNS | [addons/coredns](addons/coredns) | beta |
+| Cilium  | [addons/cilium](addons/cilium) | beta |
+| flannel | [addons/flannel](addons/flannel) | beta |
 
 ## Documentation
 
@@ -62,7 +78,7 @@ Define a Kubernetes cluster by using the Terraform module for your chosen platfo
 
 ```tf
 module "yavin" {
-  source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.24.1"
+  source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.30.1"
 
   # Google Cloud
   cluster_name  = "yavin"
@@ -101,9 +117,9 @@ In 4-8 minutes (varies by platform), the cluster will be ready. This Google Clou
 $ export KUBECONFIG=/home/user/.kube/configs/yavin-config
 $ kubectl get nodes
 NAME                                       ROLES    STATUS  AGE  VERSION
-yavin-controller-0.c.example-com.internal  <none>   Ready   6m   v1.24.1
-yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.24.1
-yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.24.1
+yavin-controller-0.c.example-com.internal  <none>   Ready   6m   v1.30.1
+yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.30.1
+yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.30.1
 ```
 
 List the pods.
@@ -156,5 +172,12 @@ Poseidon's Github [Sponsors](https://github.com/sponsors/poseidon) support the i
     <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg" width="201px">
 </a>
 <br>
+<br>
+
+<a href="https://deploy.equinix.com/">
+  <img src="https://storage.googleapis.com/poseidon/equinix.png" width="201px">
+</a>
+<br>
+<br>
 
 If you'd like your company here, please contact dghubble at psdn.io.

addons/cilium/cluster-role-binding.tf

@@ -0,0 +1,36 @@
+resource "kubernetes_cluster_role_binding" "operator" {
+  metadata {
+    name = "cilium-operator"
+  }
+
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "ClusterRole"
+    name      = "cilium-operator"
+  }
+
+  subject {
+    kind      = "ServiceAccount"
+    name      = "cilium-operator"
+    namespace = "kube-system"
+  }
+}
+
+resource "kubernetes_cluster_role_binding" "agent" {
+  metadata {
+    name = "cilium-agent"
+  }
+
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "ClusterRole"
+    name      = "cilium-agent"
+  }
+
+  subject {
+    kind      = "ServiceAccount"
+    name      = "cilium-agent"
+    namespace = "kube-system"
+  }
+}
+

addons/cilium/cluster-role.tf

@@ -0,0 +1,112 @@
+resource "kubernetes_cluster_role" "operator" {
+  metadata {
+    name = "cilium-operator"
+  }
+
+  # detect and restart [core|kube]dns pods on startup
+  rule {
+    verbs      = ["get", "list", "watch", "delete"]
+    api_groups = [""]
+    resources  = ["pods"]
+  }
+
+  rule {
+    verbs      = ["list", "watch"]
+    api_groups = [""]
+    resources  = ["nodes"]
+  }
+
+  rule {
+    verbs      = ["patch"]
+    api_groups = [""]
+    resources  = ["nodes", "nodes/status"]
+  }
+
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = ["discovery.k8s.io"]
+    resources  = ["endpointslices"]
+  }
+
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = [""]
+    resources  = ["services"]
+  }
+
+  # Perform LB IP allocation for BGP
+  rule {
+    verbs      = ["update"]
+    api_groups = [""]
+    resources  = ["services/status"]
+  }
+
+  # Perform the translation of a CNP that contains `ToGroup` to its endpoints
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = [""]
+    resources  = ["services", "endpoints", "namespaces"]
+  }
+
+  rule {
+    verbs      = ["*"]
+    api_groups = ["cilium.io"]
+    resources  = ["ciliumnetworkpolicies", "ciliumnetworkpolicies/status", "ciliumnetworkpolicies/finalizers", "ciliumclusterwidenetworkpolicies", "ciliumclusterwidenetworkpolicies/status", "ciliumclusterwidenetworkpolicies/finalizers", "ciliumendpoints", "ciliumendpoints/status", "ciliumendpoints/finalizers", "ciliumnodes", "ciliumnodes/status", "ciliumnodes/finalizers", "ciliumidentities", "ciliumidentities/status", "ciliumidentities/finalizers", "ciliumlocalredirectpolicies", "ciliumlocalredirectpolicies/status", "ciliumlocalredirectpolicies/finalizers", "ciliumendpointslices", "ciliumloadbalancerippools", "ciliumloadbalancerippools/status", "ciliumcidrgroups", "ciliuml2announcementpolicies", "ciliuml2announcementpolicies/status", "ciliumpodippools"]
+  }
+
+  rule {
+    verbs      = ["create", "get", "list", "update", "watch"]
+    api_groups = ["apiextensions.k8s.io"]
+    resources  = ["customresourcedefinitions"]
+  }
+
+  # Cilium leader elects if among multiple operator replicas
+  rule {
+    verbs      = ["create", "get", "update"]
+    api_groups = ["coordination.k8s.io"]
+    resources  = ["leases"]
+  }
+}
+
+resource "kubernetes_cluster_role" "agent" {
+  metadata {
+    name = "cilium-agent"
+  }
+
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = ["networking.k8s.io"]
+    resources  = ["networkpolicies"]
+  }
+
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = ["discovery.k8s.io"]
+    resources  = ["endpointslices"]
+  }
+
+  rule {
+    verbs      = ["get", "list", "watch"]
+    api_groups = [""]
+    resources  = ["namespaces", "services", "pods", "endpoints", "nodes"]
+  }
+
+  rule {
+    verbs      = ["patch"]
+    api_groups = [""]
+    resources  = ["nodes/status"]
+  }
+
+  rule {
+    verbs      = ["create", "get", "list", "watch", "update"]
+    api_groups = ["apiextensions.k8s.io"]
+    resources  = ["customresourcedefinitions"]
+  }
+
+  rule {
+    verbs      = ["*"]
+    api_groups = ["cilium.io"]
+    resources  = ["ciliumnetworkpolicies", "ciliumnetworkpolicies/status", "ciliumclusterwidenetworkpolicies", "ciliumclusterwidenetworkpolicies/status", "ciliumendpoints", "ciliumendpoints/status", "ciliumnodes", "ciliumnodes/status", "ciliumidentities", "ciliumidentities/status", "ciliumlocalredirectpolicies", "ciliumlocalredirectpolicies/status", "ciliumegressnatpolicies", "ciliumendpointslices", "ciliumcidrgroups", "ciliuml2announcementpolicies", "ciliuml2announcementpolicies/status", "ciliumpodippools"]
+  }
+}
+

addons/cilium/config.tf

@@ -0,0 +1,196 @@
+resource "kubernetes_config_map" "cilium" {
+  metadata {
+    name      = "cilium"
+    namespace = "kube-system"
+  }
+  data = {
+    # Identity allocation mode selects how identities are shared between cilium
+    # nodes by setting how they are stored. The options are "crd" or "kvstore".
+    # - "crd" stores identities in kubernetes as CRDs (custom resource definition).
+    #   These can be queried with:
+    #     kubectl get ciliumid
+    # - "kvstore" stores identities in a kvstore, etcd or consul, that is
+    #   configured below. Cilium versions before 1.6 supported only the kvstore
+    #   backend. Upgrades from these older cilium versions should continue using
+    #   the kvstore by commenting out the identity-allocation-mode below, or
+    #   setting it to "kvstore".
+    identity-allocation-mode    = "crd"
+    cilium-endpoint-gc-interval = "5m0s"
+    nodes-gc-interval           = "5m0s"
+
+    # If you want to run cilium in debug mode change this value to true
+    debug = "false"
+    # The agent can be put into the following three policy enforcement modes
+    # default, always and never.
+    # https://docs.cilium.io/en/latest/policy/intro/#policy-enforcement-modes
+    enable-policy = "default"
+
+    # Prometheus
+    enable-metrics                 = "true"
+    prometheus-serve-addr          = ":9962"
+    operator-prometheus-serve-addr = ":9963"
+    proxy-prometheus-port          = "9964" # envoy
+
+    # Enable IPv4 addressing. If enabled, all endpoints are allocated an IPv4
+    # address.
+    enable-ipv4 = "true"
+
+    # Enable IPv6 addressing. If enabled, all endpoints are allocated an IPv6
+    # address.
+    enable-ipv6 = "false"
+
+    # Enable probing for a more efficient clock source for the BPF datapath
+    enable-bpf-clock-probe = "true"
+
+    # Enable use of transparent proxying mechanisms (Linux 5.7+)
+    enable-bpf-tproxy = "false"
+
+    # If you want cilium monitor to aggregate tracing for packets, set this level
+    # to "low", "medium", or "maximum". The higher the level, the less packets
+    # that will be seen in monitor output.
+    monitor-aggregation = "medium"
+
+    # The monitor aggregation interval governs the typical time between monitor
+    # notification events for each allowed connection.
+    #
+    # Only effective when monitor aggregation is set to "medium" or higher.
+    monitor-aggregation-interval = "5s"
+
+    # The monitor aggregation flags determine which TCP flags which, upon the
+    # first observation, cause monitor notifications to be generated.
+    #
+    # Only effective when monitor aggregation is set to "medium" or higher.
+    monitor-aggregation-flags = "all"
+
+    # Specifies the ratio (0.0-1.0) of total system memory to use for dynamic
+    # sizing of the TCP CT, non-TCP CT, NAT and policy BPF maps.
+    bpf-map-dynamic-size-ratio = "0.0025"
+    # bpf-policy-map-max specified the maximum number of entries in endpoint
+    # policy map (per endpoint)
+    bpf-policy-map-max = "16384"
+    # bpf-lb-map-max specifies the maximum number of entries in bpf lb service,
+    # backend and affinity maps.
+    bpf-lb-map-max = "65536"
+
+    # Pre-allocation of map entries allows per-packet latency to be reduced, at
+    # the expense of up-front memory allocation for the entries in the maps. The
+    # default value below will minimize memory usage in the default installation;
+    # users who are sensitive to latency may consider setting this to "true".
+    #
+    # This option was introduced in Cilium 1.4. Cilium 1.3 and earlier ignore
+    # this option and behave as though it is set to "true".
+    #
+    # If this value is modified, then during the next Cilium startup the restore
+    # of existing endpoints and tracking of ongoing connections may be disrupted.
+    # As a result, reply packets may be dropped and the load-balancing decisions
+    # for established connections may change.
+    #
+    # If this option is set to "false" during an upgrade from 1.3 or earlier to
+    # 1.4 or later, then it may cause one-time disruptions during the upgrade.
+    preallocate-bpf-maps = "false"
+
+    # Name of the cluster. Only relevant when building a mesh of clusters.
+    cluster-name = "default"
+    # Unique ID of the cluster. Must be unique across all conneted clusters and
+    # in the range of 1 and 255. Only relevant when building a mesh of clusters.
+    cluster-id = "0"
+
+    # Encapsulation mode for communication between nodes
+    # Possible values:
+    #   - disabled
+    #   - vxlan (default)
+    #   - geneve
+    routing-mode = "tunnel"
+    tunnel       = "vxlan"
+    # Enables L7 proxy for L7 policy enforcement and visibility
+    enable-l7-proxy = "true"
+
+    auto-direct-node-routes = "false"
+
+    # enableXTSocketFallback enables the fallback compatibility solution
+    # when the xt_socket kernel module is missing and it is needed for
+    # the datapath L7 redirection to work properly.  See documentation
+    # for details on when this can be disabled:
+    # http://docs.cilium.io/en/latest/install/system_requirements/#admin-kernel-version.
+    enable-xt-socket-fallback = "true"
+
+    # installIptablesRules enables installation of iptables rules to allow for
+    # TPROXY (L7 proxy injection), itpables based masquerading and compatibility
+    # with kube-proxy. See documentation for details on when this can be
+    # disabled.
+    install-iptables-rules = "true"
+
+    # masquerade traffic leaving the node destined for outside
+    enable-ipv4-masquerade = "true"
+    enable-ipv6-masquerade = "false"
+
+    # bpfMasquerade enables masquerading with BPF instead of iptables
+    enable-bpf-masquerade = "true"
+
+    # kube-proxy
+    kube-proxy-replacement                      = "false"
+    kube-proxy-replacement-healthz-bind-address = ""
+    enable-session-affinity                     = "true"
+
+    # ClusterIPs from host namespace
+    bpf-lb-sock = "true"
+    # ClusterIPs from external nodes
+    bpf-lb-external-clusterip = "true"
+
+    # NodePort
+    enable-node-port             = "true"
+    enable-health-check-nodeport = "false"
+
+    # ExternalIPs
+    enable-external-ips = "true"
+
+    # HostPort
+    enable-host-port = "true"
+
+    # IPAM
+    ipam                        = "cluster-pool"
+    disable-cnp-status-updates  = "true"
+    cluster-pool-ipv4-cidr      = "${var.pod_cidr}"
+    cluster-pool-ipv4-mask-size = "24"
+
+    # Health
+    agent-health-port               = "9876"
+    enable-health-checking          = "true"
+    enable-endpoint-health-checking = "true"
+
+    # Identity
+    enable-well-known-identities = "false"
+    enable-remote-node-identity  = "true"
+
+    # Hubble server
+    enable-hubble                  = var.enable_hubble
+    hubble-disable-tls             = "false"
+    hubble-listen-address          = ":4244"
+    hubble-socket-path             = "/var/run/cilium/hubble.sock"
+    hubble-tls-client-ca-files     = "/var/lib/cilium/tls/hubble/client-ca.crt"
+    hubble-tls-cert-file           = "/var/lib/cilium/tls/hubble/server.crt"
+    hubble-tls-key-file            = "/var/lib/cilium/tls/hubble/server.key"
+    hubble-export-file-max-backups = "5"
+    hubble-export-file-max-size-mb = "10"
+
+    # Hubble metrics
+    hubble-metrics-server      = ":9965"
+    hubble-metrics             = "dns drop tcp flow port-distribution icmp httpV2"
+    enable-hubble-open-metrics = "false"
+
+
+    # Misc
+    enable-bandwidth-manager        = "false"
+    enable-local-redirect-policy    = "false"
+    policy-audit-mode               = "false"
+    operator-api-serve-addr         = "127.0.0.1:9234"
+    enable-l2-neigh-discovery       = "true"
+    enable-k8s-terminating-endpoint = "true"
+    enable-k8s-networkpolicy        = "true"
+    external-envoy-proxy            = "false"
+    write-cni-conf-when-ready       = "/host/etc/cni/net.d/05-cilium.conflist"
+    cni-exclusive                   = "true"
+    cni-log-file                    = "/var/run/cilium/cilium-cni.log"
+  }
+}
+

