Bump bootkube and terraform-render-bootkube to v0.8.1

* Use the v0.8.1 tagged terraform-render-bootkube module
* Use the v0.8.1 quay.io/coreos/bootkube image to bootstrap

CHANGES.md

@@ -0,0 +1,95 @@
+# Typhoon
+
+Notable changes between versions.
+
+## Latest
+
+## v1.8.2
+
+* Kubernetes v1.8.2
+  * Fixes a memory leak in the v1.8.1 apiserver ([kubernetes#53485](https://github.com/kubernetes/kubernetes/issues/53485))
+* Switch to using the `gcr.io/google_containers/hyperkube`
+* Update flannel from v0.8.0 to v0.9.0
+* Add `hairpinMode` to flannel CNI config
+* Add `--no-negcache` to kube-dns dnsmasq
+* Use kubernetes-incubator/bootkube v0.8.1
+
+## v1.8.1
+
+* Kubernetes v1.8.1
+* Use kubernetes-incubator/bootkube v0.8.0
+
+#### Digital Ocean
+
+* Run etcd cluster across controller nodes (etcd-member.service)
+* Remove support for self-hosted etcd
+* Reduce time to bootstrap a cluster
+
+## v1.7.7
+
+* Kubernetes v1.7.7
+* Use kubernetes-incubator/bootkube v0.7.0
+* Update kube-dns to 1.14.5 to fix dnsmasq [vulnerability](https://security.googleblog.com/2017/10/behind-masq-yet-more-dns-and-dhcp.html)
+* Calico v2.6.1
+* flannel-cni v0.3.0
+  * Update flannel CNI config to fix hostPort
+
+## v1.7.5
+
+* Kubernetes v1.7.5
+* Use kubernetes-incubator/bootkube v0.6.2
+* Add AWS Terraform module (alpha)
+* Add support for Calico networking (bare-metal, Google Cloud, AWS)
+* Change networking default from "flannel" to "calico"
+
+#### AWS
+
+* Add `network_mtu` to allow CNI interface MTU customization
+
+#### Bare-Metal
+
+* Add `network_mtu` to allow CNI interface MTU customization
+* Remove support for `experimental_self_hosted_etcd`
+
+## v1.7.3
+
+* Kubernetes v1.7.3
+* Use kubernete-incubator/bootkube v0.6.1
+
+#### Digital Ocean
+
+* Add cloud firewall rules (requires Terraform v0.10)
+* Change nodes tags from strings to DO tags
+
+## v1.7.1
+
+* Kubernetes v1.7.1
+* Use kubernete-incubator/bootkube v0.6.0
+* Add Bare-Metal Terraform module (stable)
+* Add Digital Ocean Terraform module (beta)
+
+#### Google Cloud
+
+* Remove `k8s_domain_name` variable, `cluster_name` + `dns_zone` resolves to controllers
+* Rename `dns_base_zone` to `dns_zone`
+* Rename `dns_base_zone_name` to `dns_zone_name`
+
+## v1.6.7
+
+* Kubernetes v1.6.7
+* Use kubernete-incubator/bootkube v0.5.1
+
+## v1.6.6
+
+* Kubernetes v1.6.6
+* Use kubernete-incubator/bootkube v0.4.5
+* Disable locksmithd on hosts, in favor of [CLUO](https://github.com/coreos/container-linux-update-operator).
+
+## v1.6.4
+
+* Kubernetes v1.6.4
+* Add Google Cloud Terraform module (stable)
+
+## Earlier
+
+Earlier versions, back to v1.3.0, used different designs and mechanisms.

README.md

@@ -1,4 +1,4 @@
-# Typhoon <img align="right" src="https://storage.googleapis.com/dghubble/spin.png">
+# Typhoon [![IRC](https://img.shields.io/badge/freenode-%23typhoon-0099ef.svg)]() <img align="right" src="https://storage.googleapis.com/dghubble/spin.png">
 
 Typhoon is a minimal and free Kubernetes distribution.
 
@@ -11,28 +11,31 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features
 
-* Kubernetes v1.7.3 (upstream, via [kubernetes-incubator/bootkube](https://github.com/kubernetes-incubator/bootkube))
-* Self-hosted control plane, single or multi master, workloads isolated to workers
-* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled
-* Ready for Ingress, Metrics, Dashboards, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+* Kubernetes v1.8.2 (upstream, via [kubernetes-incubator/bootkube](https://github.com/kubernetes-incubator/bootkube))
+* Single or multi-master, workloads isolated on workers, [Calico](https://www.projectcalico.org/) 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/)
+* Ready for Ingress, Dashboards, Metrics, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
 
 ## Modules
 
 Typhoon provides a Terraform Module for each supported operating system and platform.
 
-| Platform      | Operating System | Terraform Module |
-|---------------|------------------|------------------|
-| Bare-Metal    | Container Linux  | [bare-metal/container-linux/kubernetes](bare-metal/container-linux/kubernetes) |
-| Digital Ocean | Container Linux  | [digital-ocean/container-linux/kubernetes](digital-ocean/container-linux/kubernetes) |
-| Google Cloud  | Container Linux  | [google-cloud/container-linux/kubernetes](google-cloud/container-linux/kubernetes) |
+| Platform      | Operating System | Terraform Module | Status |
+|---------------|------------------|------------------|--------|
+| AWS           | Container Linux  | [aws/container-linux/kubernetes](aws/container-linux/kubernetes) | alpha |
+| Bare-Metal    | Container Linux  | [bare-metal/container-linux/kubernetes](bare-metal/container-linux/kubernetes) | stable |
+| Digital Ocean | Container Linux  | [digital-ocean/container-linux/kubernetes](digital-ocean/container-linux/kubernetes) | beta |
+| Google Cloud  | Container Linux  | [google-cloud/container-linux/kubernetes](google-cloud/container-linux/kubernetes) | beta |
 
 ## Usage
 
 * [Docs](https://typhoon.psdn.io)
 * [Concepts](https://typhoon.psdn.io/concepts/)
-* [Bare-Metal](https://typhoon.psdn.io/bare-metal/)
-* [Digital Ocean](https://typhoon.psdn.io/digital-ocean/)
-* [Google-Cloud](https://typhoon.psdn.io/google-cloud/)
+* Tutorials
+  * [AWS](https://typhoon.psdn.io/aws/)
+  * [Bare-Metal](https://typhoon.psdn.io/bare-metal/)
+  * [Digital Ocean](https://typhoon.psdn.io/digital-ocean/)
+  * [Google-Cloud](https://typhoon.psdn.io/google-cloud/)
 
 ## Example
 
@@ -61,6 +64,7 @@ module "google-cloud-yavin" {
 Fetch modules, plan the changes to be made, and apply the changes.
 
 ```sh
+$ terraform init
 $ terraform get --update
 $ terraform plan
 Plan: 37 to add, 0 to change, 0 to destroy.
@@ -74,9 +78,9 @@ In 5-10 minutes (varies by platform), the cluster will be ready. This Google Clo
 $ KUBECONFIG=/home/user/.secrets/clusters/yavin/auth/kubeconfig
 $ kubectl get nodes
 NAME                                          STATUS   AGE    VERSION
-yavin-controller-1682.c.example-com.internal  Ready    6m     v1.7.3+coreos.0
-yavin-worker-jrbf.c.example-com.internal      Ready    5m     v1.7.3+coreos.0
-yavin-worker-mzdm.c.example-com.internal      Ready    5m     v1.7.3+coreos.0
+yavin-controller-1682.c.example-com.internal  Ready    6m     v1.8.2
+yavin-worker-jrbf.c.example-com.internal      Ready    5m     v1.8.2
+yavin-worker-mzdm.c.example-com.internal      Ready    5m     v1.8.2
 ```
 