addons/cilium/daemonset.tf

@@ -0,0 +1,379 @@
+resource "kubernetes_daemonset" "cilium" {
+  wait_for_rollout = false
+
+  metadata {
+    name      = "cilium"
+    namespace = "kube-system"
+    labels = {
+      k8s-app = "cilium"
+    }
+  }
+  spec {
+    strategy {
+      type = "RollingUpdate"
+      rolling_update {
+        max_unavailable = "1"
+      }
+    }
+    selector {
+      match_labels = {
+        k8s-app = "cilium-agent"
+      }
+    }
+    template {
+      metadata {
+        labels = {
+          k8s-app = "cilium-agent"
+        }
+        annotations = {
+          "prometheus.io/port"   = "9962"
+          "prometheus.io/scrape" = "true"
+        }
+      }
+      spec {
+        host_network         = true
+        priority_class_name  = "system-node-critical"
+        service_account_name = "cilium-agent"
+        security_context {
+          seccomp_profile {
+            type = "RuntimeDefault"
+          }
+        }
+        toleration {
+          key      = "node-role.kubernetes.io/controller"
+          operator = "Exists"
+        }
+        toleration {
+          key      = "node.kubernetes.io/not-ready"
+          operator = "Exists"
+        }
+        dynamic "toleration" {
+          for_each = var.daemonset_tolerations
+          content {
+            key      = toleration.value
+            operator = "Exists"
+          }
+        }
+        automount_service_account_token = true
+        enable_service_links            = false
+
+        # Cilium v1.13.1 starts installing CNI plugins in yet another init container
+        # https://github.com/cilium/cilium/pull/24075
+        init_container {
+          name    = "install-cni"
+          image   = "quay.io/cilium/cilium:v1.15.5"
+          command = ["/install-plugin.sh"]
+          security_context {
+            allow_privilege_escalation = true
+            privileged                 = true
+            capabilities {
+              drop = ["ALL"]
+            }
+          }
+          volume_mount {
+            name       = "cni-bin-dir"
+            mount_path = "/host/opt/cni/bin"
+          }
+        }
+
+        # Required to mount cgroup2 filesystem on the underlying Kubernetes node.
+        # We use nsenter command with host's cgroup and mount namespaces enabled.
+        init_container {
+          name  = "mount-cgroup"
+          image = "quay.io/cilium/cilium:v1.15.5"
+          command = [
+            "sh",
+            "-ec",
+            # The statically linked Go program binary is invoked to avoid any
+            # dependency on utilities like sh and mount that can be missing on certain
+            # distros installed on the underlying host. Copy the binary to the
+            # same directory where we install cilium cni plugin so that exec permissions
+            # are available.
+            "cp /usr/bin/cilium-mount /hostbin/cilium-mount && nsenter --cgroup=/hostproc/1/ns/cgroup --mount=/hostproc/1/ns/mnt \"$${BIN_PATH}/cilium-mount\" $CGROUP_ROOT; rm /hostbin/cilium-mount"
+          ]
+          env {
+            name  = "CGROUP_ROOT"
+            value = "/run/cilium/cgroupv2"
+          }
+          env {
+            name  = "BIN_PATH"
+            value = "/opt/cni/bin"
+          }
+          security_context {
+            allow_privilege_escalation = true
+            privileged                 = true
+          }
+          volume_mount {
+            name       = "hostproc"
+            mount_path = "/hostproc"
+          }
+          volume_mount {
+            name       = "cni-bin-dir"
+            mount_path = "/hostbin"
+          }
+        }
+
+        init_container {
+          name    = "clean-cilium-state"
+          image   = "quay.io/cilium/cilium:v1.15.5"
+          command = ["/init-container.sh"]
+          security_context {
+            allow_privilege_escalation = true
+            privileged                 = true
+          }
+          volume_mount {
+            name       = "sys-fs-bpf"
+            mount_path = "/sys/fs/bpf"
+          }
+          volume_mount {
+            name       = "var-run-cilium"
+            mount_path = "/var/run/cilium"
+          }
+          # Required to mount cgroup filesystem from the host to cilium agent pod
+          volume_mount {
+            name              = "cilium-cgroup"
+            mount_path        = "/run/cilium/cgroupv2"
+            mount_propagation = "HostToContainer"
+          }
+        }
+
+        container {
+          name    = "cilium-agent"
+          image   = "quay.io/cilium/cilium:v1.15.5"
+          command = ["cilium-agent"]
+          args = [
+            "--config-dir=/tmp/cilium/config-map"
+          ]
+          env {
+            name = "K8S_NODE_NAME"
+            value_from {
+              field_ref {
+                api_version = "v1"
+                field_path  = "spec.nodeName"
+              }
+            }
+          }
+          env {
+            name = "CILIUM_K8S_NAMESPACE"
+            value_from {
+              field_ref {
+                api_version = "v1"
+                field_path  = "metadata.namespace"
+              }
+            }
+          }
+          env {
+            name = "KUBERNETES_SERVICE_HOST"
+            value_from {
+              config_map_key_ref {
+                name = "in-cluster"
+                key  = "apiserver-host"
+              }
+            }
+          }
+          env {
+            name = "KUBERNETES_SERVICE_PORT"
+            value_from {
+              config_map_key_ref {
+                name = "in-cluster"
+                key  = "apiserver-port"
+              }
+            }
+          }
+          port {
+            name           = "peer-service"
+            protocol       = "TCP"
+            container_port = 4244
+          }
+          # Metrics
+          port {
+            name           = "metrics"
+            protocol       = "TCP"
+            container_port = 9962
+          }
+          port {
+            name           = "envoy-metrics"
+            protocol       = "TCP"
+            container_port = 9964
+          }
+          port {
+            name           = "hubble-metrics"
+            protocol       = "TCP"
+            container_port = 9965
+          }
+          # Not yet used, prefer exec's
+          port {
+            name           = "health"
+            protocol       = "TCP"
+            container_port = 9876
+          }
+          lifecycle {
+            pre_stop {
+              exec {
+                command = ["/cni-uninstall.sh"]
+              }
+            }
+          }
+          security_context {
+            allow_privilege_escalation = true
+            privileged                 = true
+          }
+          liveness_probe {
+            exec {
+              command = ["cilium", "status", "--brief"]
+            }
+            initial_delay_seconds = 120
+            timeout_seconds       = 5
+            period_seconds        = 30
+            success_threshold     = 1
+            failure_threshold     = 10
+          }
+          readiness_probe {
+            exec {
+              command = ["cilium", "status", "--brief"]
+            }
+            initial_delay_seconds = 5
+            timeout_seconds       = 5
+            period_seconds        = 20
+            success_threshold     = 1
+            failure_threshold     = 3
+          }
+          # Load kernel modules
+          volume_mount {
+            name       = "lib-modules"
+            read_only  = true
+            mount_path = "/lib/modules"
+          }
+          # Access iptables concurrently
+          volume_mount {
+            name       = "xtables-lock"
+            mount_path = "/run/xtables.lock"
+          }
+          # Keep state between restarts
+          volume_mount {
+            name       = "var-run-cilium"
+            mount_path = "/var/run/cilium"
+          }
+          volume_mount {
+            name              = "sys-fs-bpf"
+            mount_path        = "/sys/fs/bpf"
+            mount_propagation = "Bidirectional"
+          }
+          # Configuration
+          volume_mount {
+            name       = "config"
+            read_only  = true
+            mount_path = "/tmp/cilium/config-map"
+          }
+          # Install config on host
+          volume_mount {
+            name       = "cni-conf-dir"
+            mount_path = "/host/etc/cni/net.d"
+          }
+          # Hubble
+          volume_mount {
+            name       = "hubble-tls"
+            mount_path = "/var/lib/cilium/tls/hubble"
+            read_only  = true
+          }
+        }
+        termination_grace_period_seconds = 1
+
+        # Load kernel modules
+        volume {
+          name = "lib-modules"
+          host_path {
+            path = "/lib/modules"
+          }
+        }
+        # Access iptables concurrently with other processes (e.g. kube-proxy)
+        volume {
+          name = "xtables-lock"
+          host_path {
+            path = "/run/xtables.lock"
+            type = "FileOrCreate"
+          }
+        }
+        # Keep state between restarts
+        volume {
+          name = "var-run-cilium"
+          host_path {
+            path = "/var/run/cilium"
+            type = "DirectoryOrCreate"
+          }
+        }
+        # Keep state for bpf maps between restarts
+        volume {
+          name = "sys-fs-bpf"
+          host_path {
+            path = "/sys/fs/bpf"
+            type = "DirectoryOrCreate"
+          }
+        }
+        # Mount host cgroup2 filesystem
+        volume {
+          name = "hostproc"
+          host_path {
+            path = "/proc"
+            type = "Directory"
+          }
+        }
+        volume {
+          name = "cilium-cgroup"
+          host_path {
+            path = "/run/cilium/cgroupv2"
+            type = "DirectoryOrCreate"
+          }
+        }
+        # Read configuration
+        volume {
+          name = "config"
+          config_map {
+            name = "cilium"
+          }
+        }
+        # Install CNI plugin and config on host
+        volume {
+          name = "cni-bin-dir"
+          host_path {
+            path = "/opt/cni/bin"
+            type = "DirectoryOrCreate"
+          }
+        }
+        volume {
+          name = "cni-conf-dir"
+          host_path {
+            path = "/etc/cni/net.d"
+            type = "DirectoryOrCreate"
+          }
+        }
+        # Hubble TLS (optional)
+        volume {
+          name = "hubble-tls"
+          projected {
+            default_mode = "0400"
+            sources {
+              secret {
+                name     = "hubble-server-certs"
+                optional = true
+                items {
+                  key  = "ca.crt"
+                  path = "client-ca.crt"
+                }
+                items {
+                  key  = "tls.crt"
+                  path = "server.crt"
+                }
+                items {
+                  key  = "tls.key"
+                  path = "server.key"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}
+

addons/cilium/deployment.tf

@@ -0,0 +1,163 @@
+resource "kubernetes_deployment" "operator" {
+  wait_for_rollout = false
+  metadata {
+    name      = "cilium-operator"
+    namespace = "kube-system"
+  }
+  spec {
+    replicas = 1
+    strategy {
+      type = "RollingUpdate"
+      rolling_update {
+        max_unavailable = "1"
+      }
+    }
+    selector {
+      match_labels = {
+        name = "cilium-operator"
+      }
+    }
+    template {
+      metadata {
+        labels = {
+          name = "cilium-operator"
+        }
+        annotations = {
+          "prometheus.io/scrape" = "true"
+          "prometheus.io/port"   = "9963"
+        }
+      }
+      spec {
+        host_network         = true
+        priority_class_name  = "system-cluster-critical"
+        service_account_name = "cilium-operator"
+        security_context {
+          seccomp_profile {
+            type = "RuntimeDefault"
+          }
+        }
+        toleration {
+          key      = "node-role.kubernetes.io/controller"
+          operator = "Exists"
+        }
+        toleration {
+          key      = "node.kubernetes.io/not-ready"
+          operator = "Exists"
+        }
+        topology_spread_constraint {
+          max_skew           = 1
+          topology_key       = "kubernetes.io/hostname"
+          when_unsatisfiable = "DoNotSchedule"
+          label_selector {
+            match_labels = {
+              name = "cilium-operator"
+            }
+          }
+        }
+        automount_service_account_token = true
+        enable_service_links            = false
+        container {
+          name    = "cilium-operator"
+          image   = "quay.io/cilium/operator-generic:v1.15.5"
+          command = ["cilium-operator-generic"]
+          args = [
+            "--config-dir=/tmp/cilium/config-map",
+            "--debug=$(CILIUM_DEBUG)"
+          ]
+          env {
+            name = "K8S_NODE_NAME"
+            value_from {
+              field_ref {
+                api_version = "v1"
+                field_path  = "spec.nodeName"
+              }
+            }
+          }
+          env {
+            name = "CILIUM_K8S_NAMESPACE"
+            value_from {
+              field_ref {
+                api_version = "v1"
+                field_path  = "metadata.namespace"
+              }
+            }
+          }
+          env {
+            name = "KUBERNETES_SERVICE_HOST"
+            value_from {
+              config_map_key_ref {
+                name = "in-cluster"
+                key  = "apiserver-host"
+              }
+            }
+          }
+          env {
+            name = "KUBERNETES_SERVICE_PORT"
+            value_from {
+              config_map_key_ref {
+                name = "in-cluster"
+                key  = "apiserver-port"
+              }
+            }
+          }
+          env {
+            name = "CILIUM_DEBUG"
+            value_from {
+              config_map_key_ref {
+                name     = "cilium"
+                key      = "debug"
+                optional = true
+              }
+            }
+          }
+          port {
+            name           = "metrics"
+            protocol       = "TCP"
+            host_port      = 9963
+            container_port = 9963
+          }
+          port {
+            name           = "health"
+            container_port = 9234
+            protocol       = "TCP"
+          }
+          liveness_probe {
+            http_get {
+              scheme = "HTTP"
+              host   = "127.0.0.1"
+              port   = "9234"
+              path   = "/healthz"
+            }
+            initial_delay_seconds = 60
+            timeout_seconds       = 3
+            period_seconds        = 10
+          }
+          readiness_probe {
+            http_get {
+              scheme = "HTTP"
+              host   = "127.0.0.1"
+              port   = "9234"
+              path   = "/healthz"
+            }
+            timeout_seconds   = 3
+            period_seconds    = 15
+            failure_threshold = 5
+          }
+          volume_mount {
+            name       = "config"
+            read_only  = true
+            mount_path = "/tmp/cilium/config-map"
+          }
+        }
+
+        volume {
+          name = "config"
+          config_map {
+            name = "cilium"
+          }
+        }
+      }
+    }
+  }
+}
+

addons/cilium/service-account.tf

@@ -0,0 +1,15 @@
+resource "kubernetes_service_account" "operator" {
+  metadata {
+    name      = "cilium-operator"
+    namespace = "kube-system"
+  }
+  automount_service_account_token = false
+}
+
+resource "kubernetes_service_account" "agent" {
+  metadata {
+    name      = "cilium-agent"
+    namespace = "kube-system"
+  }
+  automount_service_account_token = false
+}

addons/cilium/variables.tf

@@ -0,0 +1,17 @@
+variable "pod_cidr" {
+  type        = string
+  description = "CIDR IP range to assign Kubernetes pods"
+  default     = "10.2.0.0/16"
+}
+
+variable "daemonset_tolerations" {
+  type        = list(string)
+  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
+  default     = []
+}
+
+variable "enable_hubble" {
+  type        = bool
+  description = "Run the embedded Hubble Server and mount hubble-server-certs Secret"
+  default     = true
+}

addons/cilium/versions.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "~> 2.8"
+    }
+  }
+}

addons/coredns/cluster-role.tf

@@ -0,0 +1,37 @@
+resource "kubernetes_cluster_role" "coredns" {
+  metadata {
+    name = "system:coredns"
+  }
+  rule {
+    api_groups = [""]
+    resources = [
+      "endpoints",
+      "services",
+      "pods",
+      "namespaces",
+    ]
+    verbs = [
+      "list",
+      "watch",
+    ]
+  }
+  rule {
+    api_groups = [""]
+    resources = [
+      "nodes",
+    ]
+    verbs = [
+      "get",
+    ]
+  }
+  rule {
+    api_groups = ["discovery.k8s.io"]
+    resources = [
+      "endpointslices",
+    ]
+    verbs = [
+      "list",
+      "watch",
+    ]
+  }
+}

addons/coredns/config.tf

@@ -0,0 +1,30 @@
+resource "kubernetes_config_map" "coredns" {
+  metadata {
+    name      = "coredns"
+    namespace = "kube-system"
+  }
+  data = {
+    "Corefile" = <<-EOF
+      .:53 {
+          errors
+          health {
+            lameduck 5s
+          }
+          ready
+          log . {
+              class error
+          }
+          kubernetes ${var.cluster_domain_suffix} in-addr.arpa ip6.arpa {
+              pods insecure
+              fallthrough in-addr.arpa ip6.arpa
+          }
+          prometheus :9153
+          forward . /etc/resolv.conf
+          cache 30
+          loop
+          reload
+          loadbalance
+      }
+  EOF
+  }
+}

addons/coredns/deployment.tf

@@ -0,0 +1,151 @@
+resource "kubernetes_deployment" "coredns" {
+  wait_for_rollout = false
+  metadata {
+    name      = "coredns"
+    namespace = "kube-system"
+    labels = {
+      k8s-app              = "coredns"
+      "kubernetes.io/name" = "CoreDNS"
+    }
+  }
+  spec {
+    replicas = var.replicas
+    strategy {
+      type = "RollingUpdate"
+      rolling_update {
+        max_unavailable = "1"
+      }
+    }
+    selector {
+      match_labels = {
+        k8s-app = "coredns"
+        tier    = "control-plane"
+      }
+    }
+    template {
+      metadata {
+        labels = {
+          k8s-app = "coredns"
+          tier    = "control-plane"
+        }
+      }
+      spec {
+        affinity {
+          node_affinity {
+            preferred_during_scheduling_ignored_during_execution {
+              weight = 100
+              preference {
+                match_expressions {
+                  key      = "node.kubernetes.io/controller"
+                  operator = "Exists"
+                }
+              }
+            }
+          }
+          pod_anti_affinity {
+            preferred_during_scheduling_ignored_during_execution {
+              weight = 100
+              pod_affinity_term {
+                label_selector {
+                  match_expressions {
+                    key      = "tier"
+                    operator = "In"
+                    values   = ["control-plane"]
+                  }
+                  match_expressions {
+                    key      = "k8s-app"
+                    operator = "In"
+                    values   = ["coredns"]
+                  }
+                }
+                topology_key = "kubernetes.io/hostname"
+              }
+            }
+          }
+        }
+        dns_policy          = "Default"
+        priority_class_name = "system-cluster-critical"
+        security_context {
+          seccomp_profile {
+            type = "RuntimeDefault"
+          }
+        }
+        service_account_name = "coredns"
+        toleration {
+          key    = "node-role.kubernetes.io/controller"
+          effect = "NoSchedule"
+        }
+        container {
+          name  = "coredns"
+          image = "registry.k8s.io/coredns/coredns:v1.11.1"
+          args  = ["-conf", "/etc/coredns/Corefile"]
+          port {
+            name           = "dns"
+            container_port = 53
+            protocol       = "UDP"
+          }
+          port {
+            name           = "dns-tcp"
+            container_port = 53
+            protocol       = "TCP"
+          }
+          port {
+            name           = "metrics"
+            container_port = 9153
+            protocol       = "TCP"
+          }
+          resources {
+            requests = {
+              cpu    = "100m"
+              memory = "70Mi"
+            }
+            limits = {
+              memory = "170Mi"
+            }
+          }
+          security_context {
+            capabilities {
+              add  = ["NET_BIND_SERVICE"]
+              drop = ["all"]
+            }
+            read_only_root_filesystem = true
+          }
+          liveness_probe {
+            http_get {
+              path   = "/health"
+              port   = "8080"
+              scheme = "HTTP"
+            }
+            initial_delay_seconds = 60
+            timeout_seconds       = 5
+            success_threshold     = 1
+            failure_threshold     = 5
+          }
+          readiness_probe {
+            http_get {
+              path   = "/ready"
+              port   = "8181"
+              scheme = "HTTP"
+            }
+          }
+          volume_mount {
+            name       = "config"
+            mount_path = "/etc/coredns"
+            read_only  = true
+          }
+        }
+        volume {
+          name = "config"
+          config_map {
+            name = "coredns"
+            items {
+              key  = "Corefile"
+              path = "Corefile"
+            }
+          }
+        }
+      }
+    }
+  }
+}
+

addons/coredns/service-account.tf

@@ -0,0 +1,24 @@
+resource "kubernetes_service_account" "coredns" {
+  metadata {
+    name      = "coredns"
+    namespace = "kube-system"
+  }
+  automount_service_account_token = false
+}
+
+
+resource "kubernetes_cluster_role_binding" "coredns" {
+  metadata {
+    name = "system:coredns"
+  }
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "ClusterRole"
+    name      = "system:coredns"
+  }
+  subject {
+    kind      = "ServiceAccount"
+    name      = "coredns"
+    namespace = "kube-system"
+  }
+}

addons/coredns/service.tf

@@ -0,0 +1,31 @@
+resource "kubernetes_service" "coredns" {
+  metadata {
+    name      = "coredns"
+    namespace = "kube-system"
+    labels = {
+      "k8s-app"            = "coredns"
+      "kubernetes.io/name" = "CoreDNS"
+    }
+    annotations = {
+      "prometheus.io/scrape" = "true"
+      "prometheus.io/port"   = "9153"
+    }
+  }
+  spec {
+    type       = "ClusterIP"
+    cluster_ip = var.cluster_dns_service_ip
+    selector = {
+      k8s-app = "coredns"
+    }
+    port {
+      name     = "dns"
+      protocol = "UDP"
+      port     = 53
+    }
+    port {
+      name     = "dns-tcp"
+      protocol = "TCP"
+      port     = 53
+    }
+  }
+}

addons/coredns/variables.tf

@@ -0,0 +1,15 @@
+variable "replicas" {
+  type        = number
+  description = "CoreDNS replica count"
+  default     = 2
+}
+
+variable "cluster_dns_service_ip" {
+  description = "Must be set to `cluster_dns_service_ip` output by cluster"
+  default     = "10.3.0.10"
+}
+
+variable "cluster_domain_suffix" {
+  description = "Must be set to `cluster_domain_suffix` output by cluster"
+  default     = "cluster.local"
+}

addons/coredns/versions.tf

@@ -0,0 +1,9 @@
+terraform {
+  required_providers {
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "~> 2.8"
+    }
+  }
+}
+

addons/flannel/cluster-role-binding.tf

@@ -0,0 +1,18 @@
+resource "kubernetes_cluster_role_binding" "flannel" {
+  metadata {
+    name = "flannel"
+  }
+
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "ClusterRole"
+    name      = "flannel"
+  }
+
+  subject {
+    kind      = "ServiceAccount"
+    name      = "flannel"
+    namespace = "kube-system"
+  }
+}
+

addons/flannel/cluster-role.tf

@@ -0,0 +1,24 @@
+resource "kubernetes_cluster_role" "flannel" {
+  metadata {
+    name = "flannel"
+  }
+
+  rule {
+    api_groups = [""]
+    resources  = ["pods"]
+    verbs      = ["get"]
+  }
+
+  rule {
+    api_groups = [""]
+    resources  = ["nodes"]
+    verbs      = ["list", "watch"]
+  }
+
+  rule {
+    api_groups = [""]
+    resources  = ["nodes/status"]
+    verbs      = ["patch"]
+  }
+}
+

addons/flannel/config.tf

@@ -0,0 +1,44 @@
+resource "kubernetes_config_map" "config" {
+  metadata {
+    name      = "flannel-config"
+    namespace = "kube-system"
+    labels = {
+      k8s-app = "flannel"
+      tier    = "node"
+    }
+  }
+
+  data = {
+    "cni-conf.json" = <<-EOF
+      {
+        "name": "cbr0",
+        "cniVersion": "0.3.1",
+        "plugins": [
+          {
+            "type": "flannel",
+            "delegate": {
+              "hairpinMode": true,
+              "isDefaultGateway": true
+            }
+          },
+          {
+            "type": "portmap",
+            "capabilities": {
+              "portMappings": true
+            }
+          }
+        ]
+      }
+    EOF
+    "net-conf.json" = <<-EOF
+      {
+        "Network": "${var.pod_cidr}",
+        "Backend": {
+          "Type": "vxlan",
+          "Port": 4789
+        }
+      }
+    EOF
+  }
+}
+

addons/flannel/daemonset.tf

@@ -0,0 +1,167 @@
+resource "kubernetes_daemonset" "flannel" {
+  metadata {
+    name      = "flannel"
+    namespace = "kube-system"
+    labels = {
+      k8s-app = "flannel"
+    }
+  }
+  spec {
+    strategy {
+      type = "RollingUpdate"
+      rolling_update {
+        max_unavailable = "1"
+      }
+    }
+    selector {
+      match_labels = {
+        k8s-app = "flannel"
+      }
+    }
+    template {
+      metadata {
+        labels = {
+          k8s-app = "flannel"
+        }
+      }
+      spec {
+        host_network         = true
+        priority_class_name  = "system-node-critical"
+        service_account_name = "flannel"
+        security_context {
+          seccomp_profile {
+            type = "RuntimeDefault"
+          }
+        }
+        toleration {
+          key      = "node-role.kubernetes.io/controller"
+          operator = "Exists"
+        }
+        toleration {
+          key      = "node.kubernetes.io/not-ready"
+          operator = "Exists"
+        }
+        dynamic "toleration" {
+          for_each = var.daemonset_tolerations
+          content {
+            key      = toleration.value
+            operator = "Exists"
+          }
+        }
+        init_container {
+          name    = "install-cni"
+          image   = "quay.io/poseidon/flannel-cni:v0.4.2"
+          command = ["/install-cni.sh"]
+          env {
+            name = "CNI_NETWORK_CONFIG"
+            value_from {
+              config_map_key_ref {
+                name = "flannel-config"
+                key  = "cni-conf.json"
+              }
+            }
+          }
+          volume_mount {
+            name       = "cni-bin-dir"
+            mount_path = "/host/opt/cni/bin/"
+          }
+          volume_mount {
+            name       = "cni-conf-dir"
+            mount_path = "/host/etc/cni/net.d"
+          }
+        }
+
+        container {
+          name  = "flannel"
+          image = "docker.io/flannel/flannel:v0.25.1"
+          command = [
+            "/opt/bin/flanneld",
+            "--ip-masq",
+            "--kube-subnet-mgr",
+            "--iface=$(POD_IP)"
+          ]
+          env {
+            name = "POD_NAME"
+            value_from {
+              field_ref {
+                field_path = "metadata.name"
+              }
+            }
+          }
+          env {
+            name = "POD_NAMESPACE"
+            value_from {
+              field_ref {
+                field_path = "metadata.namespace"
+              }
+            }
+          }
+          env {
+            name = "POD_IP"
+            value_from {
+              field_ref {
+                field_path = "status.podIP"
+              }
+            }
+          }
+          security_context {
+            privileged = true
+          }
+          resources {
+            requests = {
+              cpu = "100m"
+            }
+          }
+          volume_mount {
+            name       = "flannel-config"
+            mount_path = "/etc/kube-flannel/"
+          }
+          volume_mount {
+            name       = "run-flannel"
+            mount_path = "/run/flannel"
+          }
+          volume_mount {
+            name       = "xtables-lock"
+            mount_path = "/run/xtables.lock"
+          }
+        }
+
+        volume {
+          name = "flannel-config"
+          config_map {
+            name = "flannel-config"
+          }
+        }
+        volume {
+          name = "run-flannel"
+          host_path {
+            path = "/run/flannel"
+          }
+        }
+        # Used by install-cni
+        volume {
+          name = "cni-bin-dir"
+          host_path {
+            path = "/opt/cni/bin"
+          }
+        }
+        volume {
+          name = "cni-conf-dir"
+          host_path {
+            path = "/etc/cni/net.d"
+            type = "DirectoryOrCreate"
+          }
+        }
+        # Acces iptables concurrently
+        volume {
+          name = "xtables-lock"
+          host_path {
+            path = "/run/xtables.lock"
+            type = "FileOrCreate"
+          }
+        }
+      }
+    }
+  }
+}
+

addons/flannel/service-account.tf

@@ -0,0 +1,7 @@
+resource "kubernetes_service_account" "flannel" {
+  metadata {
+    name      = "flannel"
+    namespace = "kube-system"
+  }
+}
+

addons/flannel/variables.tf

@@ -0,0 +1,11 @@
+variable "pod_cidr" {
+  type        = string
+  description = "CIDR IP range to assign Kubernetes pods"
+  default     = "10.2.0.0/16"
+}
+
+variable "daemonset_tolerations" {
+  type        = list(string)
+  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
+  default     = []
+}

addons/flannel/versions.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    kubernetes = {
+      source  = "hashicorp/kubernetes"
+      version = "~> 2.8"
+    }
+  }
+}

addons/grafana/deployment.yaml

@@ -24,7 +24,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: grafana
-          image: docker.io/grafana/grafana:8.5.3
+          image: docker.io/grafana/grafana:9.3.1
           env:
             - name: GF_PATHS_CONFIG
               value: "/etc/grafana/custom.ini"
@@ -32,15 +32,22 @@ spec:
             - name: http
               containerPort: 8080
           livenessProbe:
-            httpGet:
-              path: /metrics
+            tcpSocket:
               port: 8080
-            initialDelaySeconds: 10
+            initialDelaySeconds: 30
+            periodSeconds: 10
+            timeoutSeconds: 1
+            failureThreshold: 5
+            successThreshold: 1
           readinessProbe:
             httpGet:
-              path: /api/health
+              scheme: HTTP
+              path: /robots.txt
               port: 8080
             initialDelaySeconds: 10
+            periodSeconds: 30
+            successThreshold: 1
+            timeoutSeconds: 5
           resources:
             requests:
               cpu: 100m

addons/nginx-ingress/aws/deployment.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: k8s.gcr.io/ingress-nginx/controller:v1.2.1
+          image: registry.k8s.io/ingress-nginx/controller:v1.5.1
           args:
             - /nginx-ingress-controller
             - --controller-class=k8s.io/public

addons/nginx-ingress/aws/rbac/role.yaml

@@ -10,6 +10,7 @@ rules:
       - configmaps
       - pods
       - secrets
+      - endpoints
     verbs:
       - get
   - apiGroups:
@@ -37,3 +38,11 @@ rules:
       - endpoints
     verbs:
       - get
+  - apiGroups:
+      - "coordination.k8s.io"
+    resources:
+      - leases
+    verbs:
+      - create
+      - get
+      - update

addons/nginx-ingress/azure/deployment.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: k8s.gcr.io/ingress-nginx/controller:v1.2.1
+          image: registry.k8s.io/ingress-nginx/controller:v1.5.1
           args:
             - /nginx-ingress-controller
             - --controller-class=k8s.io/public

addons/nginx-ingress/azure/rbac/role.yaml

@@ -10,6 +10,7 @@ rules:
       - configmaps
       - pods
       - secrets
+      - endpoints
     verbs:
       - get
   - apiGroups:
@@ -32,8 +33,11 @@ rules:
     verbs:
       - create
   - apiGroups:
-      - ""
+      - "coordination.k8s.io"
     resources:
-      - endpoints
+      - leases
     verbs:
+      - create
       - get
+      - update
+

addons/nginx-ingress/bare-metal/deployment.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: k8s.gcr.io/ingress-nginx/controller:v1.2.1
+          image: registry.k8s.io/ingress-nginx/controller:v1.5.1
           args:
             - /nginx-ingress-controller
             - --controller-class=k8s.io/public

addons/nginx-ingress/bare-metal/rbac/role.yaml

@@ -10,6 +10,7 @@ rules:
       - configmaps
       - pods
       - secrets
+      - endpoints
     verbs:
       - get
   - apiGroups:
@@ -32,8 +33,10 @@ rules:
     verbs:
       - create
   - apiGroups:
-      - ""
+      - "coordination.k8s.io"
     resources:
-      - endpoints
+      - leases
     verbs:
+      - create
       - get
+      - update

addons/nginx-ingress/digital-ocean/daemonset.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: k8s.gcr.io/ingress-nginx/controller:v1.2.1
+          image: registry.k8s.io/ingress-nginx/controller:v1.5.1
           args:
             - /nginx-ingress-controller
             - --controller-class=k8s.io/public

addons/nginx-ingress/digital-ocean/rbac/role.yaml

@@ -10,6 +10,7 @@ rules:
       - configmaps
       - pods
       - secrets
+      - endpoints
     verbs:
       - get
   - apiGroups:
@@ -32,8 +33,10 @@ rules:
     verbs:
       - create
   - apiGroups:
-      - ""
+      - "coordination.k8s.io"
     resources:
-      - endpoints
+      - leases
     verbs:
+      - create
       - get
+      - update

addons/nginx-ingress/google-cloud/deployment.yaml

@@ -23,7 +23,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: k8s.gcr.io/ingress-nginx/controller:v1.2.1
+          image: registry.k8s.io/ingress-nginx/controller:v1.5.1
           args:
             - /nginx-ingress-controller
             - --controller-class=k8s.io/public

addons/nginx-ingress/google-cloud/rbac/cluster-role.yaml

@@ -59,4 +59,11 @@ rules:
       - get
       - list
       - watch
-
+  - apiGroups: 
+      - discovery.k8s.io
+    resources:
+      - "endpointslices"
+    verbs: 
+      - get
+      - list
+      - watch