 List the pods.
@@ -84,6 +88,9 @@ List the pods.
 ```
 $ kubectl get pods --all-namespaces
 NAMESPACE     NAME                                      READY  STATUS    RESTARTS  AGE
+kube-system   calico-node-1cs8z                         2/2    Running   0         6m
+kube-system   calico-node-d1l5b                         2/2    Running   0         6m
+kube-system   calico-node-sp9ps                         2/2    Running   0         6m
 kube-system   etcd-operator-3329263108-f443m            1/1    Running   1         6m
 kube-system   kube-apiserver-zppls                      1/1    Running   0         6m
 kube-system   kube-controller-manager-3271970485-gh9kt  1/1    Running   0         6m
@@ -91,9 +98,6 @@ kube-system   kube-controller-manager-3271970485-h90v8  1/1    Running   1
 kube-system   kube-dns-1187388186-zj5dl                 3/3    Running   0         6m
 kube-system   kube-etcd-0000                            1/1    Running   0         5m
 kube-system   kube-etcd-network-checkpointer-crznb      1/1    Running   0         6m
-kube-system   kube-flannel-1cs8z                        2/2    Running   0         6m
-kube-system   kube-flannel-d1l5b                        2/2    Running   0         6m
-kube-system   kube-flannel-sp9ps                        2/2    Running   0         6m
 kube-system   kube-proxy-117v6                          1/1    Running   0         6m
 kube-system   kube-proxy-9886n                          1/1    Running   0         6m
 kube-system   kube-proxy-njn47                          1/1    Running   0         6m
@@ -110,6 +114,10 @@ Typhoon is strict about minimalism, maturity, and scope. These are not in scope:
 * Adding every possible option
 * Openstack or Mesos platforms
 
+## Help
+
+Ask questions on the IRC #typhoon channel on [freenode.net](http://freenode.net/).
+
 ## Background
 
 Typhoon powers the author's cloud and colocation clusters. The project has evolved through operational experience and Kubernetes changes. Typhoon is shared under a free license to allow others to use the work freely and contribute to its upkeep.

addons/cluo/cluster-role-binding.yaml

@@ -0,0 +1,12 @@
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: reboot-coordinator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: reboot-coordinator
+subjects:
+  - kind: ServiceAccount
+    namespace: reboot-coordinator
+    name: default

addons/cluo/cluster-role.yaml

@@ -0,0 +1,45 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: reboot-coordinator
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - nodes
+    verbs:
+      - get
+      - list
+      - watch
+      - update
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    verbs:
+      - create
+      - get
+      - update
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+      - events
+    verbs:
+      - create
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+    verbs:
+      - get
+      - list
+      - delete
+  - apiGroups:
+      - "extensions"
+    resources:
+      - daemonsets
+    verbs:
+      - get

addons/cluo/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: reboot-coordinator

addons/cluo/update-agent.yaml

@@ -2,7 +2,7 @@ apiVersion: extensions/v1beta1
 kind: DaemonSet
 metadata:
   name: container-linux-update-agent
-  namespace: kube-system
+  namespace: reboot-coordinator
 spec:
   updateStrategy:
     type: RollingUpdate
@@ -15,7 +15,7 @@ spec:
     spec:
       containers:
       - name: update-agent
-        image: quay.io/coreos/container-linux-update-operator:v0.3.1
+        image: quay.io/coreos/container-linux-update-operator:v0.4.1
         command:
         - "/bin/update-agent"
         volumeMounts:

addons/cluo/update-operator.yaml

@@ -2,7 +2,7 @@ apiVersion: extensions/v1beta1
 kind: Deployment
 metadata:
   name: container-linux-update-operator
-  namespace: kube-system
+  namespace: reboot-coordinator
 spec:
   replicas: 1
   template:
@@ -12,12 +12,15 @@ spec:
     spec:
       containers:
       - name: update-operator
-        image: quay.io/coreos/container-linux-update-operator:v0.3.1
+        image: quay.io/coreos/container-linux-update-operator:v0.4.1
         command:
         - "/bin/update-operator"
-        - "--analytics=false"
         env:
         - name: POD_NAMESPACE
           valueFrom:
             fieldRef:
               fieldPath: metadata.namespace
+      tolerations:
+      - key: node-role.kubernetes.io/master
+        operator: Exists
+        effect: NoSchedule

addons/heapster/deployment.yaml

@@ -3,27 +3,23 @@ kind: Deployment
 metadata:
   name: heapster
   namespace: kube-system
-  labels:
-    k8s-app: heapster
-    kubernetes.io/cluster-service: "true"
-    version: v1.4.0
 spec:
   replicas: 1
   selector:
     matchLabels:
-      k8s-app: heapster
-      version: v1.4.0
+      name: heapster
+      phase: prod
   template:
     metadata:
       labels:
-        k8s-app: heapster
-        version: v1.4.0
+        name: heapster
+        phase: prod
       annotations:
         scheduler.alpha.kubernetes.io/critical-pod: ''
     spec:
       containers:
         - name: heapster
-          image: gcr.io/google_containers/heapster-amd64:v1.4.0
+          image: gcr.io/google_containers/heapster-amd64:v1.4.3
           command:
             - /heapster
             - --source=kubernetes.summary_api:''
@@ -42,7 +38,7 @@ spec:
             - --extra-cpu=0.5m
             - --memory=140Mi
             - --extra-memory=4Mi
-            - --deployment=heapster-v1.4.0
+            - --deployment=heapster
             - --container=heapster
             - --poll-period=300000
           env:

addons/heapster/service.yaml

@@ -3,13 +3,10 @@ kind: Service
 metadata: 
   name: heapster
   namespace: kube-system
-  labels: 
-    kubernetes.io/cluster-service: "true"
-    kubernetes.io/name: "Heapster"
 spec: 
   type: ClusterIP
   selector:
-    k8s-app: heapster
+    name: heapster
   ports: 
     - port: 80
       targetPort: 8082

addons/nginx-ingress/aws/default-backend/deployment.yaml

@@ -0,0 +1,36 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        name: default-backend
+        phase: prod
+    spec:
+      containers:
+        - name: default-backend
+          # Any image is permissable as long as:
+          # 1. It serves a 404 page at /
+          # 2. It serves 200 on a /healthz endpoint
+          image: gcr.io/google_containers/defaultbackend:1.4
+          ports:
+            - containerPort: 8080
+          resources:
+            limits:
+              cpu: 10m
+              memory: 20Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: 8080
+              scheme: HTTP
+            initialDelaySeconds: 30
+            timeoutSeconds: 5
+      terminationGracePeriodSeconds: 60

addons/nginx-ingress/aws/default-backend/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: default-backend
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 8080

addons/nginx-ingress/aws/deployment.yaml

@@ -0,0 +1,67 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  replicas: 2
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 1
+  template:
+    metadata:
+      labels:
+        name: nginx-ingress-controller
+        phase: prod
+    spec:
+      nodeSelector:
+        node-role.kubernetes.io/node: ""
+      hostNetwork: true
+      containers:
+        - name: nginx-ingress-controller
+          image: gcr.io/google_containers/nginx-ingress-controller:0.9.0-beta.15
+          args:
+            - /nginx-ingress-controller
+            - --default-backend-service=$(POD_NAMESPACE)/default-backend
+            - --ingress-class=public
+          # use downward API
+          env:
+            - name: POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            - name: POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          ports:
+            - name: http
+              containerPort: 80
+              hostPort: 80
+            - name: https
+              containerPort: 443
+              hostPort: 443
+            - name: health
+              containerPort: 10254
+              hostPort: 10254
+          livenessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+      restartPolicy: Always
+      terminationGracePeriodSeconds: 60

addons/nginx-ingress/aws/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: ingress

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

@@ -0,0 +1,12 @@
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,51 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - endpoints
+      - nodes
+      - pods
+      - secrets
+    verbs:
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+      - nodes
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - services
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+        - events
+    verbs:
+        - create
+        - patch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses/status
+    verbs:
+      - update

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

@@ -0,0 +1,13 @@
+kind: RoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,41 @@
+kind: Role
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - pods
+      - secrets
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    resourceNames:
+      # Defaults to "<election-id>-<ingress-class>"
+      # Here: "<ingress-controller-leader>-<nginx>"
+      # This has to be adapted if you change either parameter
+      # when launching the nginx-ingress-controller.
+      - "ingress-controller-leader-public"
+    verbs:
+      - get
+      - update
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    verbs:
+      - create
+  - apiGroups:
+      - ""
+    resources:
+      - endpoints
+    verbs:
+      - get
+      - create
+      - update

addons/nginx-ingress/aws/service.yaml

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: nginx-ingress-controller
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 80
+    - name: https
+      protocol: TCP
+      port: 443
+      targetPort: 443

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

@@ -0,0 +1,67 @@
+apiVersion: extensions/v1beta1
+kind: DaemonSet
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  updateStrategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  template:
+    metadata:
+      labels:
+        name: nginx-ingress-controller
+        phase: prod
+    spec:
+      nodeSelector:
+        node-role.kubernetes.io/node: ""
+      hostNetwork: true
+      containers:
+        - name: nginx-ingress-controller
+          image: gcr.io/google_containers/nginx-ingress-controller:0.9.0-beta.15
+          args:
+            - /nginx-ingress-controller
+            - --default-backend-service=$(POD_NAMESPACE)/default-backend
+            - --ingress-class=public
+          # use downward API
+          env:
+            - name: POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            - name: POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          ports:
+            - name: http
+              containerPort: 80
+              hostPort: 80
+            - name: https
+              containerPort: 443
+              hostPort: 443
+            - name: health
+              containerPort: 10254
+              hostPort: 10254
+          livenessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+      restartPolicy: Always
+      terminationGracePeriodSeconds: 60

addons/nginx-ingress/digital-ocean/default-backend/deployment.yaml

@@ -0,0 +1,36 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        name: default-backend
+        phase: prod
+    spec:
+      containers:
+        - name: default-backend
+          # Any image is permissable as long as:
+          # 1. It serves a 404 page at /
+          # 2. It serves 200 on a /healthz endpoint
+          image: gcr.io/google_containers/defaultbackend:1.4