addons/nginx-ingress/google-cloud/rbac/role.yaml

@@ -10,6 +10,7 @@ rules:
       - configmaps
       - pods
       - secrets
+      - endpoints
     verbs:
       - get
   - apiGroups:
@@ -32,8 +33,10 @@ rules:
     verbs:
       - create
   - apiGroups:
-      - ""
+      - "coordination.k8s.io"
     resources:
-      - endpoints
+      - leases
     verbs:
+      - create
       - get
+      - update

addons/prometheus/deployment.yaml

@@ -21,7 +21,7 @@ spec:
       serviceAccountName: prometheus
       containers:
         - name: prometheus
-          image: quay.io/prometheus/prometheus:v2.36.0
+          image: quay.io/prometheus/prometheus:v2.40.5
           args:
             - --web.listen-address=0.0.0.0:9090
             - --config.file=/etc/prometheus/prometheus.yaml

addons/prometheus/exporters/kube-state-metrics/deployment.yaml

@@ -25,7 +25,7 @@ spec:
       serviceAccountName: kube-state-metrics
       containers:
       - name: kube-state-metrics
-        image: k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.4.2
+        image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.7.0
         ports:
           - name: metrics
             containerPort: 8080

addons/prometheus/exporters/node-exporter/daemonset.yaml

@@ -22,19 +22,19 @@ spec:
       securityContext:
         runAsNonRoot: true
         runAsUser: 65534
+        runAsGroup: 65534
+        fsGroup: 65534
         seccompProfile:
           type: RuntimeDefault
       hostNetwork: true
       hostPID: true
       containers:
       - name: node-exporter
-        image: quay.io/prometheus/node-exporter:v1.3.1
+        image: quay.io/prometheus/node-exporter:v1.5.0
         args:
           - --path.procfs=/host/proc
           - --path.sysfs=/host/sys
           - --path.rootfs=/host/root
-          - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+)($|/)
-          - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
         ports:
           - name: metrics
             containerPort: 9100
@@ -46,6 +46,9 @@ spec:
           limits:
             cpu: 200m
             memory: 100Mi
+        securityContext:
+          seLinuxOptions:
+            type: spc_t
         volumeMounts:
           - name: proc
             mountPath: /host/proc
@@ -55,9 +58,12 @@ spec:
             readOnly: true
           - name: root
             mountPath: /host/root
+            mountPropagation: HostToContainer
             readOnly: true
       tolerations:
-        - key: node-role.kubernetes.io/master
+        - key: node-role.kubernetes.io/controller
+          operator: Exists
+        - key: node-role.kubernetes.io/control-plane
           operator: Exists
         - key: node.kubernetes.io/not-ready
           operator: Exists

aws/fedora-coreos/kubernetes/README.md

@@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
 * Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/fedora-coreos/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization

aws/fedora-coreos/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=f325be50417e27dde6599a293409cb7d068cda0c"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=e1b1e0c75e77e042cf369f463f0e656297a201a8"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]
@@ -13,5 +13,6 @@ module "bootstrap" {
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
   daemonset_tolerations = var.daemonset_tolerations
+  components            = var.components
 }
 

aws/fedora-coreos/kubernetes/butane/controller.yaml

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.4.0
+version: 1.5.0
 systemd:
   units:
     - name: etcd-member.service
@@ -9,15 +9,16 @@ systemd:
         [Unit]
         Description=etcd (System Container)
         Documentation=https://github.com/etcd-io/etcd
-        Wants=network-online.target network.target
+        Wants=network-online.target
         After=network-online.target
         [Service]
-        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.4
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
         Type=exec
         ExecStartPre=/bin/mkdir -p /var/lib/etcd
         ExecStartPre=-/usr/bin/podman rm etcd
         ExecStart=/usr/bin/podman run --name etcd \
           --env-file /etc/etcd/etcd.env \
+          --log-driver k8s-file \
           --network host \
           --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
           --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
@@ -56,7 +57,7 @@ systemd:
         After=afterburn.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         EnvironmentFile=/run/metadata/afterburn
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -66,6 +67,7 @@ systemd:
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
         ExecStartPre=-/usr/bin/podman rm kubelet
         ExecStart=/usr/bin/podman run --name kubelet \
+          --log-driver k8s-file \
           --privileged \
           --pid host \
           --network host \
@@ -85,28 +87,13 @@ systemd:
           --volume /var/run/lock:/var/run/lock:z \
           --volume /opt/cni/bin:/opt/cni/bin:z \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --cgroups-per-qos=true \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --enforce-node-allocatable=pods \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID} \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
         Restart=always
@@ -129,7 +116,7 @@ systemd:
             --volume /opt/bootstrap/assets:/assets:ro,Z \
             --volume /opt/bootstrap/apply:/apply:ro,Z \
             --entrypoint=/apply \
-            quay.io/poseidon/kubelet:v1.24.1
+            quay.io/poseidon/kubelet:v1.30.1
         ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
         ExecStartPost=-/usr/bin/podman stop bootstrap
 storage:
@@ -144,12 +131,39 @@ storage:
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
     - path: /opt/bootstrap/layout
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          mkdir -p -- auth tls/{etcd,k8s} static-manifests manifests/{coredns,kube-proxy,network}
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
           mkdir -p /etc/kubernetes/pki
@@ -163,8 +177,7 @@ storage:
           mv static-manifests/* /etc/kubernetes/manifests/
           mkdir -p /opt/bootstrap/assets
           mv manifests /opt/bootstrap/assets/manifests
-          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls manifests-networking
+          rm -rf assets auth static-manifests tls manifests
           chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
     - path: /opt/bootstrap/apply
       mode: 0544
@@ -180,6 +193,11 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
       contents:
         inline: |
@@ -224,7 +242,6 @@ storage:
           ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
           ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
           ETCD_PEER_CLIENT_CERT_AUTH=true
-    - path: /etc/fedora-coreos/iptables-legacy.stamp
     - path: /etc/containerd/config.toml
       overwrite: true
       contents:

aws/fedora-coreos/kubernetes/controllers.tf

@@ -23,7 +23,7 @@ resource "aws_instance" "controllers" {
 
   instance_type = var.controller_type
   ami           = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
-  user_data     = data.ct_config.controller-ignitions.*.rendered[count.index]
+  user_data     = data.ct_config.controllers.*.rendered[count.index]
 
   # storage
   root_block_device {
@@ -31,6 +31,7 @@ resource "aws_instance" "controllers" {
     volume_size = var.disk_size
     iops        = var.disk_iops
     encrypted   = true
+    tags        = {}
   }
 
   # network
@@ -46,41 +47,22 @@ resource "aws_instance" "controllers" {
   }
 }
 
-# Controller Ignition configs
-data "ct_config" "controller-ignitions" {
-  count    = var.controller_count
-  content  = data.template_file.controller-configs.*.rendered[count.index]
-  strict   = true
-  snippets = var.controller_snippets
-}
-
-# Controller Fedora CoreOS configs
-data "template_file" "controller-configs" {
+# Fedora CoreOS controllers
+data "ct_config" "controllers" {
   count = var.controller_count
-
-  template = file("${path.module}/fcc/controller.yaml")
-
-  vars = {
+  content = templatefile("${path.module}/butane/controller.yaml", {
     # Cannot use cyclic dependencies on controllers or their DNS records
     etcd_name   = "etcd${count.index}"
     etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
     # etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
-    etcd_initial_cluster   = join(",", data.template_file.etcds.*.rendered)
+    etcd_initial_cluster = join(",", [
+      for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
+    ])
     kubeconfig             = indent(10, module.bootstrap.kubeconfig-kubelet)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
-  }
+  })
+  strict   = true
+  snippets = var.controller_snippets
 }
-
-data "template_file" "etcds" {
-  count    = var.controller_count
-  template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
-
-  vars = {
-    index        = count.index
-    cluster_name = var.cluster_name
-    dns_zone     = var.dns_zone
-  }
-}
-

aws/fedora-coreos/kubernetes/security.tf

@@ -92,6 +92,30 @@ resource "aws_security_group_rule" "controller-cilium-health-self" {
   self      = true
 }
 
+resource "aws_security_group_rule" "controller-cilium-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 9962
+  to_port                  = 9965
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-cilium-metrics-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 9962
+  to_port   = 9965
+  self      = true
+}
+
 # IANA VXLAN default
 resource "aws_security_group_rule" "controller-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
@@ -379,6 +403,30 @@ resource "aws_security_group_rule" "worker-cilium-health-self" {
   self      = true
 }
 
+resource "aws_security_group_rule" "worker-cilium-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 9962
+  to_port                  = 9965
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-cilium-metrics-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 9962
+  to_port   = 9965
+  self      = true
+}
+
 # IANA VXLAN default
 resource "aws_security_group_rule" "worker-vxlan" {
   count = var.networking == "flannel" ? 1 : 0

aws/fedora-coreos/kubernetes/variables.tf

@@ -176,3 +176,19 @@ variable "daemonset_tolerations" {
   description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
   default     = []
 }
+
+variable "components" {
+  description = "Configure pre-installed cluster components"
+  # Component configs are passed through to terraform-render-bootstrap,
+  # which handles type enforcement and defines defaults
+  # https://github.com/poseidon/terraform-render-bootstrap/blob/main/variables.tf#L95
+  type = object({
+    enable     = optional(bool)
+    coredns    = optional(map(any))
+    kube_proxy = optional(map(any))
+    flannel    = optional(map(any))
+    calico     = optional(map(any))
+    cilium     = optional(map(any))
+  })
+  default = null
+}

aws/fedora-coreos/kubernetes/versions.tf

@@ -3,13 +3,11 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    aws      = ">= 2.23, <= 5.0"
-    template = "~> 2.2"
-    null     = ">= 2.1"
-
+    aws  = ">= 2.23, <= 6.0"
+    null = ">= 2.1"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

aws/fedora-coreos/kubernetes/workers/ami.tf

@@ -1,3 +1,7 @@
+locals {
+  ami_id = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
+}
+
 data "aws_ami" "fedora-coreos" {
   most_recent = true
   owners      = ["125523088429"]

aws/fedora-coreos/kubernetes/workers/butane/worker.yaml

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.4.0
+version: 1.5.0
 systemd:
   units:
     - name: containerd.service
@@ -29,7 +29,7 @@ systemd:
         After=afterburn.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         EnvironmentFile=/run/metadata/afterburn
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -39,6 +39,7 @@ systemd:
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
         ExecStartPre=-/usr/bin/podman rm kubelet
         ExecStart=/usr/bin/podman run --name kubelet \
+          --log-driver k8s-file \
           --privileged \
           --pid host \
           --network host \
@@ -58,19 +59,9 @@ systemd:
           --volume /var/run/lock:/var/run/lock:z \
           --volume /opt/cni/bin:/opt/cni/bin:z \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --cgroups-per-qos=true \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --enforce-node-allocatable=pods \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/node \
           %{~ for label in split(",", node_labels) ~}
@@ -79,31 +70,13 @@ systemd:
           %{~ for taint in split(",", node_taints) ~}
           --register-with-taints=${taint} \
           %{~ endfor ~}
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID} \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID}
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
         Restart=always
         RestartSec=10
         [Install]
         WantedBy=multi-user.target
-    - name: delete-node.service
-      enabled: true
-      contents: |
-        [Unit]
-        Description=Delete Kubernetes node on shutdown
-        [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/bin/bash -c '/usr/bin/podman run --volume /var/lib/kubelet:/var/lib/kubelet:ro,z --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
-        [Install]
-        WantedBy=multi-user.target
 storage:
   directories:
     - path: /etc/kubernetes
@@ -113,6 +86,38 @@ storage:
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
       contents:
         inline: |
@@ -136,7 +141,6 @@ storage:
           DefaultCPUAccounting=yes
           DefaultMemoryAccounting=yes
           DefaultBlockIOAccounting=yes
-    - path: /etc/fedora-coreos/iptables-legacy.stamp
     - path: /etc/containerd/config.toml
       overwrite: true
       contents:

aws/fedora-coreos/kubernetes/workers/versions.tf

@@ -3,12 +3,10 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    aws      = ">= 2.23, <= 5.0"
-    template = "~> 2.2"
-
+    aws = ">= 2.23, <= 6.0"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

aws/fedora-coreos/kubernetes/workers/workers.tf

@@ -1,6 +1,6 @@
 # Workers AutoScaling Group
 resource "aws_autoscaling_group" "workers" {
-  name = "${var.name}-worker ${aws_launch_configuration.worker.name}"
+  name = "${var.name}-worker"
 
   # count
   desired_capacity          = var.worker_count
@@ -13,7 +13,10 @@ resource "aws_autoscaling_group" "workers" {
   vpc_zone_identifier = var.subnet_ids
 
   # template
-  launch_configuration = aws_launch_configuration.worker.name
+  launch_template {
+    id      = aws_launch_template.worker.id
+    version = aws_launch_template.worker.latest_version
+  }
 
   # target groups to which instances should be added
   target_group_arns = flatten([
@@ -22,6 +25,14 @@ resource "aws_autoscaling_group" "workers" {
     var.target_groups,
   ])
 
+  instance_refresh {
+    strategy = "Rolling"
+    preferences {
+      instance_warmup        = 120
+      min_healthy_percentage = 90
+    }
+  }
+
   lifecycle {
     # override the default destroy and replace update behavior
     create_before_destroy = true
@@ -41,24 +52,47 @@ resource "aws_autoscaling_group" "workers" {
 }
 
 # Worker template
-resource "aws_launch_configuration" "worker" {
-  image_id          = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
-  instance_type     = var.instance_type
-  spot_price        = var.spot_price > 0 ? var.spot_price : null
-  enable_monitoring = false
+resource "aws_launch_template" "worker" {
+  name_prefix   = "${var.name}-worker"
+  image_id      = local.ami_id
+  instance_type = var.instance_type
+  monitoring {
+    enabled = false
+  }
 
-  user_data = data.ct_config.worker-ignition.rendered
+  user_data = sensitive(base64encode(data.ct_config.worker.rendered))
 
   # storage
-  root_block_device {
-    volume_type = var.disk_type
-    volume_size = var.disk_size
-    iops        = var.disk_iops
-    encrypted   = true
+  ebs_optimized = true
+  block_device_mappings {
+    device_name = "/dev/xvda"
+    ebs {
+      volume_type           = var.disk_type
+      volume_size           = var.disk_size
+      iops                  = var.disk_iops
+      encrypted             = true
+      delete_on_termination = true
+    }
   }
 
   # network
-  security_groups = var.security_groups
+  vpc_security_group_ids = var.security_groups
+
+  # metadata
+  metadata_options {
+    http_tokens = "optional"
+  }
+
+  # spot
+  dynamic "instance_market_options" {
+    for_each = var.spot_price > 0 ? [1] : []
+    content {
+      market_type = "spot"
+      spot_options {
+        max_price = var.spot_price
+      }
+    }
+  }
 
   lifecycle {
     // Override the default destroy and replace update behavior
@@ -67,24 +101,16 @@ resource "aws_launch_configuration" "worker" {
   }
 }
 