+          ports:
+            - containerPort: 8080
+          resources:
+            limits:
+              cpu: 10m
+              memory: 20Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: 8080
+              scheme: HTTP
+            initialDelaySeconds: 30
+            timeoutSeconds: 5
+      terminationGracePeriodSeconds: 60

addons/nginx-ingress/digital-ocean/default-backend/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: default-backend
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 8080

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

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: ingress

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

@@ -0,0 +1,12 @@
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,51 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - endpoints
+      - nodes
+      - pods
+      - secrets
+    verbs:
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+      - nodes
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - services
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+        - events
+    verbs:
+        - create
+        - patch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses/status
+    verbs:
+      - update

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

@@ -0,0 +1,13 @@
+kind: RoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,41 @@
+kind: Role
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - pods
+      - secrets
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    resourceNames:
+      # Defaults to "<election-id>-<ingress-class>"
+      # Here: "<ingress-controller-leader>-<nginx>"
+      # This has to be adapted if you change either parameter
+      # when launching the nginx-ingress-controller.
+      - "ingress-controller-leader-public"
+    verbs:
+      - get
+      - update
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    verbs:
+      - create
+  - apiGroups:
+      - ""
+    resources:
+      - endpoints
+    verbs:
+      - get
+      - create
+      - update

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

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: nginx-ingress-controller
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 80
+    - name: https
+      protocol: TCP
+      port: 443
+      targetPort: 443

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

@@ -0,0 +1,36 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        name: default-backend
+        phase: prod
+    spec:
+      containers:
+        - name: default-backend
+          # Any image is permissable as long as:
+          # 1. It serves a 404 page at /
+          # 2. It serves 200 on a /healthz endpoint
+          image: gcr.io/google_containers/defaultbackend:1.4
+          ports:
+            - containerPort: 8080
+          resources:
+            limits:
+              cpu: 10m
+              memory: 20Mi
+            requests:
+              cpu: 10m
+              memory: 20Mi
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: 8080
+              scheme: HTTP
+            initialDelaySeconds: 30
+            timeoutSeconds: 5
+      terminationGracePeriodSeconds: 60

addons/nginx-ingress/google-cloud/default-backend/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: default-backend
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: default-backend
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 8080

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

@@ -0,0 +1,67 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  replicas: 2
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 1
+  template:
+    metadata:
+      labels:
+        name: nginx-ingress-controller
+        phase: prod
+    spec:
+      nodeSelector:
+        node-role.kubernetes.io/node: ""
+      hostNetwork: true
+      containers:
+        - name: nginx-ingress-controller
+          image: gcr.io/google_containers/nginx-ingress-controller:0.9.0-beta.15
+          args:
+            - /nginx-ingress-controller
+            - --default-backend-service=$(POD_NAMESPACE)/default-backend
+            - --ingress-class=public
+          # use downward API
+          env:
+            - name: POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            - name: POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+          ports:
+            - name: http
+              containerPort: 80
+              hostPort: 80
+            - name: https
+              containerPort: 443
+              hostPort: 443
+            - name: health
+              containerPort: 10254
+              hostPort: 10254
+          livenessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            initialDelaySeconds: 10
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /healthz
+              port: 10254
+              scheme: HTTP
+            periodSeconds: 10
+            successThreshold: 1
+            timeoutSeconds: 1
+      restartPolicy: Always
+      terminationGracePeriodSeconds: 60

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

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: ingress

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

@@ -0,0 +1,12 @@
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,51 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - endpoints
+      - nodes
+      - pods
+      - secrets
+    verbs:
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+      - nodes
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - services
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - ""
+    resources:
+        - events
+    verbs:
+        - create
+        - patch
+  - apiGroups:
+      - "extensions"
+    resources:
+      - ingresses/status
+    verbs:
+      - update

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

@@ -0,0 +1,13 @@
+kind: RoleBinding
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: ingress
+subjects:
+  - kind: ServiceAccount
+    namespace: ingress
+    name: default

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

@@ -0,0 +1,41 @@
+kind: Role
+apiVersion: rbac.authorization.k8s.io/v1beta1
+metadata:
+  name: ingress
+  namespace: ingress
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+      - pods
+      - secrets
+    verbs:
+      - get
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    resourceNames:
+      # Defaults to "<election-id>-<ingress-class>"
+      # Here: "<ingress-controller-leader>-<nginx>"
+      # This has to be adapted if you change either parameter
+      # when launching the nginx-ingress-controller.
+      - "ingress-controller-leader-public"
+    verbs:
+      - get
+      - update
+  - apiGroups:
+      - ""
+    resources:
+      - configmaps
+    verbs:
+      - create
+  - apiGroups:
+      - ""
+    resources:
+      - endpoints
+    verbs:
+      - get
+      - create
+      - update

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

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: nginx-ingress-controller
+  namespace: ingress
+spec:
+  type: ClusterIP
+  selector:
+    name: nginx-ingress-controller
+    phase: prod
+  ports:
+    - name: http
+      protocol: TCP
+      port: 80
+      targetPort: 80
+    - name: https
+      protocol: TCP
+      port: 443
+      targetPort: 443

addons/prometheus/config.yaml

@@ -0,0 +1,216 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+  namespace: monitoring
+data:
+  prometheus.yaml: |-
+    # Global config
+    global:
+      scrape_interval: 15s
+    # Scrape configs for running Prometheus on a Kubernetes cluster.
+    # This uses separate scrape configs for cluster components (i.e. API server, node)
+    # and services to allow each to use different authentication configs.
+    #
+    # Kubernetes labels will be added as Prometheus labels on metrics via the
+    # `labelmap` relabeling action.
+    scrape_configs:
+
+    # Scrape config for API servers.
+    #
+    # Kubernetes exposes API servers as endpoints to the default/kubernetes
+    # service so this uses `endpoints` role and uses relabelling to only keep
+    # the endpoints associated with the default/kubernetes service using the
+    # default named port `https`. This works for single API server deployments as
+    # well as HA API server deployments.
+    - job_name: 'kubernetes-apiservers'
+      kubernetes_sd_configs:
+      - role: endpoints
+      
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        # Using endpoints to discover kube-apiserver targets finds the pod IP
+        # (host IP since apiserver is uses host network) which is not used in
+        # the server certificate.
+        insecure_skip_verify: true
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      # Keep only the default/kubernetes service endpoints for the https port. This
+      # will add targets for each API server which Kubernetes adds an endpoint to
+      # the default/kubernetes service.
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+        action: keep
+        regex: default;kubernetes;https
+
+    # Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
+    # metrics from a node by scraping kubelet (127.0.0.1:10255/metrics).
+    #
+    # Rather than connecting directly to the node, the scrape is proxied though the
+    # Kubernetes apiserver.  This means it will work if Prometheus is running out of
+    # cluster, or can't connect to nodes for some other reason (e.g. because of
+    # firewalling).
+    - job_name: 'kubernetes-nodes'
+      kubernetes_sd_configs:
+      - role: node
+      
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics
+
+    # Scrape config for Kubelet cAdvisor. Explore metrics from a node by
+    # scraping kubelet (127.0.0.1:10255/metrics/cadvisor).
+    #
+    # This is required for Kubernetes 1.7.3 and later, where cAdvisor metrics
+    # (those whose names begin with 'container_') have been removed from the
+    # Kubelet metrics endpoint.  This job scrapes the cAdvisor endpoint to
+    # retrieve those metrics.
+    #
+    # Rather than connecting directly to the node, the scrape is proxied though the
+    # Kubernetes apiserver.  This means it will work if Prometheus is running out of
+    # cluster, or can't connect to nodes for some other reason (e.g. because of
+    # firewalling).
+    - job_name: 'kubernetes-cadvisor'
+      kubernetes_sd_configs:
+      - role: node
+      
+      scheme: https
+      tls_config:
+        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+
+      relabel_configs:
+      - action: labelmap
+        regex: __meta_kubernetes_node_label_(.+)
+      - target_label: __address__
+        replacement: kubernetes.default.svc:443
+      - source_labels: [__meta_kubernetes_node_name]
+        regex: (.+)
+        target_label: __metrics_path__
+        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+    
+    # Scrape config for service endpoints.
+    #
+    # The relabeling allows the actual service scrape endpoint to be configured
+    # via the following annotations:
+    #
+    # * `prometheus.io/scrape`: Only scrape services that have a value of `true`
+    # * `prometheus.io/scheme`: If the metrics endpoint is secured then you will need
+    # to set this to `https` & most likely set the `tls_config` of the scrape config.
+    # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
+    # * `prometheus.io/port`: If the metrics are exposed on a different port to the
+    # service then set this appropriately.
+    - job_name: 'kubernetes-service-endpoints'
+
+      kubernetes_sd_configs:
+      - role: endpoints
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+        action: replace
+        target_label: __scheme__
+        regex: (https?)
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+        action: replace
+        target_label: __address__
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+      - action: labelmap
+        regex: __meta_kubernetes_service_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_service_name]
+        action: replace
+        target_label: kubernetes_name
+
+    # Example scrape config for probing services via the Blackbox Exporter.
+    #
+    # The relabeling allows the actual service scrape endpoint to be configured
+    # via the following annotations:
+    #
+    # * `prometheus.io/probe`: Only probe services that have a value of `true`
+    - job_name: 'kubernetes-services'
+
+      metrics_path: /probe
+      params:
+        module: [http_2xx]
+
+      kubernetes_sd_configs:
+      - role: service
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
+        action: keep
+        regex: true
+      - source_labels: [__address__]
+        target_label: __param_target
+      - target_label: __address__
+        replacement: blackbox
+      - source_labels: [__param_target]
+        target_label: instance
+      - action: labelmap
+        regex: __meta_kubernetes_service_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_service_name]
+        target_label: kubernetes_name
+
+    # Example scrape config for pods
+    #
+    # The relabeling allows the actual pod scrape endpoint to be configured via the
+    # following annotations:
+    #
+    # * `prometheus.io/scrape`: Only scrape pods that have a value of `true`
+    # * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
+    # * `prometheus.io/port`: Scrape the pod on the indicated port instead of the
+    # pod's declared ports (default is a port-free target if none are declared).
+    - job_name: 'kubernetes-pods'
+
+      kubernetes_sd_configs:
+      - role: pod
+
+      relabel_configs:
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+        action: keep
+        regex: true
+      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+        action: replace
+        target_label: __metrics_path__
+        regex: (.+)
+      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+        action: replace
+        regex: ([^:]+)(?::\d+)?;(\d+)
+        replacement: $1:$2
+        target_label: __address__
+      - action: labelmap
+        regex: __meta_kubernetes_pod_label_(.+)
+      - source_labels: [__meta_kubernetes_namespace]
+        action: replace
+        target_label: kubernetes_namespace
+      - source_labels: [__meta_kubernetes_pod_name]
+        action: replace
+        target_label: kubernetes_pod_name
+
+    # Rule files
+    rule_files:
+      - "/etc/prometheus/rules/*.rules"

addons/prometheus/deployment.yaml

@@ -0,0 +1,45 @@
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  replicas: 1
+  strategy:
+    rollingUpdate:
+      maxUnavailable: 1
+  template:
+    metadata:
+      labels:
+        name: prometheus
+        phase: prod
+    spec:
+      containers:
+      - name: prometheus
+        image: quay.io/prometheus/prometheus:v1.8.0
+        args:
+          - '-config.file=/etc/prometheus/prometheus.yaml'
+          - '-storage.local.retention=12h'
+          - '-storage.local.memory-chunks=500000'
+        ports:
+        - name: web
+          containerPort: 9090
+        volumeMounts:
+        - name: config
+          mountPath: /etc/prometheus
+        - name: rules
+          mountPath: /etc/prometheus/rules
+        - name: data
+          mountPath: /var/lib/prometheus
+      dnsPolicy: ClusterFirst
+      restartPolicy: Always
+      terminationGracePeriodSeconds: 30
+      volumes:
+      - name: config
+        configMap:
+          name: prometheus-config
+      - name: rules
+        configMap:
+          name: prometheus-rules
+      - name: data
+        emptyDir: {}

addons/prometheus/exporters/kube-state-metrics/cluster-role-binding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: kube-state-metrics
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kube-state-metrics
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: monitoring

addons/prometheus/exporters/kube-state-metrics/cluster-role.yaml

@@ -0,0 +1,31 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: kube-state-metrics
+rules:
+- apiGroups: [""]
+  resources:
+  - nodes
+  - pods
+  - services
+  - resourcequotas
+  - replicationcontrollers
+  - limitranges
+  - persistentvolumeclaims
+  - namespaces
+  verbs: ["list", "watch"]
+- apiGroups: ["extensions"]
+  resources:
+  - daemonsets
+  - deployments
+  - replicasets
+  verbs: ["list", "watch"]
+- apiGroups: ["apps"]
+  resources:
+  - statefulsets
+  verbs: ["list", "watch"]
+- apiGroups: ["batch"]
+  resources:
+  - cronjobs
+  - jobs
+  verbs: ["list", "watch"]

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

@@ -0,0 +1,67 @@
+apiVersion: apps/v1beta2
+kind: Deployment
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  replicas: 1
+  strategy:
+    rollingUpdate:
+      maxUnavilable: 1
+  selector:
+    matchLabels:
+      name: kube-state-metrics
+      phase: prod
+  template:
+    metadata:
+      labels:
+        name: kube-state-metrics
+        phase: prod
+    spec:
+      serviceAccountName: kube-state-metrics
+      containers:
+      - name: kube-state-metrics
+        image: quay.io/coreos/kube-state-metrics:v1.1.0
+        ports:
+          - name: metrics
+            containerPort: 8080
+        readinessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        resources:
+          requests:
+            memory: 100Mi
+            cpu: 100m
+          limits:
+            memory: 200Mi
+            cpu: 200m
+      - name: addon-resizer
+        image: gcr.io/google_containers/addon-resizer:1.0
+        resources:
+          limits:
+            cpu: 100m
+            memory: 30Mi
+          requests:
+            cpu: 100m
+            memory: 30Mi
+        env:
+          - name: MY_POD_NAME
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.name
+          - name: MY_POD_NAMESPACE
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.namespace
+        command:
+          - /pod_nanny
+          - --container=kube-state-metrics
+          - --cpu=100m
+          - --extra-cpu=1m
+          - --memory=100Mi
+          - --extra-memory=2Mi
+          - --threshold=5
+          - --deployment=kube-state-metrics

addons/prometheus/exporters/kube-state-metrics/resizer-role-binding.yaml

@@ -0,0 +1,13 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: kube-state-metrics-resizer
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: monitoring

addons/prometheus/exporters/kube-state-metrics/resizer-role.yaml

@@ -0,0 +1,15 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: kube-state-metrics-resizer
+  namespace: monitoring
+rules:
+- apiGroups: [""]
+  resources:
+  - pods
+  verbs: ["get"]
+- apiGroups: ["extensions"]
+  resources:
+  - deployments
+  resourceNames: ["kube-state-metrics"]
+  verbs: ["get", "update"]

addons/prometheus/exporters/kube-state-metrics/service-account.yaml

@@ -0,0 +1,5 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring

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

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  selector:
+    name: kube-state-metrics
+    phase: prod
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 80
+      targetPort: 8080

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

@@ -0,0 +1,57 @@
+apiVersion: apps/v1beta2
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+spec:
+  updateStrategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 1
+  selector:
+    matchLabels:
+      name: node-exporter
+      phase: prod
+  template:
+    metadata:
+      labels:
+        name: node-exporter
+        phase: prod
+    spec:
+      hostNetwork: true
+      hostPID: true
+      containers:
+      - name: node-exporter
+        image: quay.io/prometheus/node-exporter:v0.15.0
+        args:
+          - "--path.procfs=/host/proc"
+          - "--path.sysfs=/host/sys"
+        ports:
+          - name: metrics
+            containerPort: 9100
+            hostPort: 9100
+        resources:
+          requests:
+            memory: 30Mi
+            cpu: 100m
+          limits:
+            memory: 50Mi
+            cpu: 200m
+        volumeMounts:
+          - name: proc
+            mountPath: /host/proc
+            readOnly:  true
+          - name: sys
+            mountPath: /host/sys
+            readOnly: true
+      tolerations:
+        - key: node-role.kubernetes.io/master
+          operator: Exists
+          effect: NoSchedule
+      volumes:
+        - name: proc
+          hostPath:
+            path: /proc
+        - name: sys
+          hostPath:
+            path: /sys

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

@@ -0,0 +1,19 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  annotations:
+    prometheus.io/scrape: 'true'
+spec:
+  type: ClusterIP
+  # service is created to allow prometheus to scape endpoints
+  clusterIP: None
+  selector:
+    name: node-exporter
+    phase: prod
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 80
+      targetPort: 9100

addons/prometheus/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

addons/prometheus/rbac/cluster-role-binding.yaml

@@ -0,0 +1,12 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+- kind: ServiceAccount
+  name: default
+  namespace: monitoring

addons/prometheus/rbac/cluster-role.yaml

@@ -0,0 +1,15 @@
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: prometheus
+rules:
+- apiGroups: [""]
+  resources:
+  - nodes
+  - nodes/proxy
+  - services
+  - endpoints
+  - pods
+  verbs: ["get", "list", "watch"]
+- nonResourceURLs: ["/metrics"]
+  verbs: ["get"]

addons/prometheus/rules.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-rules
+  namespace: monitoring
+data:
+  example.rule: |
+    job_service:rpc_durations_seconds_count:avg_rate5m = avg(rate(rpc_durations_seconds_count[5m])) by (job, service)

addons/prometheus/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+spec:
+  type: ClusterIP
+  selector:
+    name: prometheus
+    phase: prod
+  ports:
+    - name: web
+      protocol: TCP
+      port: 80
+      targetPort: 9090

aws/container-linux/kubernetes/LICENSE

@@ -0,0 +1,23 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 Typhoon Authors
+Copyright (c) 2017 Dalton Hubble
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+

aws/container-linux/kubernetes/README.md

@@ -0,0 +1,22 @@
+# Typhoon
+
+Typhoon is a minimal and free Kubernetes distribution.
+
+* Minimal, stable base Kubernetes distribution
+* Declarative infrastructure and configuration
+* Free (freedom and cost) and privacy-respecting
+* Practical for labs, datacenters, and clouds
+
+Typhoon distributes upstream Kubernetes, architectural conventions, and cluster addons, much like a GNU/Linux distribution provides the Linux kernel and userspace components.
+
+## Features
+
+* Kubernetes v1.8.2 (upstream, via [kubernetes-incubator/bootkube](https://github.com/kubernetes-incubator/bootkube))
+* Single or multi-master, workloads isolated on workers, [Calico](https://www.projectcalico.org/) 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/)
+* Ready for Ingress, Dashboards, Metrics, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+
+## Docs
+
+Please see the [official docs](https://typhoon.psdn.io) and the AWS [tutorial](https://typhoon.psdn.io/aws/).
+

aws/container-linux/kubernetes/ami.tf

@@ -0,0 +1,19 @@
+data "aws_ami" "coreos" {
+  most_recent = true
+  owners      = ["595879546273"]
+
+  filter {
+    name   = "architecture"
+    values = ["x86_64"]
+  }
+
+  filter {
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+
+  filter {
+    name   = "name"
+    values = ["CoreOS-${var.os_channel}-*"]
+  }
+}