-# Worker Ignition config
-data "ct_config" "worker-ignition" {
-  content  = data.template_file.worker-config.rendered
-  strict   = true
-  snippets = var.snippets
-}
-
-# Worker Fedora CoreOS config
-data "template_file" "worker-config" {
-  template = file("${path.module}/fcc/worker.yaml")
-
-  vars = {
+# Fedora CoreOS worker
+data "ct_config" "worker" {
+  content = templatefile("${path.module}/butane/worker.yaml", {
     kubeconfig             = indent(10, var.kubeconfig)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
     node_labels            = join(",", var.node_labels)
     node_taints            = join(",", var.node_taints)
-  }
+  })
+  strict   = true
+  snippets = var.snippets
 }
-

aws/flatcar-linux/kubernetes/README.md

@@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
 * Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/flatcar-linux/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization

aws/flatcar-linux/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=f325be50417e27dde6599a293409cb7d068cda0c"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=e1b1e0c75e77e042cf369f463f0e656297a201a8"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]
@@ -13,5 +13,6 @@ module "bootstrap" {
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
   daemonset_tolerations = var.daemonset_tolerations
+  components            = var.components
 }
 

aws/flatcar-linux/kubernetes/butane/controller.yaml

@@ -1,4 +1,5 @@
----
+variant: flatcar
+version: 1.0.0
 systemd:
   units:
     - name: etcd-member.service
@@ -10,7 +11,7 @@ systemd:
         Requires=docker.service
         After=docker.service
         [Service]
-        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.4
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
         ExecStartPre=/usr/bin/docker run -d \
           --name etcd \
           --network host \
@@ -57,7 +58,7 @@ systemd:
         After=coreos-metadata.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         EnvironmentFile=/run/metadata/coreos
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -83,26 +84,13 @@ systemd:
           -v /var/log:/var/log \
           -v /opt/cni/bin:/opt/cni/bin \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID} \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
         ExecStart=docker logs -f kubelet
         ExecStop=docker stop kubelet
         ExecStopPost=docker rm kubelet
@@ -121,7 +109,7 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStart=/usr/bin/docker run \
             -v /etc/kubernetes/pki:/etc/kubernetes/pki:ro \
             -v /opt/bootstrap/assets:/assets:ro \
@@ -134,23 +122,47 @@ systemd:
 storage:
   directories:
     - path: /var/lib/etcd
-      filesystem: root
       mode: 0700
       overwrite: true
   files:
     - path: /etc/kubernetes/kubeconfig
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
     - path: /opt/bootstrap/layout
-      filesystem: root
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          mkdir -p -- auth tls/{etcd,k8s} static-manifests manifests/{coredns,kube-proxy,network}
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
           mkdir -p /etc/kubernetes/pki
@@ -165,10 +177,8 @@ storage:
           mv static-manifests/* /etc/kubernetes/manifests/
           mkdir -p /opt/bootstrap/assets
           mv manifests /opt/bootstrap/assets/manifests
-          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls manifests-networking
+          rm -rf assets auth static-manifests tls manifests
     - path: /opt/bootstrap/apply
-      filesystem: root
       mode: 0544
       contents:
         inline: |
@@ -182,14 +192,17 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
     - path: /etc/etcd/etcd.env
-      filesystem: root
       mode: 0644
       contents:
           inline: |

aws/flatcar-linux/kubernetes/controllers.tf

@@ -24,7 +24,7 @@ resource "aws_instance" "controllers" {
   instance_type = var.controller_type
 
   ami       = local.ami_id
-  user_data = data.ct_config.controller-ignitions.*.rendered[count.index]
+  user_data = data.ct_config.controllers.*.rendered[count.index]
 
   # storage
   root_block_device {
@@ -32,6 +32,7 @@ resource "aws_instance" "controllers" {
     volume_size = var.disk_size
     iops        = var.disk_iops
     encrypted   = true
+    tags        = {}
   }
 
   # network
@@ -47,41 +48,22 @@ resource "aws_instance" "controllers" {
   }
 }
 
-# Controller Ignition configs
-data "ct_config" "controller-ignitions" {
-  count    = var.controller_count
-  content  = data.template_file.controller-configs.*.rendered[count.index]
-  strict   = true
-  snippets = var.controller_snippets
-}
-
-# Controller Container Linux configs
-data "template_file" "controller-configs" {
+# Flatcar Linux controllers
+data "ct_config" "controllers" {
   count = var.controller_count
-
-  template = file("${path.module}/cl/controller.yaml")
-
-  vars = {
+  content = templatefile("${path.module}/butane/controller.yaml", {
     # Cannot use cyclic dependencies on controllers or their DNS records
     etcd_name   = "etcd${count.index}"
     etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
     # etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
-    etcd_initial_cluster   = join(",", data.template_file.etcds.*.rendered)
+    etcd_initial_cluster = join(",", [
+      for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
+    ])
     kubeconfig             = indent(10, module.bootstrap.kubeconfig-kubelet)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
-  }
+  })
+  strict   = true
+  snippets = var.controller_snippets
 }
-
-data "template_file" "etcds" {
-  count    = var.controller_count
-  template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
-
-  vars = {
-    index        = count.index
-    cluster_name = var.cluster_name
-    dns_zone     = var.dns_zone
-  }
-}
-

aws/flatcar-linux/kubernetes/security.tf

@@ -92,6 +92,30 @@ resource "aws_security_group_rule" "controller-cilium-health-self" {
   self      = true
 }
 
+resource "aws_security_group_rule" "controller-cilium-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 9962
+  to_port                  = 9965
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-cilium-metrics-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 9962
+  to_port   = 9965
+  self      = true
+}
+
 # IANA VXLAN default
 resource "aws_security_group_rule" "controller-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
@@ -379,6 +403,30 @@ resource "aws_security_group_rule" "worker-cilium-health-self" {
   self      = true
 }
 
+resource "aws_security_group_rule" "worker-cilium-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 9962
+  to_port                  = 9965
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-cilium-metrics-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 9962
+  to_port   = 9965
+  self      = true
+}
+
 # IANA VXLAN default
 resource "aws_security_group_rule" "worker-vxlan" {
   count = var.networking == "flannel" ? 1 : 0

aws/flatcar-linux/kubernetes/variables.tf

@@ -176,3 +176,19 @@ variable "daemonset_tolerations" {
   description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
   default     = []
 }
+
+variable "components" {
+  description = "Configure pre-installed cluster components"
+  # Component configs are passed through to terraform-render-bootstrap,
+  # which handles type enforcement and defines defaults
+  # https://github.com/poseidon/terraform-render-bootstrap/blob/main/variables.tf#L95
+  type = object({
+    enable     = optional(bool)
+    coredns    = optional(map(any))
+    kube_proxy = optional(map(any))
+    flannel    = optional(map(any))
+    calico     = optional(map(any))
+    cilium     = optional(map(any))
+  })
+  default = null
+}

aws/flatcar-linux/kubernetes/versions.tf

@@ -3,13 +3,11 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    aws      = ">= 2.23, <= 5.0"
-    template = "~> 2.2"
-    null     = ">= 2.1"
-
+    aws  = ">= 2.23, <= 6.0"
+    null = ">= 2.1"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

aws/flatcar-linux/kubernetes/workers/butane/worker.yaml

@@ -1,4 +1,5 @@
----
+variant: flatcar
+version: 1.0.0
 systemd:
   units:
     - name: docker.service
@@ -29,7 +30,7 @@ systemd:
         After=coreos-metadata.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         EnvironmentFile=/run/metadata/coreos
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -58,17 +59,9 @@ systemd:
           -v /var/log:/var/log \
           -v /opt/cni/bin:/opt/cni/bin \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/node \
           %{~ for label in split(",", node_labels) ~}
@@ -77,12 +70,7 @@ systemd:
           %{~ for taint in split(",", node_taints) ~}
           --register-with-taints=${taint} \
           %{~ endfor ~}
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID} \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID}
         ExecStart=docker logs -f kubelet
         ExecStop=docker stop kubelet
         ExecStopPost=docker rm kubelet
@@ -90,29 +78,46 @@ systemd:
         RestartSec=5
         [Install]
         WantedBy=multi-user.target
-    - name: delete-node.service
-      enabled: true
-      contents: |
-        [Unit]
-        Description=Delete Kubernetes node on shutdown
-        [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/bin/bash -c '/usr/bin/docker run -v /var/lib/kubelet:/var/lib/kubelet:ro --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
-        [Install]
-        WantedBy=multi-user.target
 storage:
   files:
     - path: /etc/kubernetes/kubeconfig
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
       mode: 0644
       contents:
         inline: |

aws/flatcar-linux/kubernetes/workers/versions.tf

@@ -3,12 +3,10 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    aws      = ">= 2.23, <= 5.0"
-    template = "~> 2.2"
-
+    aws = ">= 2.23, <= 6.0"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

aws/flatcar-linux/kubernetes/workers/workers.tf

@@ -1,6 +1,6 @@
 # Workers AutoScaling Group
 resource "aws_autoscaling_group" "workers" {
-  name = "${var.name}-worker ${aws_launch_configuration.worker.name}"
+  name = "${var.name}-worker"
 
   # count
   desired_capacity          = var.worker_count
@@ -13,7 +13,10 @@ resource "aws_autoscaling_group" "workers" {
   vpc_zone_identifier = var.subnet_ids
 
   # template
-  launch_configuration = aws_launch_configuration.worker.name
+  launch_template {
+    id      = aws_launch_template.worker.id
+    version = aws_launch_template.worker.latest_version
+  }
 
   # target groups to which instances should be added
   target_group_arns = flatten([
@@ -22,6 +25,14 @@ resource "aws_autoscaling_group" "workers" {
     var.target_groups,
   ])
 
+  instance_refresh {
+    strategy = "Rolling"
+    preferences {
+      instance_warmup        = 120
+      min_healthy_percentage = 90
+    }
+  }
+
   lifecycle {
     # override the default destroy and replace update behavior
     create_before_destroy = true
@@ -41,24 +52,47 @@ resource "aws_autoscaling_group" "workers" {
 }
 
 # Worker template
-resource "aws_launch_configuration" "worker" {
-  image_id          = local.ami_id
-  instance_type     = var.instance_type
-  spot_price        = var.spot_price > 0 ? var.spot_price : null
-  enable_monitoring = false
+resource "aws_launch_template" "worker" {
+  name_prefix   = "${var.name}-worker"
+  image_id      = local.ami_id
+  instance_type = var.instance_type
+  monitoring {
+    enabled = false
+  }
 
-  user_data = data.ct_config.worker-ignition.rendered
+  user_data = sensitive(base64encode(data.ct_config.worker.rendered))
 
   # storage
-  root_block_device {
-    volume_type = var.disk_type
-    volume_size = var.disk_size
-    iops        = var.disk_iops
-    encrypted   = true
+  ebs_optimized = true
+  block_device_mappings {
+    device_name = "/dev/xvda"
+    ebs {
+      volume_type           = var.disk_type
+      volume_size           = var.disk_size
+      iops                  = var.disk_iops
+      encrypted             = true
+      delete_on_termination = true
+    }
   }
 
   # network
-  security_groups = var.security_groups
+  vpc_security_group_ids = var.security_groups
+
+  # metadata
+  metadata_options {
+    http_tokens = "optional"
+  }
+
+  # spot
+  dynamic "instance_market_options" {
+    for_each = var.spot_price > 0 ? [1] : []
+    content {
+      market_type = "spot"
+      spot_options {
+        max_price = var.spot_price
+      }
+    }
+  }
 
   lifecycle {
     // Override the default destroy and replace update behavior
@@ -67,24 +101,16 @@ resource "aws_launch_configuration" "worker" {
   }
 }
 
-# Worker Ignition config
-data "ct_config" "worker-ignition" {
-  content  = data.template_file.worker-config.rendered
-  strict   = true
-  snippets = var.snippets
-}
-
-# Worker Container Linux config
-data "template_file" "worker-config" {
-  template = file("${path.module}/cl/worker.yaml")
-
-  vars = {
+# Flatcar Linux worker
+data "ct_config" "worker" {
+  content = templatefile("${path.module}/butane/worker.yaml", {
     kubeconfig             = indent(10, var.kubeconfig)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
     node_labels            = join(",", var.node_labels)
     node_taints            = join(",", var.node_taints)
-  }
+  })
+  strict   = true
+  snippets = var.snippets
 }
-

azure/fedora-coreos/kubernetes/README.md

@@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
 * Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot priority](https://typhoon.psdn.io/fedora-coreos/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization

azure/fedora-coreos/kubernetes/bootstrap.tf

@@ -1,13 +1,12 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=f325be50417e27dde6599a293409cb7d068cda0c"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=e1b1e0c75e77e042cf369f463f0e656297a201a8"
 
   cluster_name = var.cluster_name
   api_servers  = [format("%s.%s", var.cluster_name, var.dns_zone)]
   etcd_servers = formatlist("%s.%s", azurerm_dns_a_record.etcds.*.name, var.dns_zone)
 
   networking = var.networking
-
   # only effective with Calico networking
   # we should be able to use 1450 MTU, but in practice, 1410 was needed
   network_encapsulation = "vxlan"
@@ -19,5 +18,6 @@ module "bootstrap" {
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
   daemonset_tolerations = var.daemonset_tolerations
+  components            = var.components
 }
 

azure/fedora-coreos/kubernetes/butane/controller.yaml

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.4.0
+version: 1.5.0
 systemd:
   units:
     - name: etcd-member.service
@@ -9,15 +9,16 @@ systemd:
         [Unit]
         Description=etcd (System Container)
         Documentation=https://github.com/etcd-io/etcd
-        Wants=network-online.target network.target
+        Wants=network-online.target
         After=network-online.target
         [Service]
-        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.4
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
         Type=exec
         ExecStartPre=/bin/mkdir -p /var/lib/etcd
         ExecStartPre=-/usr/bin/podman rm etcd
         ExecStart=/usr/bin/podman run --name etcd \
           --env-file /etc/etcd/etcd.env \
+          --log-driver k8s-file \
           --network host \
           --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
           --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
@@ -53,7 +54,7 @@ systemd:
         Description=Kubelet (System Container)
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -62,13 +63,14 @@ systemd:
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
         ExecStartPre=-/usr/bin/podman rm kubelet
         ExecStart=/usr/bin/podman run --name kubelet \
+          --log-driver k8s-file \
           --privileged \
           --pid host \
           --network host \
           --volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
           --volume /etc/kubernetes:/etc/kubernetes:ro,z \
-          --volume /usr/lib/os-release:/etc/os-release:ro \
           --volume /etc/machine-id:/etc/machine-id:ro \
+          --volume /usr/lib/os-release:/etc/os-release:ro \
           --volume /lib/modules:/lib/modules:ro \
           --volume /run:/run \
           --volume /sys/fs/cgroup:/sys/fs/cgroup \
@@ -81,27 +83,12 @@ systemd:
           --volume /var/run/lock:/var/run/lock:z \
           --volume /opt/cni/bin:/opt/cni/bin:z \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --cgroups-per-qos=true \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --enforce-node-allocatable=pods \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
         Restart=always
@@ -124,7 +111,7 @@ systemd:
             --volume /opt/bootstrap/assets:/assets:ro,Z \
             --volume /opt/bootstrap/apply:/apply:ro,Z \
             --entrypoint=/apply \
-            quay.io/poseidon/kubelet:v1.24.1
+            quay.io/poseidon/kubelet:v1.30.1
         ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
         ExecStartPost=-/usr/bin/podman stop bootstrap
 storage:
@@ -139,12 +126,39 @@ storage:
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
     - path: /opt/bootstrap/layout
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          mkdir -p -- auth tls/{etcd,k8s} static-manifests manifests/{coredns,kube-proxy,network}
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
           mkdir -p /etc/kubernetes/pki
@@ -158,8 +172,7 @@ storage:
           mv static-manifests/* /etc/kubernetes/manifests/
           mkdir -p /opt/bootstrap/assets
           mv manifests /opt/bootstrap/assets/manifests
-          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls manifests-networking
+          rm -rf assets auth static-manifests tls manifests
           chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
     - path: /opt/bootstrap/apply
       mode: 0544
@@ -175,6 +188,11 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
       contents:
         inline: |
@@ -219,7 +237,6 @@ storage:
           ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
           ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
           ETCD_PEER_CLIENT_CERT_AUTH=true
-    - path: /etc/fedora-coreos/iptables-legacy.stamp
     - path: /etc/containerd/config.toml
       overwrite: true
       contents:
@@ -244,3 +261,4 @@ passwd:
     - name: core
       ssh_authorized_keys:
         - ${ssh_authorized_key}
+

azure/fedora-coreos/kubernetes/controllers.tf

@@ -1,3 +1,11 @@
+locals {
+  # Typhoon ssh_authorized_key supports RSA or a newer formats (e.g. ed25519).
+  # However, Azure requires an older RSA key to pass validations. To use a
+  # newer key format, pass a dummy RSA key as the azure_authorized_key and
+  # delete the associated private key so it's never used.
+  azure_authorized_key = var.azure_authorized_key == "" ? var.ssh_authorized_key : var.azure_authorized_key
+}
+
 # Discrete DNS records for each controller's private IPv4 for etcd usage
 resource "azurerm_dns_a_record" "etcds" {
   count               = var.controller_count
@@ -35,7 +43,7 @@ resource "azurerm_linux_virtual_machine" "controllers" {
   availability_set_id = azurerm_availability_set.controllers.id
 
   size        = var.controller_type
-  custom_data = base64encode(data.ct_config.controller-ignitions.*.rendered[count.index])
+  custom_data = base64encode(data.ct_config.controllers.*.rendered[count.index])
 