aws/container-linux/kubernetes/bootkube.tf

@@ -0,0 +1,14 @@
+# Self-hosted Kubernetes assets (kubeconfig, manifests)
+module "bootkube" {
+  source = "git::https://github.com/poseidon/terraform-render-bootkube.git?ref=v0.8.1"
+
+  cluster_name                  = "${var.cluster_name}"
+  api_servers                   = ["${format("%s.%s", var.cluster_name, var.dns_zone)}"]
+  etcd_servers                  = ["http://127.0.0.1:2379"]
+  asset_dir                     = "${var.asset_dir}"
+  networking                    = "${var.networking}"
+  network_mtu                   = "${var.network_mtu}"
+  pod_cidr                      = "${var.pod_cidr}"
+  service_cidr                  = "${var.service_cidr}"
+  experimental_self_hosted_etcd = "true"
+}

aws/container-linux/kubernetes/cl/controller.yaml.tmpl

@@ -0,0 +1,149 @@
+---
+systemd:
+  units:
+    - name: docker.service
+      enable: true
+    - name: locksmithd.service
+      mask: true
+    - name: wait-for-dns.service
+      enable: true
+      contents: |
+        [Unit]
+        Description=Wait for DNS entries
+        Wants=systemd-resolved.service
+        Before=kubelet.service
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
+        [Install]
+        RequiredBy=kubelet.service
+    - name: kubelet.service
+      enable: true
+      contents: |
+        [Unit]
+        Description=Kubelet via Hyperkube ACI
+        Wants=rpc-statd.service
+        [Service]
+        EnvironmentFile=/etc/kubernetes/kubelet.env
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
+          --volume=resolv,kind=host,source=/etc/resolv.conf \
+          --mount volume=resolv,target=/etc/resolv.conf \
+          --volume var-lib-cni,kind=host,source=/var/lib/cni \
+          --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
+          --volume var-log,kind=host,source=/var/log \
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
+        ExecStartPre=/bin/mkdir -p /var/lib/cni
+        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
+        ExecStart=/usr/lib/coreos/kubelet-wrapper \
+          --allow-privileged \
+          --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${k8s_dns_service_ip} \
+          --cluster_domain=cluster.local \
+          --cni-conf-dir=/etc/kubernetes/cni/net.d \
+          --exit-on-lock-contention \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
+          --node-labels=node-role.kubernetes.io/master \
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
+        Restart=always
+        RestartSec=10
+        [Install]
+        WantedBy=multi-user.target
+    - name: bootkube.service
+      contents: |
+        [Unit]
+        Description=Bootstrap a Kubernetes cluster
+        ConditionPathExists=!/opt/bootkube/init_bootkube.done
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        WorkingDirectory=/opt/bootkube
+        ExecStart=/opt/bootkube/bootkube-start
+        ExecStartPost=/bin/touch /opt/bootkube/init_bootkube.done
+        [Install]
+        WantedBy=multi-user.target
+storage:
+  files:
+    - path: /etc/kubernetes/kubeconfig
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          apiVersion: v1
+          kind: Config
+          clusters:
+          - name: local
+            cluster:
+              server: ${kubeconfig_server}
+              certificate-authority-data: ${kubeconfig_ca_cert}
+          users:
+          - name: kubelet
+            user:
+              client-certificate-data: ${kubeconfig_kubelet_cert}
+              client-key-data: ${kubeconfig_kubelet_key}
+          contexts:
+          - context:
+              cluster: local
+              user: kubelet
+    - path: /etc/kubernetes/kubelet.env
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
+    - path: /etc/sysctl.d/max-user-watches.conf
+      filesystem: root
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+    - path: /opt/bootkube/bootkube-start
+      filesystem: root
+      mode: 0544
+      user:
+        id: 500
+      group:
+        id: 500
+      contents:
+        inline: |
+          #!/bin/bash
+          # Wrapper for bootkube start
+          set -e
+          # Move experimental manifests
+          [ -d /opt/bootkube/assets/manifests-* ] && mv /opt/bootkube/assets/manifests-*/* /opt/bootkube/assets/manifests && rm -rf /opt/bootkube/assets/manifests-*
+          [ -d /opt/bootkube/assets/experimental/manifests ] && mv /opt/bootkube/assets/experimental/manifests/* /opt/bootkube/assets/manifests && rm -r /opt/bootkube/assets/experimental/manifests
+          [ -d /opt/bootkube/assets/experimental/bootstrap-manifests ] && mv /opt/bootkube/assets/experimental/bootstrap-manifests/* /opt/bootkube/assets/bootstrap-manifests && rm -r /opt/bootkube/assets/experimental/bootstrap-manifests
+          BOOTKUBE_ACI="$${BOOTKUBE_ACI:-quay.io/coreos/bootkube}"
+          BOOTKUBE_VERSION="$${BOOTKUBE_VERSION:-v0.8.1}"
+          BOOTKUBE_ASSETS="$${BOOTKUBE_ASSETS:-/opt/bootkube/assets}"
+          exec /usr/bin/rkt run \
+            --trust-keys-from-https \
+            --volume assets,kind=host,source=$${BOOTKUBE_ASSETS} \
+            --mount volume=assets,target=/assets \
+            --volume bootstrap,kind=host,source=/etc/kubernetes \
+            --mount volume=bootstrap,target=/etc/kubernetes \
+            $${RKT_OPTS} \
+            $${BOOTKUBE_ACI}:$${BOOTKUBE_VERSION} \
+            --net=host \
+            --dns=host \
+            --exec=/bootkube -- start --asset-dir=/assets "$@"
+passwd:
+  users:
+    - name: core
+      ssh_authorized_keys:
+        - "${ssh_authorized_key}"

aws/container-linux/kubernetes/cl/worker.yaml.tmpl

@@ -23,37 +23,42 @@ systemd:
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --anonymous-auth=false \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --exit-on-lock-contention \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --allow-privileged \
-          --node-labels=node-role.kubernetes.io/node \
+          --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
           --cluster_dns=${k8s_dns_service_ip} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --cluster_domain=cluster.local \
+          --cni-conf-dir=/etc/kubernetes/cni/net.d \
+          --exit-on-lock-contention \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
+          --node-labels=node-role.kubernetes.io/node \
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=5
         [Install]
@@ -98,8 +103,8 @@ storage:
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
       contents:
@@ -116,7 +121,8 @@ storage:
             --trust-keys-from-https \
             --volume config,kind=host,source=/etc/kubernetes \
             --mount volume=config,target=/etc/kubernetes \
-            quay.io/coreos/hyperkube:v1.7.3_coreos.0 \
+            --insecure-options=image \
+            docker://gcr.io/google_containers/hyperkube:v1.8.2 \
             --net=host \
             --dns=host \
             --exec=/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)

aws/container-linux/kubernetes/controllers.tf

@@ -0,0 +1,244 @@
+# Controllers AutoScaling Group
+resource "aws_autoscaling_group" "controllers" {
+  name           = "${var.cluster_name}-controller"
+  load_balancers = ["${aws_elb.controllers.id}"]
+
+  # count
+  desired_capacity = "${var.controller_count}"
+  min_size         = "${var.controller_count}"
+  max_size         = "${var.controller_count}"
+
+  # network
+  vpc_zone_identifier = ["${aws_subnet.public.*.id}"]
+
+  # template
+  launch_configuration = "${aws_launch_configuration.controller.name}"
+
+  lifecycle {
+    # override the default destroy and replace update behavior
+    create_before_destroy = true
+    ignore_changes        = ["image_id"]
+  }
+
+  tags = [{
+    key                 = "Name"
+    value               = "${var.cluster_name}-controller"
+    propagate_at_launch = true
+  }]
+}
+
+# Controller template
+resource "aws_launch_configuration" "controller" {
+  name_prefix   = "${var.cluster_name}-controller-template-"
+  image_id      = "${data.aws_ami.coreos.image_id}"
+  instance_type = "${var.controller_type}"
+
+  user_data = "${data.ct_config.controller_ign.rendered}"
+
+  # storage
+  root_block_device {
+    volume_type = "standard"
+    volume_size = "${var.disk_size}"
+  }
+
+  # network
+  associate_public_ip_address = true
+  security_groups             = ["${aws_security_group.controller.id}"]
+
+  lifecycle {
+    // Override the default destroy and replace update behavior
+    create_before_destroy = true
+  }
+}
+
+# Controller Container Linux Config
+data "template_file" "controller_config" {
+  template = "${file("${path.module}/cl/controller.yaml.tmpl")}"
+
+  vars = {
+    k8s_dns_service_ip      = "${cidrhost(var.service_cidr, 10)}"
+    k8s_etcd_service_ip     = "${cidrhost(var.service_cidr, 15)}"
+    ssh_authorized_key      = "${var.ssh_authorized_key}"
+    kubeconfig_ca_cert      = "${module.bootkube.ca_cert}"
+    kubeconfig_kubelet_cert = "${module.bootkube.kubelet_cert}"
+    kubeconfig_kubelet_key  = "${module.bootkube.kubelet_key}"
+    kubeconfig_server       = "${module.bootkube.server}"
+  }
+}
+
+data "ct_config" "controller_ign" {
+  content      = "${data.template_file.controller_config.rendered}"
+  pretty_print = false
+}
+
+# Security Group (instance firewall)
+
+resource "aws_security_group" "controller" {
+  name        = "${var.cluster_name}-controller"
+  description = "${var.cluster_name} controller security group"
+
+  vpc_id = "${aws_vpc.network.id}"
+
+  tags = "${map("Name", "${var.cluster_name}-controller")}"
+}
+
+resource "aws_security_group_rule" "controller-icmp" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type        = "ingress"
+  protocol    = "icmp"
+  from_port   = 0
+  to_port     = 0
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "controller-ssh" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type        = "ingress"
+  protocol    = "tcp"
+  from_port   = 22
+  to_port     = 22
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "controller-apiserver" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type        = "ingress"
+  protocol    = "tcp"
+  from_port   = 443
+  to_port     = 443
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "controller-etcd" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 2379
+  to_port   = 2380
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-bootstrap-etcd" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 12379
+  to_port   = 12380
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-flannel" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = "${aws_security_group.worker.id}"
+}
+
+resource "aws_security_group_rule" "controller-flannel-self" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-kubelet-read" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10255
+  to_port                  = 10255
+  source_security_group_id = "${aws_security_group.worker.id}"
+}
+
+resource "aws_security_group_rule" "controller-kubelet-read-self" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 10255
+  to_port   = 10255
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-bgp" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 179
+  to_port                  = 179
+  source_security_group_id = "${aws_security_group.worker.id}"
+}
+
+resource "aws_security_group_rule" "controller-bgp-self" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 179
+  to_port   = 179
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-ipip" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type                     = "ingress"
+  protocol                 = 4
+  from_port                = 0
+  to_port                  = 0
+  source_security_group_id = "${aws_security_group.worker.id}"
+}
+