   # storage
   source_image_id = var.os_image
@@ -55,7 +63,7 @@ resource "azurerm_linux_virtual_machine" "controllers" {
   admin_username = "core"
   admin_ssh_key {
     username   = "core"
-    public_key = var.ssh_authorized_key
+    public_key = local.azure_authorized_key
   }
 
   lifecycle {
@@ -111,41 +119,22 @@ resource "azurerm_network_interface_backend_address_pool_association" "controlle
   backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
 }
 
-# Controller Ignition configs
-data "ct_config" "controller-ignitions" {
-  count    = var.controller_count
-  content  = data.template_file.controller-configs.*.rendered[count.index]
-  strict   = true
-  snippets = var.controller_snippets
-}
-
-# Controller Fedora CoreOS configs
-data "template_file" "controller-configs" {
+# Fedora CoreOS controllers
+data "ct_config" "controllers" {
   count = var.controller_count
-
-  template = file("${path.module}/fcc/controller.yaml")
-
-  vars = {
+  content = templatefile("${path.module}/butane/controller.yaml", {
     # Cannot use cyclic dependencies on controllers or their DNS records
     etcd_name   = "etcd${count.index}"
     etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
     # etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
-    etcd_initial_cluster   = join(",", data.template_file.etcds.*.rendered)
+    etcd_initial_cluster = join(",", [
+      for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
+    ])
     kubeconfig             = indent(10, module.bootstrap.kubeconfig-kubelet)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
-  }
+  })
+  strict   = true
+  snippets = var.controller_snippets
 }
-
-data "template_file" "etcds" {
-  count    = var.controller_count
-  template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
-
-  vars = {
-    index        = count.index
-    cluster_name = var.cluster_name
-    dns_zone     = var.dns_zone
-  }
-}
-

azure/fedora-coreos/kubernetes/outputs.tf

@@ -39,8 +39,19 @@ output "kubeconfig" {
 
 # Outputs for custom firewalling
 
+output "controller_security_group_name" {
+  description = "Network Security Group for controller nodes"
+  value       = azurerm_network_security_group.controller.name
+}
+
 output "worker_security_group_name" {
-  value = azurerm_network_security_group.worker.name
+  description = "Network Security Group for worker nodes"
+  value       = azurerm_network_security_group.worker.name
+}
+
+output "controller_address_prefixes" {
+  description = "Controller network subnet CIDR addresses (for source/destination)"
+  value       = azurerm_subnet.controller.address_prefixes
 }
 
 output "worker_address_prefixes" {

azure/fedora-coreos/kubernetes/security.tf

@@ -121,7 +121,7 @@ resource "azurerm_network_security_rule" "controller-cilium-health" {
 
   name                         = "allow-cilium-health"
   network_security_group_name  = azurerm_network_security_group.controller.name
-  priority                     = "2019"
+  priority                     = "2018"
   access                       = "Allow"
   direction                    = "Inbound"
   protocol                     = "Tcp"
@@ -131,6 +131,22 @@ resource "azurerm_network_security_rule" "controller-cilium-health" {
   destination_address_prefixes = azurerm_subnet.controller.address_prefixes
 }
 
+resource "azurerm_network_security_rule" "controller-cilium-metrics" {
+  resource_group_name = azurerm_resource_group.cluster.name
+  count               = var.networking == "cilium" ? 1 : 0
+
+  name                         = "allow-cilium-metrics"
+  network_security_group_name  = azurerm_network_security_group.controller.name
+  priority                     = "2019"
+  access                       = "Allow"
+  direction                    = "Inbound"
+  protocol                     = "Tcp"
+  source_port_range            = "*"
+  destination_port_range       = "9962-9965"
+  source_address_prefixes      = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
+  destination_address_prefixes = azurerm_subnet.controller.address_prefixes
+}
+
 resource "azurerm_network_security_rule" "controller-vxlan" {
   resource_group_name = azurerm_resource_group.cluster.name
 
@@ -303,7 +319,7 @@ resource "azurerm_network_security_rule" "worker-cilium-health" {
 
   name                         = "allow-cilium-health"
   network_security_group_name  = azurerm_network_security_group.worker.name
-  priority                     = "2014"
+  priority                     = "2013"
   access                       = "Allow"
   direction                    = "Inbound"
   protocol                     = "Tcp"
@@ -313,6 +329,22 @@ resource "azurerm_network_security_rule" "worker-cilium-health" {
   destination_address_prefixes = azurerm_subnet.worker.address_prefixes
 }
 
+resource "azurerm_network_security_rule" "worker-cilium-metrics" {
+  resource_group_name = azurerm_resource_group.cluster.name
+  count               = var.networking == "cilium" ? 1 : 0
+
+  name                         = "allow-cilium-metrics"
+  network_security_group_name  = azurerm_network_security_group.worker.name
+  priority                     = "2014"
+  access                       = "Allow"
+  direction                    = "Inbound"
+  protocol                     = "Tcp"
+  source_port_range            = "*"
+  destination_port_range       = "9962-9965"
+  source_address_prefixes      = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
+  destination_address_prefixes = azurerm_subnet.worker.address_prefixes
+}
+
 resource "azurerm_network_security_rule" "worker-vxlan" {
   resource_group_name = azurerm_resource_group.cluster.name
 

azure/fedora-coreos/kubernetes/variables.tf

@@ -43,7 +43,7 @@ variable "controller_type" {
 variable "worker_type" {
   type        = string
   description = "Machine type for workers (see `az vm list-skus --location centralus`)"
-  default     = "Standard_DS1_v2"
+  default     = "Standard_D2as_v5"
 }
 
 variable "os_image" {
@@ -82,6 +82,12 @@ variable "ssh_authorized_key" {
   description = "SSH public key for user 'core'"
 }
 
+variable "azure_authorized_key" {
+  type        = string
+  description = "Optionally, pass a dummy RSA key to satisfy Azure validations (then use an ed25519 key set above)"
+  default     = ""
+}
+
 variable "networking" {
   type        = string
   description = "Choice of networking provider (flannel, calico, or cilium)"
@@ -140,3 +146,19 @@ variable "daemonset_tolerations" {
   description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
   default     = []
 }
+
+variable "components" {
+  description = "Configure pre-installed cluster components"
+  # Component configs are passed through to terraform-render-bootstrap,
+  # which handles type enforcement and defines defaults
+  # https://github.com/poseidon/terraform-render-bootstrap/blob/main/variables.tf#L95
+  type = object({
+    enable     = optional(bool)
+    coredns    = optional(map(any))
+    kube_proxy = optional(map(any))
+    flannel    = optional(map(any))
+    calico     = optional(map(any))
+    cilium     = optional(map(any))
+  })
+  default = null
+}

azure/fedora-coreos/kubernetes/versions.tf

@@ -3,13 +3,11 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    azurerm  = ">= 2.8, < 4.0"
-    template = "~> 2.2"
-    null     = ">= 2.1"
-
+    azurerm = ">= 2.8, < 4.0"
+    null    = ">= 2.1"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

azure/fedora-coreos/kubernetes/workers.tf

@@ -17,6 +17,7 @@ module "workers" {
   # configuration
   kubeconfig            = module.bootstrap.kubeconfig-kubelet
   ssh_authorized_key    = var.ssh_authorized_key
+  azure_authorized_key  = var.azure_authorized_key
   service_cidr          = var.service_cidr
   cluster_domain_suffix = var.cluster_domain_suffix
   snippets              = var.worker_snippets

azure/fedora-coreos/kubernetes/workers/butane/worker.yaml

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.4.0
+version: 1.5.0
 systemd:
   units:
     - name: containerd.service
@@ -26,7 +26,7 @@ systemd:
         Description=Kubelet (System Container)
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -35,6 +35,7 @@ systemd:
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
         ExecStartPre=-/usr/bin/podman rm kubelet
         ExecStart=/usr/bin/podman run --name kubelet \
+          --log-driver k8s-file \
           --privileged \
           --pid host \
           --network host \
@@ -54,51 +55,23 @@ systemd:
           --volume /var/run/lock:/var/run/lock:z \
           --volume /opt/cni/bin:/opt/cni/bin:z \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --cgroups-per-qos=true \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --enforce-node-allocatable=pods \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
-          --node-labels=node.kubernetes.io/node \
           %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
           %{~ endfor ~}
           %{~ for taint in split(",", node_taints) ~}
           --register-with-taints=${taint} \
           %{~ endfor ~}
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --node-labels=node.kubernetes.io/node
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
         Restart=always
         RestartSec=10
         [Install]
         WantedBy=multi-user.target
-    - name: delete-node.service
-      enabled: true
-      contents: |
-        [Unit]
-        Description=Delete Kubernetes node on shutdown
-        [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/bin/bash -c '/usr/bin/podman run --volume /var/lib/kubelet:/var/lib/kubelet:ro,z --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
-        [Install]
-        WantedBy=multi-user.target
 storage:
   directories:
     - path: /etc/kubernetes
@@ -108,6 +81,38 @@ storage:
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
       contents:
         inline: |
@@ -131,7 +136,6 @@ storage:
           DefaultCPUAccounting=yes
           DefaultMemoryAccounting=yes
           DefaultBlockIOAccounting=yes
-    - path: /etc/fedora-coreos/iptables-legacy.stamp
     - path: /etc/containerd/config.toml
       overwrite: true
       contents:

azure/fedora-coreos/kubernetes/workers/variables.tf

@@ -41,7 +41,7 @@ variable "worker_count" {
 variable "vm_type" {
   type        = string
   description = "Machine type for instances (see `az vm list-skus --location centralus`)"
-  default     = "Standard_DS1_v2"
+  default     = "Standard_D2as_v5"
 }
 
 variable "os_image" {
@@ -73,6 +73,12 @@ variable "ssh_authorized_key" {
   description = "SSH public key for user 'core'"
 }
 
+variable "azure_authorized_key" {
+  type        = string
+  description = "Optionally, pass a dummy RSA key to satisfy Azure validations (then use an ed25519 key set above)"
+  default     = ""
+}
+
 variable "service_cidr" {
   type        = string
   description = <<EOD

azure/fedora-coreos/kubernetes/workers/versions.tf

@@ -3,12 +3,10 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    azurerm  = ">= 2.8, < 4.0"
-    template = "~> 2.2"
-
+    azurerm = ">= 2.8, < 4.0"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

azure/fedora-coreos/kubernetes/workers/workers.tf

@@ -1,3 +1,7 @@
+locals {
+  azure_authorized_key = var.azure_authorized_key == "" ? var.ssh_authorized_key : var.azure_authorized_key
+}
+
 # Workers scale set
 resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   resource_group_name = var.resource_group_name
@@ -9,7 +13,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   # instance name prefix for instances in the set
   computer_name_prefix   = "${var.name}-worker"
   single_placement_group = false
-  custom_data            = base64encode(data.ct_config.worker-ignition.rendered)
+  custom_data            = base64encode(data.ct_config.worker.rendered)
 
   # storage
   source_image_id = var.os_image
@@ -22,7 +26,7 @@ resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   admin_username = "core"
   admin_ssh_key {
     username   = "core"
-    public_key = var.ssh_authorized_key
+    public_key = var.azure_authorized_key
   }
 
   # network
@@ -70,24 +74,17 @@ resource "azurerm_monitor_autoscale_setting" "workers" {
   }
 }
 
-# Worker Ignition configs
-data "ct_config" "worker-ignition" {
-  content  = data.template_file.worker-config.rendered
-  strict   = true
-  snippets = var.snippets
-}
-
-# Worker Fedora CoreOS configs
-data "template_file" "worker-config" {
-  template = file("${path.module}/fcc/worker.yaml")
-
-  vars = {
+# Fedora CoreOS worker
+data "ct_config" "worker" {
+  content = templatefile("${path.module}/butane/worker.yaml", {
     kubeconfig             = indent(10, var.kubeconfig)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
     node_labels            = join(",", var.node_labels)
     node_taints            = join(",", var.node_taints)
-  }
+  })
+  strict   = true
+  snippets = var.snippets
 }
 

azure/flatcar-linux/kubernetes/README.md

@@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
 * Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [low-priority](https://typhoon.psdn.io/flatcar-linux/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization

azure/flatcar-linux/kubernetes/bootstrap.tf

@@ -1,13 +1,12 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=f325be50417e27dde6599a293409cb7d068cda0c"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=e1b1e0c75e77e042cf369f463f0e656297a201a8"
 
   cluster_name = var.cluster_name
   api_servers  = [format("%s.%s", var.cluster_name, var.dns_zone)]
   etcd_servers = formatlist("%s.%s", azurerm_dns_a_record.etcds.*.name, var.dns_zone)
 
   networking = var.networking
-
   # only effective with Calico networking
   # we should be able to use 1450 MTU, but in practice, 1410 was needed
   network_encapsulation = "vxlan"
@@ -19,5 +18,6 @@ module "bootstrap" {
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
   daemonset_tolerations = var.daemonset_tolerations
+  components            = var.components
 }
 

azure/flatcar-linux/kubernetes/butane/controller.yaml

@@ -1,4 +1,5 @@
----
+variant: flatcar
+version: 1.0.0
 systemd:
   units:
     - name: etcd-member.service
@@ -10,7 +11,7 @@ systemd:
         Requires=docker.service
         After=docker.service
         [Service]
-        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.4
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
         ExecStartPre=/usr/bin/docker run -d \
           --name etcd \
           --network host \
@@ -55,7 +56,7 @@ systemd:
         After=docker.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -80,25 +81,12 @@ systemd:
           -v /var/log:/var/log \
           -v /opt/cni/bin:/opt/cni/bin \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
         ExecStart=docker logs -f kubelet
         ExecStop=docker stop kubelet
         ExecStopPost=docker rm kubelet
@@ -117,7 +105,7 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStart=/usr/bin/docker run \
             -v /etc/kubernetes/pki:/etc/kubernetes/pki:ro \
             -v /opt/bootstrap/assets:/assets:ro \
@@ -130,23 +118,47 @@ systemd:
 storage:
   directories:
     - path: /var/lib/etcd
-      filesystem: root
       mode: 0700
       overwrite: true
   files:
     - path: /etc/kubernetes/kubeconfig
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
     - path: /opt/bootstrap/layout
-      filesystem: root
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          mkdir -p -- auth tls/{etcd,k8s} static-manifests manifests/{coredns,kube-proxy,network}
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
           mkdir -p /etc/kubernetes/pki
@@ -161,10 +173,8 @@ storage:
           mv static-manifests/* /etc/kubernetes/manifests/
           mkdir -p /opt/bootstrap/assets
           mv manifests /opt/bootstrap/assets/manifests
-          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls manifests-networking
+          rm -rf assets auth static-manifests tls manifests
     - path: /opt/bootstrap/apply
-      filesystem: root
       mode: 0544
       contents:
         inline: |
@@ -178,14 +188,17 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
     - path: /etc/etcd/etcd.env
-      filesystem: root
       mode: 0644
       contents:
           inline: |

azure/flatcar-linux/kubernetes/controllers.tf

@@ -17,7 +17,15 @@ resource "azurerm_dns_a_record" "etcds" {
 locals {
   # Container Linux derivative
   # flatcar-stable -> Flatcar Linux Stable
-  channel = split("-", var.os_image)[1]
+  channel      = split("-", var.os_image)[1]
+  offer_suffix = var.arch == "arm64" ? "corevm" : "free"
+  urn          = var.arch == "arm64" ? local.channel : "${local.channel}-gen2"
+
+  # Typhoon ssh_authorized_key supports RSA or a newer formats (e.g. ed25519).
+  # However, Azure requires an older RSA key to pass validations. To use a
+  # newer key format, pass a dummy RSA key as the azure_authorized_key and
+  # delete the associated private key so it's never used.
+  azure_authorized_key = var.azure_authorized_key == "" ? var.ssh_authorized_key : var.azure_authorized_key
 }
 