+resource "aws_security_group_rule" "controller-ipip-self" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = 4
+  from_port = 0
+  to_port   = 0
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-ipip-legacy" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type                     = "ingress"
+  protocol                 = 94
+  from_port                = 0
+  to_port                  = 0
+  source_security_group_id = "${aws_security_group.worker.id}"
+}
+
+resource "aws_security_group_rule" "controller-ipip-legacy-self" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type      = "ingress"
+  protocol  = 94
+  from_port = 0
+  to_port   = 0
+  self      = true
+}
+
+resource "aws_security_group_rule" "controller-egress" {
+  security_group_id = "${aws_security_group.controller.id}"
+
+  type             = "egress"
+  protocol         = "-1"
+  from_port        = 0
+  to_port          = 0
+  cidr_blocks      = ["0.0.0.0/0"]
+  ipv6_cidr_blocks = ["::/0"]
+}

aws/container-linux/kubernetes/elb.tf

@@ -0,0 +1,48 @@
+# Controller Network Load Balancer DNS Record
+resource "aws_route53_record" "controllers" {
+  zone_id = "${var.dns_zone_id}"
+
+  name = "${format("%s.%s.", var.cluster_name, var.dns_zone)}"
+  type = "A"
+
+  # AWS recommends their special "alias" records for ELBs
+  alias {
+    name                   = "${aws_elb.controllers.dns_name}"
+    zone_id                = "${aws_elb.controllers.zone_id}"
+    evaluate_target_health = true
+  }
+}
+
+# Controller Network Load Balancer
+resource "aws_elb" "controllers" {
+  name            = "${var.cluster_name}-controllers"
+  subnets         = ["${aws_subnet.public.*.id}"]
+  security_groups = ["${aws_security_group.controller.id}"]
+
+  listener {
+    lb_port           = 22
+    lb_protocol       = "tcp"
+    instance_port     = 22
+    instance_protocol = "tcp"
+  }
+
+  listener {
+    lb_port           = 443
+    lb_protocol       = "tcp"
+    instance_port     = 443
+    instance_protocol = "tcp"
+  }
+
+  # Kubelet HTTP health check
+  health_check {
+    target              = "HTTP:10255/healthz"
+    healthy_threshold   = 2
+    unhealthy_threshold = 4
+    timeout             = 5
+    interval            = 6
+  }
+
+  idle_timeout                = 1800
+  connection_draining         = true
+  connection_draining_timeout = 300
+}

aws/container-linux/kubernetes/ingress.tf

@@ -0,0 +1,32 @@
+# Ingress Network Load Balancer
+resource "aws_elb" "ingress" {
+  name            = "${var.cluster_name}-ingress"
+  subnets         = ["${aws_subnet.public.*.id}"]
+  security_groups = ["${aws_security_group.worker.id}"]
+
+  listener {
+    lb_port           = 80
+    lb_protocol       = "tcp"
+    instance_port     = 80
+    instance_protocol = "tcp"
+  }
+
+  listener {
+    lb_port           = 443
+    lb_protocol       = "tcp"
+    instance_port     = 443
+    instance_protocol = "tcp"
+  }
+
+  # Ingress Controller HTTP health check
+  health_check {
+    target              = "HTTP:10254/healthz"
+    healthy_threshold   = 2
+    unhealthy_threshold = 4
+    timeout             = 5
+    interval            = 6
+  }
+
+  connection_draining         = true
+  connection_draining_timeout = 300
+}

aws/container-linux/kubernetes/network.tf

@@ -0,0 +1,57 @@
+data "aws_availability_zones" "all" {}
+
+# Network VPC, gateway, and routes
+
+resource "aws_vpc" "network" {
+  cidr_block                       = "${var.host_cidr}"
+  assign_generated_ipv6_cidr_block = true
+  enable_dns_support               = true
+  enable_dns_hostnames             = true
+
+  tags = "${map("Name", "${var.cluster_name}")}"
+}
+
+resource "aws_internet_gateway" "gateway" {
+  vpc_id = "${aws_vpc.network.id}"
+
+  tags = "${map("Name", "${var.cluster_name}")}"
+}
+
+resource "aws_route_table" "default" {
+  vpc_id = "${aws_vpc.network.id}"
+
+  route {
+    cidr_block = "0.0.0.0/0"
+    gateway_id = "${aws_internet_gateway.gateway.id}"
+  }
+
+  route {
+    ipv6_cidr_block = "::/0"
+    gateway_id      = "${aws_internet_gateway.gateway.id}"
+  }
+
+  tags = "${map("Name", "${var.cluster_name}")}"
+}
+
+# Subnets (one per availability zone)
+
+resource "aws_subnet" "public" {
+  count = "${length(data.aws_availability_zones.all.names)}"
+
+  vpc_id            = "${aws_vpc.network.id}"
+  availability_zone = "${data.aws_availability_zones.all.names[count.index]}"
+
+  cidr_block                      = "${cidrsubnet(var.host_cidr, 4, count.index)}"
+  ipv6_cidr_block                 = "${cidrsubnet(aws_vpc.network.ipv6_cidr_block, 8, count.index)}"
+  map_public_ip_on_launch         = true
+  assign_ipv6_address_on_creation = true
+
+  tags = "${map("Name", "${var.cluster_name}-public-${count.index}")}"
+}
+
+resource "aws_route_table_association" "public" {
+  count = "${length(data.aws_availability_zones.all.names)}"
+
+  route_table_id = "${aws_route_table.default.id}"
+  subnet_id      = "${element(aws_subnet.public.*.id, count.index)}"
+}

aws/container-linux/kubernetes/outputs.tf

@@ -0,0 +1,4 @@
+output "ingress_dns_name" {
+  value       = "${aws_elb.ingress.dns_name}"
+  description = "DNS name of the ELB for distributing traffic to Ingress controllers"
+}

aws/container-linux/kubernetes/require.tf

@@ -0,0 +1,25 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.10.4"
+}
+
+provider "aws" {
+  version = "~> 1.0"
+}
+
+provider "local" {
+  version = "~> 1.0"
+}
+
+provider "null" {
+  version = "~> 1.0"
+}
+
+provider "template" {
+  version = "~> 1.0"
+}
+
+provider "tls" {
+  version = "~> 1.0"
+}

aws/container-linux/kubernetes/ssh.tf

@@ -0,0 +1,25 @@
+# Secure copy bootkube assets to ONE controller and start bootkube to perform
+# one-time self-hosted cluster bootstrapping.
+resource "null_resource" "bootkube-start" {
+  depends_on = ["module.bootkube", "aws_autoscaling_group.controllers"]
+
+  # TODO: SSH to a controller's IP instead of waiting on DNS resolution
+  connection {
+    type    = "ssh"
+    host    = "${aws_route53_record.controllers.fqdn}"
+    user    = "core"
+    timeout = "15m"
+  }
+
+  provisioner "file" {
+    source      = "${var.asset_dir}"
+    destination = "$HOME/assets"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "sudo mv /home/core/assets /opt/bootkube",
+      "sudo systemctl start bootkube",
+    ]
+  }
+}

aws/container-linux/kubernetes/variables.tf

@@ -0,0 +1,96 @@
+variable "cluster_name" {
+  type        = "string"
+  description = "Cluster name"
+}
+
+variable "dns_zone" {
+  type        = "string"
+  description = "AWS DNS Zone (e.g. aws.dghubble.io)"
+}
+
+variable "dns_zone_id" {
+  type        = "string"
+  description = "AWS DNS Zone ID (e.g. Z3PAABBCFAKEC0)"
+}
+
+variable "ssh_authorized_key" {
+  type        = "string"
+  description = "SSH public key for user 'core'"
+}
+
+variable "os_channel" {
+  type        = "string"
+  default     = "stable"
+  description = "Container Linux AMI channel (stable, beta, alpha)"
+}
+
+variable "disk_size" {
+  type        = "string"
+  default     = "40"
+  description = "The size of the disk in Gigabytes"
+}
+
+variable "host_cidr" {
+  description = "CIDR IPv4 range to assign to EC2 nodes"
+  type        = "string"
+  default     = "10.0.0.0/16"
+}
+
+variable "controller_count" {
+  type        = "string"
+  default     = "1"
+  description = "Number of controllers"
+}
+
+variable "controller_type" {
+  type        = "string"
+  default     = "t2.small"
+  description = "Controller EC2 instance type"
+}
+
+variable "worker_count" {
+  type        = "string"
+  default     = "1"
+  description = "Number of workers"
+}
+
+variable "worker_type" {
+  type        = "string"
+  default     = "t2.small"
+  description = "Worker EC2 instance type"
+}
+
+# bootkube assets
+
+variable "asset_dir" {
+  description = "Path to a directory where generated assets should be placed (contains secrets)"
+  type        = "string"
+}
+
+variable "networking" {
+  description = "Choice of networking provider (calico or flannel)"
+  type        = "string"
+  default     = "calico"
+}
+
+variable "network_mtu" {
+  description = "CNI interface MTU (applies to calico only). Use 8981 if using instances types with Jumbo frames."
+  type        = "string"
+  default     = "1480"
+}
+
+variable "pod_cidr" {
+  description = "CIDR IPv4 range to assign Kubernetes pods"
+  type        = "string"
+  default     = "10.2.0.0/16"
+}
+
+variable "service_cidr" {
+  description = <<EOD
+CIDR IPv4 range to assign Kubernetes services.
+The 1st IP will be reserved for kube_apiserver, the 10th IP will be reserved for kube-dns, the 15th IP will be reserved for self-hosted etcd, and the 200th IP will be reserved for bootstrap self-hosted etcd.
+EOD
+
+  type    = "string"
+  default = "10.3.0.0/16"
+}

aws/container-linux/kubernetes/workers.tf

@@ -0,0 +1,264 @@
+# Workers AutoScaling Group
+resource "aws_autoscaling_group" "workers" {
+  name           = "${var.cluster_name}-worker ${aws_launch_configuration.worker.name}"
+  load_balancers = ["${aws_elb.ingress.id}"]
+
+  # count
+  desired_capacity          = "${var.worker_count}"
+  min_size                  = "${var.worker_count}"
+  max_size                  = "${var.worker_count + 2}"
+  default_cooldown          = 30
+  health_check_grace_period = 30
+
+  # network
+  vpc_zone_identifier = ["${aws_subnet.public.*.id}"]
+
+  # template
+  launch_configuration = "${aws_launch_configuration.worker.name}"
+
+  lifecycle {
+    # override the default destroy and replace update behavior
+    create_before_destroy = true
+    ignore_changes        = ["image_id"]
+  }
+
+  tags = [{
+    key                 = "Name"
+    value               = "${var.cluster_name}-worker"
+    propagate_at_launch = true
+  }]
+}
+
+# Worker template
+resource "aws_launch_configuration" "worker" {
+  image_id      = "${data.aws_ami.coreos.image_id}"
+  instance_type = "${var.worker_type}"
+
+  user_data = "${data.ct_config.worker_ign.rendered}"
+
+  # storage
+  root_block_device {
+    volume_type = "standard"
+    volume_size = "${var.disk_size}"
+  }
+
+  # network
+  security_groups = ["${aws_security_group.worker.id}"]
+
+  lifecycle {
+    // Override the default destroy and replace update behavior
+    create_before_destroy = true
+  }
+}
+
+# Worker Container Linux Config
+data "template_file" "worker_config" {
+  template = "${file("${path.module}/cl/worker.yaml.tmpl")}"
+
+  vars = {
+    k8s_dns_service_ip      = "${cidrhost(var.service_cidr, 10)}"
+    k8s_etcd_service_ip     = "${cidrhost(var.service_cidr, 15)}"
+    ssh_authorized_key      = "${var.ssh_authorized_key}"
+    kubeconfig_ca_cert      = "${module.bootkube.ca_cert}"
+    kubeconfig_kubelet_cert = "${module.bootkube.kubelet_cert}"
+    kubeconfig_kubelet_key  = "${module.bootkube.kubelet_key}"
+    kubeconfig_server       = "${module.bootkube.server}"
+  }
+}
+
+data "ct_config" "worker_ign" {
+  content      = "${data.template_file.worker_config.rendered}"
+  pretty_print = false
+}
+
+# Security Group (instance firewall)
+
+resource "aws_security_group" "worker" {
+  name        = "${var.cluster_name}-worker"
+  description = "${var.cluster_name} worker security group"
+
+  vpc_id = "${aws_vpc.network.id}"
+
+  tags = "${map("Name", "${var.cluster_name}-worker")}"
+}
+
+resource "aws_security_group_rule" "worker-icmp" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type        = "ingress"
+  protocol    = "icmp"
+  from_port   = 0
+  to_port     = 0
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "worker-ssh" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type        = "ingress"
+  protocol    = "tcp"
+  from_port   = 22
+  to_port     = 22
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "worker-http" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type        = "ingress"
+  protocol    = "tcp"
+  from_port   = 80
+  to_port     = 80