 # Controller availability set to spread controllers
@@ -41,7 +49,10 @@ resource "azurerm_linux_virtual_machine" "controllers" {
   availability_set_id = azurerm_availability_set.controllers.id
 
   size        = var.controller_type
-  custom_data = base64encode(data.ct_config.controller-ignitions.*.rendered[count.index])
+  custom_data = base64encode(data.ct_config.controllers.*.rendered[count.index])
+  boot_diagnostics {
+    # defaults to a managed storage account
+  }
 
   # storage
   os_disk {
@@ -53,28 +64,31 @@ resource "azurerm_linux_virtual_machine" "controllers" {
 
   # Flatcar Container Linux
   source_image_reference {
-    publisher = "Kinvolk"
-    offer     = "flatcar-container-linux-free"
-    sku       = local.channel
+    publisher = "kinvolk"
+    offer     = "flatcar-container-linux-${local.offer_suffix}"
+    sku       = local.urn
     version   = "latest"
   }
 
-  plan {
-    name      = local.channel
-    publisher = "kinvolk"
-    product   = "flatcar-container-linux-free"
+  dynamic "plan" {
+    for_each = var.arch == "arm64" ? [] : [1]
+    content {
+      publisher = "kinvolk"
+      product   = "flatcar-container-linux-${local.offer_suffix}"
+      name      = local.urn
+    }
   }
 
   # network
   network_interface_ids = [
-    azurerm_network_interface.controllers.*.id[count.index]
+    azurerm_network_interface.controllers[count.index].id
   ]
 
   # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
   admin_username = "core"
   admin_ssh_key {
     username   = "core"
-    public_key = var.ssh_authorized_key
+    public_key = local.azure_authorized_key
   }
 
   lifecycle {
@@ -130,41 +144,22 @@ resource "azurerm_network_interface_backend_address_pool_association" "controlle
   backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
 }
 
-# Controller Ignition configs
-data "ct_config" "controller-ignitions" {
-  count    = var.controller_count
-  content  = data.template_file.controller-configs.*.rendered[count.index]
-  strict   = true
-  snippets = var.controller_snippets
-}
-
-# Controller Container Linux configs
-data "template_file" "controller-configs" {
+# Flatcar Linux controllers
+data "ct_config" "controllers" {
   count = var.controller_count
-
-  template = file("${path.module}/cl/controller.yaml")
-
-  vars = {
+  content = templatefile("${path.module}/butane/controller.yaml", {
     # Cannot use cyclic dependencies on controllers or their DNS records
     etcd_name   = "etcd${count.index}"
     etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
     # etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
-    etcd_initial_cluster   = join(",", data.template_file.etcds.*.rendered)
+    etcd_initial_cluster = join(",", [
+      for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
+    ])
     kubeconfig             = indent(10, module.bootstrap.kubeconfig-kubelet)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
-  }
+  })
+  strict   = true
+  snippets = var.controller_snippets
 }
-
-data "template_file" "etcds" {
-  count    = var.controller_count
-  template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
-
-  vars = {
-    index        = count.index
-    cluster_name = var.cluster_name
-    dns_zone     = var.dns_zone
-  }
-}
-

azure/flatcar-linux/kubernetes/outputs.tf

@@ -39,8 +39,19 @@ output "kubeconfig" {
 
 # Outputs for custom firewalling
 
+output "controller_security_group_name" {
+  description = "Network Security Group for controller nodes"
+  value       = azurerm_network_security_group.controller.name
+}
+
 output "worker_security_group_name" {
-  value = azurerm_network_security_group.worker.name
+  description = "Network Security Group for worker nodes"
+  value       = azurerm_network_security_group.worker.name
+}
+
+output "controller_address_prefixes" {
+  description = "Controller network subnet CIDR addresses (for source/destination)"
+  value       = azurerm_subnet.controller.address_prefixes
 }
 
 output "worker_address_prefixes" {

azure/flatcar-linux/kubernetes/security.tf

@@ -121,7 +121,7 @@ resource "azurerm_network_security_rule" "controller-cilium-health" {
 
   name                         = "allow-cilium-health"
   network_security_group_name  = azurerm_network_security_group.controller.name
-  priority                     = "2019"
+  priority                     = "2018"
   access                       = "Allow"
   direction                    = "Inbound"
   protocol                     = "Tcp"
@@ -131,6 +131,22 @@ resource "azurerm_network_security_rule" "controller-cilium-health" {
   destination_address_prefixes = azurerm_subnet.controller.address_prefixes
 }
 
+resource "azurerm_network_security_rule" "controller-cilium-metrics" {
+  resource_group_name = azurerm_resource_group.cluster.name
+  count               = var.networking == "cilium" ? 1 : 0
+
+  name                         = "allow-cilium-metrics"
+  network_security_group_name  = azurerm_network_security_group.controller.name
+  priority                     = "2019"
+  access                       = "Allow"
+  direction                    = "Inbound"
+  protocol                     = "Tcp"
+  source_port_range            = "*"
+  destination_port_range       = "9962-9965"
+  source_address_prefixes      = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
+  destination_address_prefixes = azurerm_subnet.controller.address_prefixes
+}
+
 resource "azurerm_network_security_rule" "controller-vxlan" {
   resource_group_name = azurerm_resource_group.cluster.name
 
@@ -303,7 +319,7 @@ resource "azurerm_network_security_rule" "worker-cilium-health" {
 
   name                         = "allow-cilium-health"
   network_security_group_name  = azurerm_network_security_group.worker.name
-  priority                     = "2014"
+  priority                     = "2013"
   access                       = "Allow"
   direction                    = "Inbound"
   protocol                     = "Tcp"
@@ -313,6 +329,22 @@ resource "azurerm_network_security_rule" "worker-cilium-health" {
   destination_address_prefixes = azurerm_subnet.worker.address_prefixes
 }
 
+resource "azurerm_network_security_rule" "worker-cilium-metrics" {
+  resource_group_name = azurerm_resource_group.cluster.name
+  count               = var.networking == "cilium" ? 1 : 0
+
+  name                         = "allow-cilium-metrics"
+  network_security_group_name  = azurerm_network_security_group.worker.name
+  priority                     = "2014"
+  access                       = "Allow"
+  direction                    = "Inbound"
+  protocol                     = "Tcp"
+  source_port_range            = "*"
+  destination_port_range       = "9962-9965"
+  source_address_prefixes      = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
+  destination_address_prefixes = azurerm_subnet.worker.address_prefixes
+}
+
 resource "azurerm_network_security_rule" "worker-vxlan" {
   resource_group_name = azurerm_resource_group.cluster.name
 

azure/flatcar-linux/kubernetes/variables.tf

@@ -43,7 +43,7 @@ variable "controller_type" {
 variable "worker_type" {
   type        = string
   description = "Machine type for workers (see `az vm list-skus --location centralus`)"
-  default     = "Standard_DS1_v2"
+  default     = "Standard_D2as_v5"
 }
 
 variable "os_image" {
@@ -88,6 +88,12 @@ variable "ssh_authorized_key" {
   description = "SSH public key for user 'core'"
 }
 
+variable "azure_authorized_key" {
+  type        = string
+  description = "Optionally, pass a dummy RSA key to satisfy Azure validations (then use an ed25519 key set above)"
+  default     = ""
+}
+
 variable "networking" {
   type        = string
   description = "Choice of networking provider (flannel, calico, or cilium)"
@@ -133,6 +139,23 @@ variable "worker_node_labels" {
   default     = []
 }
 
+variable "arch" {
+  type        = string
+  description = "Container architecture (amd64 or arm64)"
+  default     = "amd64"
+
+  validation {
+    condition     = var.arch == "amd64" || var.arch == "arm64"
+    error_message = "The arch must be amd64 or arm64."
+  }
+}
+
+variable "daemonset_tolerations" {
+  type        = list(string)
+  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
+  default     = []
+}
+
 # unofficial, undocumented, unsupported
 
 variable "cluster_domain_suffix" {
@@ -141,8 +164,18 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
-variable "daemonset_tolerations" {
-  type        = list(string)
-  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
-  default     = []
+variable "components" {
+  description = "Configure pre-installed cluster components"
+  # Component configs are passed through to terraform-render-bootstrap,
+  # which handles type enforcement and defines defaults
+  # https://github.com/poseidon/terraform-render-bootstrap/blob/main/variables.tf#L95
+  type = object({
+    enable     = optional(bool)
+    coredns    = optional(map(any))
+    kube_proxy = optional(map(any))
+    flannel    = optional(map(any))
+    calico     = optional(map(any))
+    cilium     = optional(map(any))
+  })
+  default = null
 }

azure/flatcar-linux/kubernetes/versions.tf

@@ -3,13 +3,11 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    azurerm  = ">= 2.8, < 4.0"
-    template = "~> 2.2"
-    null     = ">= 2.1"
-
+    azurerm = ">= 2.8, < 4.0"
+    null    = ">= 2.1"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

azure/flatcar-linux/kubernetes/workers.tf

@@ -17,8 +17,10 @@ module "workers" {
   # configuration
   kubeconfig            = module.bootstrap.kubeconfig-kubelet
   ssh_authorized_key    = var.ssh_authorized_key
+  azure_authorized_key  = var.azure_authorized_key
   service_cidr          = var.service_cidr
   cluster_domain_suffix = var.cluster_domain_suffix
   snippets              = var.worker_snippets
   node_labels           = var.worker_node_labels
+  arch                  = var.arch
 }

azure/flatcar-linux/kubernetes/workers/butane/worker.yaml

@@ -1,4 +1,5 @@
----
+variant: flatcar
+version: 1.0.0
 systemd:
   units:
     - name: docker.service
@@ -27,7 +28,7 @@ systemd:
         After=docker.service
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -55,30 +56,17 @@ systemd:
           -v /var/log:/var/log \
           -v /opt/cni/bin:/opt/cni/bin \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
-          --node-labels=node.kubernetes.io/node \
           %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
           %{~ endfor ~}
           %{~ for taint in split(",", node_taints) ~}
           --register-with-taints=${taint} \
           %{~ endfor ~}
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --node-labels=node.kubernetes.io/node
         ExecStart=docker logs -f kubelet
         ExecStop=docker stop kubelet
         ExecStopPost=docker rm kubelet
@@ -86,29 +74,46 @@ systemd:
         RestartSec=5
         [Install]
         WantedBy=multi-user.target
-    - name: delete-node.service
-      enabled: true
-      contents: |
-        [Unit]
-        Description=Delete Kubernetes node on shutdown
-        [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/bin/bash -c '/usr/bin/docker run -v /var/lib/kubelet:/var/lib/kubelet:ro --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
-        [Install]
-        WantedBy=multi-user.target
 storage:
   files:
     - path: /etc/kubernetes/kubeconfig
-      filesystem: root
       mode: 0644
       contents:
         inline: |
           ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
       mode: 0644
       contents:
         inline: |

azure/flatcar-linux/kubernetes/workers/variables.tf

@@ -41,7 +41,7 @@ variable "worker_count" {
 variable "vm_type" {
   type        = string
   description = "Machine type for instances (see `az vm list-skus --location centralus`)"
-  default     = "Standard_DS1_v2"
+  default     = "Standard_D2as_v5"
 }
 
 variable "os_image" {
@@ -79,6 +79,12 @@ variable "ssh_authorized_key" {
   description = "SSH public key for user 'core'"
 }
 
+variable "azure_authorized_key" {
+  type        = string
+  description = "Optionally, pass a dummy RSA key to satisfy Azure validations (then use an ed25519 key set above)"
+  default     = ""
+}
+
 variable "service_cidr" {
   type        = string
   description = <<EOD
@@ -100,6 +106,17 @@ variable "node_taints" {
   default     = []
 }
 
+variable "arch" {
+  type        = string
+  description = "Container architecture (amd64 or arm64)"
+  default     = "amd64"
+
+  validation {
+    condition     = var.arch == "amd64" || var.arch == "arm64"
+    error_message = "The arch must be amd64 or arm64."
+  }
+}
+
 # unofficial, undocumented, unsupported
 
 variable "cluster_domain_suffix" {

azure/flatcar-linux/kubernetes/workers/versions.tf

@@ -3,12 +3,10 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    azurerm  = ">= 2.8, < 4.0"
-    template = "~> 2.2"
-
+    azurerm = ">= 2.8, < 4.0"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
   }
 }

azure/flatcar-linux/kubernetes/workers/workers.tf

@@ -1,6 +1,10 @@
 locals {
   # flatcar-stable -> Flatcar Linux Stable
-  channel = split("-", var.os_image)[1]
+  channel      = split("-", var.os_image)[1]
+  offer_suffix = var.arch == "arm64" ? "corevm" : "free"
+  urn          = var.arch == "arm64" ? local.channel : "${local.channel}-gen2"
+
+  azure_authorized_key = var.azure_authorized_key == "" ? var.ssh_authorized_key : var.azure_authorized_key
 }
 
 # Workers scale set
@@ -14,7 +18,10 @@ resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   # instance name prefix for instances in the set
   computer_name_prefix   = "${var.name}-worker"
   single_placement_group = false
-  custom_data            = base64encode(data.ct_config.worker-ignition.rendered)
+  custom_data            = base64encode(data.ct_config.worker.rendered)
+  boot_diagnostics {
+    # defaults to a managed storage account
+  }
 
   # storage
   os_disk {
@@ -24,23 +31,26 @@ resource "azurerm_linux_virtual_machine_scale_set" "workers" {
 
   # Flatcar Container Linux
   source_image_reference {
-    publisher = "Kinvolk"
-    offer     = "flatcar-container-linux-free"
-    sku       = local.channel
+    publisher = "kinvolk"
+    offer     = "flatcar-container-linux-${local.offer_suffix}"
+    sku       = local.urn
     version   = "latest"
   }
 
-  plan {
-    name      = local.channel
-    publisher = "kinvolk"
-    product   = "flatcar-container-linux-free"
+  dynamic "plan" {
+    for_each = var.arch == "arm64" ? [] : [1]
+    content {
+      publisher = "kinvolk"
+      product   = "flatcar-container-linux-${local.offer_suffix}"
+      name      = local.urn
+    }
   }
 
   # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
   admin_username = "core"
   admin_ssh_key {
     username   = "core"
-    public_key = var.ssh_authorized_key
+    public_key = local.azure_authorized_key
   }
 
   # network
@@ -64,6 +74,9 @@ resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   # eviction policy may only be set when priority is Spot
   priority        = var.priority
   eviction_policy = var.priority == "Spot" ? "Delete" : null
+  termination_notification {
+    enabled = true
+  }
 }
 
 # Scale up or down to maintain desired number, tolerating deallocations.
@@ -88,24 +101,16 @@ resource "azurerm_monitor_autoscale_setting" "workers" {
   }
 }
 