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "worker-https" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type        = "ingress"
+  protocol    = "tcp"
+  from_port   = 443
+  to_port     = 443
+  cidr_blocks = ["0.0.0.0/0"]
+}
+
+resource "aws_security_group_rule" "worker-flannel" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-flannel-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-kubelet" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10250
+  to_port                  = 10250
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-kubelet-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 10250
+  to_port   = 10250
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-kubelet-read" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10255
+  to_port                  = 10255
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-kubelet-read-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 10255
+  to_port   = 10255
+  self      = true
+}
+
+resource "aws_security_group_rule" "ingress-health-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 10254
+  to_port   = 10254
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-bgp" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 179
+  to_port                  = 179
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-bgp-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 179
+  to_port   = 179
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-ipip" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = 4
+  from_port                = 0
+  to_port                  = 0
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-ipip-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = 4
+  from_port = 0
+  to_port   = 0
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-ipip-legacy" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type                     = "ingress"
+  protocol                 = 94
+  from_port                = 0
+  to_port                  = 0
+  source_security_group_id = "${aws_security_group.controller.id}"
+}
+
+resource "aws_security_group_rule" "worker-ipip-legacy-self" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type      = "ingress"
+  protocol  = 94
+  from_port = 0
+  to_port   = 0
+  self      = true
+}
+
+resource "aws_security_group_rule" "worker-egress" {
+  security_group_id = "${aws_security_group.worker.id}"
+
+  type             = "egress"
+  protocol         = "-1"
+  from_port        = 0
+  to_port          = 0
+  cidr_blocks      = ["0.0.0.0/0"]
+  ipv6_cidr_blocks = ["::/0"]
+}

bare-metal/container-linux/kubernetes/LICENSE

@@ -0,0 +1,23 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 Typhoon Authors
+Copyright (c) 2017 Dalton Hubble
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+

bare-metal/container-linux/kubernetes/README.md

@@ -0,0 +1,22 @@
+# Typhoon
+
+Typhoon is a minimal and free Kubernetes distribution.
+
+* Minimal, stable base Kubernetes distribution
+* Declarative infrastructure and configuration
+* Free (freedom and cost) and privacy-respecting
+* Practical for labs, datacenters, and clouds
+
+Typhoon distributes upstream Kubernetes, architectural conventions, and cluster addons, much like a GNU/Linux distribution provides the Linux kernel and userspace components.
+
+## Features
+
+* Kubernetes v1.8.2 (upstream, via [kubernetes-incubator/bootkube](https://github.com/kubernetes-incubator/bootkube))
+* Single or multi-master, workloads isolated on workers, [Calico](https://www.projectcalico.org/) 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/)
+* Ready for Ingress, Dashboards, Metrics, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+
+## Docs
+
+Please see the [official docs](https://typhoon.psdn.io) and the bare-metal [tutorial](https://typhoon.psdn.io/bare-metal/).
+

bare-metal/container-linux/kubernetes/bootkube.tf

@@ -1,14 +1,13 @@
 # Self-hosted Kubernetes assets (kubeconfig, manifests)
 module "bootkube" {
-  source = "git::https://github.com/poseidon/bootkube-terraform.git?ref=5ffbfec46dc05721eaf9d15c3c9bbedefaead1bc"
+  source = "git::https://github.com/poseidon/terraform-render-bootkube.git?ref=v0.8.1"
 
-  cluster_name                  = "${var.cluster_name}"
-  api_servers                   = ["${var.k8s_domain_name}"]
-  etcd_servers                  = ["${var.controller_domains}"]
-  asset_dir                     = "${var.asset_dir}"
-  networking                    = "${var.networking}"
-  network_mtu                   = "${var.network_mtu}"
-  pod_cidr                      = "${var.pod_cidr}"
-  service_cidr                  = "${var.service_cidr}"
-  experimental_self_hosted_etcd = "${var.experimental_self_hosted_etcd}"
+  cluster_name = "${var.cluster_name}"
+  api_servers  = ["${var.k8s_domain_name}"]
+  etcd_servers = ["${var.controller_domains}"]
+  asset_dir    = "${var.asset_dir}"
+  networking   = "${var.networking}"
+  network_mtu  = "${var.network_mtu}"
+  pod_cidr     = "${var.pod_cidr}"
+  service_cidr = "${var.service_cidr}"
 }

bare-metal/container-linux/kubernetes/cl/container-linux-install.yaml.tmpl

@@ -32,6 +32,11 @@ storage:
           systemctl reboot
 passwd:
   users:
-    - name: core
+    # Avoid using standard name "core" so terraform apply cannot SSH until post-install.
+    - name: debug
+      create:
+        groups:
+          - sudo
+          - docker
       ssh_authorized_keys:
         - {{.ssh_authorized_key}}

bare-metal/container-linux/kubernetes/cl/controller.yaml.tmpl

@@ -1,7 +1,6 @@
 ---
 systemd:
   units:
-    {{ if eq .etcd_on_host "true" }}
     - name: etcd-member.service
       enable: true
       dropins:
@@ -9,12 +8,12 @@ systemd:
           contents: |
             [Service]
             Environment="ETCD_IMAGE_TAG=v3.2.0"
-            Environment="ETCD_NAME={{.etcd_name}}"
-            Environment="ETCD_ADVERTISE_CLIENT_URLS=https://{{.domain_name}}:2379"
-            Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://{{.domain_name}}:2380"
+            Environment="ETCD_NAME=${etcd_name}"
+            Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${domain_name}:2379"
+            Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${domain_name}:2380"
             Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
             Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
-            Environment="ETCD_INITIAL_CLUSTER={{.etcd_initial_cluster}}"
+            Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
             Environment="ETCD_STRICT_RECONFIG_CHECK=true"
             Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
             Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
@@ -25,7 +24,6 @@ systemd:
             Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
             Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
             Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
-    {{ end }}
     - name: docker.service
       enable: true
     - name: locksmithd.service
@@ -56,39 +54,44 @@ systemd:
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --anonymous-auth=false \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --exit-on-lock-contention \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --allow-privileged \
-          --hostname-override={{.domain_name}} \
+          --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${k8s_dns_service_ip} \
+          --cluster_domain=cluster.local \
+          --cni-conf-dir=/etc/kubernetes/cni/net.d \
+          --exit-on-lock-contention \
+          --hostname-override=${domain_name} \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
           --node-labels=node-role.kubernetes.io/master \
+          --pod-manifest-path=/etc/kubernetes/manifests \
           --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
-          --cluster_dns={{.k8s_dns_service_ip}} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=10
         [Install]
@@ -105,36 +108,20 @@ systemd:
         ExecStart=/opt/bootkube/bootkube-start
         ExecStartPost=/bin/touch /opt/bootkube/init_bootkube.done
 storage:
-  {{ if index . "pxe" }}
-  disks:
-    - device: /dev/sda
-      wipe_table: true
-      partitions:
-        - label: ROOT
-  filesystems:
-    - name: root
-      mount:
-        device: "/dev/sda1"
-        format: "ext4"
-        create:
-          force: true
-          options:
-            - "-LROOT"
-  {{end}}
   files:
     - path: /etc/kubernetes/kubelet.env
       filesystem: root
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/hostname
       filesystem: root
       mode: 0644
       contents:
         inline:
-          {{.domain_name}}
+          ${domain_name}
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
       contents:
@@ -156,23 +143,24 @@ storage:
           [ -d /opt/bootkube/assets/manifests-* ] && mv /opt/bootkube/assets/manifests-*/* /opt/bootkube/assets/manifests && rm -rf /opt/bootkube/assets/manifests-*
           [ -d /opt/bootkube/assets/experimental/manifests ] && mv /opt/bootkube/assets/experimental/manifests/* /opt/bootkube/assets/manifests && rm -r /opt/bootkube/assets/experimental/manifests
           [ -d /opt/bootkube/assets/experimental/bootstrap-manifests ] && mv /opt/bootkube/assets/experimental/bootstrap-manifests/* /opt/bootkube/assets/bootstrap-manifests && rm -r /opt/bootkube/assets/experimental/bootstrap-manifests
-          BOOTKUBE_ACI="${BOOTKUBE_ACI:-quay.io/coreos/bootkube}"
-          BOOTKUBE_VERSION="${BOOTKUBE_VERSION:-v0.6.1}"
-          BOOTKUBE_ASSETS="${BOOTKUBE_ASSETS:-/opt/bootkube/assets}"
+          BOOTKUBE_ACI="$${BOOTKUBE_ACI:-quay.io/coreos/bootkube}"
+          BOOTKUBE_VERSION="$${BOOTKUBE_VERSION:-v0.8.1}"
+          BOOTKUBE_ASSETS="$${BOOTKUBE_ASSETS:-/opt/bootkube/assets}"
           exec /usr/bin/rkt run \
             --trust-keys-from-https \
             --volume assets,kind=host,source=$BOOTKUBE_ASSETS \
             --mount volume=assets,target=/assets \
             --volume bootstrap,kind=host,source=/etc/kubernetes \
             --mount volume=bootstrap,target=/etc/kubernetes \
-            $RKT_OPTS \
-            ${BOOTKUBE_ACI}:${BOOTKUBE_VERSION} \
+            $$RKT_OPTS \
+            $${BOOTKUBE_ACI}:$${BOOTKUBE_VERSION} \
             --net=host \
             --dns=host \
             --exec=/bootkube -- start --asset-dir=/assets "$@"
+networkd:
+  ${networkd_content}
 passwd:
   users:
     - name: core
       ssh_authorized_keys:
-        - {{.ssh_authorized_key}}
-
+        - ${ssh_authorized_key}

bare-metal/container-linux/kubernetes/cl/worker.yaml.tmpl

@@ -31,82 +31,73 @@ systemd:
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --anonymous-auth=false \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --exit-on-lock-contention \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --allow-privileged \
-          --hostname-override={{.domain_name}} \
+          --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${k8s_dns_service_ip} \
+          --cluster_domain=cluster.local \
+          --cni-conf-dir=/etc/kubernetes/cni/net.d \
+          --exit-on-lock-contention \
+          --hostname-override=${domain_name} \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
           --node-labels=node-role.kubernetes.io/node \
-          --cluster_dns={{.k8s_dns_service_ip}} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=5
         [Install]
         WantedBy=multi-user.target
 
 storage:
-  {{ if index . "pxe" }}
-  disks:
-    - device: /dev/sda
-      wipe_table: true
-      partitions:
-        - label: ROOT
-  filesystems:
-    - name: root
-      mount:
-        device: "/dev/sda1"
-        format: "ext4"
-        create:
-          force: true
-          options:
-            - "-LROOT"
-  {{end}}
   files:
     - path: /etc/kubernetes/kubelet.env