-# Worker Ignition configs
-data "ct_config" "worker-ignition" {
-  content  = data.template_file.worker-config.rendered
-  strict   = true
-  snippets = var.snippets
-}
-
-# Worker Container Linux configs
-data "template_file" "worker-config" {
-  template = file("${path.module}/cl/worker.yaml")
-
-  vars = {
+# Flatcar Linux worker
+data "ct_config" "worker" {
+  content = templatefile("${path.module}/butane/worker.yaml", {
     kubeconfig             = indent(10, var.kubeconfig)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
     node_labels            = join(",", var.node_labels)
     node_taints            = join(",", var.node_taints)
-  }
+  })
+  strict   = true
+  snippets = var.snippets
 }
-

bare-metal/fedora-coreos/kubernetes/README.md

@@ -11,7 +11,7 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.24.1 (upstream)
+* Kubernetes v1.30.1 (upstream)
 * Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
 * On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
 * Advanced features like [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization

bare-metal/fedora-coreos/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=f325be50417e27dde6599a293409cb7d068cda0c"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=e1b1e0c75e77e042cf369f463f0e656297a201a8"
 
   cluster_name                    = var.cluster_name
   api_servers                     = [var.k8s_domain_name]
@@ -13,6 +13,7 @@ module "bootstrap" {
   cluster_domain_suffix           = var.cluster_domain_suffix
   enable_reporting                = var.enable_reporting
   enable_aggregation              = var.enable_aggregation
+  components                      = var.components
 }
 
 

bare-metal/fedora-coreos/kubernetes/butane/controller.yaml

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.4.0
+version: 1.5.0
 systemd:
   units:
     - name: etcd-member.service
@@ -9,15 +9,16 @@ systemd:
         [Unit]
         Description=etcd (System Container)
         Documentation=https://github.com/etcd-io/etcd
-        Wants=network-online.target network.target
+        Wants=network-online.target
         After=network-online.target
         [Service]
-        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.4
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.13
         Type=exec
         ExecStartPre=/bin/mkdir -p /var/lib/etcd
         ExecStartPre=-/usr/bin/podman rm etcd
         ExecStart=/usr/bin/podman run --name etcd \
           --env-file /etc/etcd/etcd.env \
+          --log-driver k8s-file \
           --network host \
           --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
           --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
@@ -52,7 +53,7 @@ systemd:
         Description=Kubelet (System Container)
         Wants=rpc-statd.service
         [Service]
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -61,6 +62,7 @@ systemd:
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
         ExecStartPre=-/usr/bin/podman rm kubelet
         ExecStart=/usr/bin/podman run --name kubelet \
+          --log-driver k8s-file \
           --privileged \
           --pid host \
           --network host \
@@ -80,28 +82,13 @@ systemd:
           --volume /var/run/lock:/var/run/lock:z \
           --volume /opt/cni/bin:/opt/cni/bin:z \
           $${KUBELET_IMAGE} \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
           --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
-          --cgroup-driver=systemd \
-          --cgroups-per-qos=true \
-          --container-runtime=remote \
+          --config=/etc/kubernetes/kubelet.yaml \
           --container-runtime-endpoint=unix:///run/containerd/containerd.sock \
-          --enforce-node-allocatable=pods \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --healthz-port=0 \
           --hostname-override=${domain_name} \
           --kubeconfig=/var/lib/kubelet/kubeconfig \
           --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --resolv-conf=/run/systemd/resolve/resolv.conf \
-          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
-          --rotate-certificates \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
         Restart=always
@@ -126,7 +113,7 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.24.1
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.30.1
         ExecStartPre=-/usr/bin/podman rm bootstrap
         ExecStart=/usr/bin/podman run --name bootstrap \
             --network host \
@@ -149,12 +136,39 @@ storage:
       contents:
         inline:
           ${domain_name}
+    - path: /etc/kubernetes/kubelet.yaml
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: kubelet.config.k8s.io/v1beta1
+          kind: KubeletConfiguration
+          authentication:
+            anonymous:
+              enabled: false
+            webhook:
+              enabled: true
+            x509:
+              clientCAFile: /etc/kubernetes/ca.crt
+          authorization:
+            mode: Webhook
+          cgroupDriver: systemd
+          clusterDNS:
+            - ${cluster_dns_service_ip}
+          clusterDomain: ${cluster_domain_suffix}
+          healthzPort: 0
+          rotateCertificates: true
+          shutdownGracePeriod: 45s
+          shutdownGracePeriodCriticalPods: 30s
+          staticPodPath: /etc/kubernetes/manifests
+          readOnlyPort: 0
+          resolvConf: /run/systemd/resolve/resolv.conf
+          volumePluginDir: /var/lib/kubelet/volumeplugins
     - path: /opt/bootstrap/layout
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          mkdir -p -- auth tls/{etcd,k8s} static-manifests manifests/{coredns,kube-proxy,network}
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
           mkdir -p /etc/kubernetes/pki
@@ -168,8 +182,7 @@ storage:
           mv static-manifests/* /etc/kubernetes/manifests/
           mkdir -p /opt/bootstrap/assets
           mv manifests /opt/bootstrap/assets/manifests
-          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls manifests-networking
+          rm -rf assets auth static-manifests tls manifests
           chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
     - path: /opt/bootstrap/apply
       mode: 0544
@@ -185,6 +198,11 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
+    - path: /etc/systemd/logind.conf.d/inhibitors.conf
+      contents:
+        inline: |
+          [Login]
+          InhibitDelayMaxSec=45s
     - path: /etc/sysctl.d/max-user-watches.conf
       contents:
         inline: |
@@ -229,7 +247,6 @@ storage:
           ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
           ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
           ETCD_PEER_CLIENT_CERT_AUTH=true
-    - path: /etc/fedora-coreos/iptables-legacy.stamp
     - path: /etc/containerd/config.toml
       overwrite: true
       contents:

bare-metal/fedora-coreos/kubernetes/groups.tf

@@ -1,22 +0,0 @@
-# Match each controller or worker to a profile
-
-resource "matchbox_group" "controller" {
-  count   = length(var.controllers)
-  name    = format("%s-%s", var.cluster_name, var.controllers.*.name[count.index])
-  profile = matchbox_profile.controllers.*.name[count.index]
-
-  selector = {
-    mac = var.controllers.*.mac[count.index]
-  }
-}
-
-resource "matchbox_group" "worker" {
-  count   = length(var.workers)
-  name    = format("%s-%s", var.cluster_name, var.workers.*.name[count.index])
-  profile = matchbox_profile.workers.*.name[count.index]
-
-  selector = {
-    mac = var.workers.*.mac[count.index]
-  }
-}
-

bare-metal/fedora-coreos/kubernetes/outputs.tf

@@ -3,6 +3,13 @@ output "kubeconfig-admin" {
   sensitive = true
 }
 
+# Outputs for workers
+
+output "kubeconfig" {
+  value     = module.bootstrap.kubeconfig-kubelet
+  sensitive = true
+}
+
 # Outputs for debug
 
 output "assets_dist" {

bare-metal/fedora-coreos/kubernetes/profiles.tf

@@ -1,34 +1,26 @@
 locals {
   remote_kernel = "https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-live-kernel-x86_64"
   remote_initrd = [
-    "https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-live-initramfs.x86_64.img",
-    "https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-live-rootfs.x86_64.img"
+    "--name main https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-live-initramfs.x86_64.img",
   ]
 
   remote_args = [
-    "ip=dhcp",
-    "rd.neednet=1",
+    "initrd=main",
+    "coreos.live.rootfs_url=https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-live-rootfs.x86_64.img",
     "coreos.inst.install_dev=${var.install_disk}",
     "coreos.inst.ignition_url=${var.matchbox_http_endpoint}/ignition?uuid=$${uuid}&mac=$${mac:hexhyp}",
-    "coreos.inst.image_url=https://builds.coreos.fedoraproject.org/prod/streams/${var.os_stream}/builds/${var.os_version}/x86_64/fedora-coreos-${var.os_version}-metal.x86_64.raw.xz",
-    "console=tty0",
-    "console=ttyS0",
   ]
 
   cached_kernel = "/assets/fedora-coreos/fedora-coreos-${var.os_version}-live-kernel-x86_64"
   cached_initrd = [
     "/assets/fedora-coreos/fedora-coreos-${var.os_version}-live-initramfs.x86_64.img",
-    "/assets/fedora-coreos/fedora-coreos-${var.os_version}-live-rootfs.x86_64.img"
   ]
 
   cached_args = [
-    "ip=dhcp",
-    "rd.neednet=1",
+    "initrd=main",
+    "coreos.live.rootfs_url=${var.matchbox_http_endpoint}/assets/fedora-coreos/fedora-coreos-${var.os_version}-live-rootfs.x86_64.img",
     "coreos.inst.install_dev=${var.install_disk}",
     "coreos.inst.ignition_url=${var.matchbox_http_endpoint}/ignition?uuid=$${uuid}&mac=$${mac:hexhyp}",
-    "coreos.inst.image_url=${var.matchbox_http_endpoint}/assets/fedora-coreos/fedora-coreos-${var.os_version}-metal.x86_64.raw.xz",
-    "console=tty0",
-    "console=ttyS0",
   ]
 
   kernel = var.cached_install ? local.cached_kernel : local.remote_kernel
@@ -36,6 +28,16 @@ locals {
   args   = var.cached_install ? local.cached_args : local.remote_args
 }
 
+# Match a controller to a profile by MAC
+resource "matchbox_group" "controller" {
+  count   = length(var.controllers)
+  name    = format("%s-%s", var.cluster_name, var.controllers.*.name[count.index])
+  profile = matchbox_profile.controllers.*.name[count.index]
+
+  selector = {
+    mac = var.controllers.*.mac[count.index]
+  }
+}
 
 // Fedora CoreOS controller profile
 resource "matchbox_profile" "controllers" {
@@ -46,62 +48,20 @@ resource "matchbox_profile" "controllers" {
   initrd = local.initrd
   args   = concat(local.args, var.kernel_args)
 
-  raw_ignition = data.ct_config.controller-ignitions.*.rendered[count.index]
+  raw_ignition = data.ct_config.controllers.*.rendered[count.index]
 }
 
-data "ct_config" "controller-ignitions" {
+# Fedora CoreOS controllers
+data "ct_config" "controllers" {
   count = length(var.controllers)
-
-  content  = data.template_file.controller-configs.*.rendered[count.index]
-  strict   = true
-  snippets = lookup(var.snippets, var.controllers.*.name[count.index], [])
-}
-
-data "template_file" "controller-configs" {
-  count = length(var.controllers)
-
-  template = file("${path.module}/fcc/controller.yaml")
-  vars = {
+  content = templatefile("${path.module}/butane/controller.yaml", {
     domain_name            = var.controllers.*.domain[count.index]
     etcd_name              = var.controllers.*.name[count.index]
     etcd_initial_cluster   = join(",", formatlist("%s=https://%s:2380", var.controllers.*.name, var.controllers.*.domain))
     cluster_dns_service_ip = module.bootstrap.cluster_dns_service_ip
     cluster_domain_suffix  = var.cluster_domain_suffix
     ssh_authorized_key     = var.ssh_authorized_key
-  }
-}
-
-// Fedora CoreOS worker profile
-resource "matchbox_profile" "workers" {
-  count = length(var.workers)
-  name  = format("%s-worker-%s", var.cluster_name, var.workers.*.name[count.index])
-
-  kernel = local.kernel
-  initrd = local.initrd
-  args   = concat(local.args, var.kernel_args)
-
-  raw_ignition = data.ct_config.worker-ignitions.*.rendered[count.index]
-}
-
-data "ct_config" "worker-ignitions" {
-  count = length(var.workers)
-
-  content  = data.template_file.worker-configs.*.rendered[count.index]
+  })
   strict   = true
-  snippets = lookup(var.snippets, var.workers.*.name[count.index], [])
+  snippets = lookup(var.snippets, var.controllers.*.name[count.index], [])
 }
-
-data "template_file" "worker-configs" {
-  count = length(var.workers)
-
-  template = file("${path.module}/fcc/worker.yaml")
-  vars = {
-    domain_name            = var.workers.*.domain[count.index]
-    cluster_dns_service_ip = module.bootstrap.cluster_dns_service_ip
-    cluster_domain_suffix  = var.cluster_domain_suffix
-    ssh_authorized_key     = var.ssh_authorized_key
-    node_labels            = join(",", lookup(var.worker_node_labels, var.workers.*.name[count.index], []))
-    node_taints            = join(",", lookup(var.worker_node_taints, var.workers.*.name[count.index], []))
-  }
-}
-

bare-metal/fedora-coreos/kubernetes/ssh.tf

@@ -15,7 +15,6 @@ resource "null_resource" "copy-controller-secrets" {
   # matchbox groups are written, causing a deadlock.
   depends_on = [
     matchbox_group.controller,
-    matchbox_group.worker,
     module.bootstrap,
   ]
 
@@ -45,37 +44,6 @@ resource "null_resource" "copy-controller-secrets" {
   }
 }
 
-# Secure copy kubeconfig to all workers. Activates kubelet.service
-resource "null_resource" "copy-worker-secrets" {
-  count = length(var.workers)
-
-  # Without depends_on, remote-exec could start and wait for machines before
-  # matchbox groups are written, causing a deadlock.
-  depends_on = [
-    matchbox_group.controller,
-    matchbox_group.worker,
-  ]
-
-  connection {
-    type    = "ssh"
-    host    = var.workers.*.domain[count.index]
-    user    = "core"
-    timeout = "60m"
-  }
-
-  provisioner "file" {
-    content     = module.bootstrap.kubeconfig-kubelet
-    destination = "/home/core/kubeconfig"
-  }
-
-  provisioner "remote-exec" {
-    inline = [
-      "sudo mv /home/core/kubeconfig /etc/kubernetes/kubeconfig",
-      "sudo touch /etc/kubernetes",
-    ]
-  }
-}
-
 # Connect to a controller to perform one-time cluster bootstrap.
 resource "null_resource" "bootstrap" {
   # Without depends_on, this remote-exec may start before the kubeconfig copy.
@@ -83,7 +51,6 @@ resource "null_resource" "bootstrap" {
   # while no Kubelets are running.
   depends_on = [
     null_resource.copy-controller-secrets,
-    null_resource.copy-worker-secrets,
   ]
 
   connection {

bare-metal/fedora-coreos/kubernetes/variables.tf

@@ -53,6 +53,7 @@ List of worker machine details (unique name, identifying MAC address, FQDN)
   { name = "node3", mac = "52:54:00:c3:61:77", domain = "node3.example.com"}
 ]
 EOD
+  default     = []
 }
 
 variable "snippets" {
@@ -158,3 +159,18 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
+variable "components" {
+  description = "Configure pre-installed cluster components"
+  # Component configs are passed through to terraform-render-bootstrap,
+  # which handles type enforcement and defines defaults
+  # https://github.com/poseidon/terraform-render-bootstrap/blob/main/variables.tf#L95
+  type = object({
+    enable     = optional(bool)
+    coredns    = optional(map(any))
+    kube_proxy = optional(map(any))
+    flannel    = optional(map(any))
+    calico     = optional(map(any))
+    cilium     = optional(map(any))
+  })
+  default = null
+}

bare-metal/fedora-coreos/kubernetes/versions.tf

@@ -3,14 +3,11 @@
 terraform {
   required_version = ">= 0.13.0, < 2.0.0"
   required_providers {
-    template = "~> 2.2"
-    null     = ">= 2.1"
-
+    null = ">= 2.1"
     ct = {
       source  = "poseidon/ct"
-      version = "~> 0.9"
+      version = "~> 0.13"
     }
-
     matchbox = {
       source  = "poseidon/matchbox"
       version = "~> 0.5.0"