       filesystem: root
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/hostname
       filesystem: root
       mode: 0644
       contents:
         inline:
-          {{.domain_name}}
+          ${domain_name}
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
+networkd:
+  ${networkd_content}
 passwd:
   users:
     - name: core
       ssh_authorized_keys:
-        - {{.ssh_authorized_key}}
+        - ${ssh_authorized_key}
 

bare-metal/container-linux/kubernetes/groups.tf

@@ -17,37 +17,21 @@ resource "matchbox_group" "container-linux-install" {
 resource "matchbox_group" "controller" {
   count   = "${length(var.controller_names)}"
   name    = "${format("%s-%s", var.cluster_name, element(var.controller_names, count.index))}"
-  profile = "${matchbox_profile.controller.name}"
+  profile = "${element(matchbox_profile.controllers.*.name, count.index)}"
 
   selector {
     mac = "${element(var.controller_macs, count.index)}"
     os  = "installed"
   }
-
-  metadata {
-    domain_name          = "${element(var.controller_domains, count.index)}"
-    etcd_name            = "${element(var.controller_names, count.index)}"
-    etcd_initial_cluster = "${join(",", formatlist("%s=https://%s:2380", var.controller_names, var.controller_domains))}"
-    etcd_on_host         = "${var.experimental_self_hosted_etcd ? "false" : "true"}"
-    k8s_dns_service_ip   = "${module.bootkube.kube_dns_service_ip}"
-    ssh_authorized_key   = "${var.ssh_authorized_key}"
-  }
 }
 
 resource "matchbox_group" "worker" {
   count   = "${length(var.worker_names)}"
   name    = "${format("%s-%s", var.cluster_name, element(var.worker_names, count.index))}"
-  profile = "${matchbox_profile.worker.name}"
+  profile = "${element(matchbox_profile.workers.*.name, count.index)}"
 
   selector {
     mac = "${element(var.worker_macs, count.index)}"
     os  = "installed"
   }
-
-  metadata {
-    domain_name        = "${element(var.worker_domains, count.index)}"
-    etcd_on_host       = "${var.experimental_self_hosted_etcd ? "false" : "true"}"
-    k8s_dns_service_ip = "${module.bootkube.kube_dns_service_ip}"
-    ssh_authorized_key = "${var.ssh_authorized_key}"
-  }
 }

bare-metal/container-linux/kubernetes/profiles.tf

@@ -12,6 +12,7 @@ resource "matchbox_profile" "container-linux-install" {
     "coreos.first_boot=yes",
     "console=tty0",
     "console=ttyS0",
+    "${var.kernel_args}",
   ]
 
   container_linux_config = "${data.template_file.container-linux-install-config.rendered}"
@@ -47,6 +48,7 @@ resource "matchbox_profile" "cached-container-linux-install" {
     "coreos.first_boot=yes",
     "console=tty0",
     "console=ttyS0",
+    "${var.kernel_args}",
   ]
 
   container_linux_config = "${data.template_file.cached-container-linux-install-config.rendered}"
@@ -67,14 +69,48 @@ data "template_file" "cached-container-linux-install-config" {
   }
 }
 
-// Kubernetes Controller profile
-resource "matchbox_profile" "controller" {
-  name                   = "controller"
-  container_linux_config = "${file("${path.module}/cl/controller.yaml.tmpl")}"
+// Kubernetes Controller profiles
+resource "matchbox_profile" "controllers" {
+  count                  = "${length(var.controller_names)}"
+  name                   = "${format("%s-controller-%s", var.cluster_name, element(var.controller_names, count.index))}"
+  container_linux_config = "${element(data.template_file.controller-configs.*.rendered, count.index)}"
 }
 
-// Kubernetes Worker profile
-resource "matchbox_profile" "worker" {
-  name                   = "worker"
-  container_linux_config = "${file("${path.module}/cl/worker.yaml.tmpl")}"
+data "template_file" "controller-configs" {
+  count = "${length(var.controller_names)}"
+
+  template = "${file("${path.module}/cl/controller.yaml.tmpl")}"
+
+  vars {
+    domain_name          = "${element(var.controller_domains, count.index)}"
+    etcd_name            = "${element(var.controller_names, count.index)}"
+    etcd_initial_cluster = "${join(",", formatlist("%s=https://%s:2380", var.controller_names, var.controller_domains))}"
+    k8s_dns_service_ip   = "${module.bootkube.kube_dns_service_ip}"
+    ssh_authorized_key   = "${var.ssh_authorized_key}"
+
+    # Terraform evaluates both sides regardless and element cannot be used on 0 length lists
+    networkd_content = "${length(var.controller_networkds) == 0 ? "" : element(concat(var.controller_networkds, list("")), count.index)}"
+  }
+}
+
+// Kubernetes Worker profiles
+resource "matchbox_profile" "workers" {
+  count                  = "${length(var.worker_names)}"
+  name                   = "${format("%s-worker-%s", var.cluster_name, element(var.worker_names, count.index))}"
+  container_linux_config = "${element(data.template_file.worker-configs.*.rendered, count.index)}"
+}
+
+data "template_file" "worker-configs" {
+  count = "${length(var.worker_names)}"
+
+  template = "${file("${path.module}/cl/worker.yaml.tmpl")}"
+
+  vars {
+    domain_name        = "${element(var.worker_domains, count.index)}"
+    k8s_dns_service_ip = "${module.bootkube.kube_dns_service_ip}"
+    ssh_authorized_key = "${var.ssh_authorized_key}"
+
+    # Terraform evaluates both sides regardless and element cannot be used on 0 length lists
+    networkd_content = "${length(var.worker_networkds) == 0 ? "" : element(concat(var.worker_networkds, list("")), count.index)}"
+  }
 }

bare-metal/container-linux/kubernetes/require.tf

@@ -0,0 +1,21 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.10.4"
+}
+
+provider "local" {
+  version = "~> 1.0"
+}
+
+provider "null" {
+  version = "~> 1.0"
+}
+
+provider "template" {
+  version = "~> 1.0"
+}
+
+provider "tls" {
+  version = "~> 1.0"
+}

bare-metal/container-linux/kubernetes/ssh.tf

@@ -1,10 +1,10 @@
-# Secure copy etcd TLS assets and kubeconfig to all nodes. Activates kubelet.service
-resource "null_resource" "copy-secrets" {
-  count = "${length(var.controller_names) + length(var.worker_names)}"
+# Secure copy etcd TLS assets and kubeconfig to controllers. Activates kubelet.service
+resource "null_resource" "copy-etcd-secrets" {
+  count = "${length(var.controller_names)}"
 
   connection {
     type    = "ssh"
-    host    = "${element(concat(var.controller_domains, var.worker_domains), count.index)}"
+    host    = "${element(var.controller_domains, count.index)}"
     user    = "core"
     timeout = "60m"
   }
@@ -66,20 +66,42 @@ resource "null_resource" "copy-secrets" {
   }
 }
 
+# Secure copy kubeconfig to all workers. Activates kubelet.service
+resource "null_resource" "copy-kubeconfig" {
+  count = "${length(var.worker_names)}"
+
+  connection {
+    type    = "ssh"
+    host    = "${element(var.worker_domains, count.index)}"
+    user    = "core"
+    timeout = "60m"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.kubeconfig}"
+    destination = "$HOME/kubeconfig"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "sudo mv /home/core/kubeconfig /etc/kubernetes/kubeconfig",
+    ]
+  }
+}
+
 # Secure copy bootkube assets to ONE controller and start bootkube to perform
 # one-time self-hosted cluster bootstrapping.
 resource "null_resource" "bootkube-start" {
   # Without depends_on, this remote-exec may start before the kubeconfig copy.
   # Terraform only does one task at a time, so it would try to bootstrap
-  # Kubernetes and Tectonic while no Kubelets are running. Ensure all nodes
-  # receive a kubeconfig before proceeding with bootkube.
-  depends_on = ["null_resource.copy-secrets"]
+  # while no Kubelets are running.
+  depends_on = ["null_resource.copy-etcd-secrets", "null_resource.copy-kubeconfig"]
 
   connection {
     type    = "ssh"
     host    = "${element(var.controller_domains, 0)}"
     user    = "core"
-    timeout = "60m"
+    timeout = "30m"
   }
 
   provisioner "file" {

bare-metal/container-linux/kubernetes/variables.tf

@@ -65,7 +65,7 @@ variable "asset_dir" {
 variable "networking" {
   description = "Choice of networking provider (flannel or calico)"
   type        = "string"
-  default     = "flannel"
+  default     = "calico"
 }
 
 variable "network_mtu" {
@@ -110,7 +110,22 @@ variable "container_linux_oem" {
   description = "Specify an OEM image id to use as base for the installation (e.g. ami, vmware_raw, xen) or leave blank for the default image"
 }
 
-variable "experimental_self_hosted_etcd" {
-  default     = "false"
-  description = "Create self-hosted etcd cluster as pods on Kubernetes, instead of on-hosts"
+variable "kernel_args" {
+  description = "Additional kernel arguments to provide at PXE boot."
+  type        = "list"
+  default     = []
+}
+
+# unofficial, undocumented, unsupported, temporary
+
+variable "controller_networkds" {
+  type        = "list"
+  description = "Controller Container Linux config networkd section"
+  default     = []
+}
+
+variable "worker_networkds" {
+  type        = "list"
+  description = "Worker Container Linux config networkd section"
+  default     = []
 }

bare-metal/container-linux/pxe-worker/cl/bootkube-worker.yaml.tmpl

@@ -31,38 +31,43 @@ systemd:
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --anonymous-auth=false \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --exit-on-lock-contention \
-          --pod-manifest-path=/etc/kubernetes/manifests \
           --allow-privileged \
-          --hostname-override={{.domain_name}} \
-          --node-labels=node-role.kubernetes.io/node \
+          --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
           --cluster_dns={{.k8s_dns_service_ip}} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --cluster_domain=cluster.local \
+          --cni-conf-dir=/etc/kubernetes/cni/net.d \
+          --exit-on-lock-contention \
+          --hostname-override={{.domain_name}} \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
+          --node-labels=node-role.kubernetes.io/node \
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=5
         [Install]
@@ -91,8 +96,8 @@ storage:
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/hostname
       filesystem: root
       mode: 0644

bare-metal/container-linux/pxe-worker/profiles.tf

@@ -8,12 +8,11 @@ resource "matchbox_profile" "bootkube-worker-pxe" {
   ]
 
   args = [
-    "root=/dev/sda1",
     "coreos.config.url=${var.matchbox_http_endpoint}/ignition?uuid=$${uuid}&mac=$${mac:hexhyp}",
     "coreos.first_boot=yes",
     "console=tty0",
     "console=ttyS0",
-    "kvm-intel.nested=1",
+    "${var.kernel_args}",
   ]
 
   container_linux_config = "${file("${path.module}/cl/bootkube-worker.yaml.tmpl")}"

bare-metal/container-linux/pxe-worker/variables.tf

@@ -53,3 +53,14 @@ variable "kube_dns_service_ip" {
   type        = "string"
   default     = "10.3.0.10"
 }
+
+# optional
+
+variable "kernel_args" {
+  description = "Additional kernel arguments to provide at PXE boot."
+  type        = "list"
+
+  default = [
+    "root=/dev/sda1",
+  ]
+}

digital-ocean/container-linux/kubernetes/LICENSE

@@ -0,0 +1,23 @@
+The MIT License (MIT)
+
+Copyright (c) 2017 Typhoon Authors
+Copyright (c) 2017 Dalton Hubble
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+

digital-ocean/container-linux/kubernetes/README.md

@@ -0,0 +1,22 @@
+# Typhoon
+
+Typhoon is a minimal and free Kubernetes distribution.
+
+* Minimal, stable base Kubernetes distribution
+* Declarative infrastructure and configuration
+* Free (freedom and cost) and privacy-respecting
+* Practical for labs, datacenters, and clouds
+
+Typhoon distributes upstream Kubernetes, architectural conventions, and cluster addons, much like a GNU/Linux distribution provides the Linux kernel and userspace components.
+
+## Features
+
+* Kubernetes v1.8.2 (upstream, via [kubernetes-incubator/bootkube](https://github.com/kubernetes-incubator/bootkube))
+* Single or multi-master, workloads isolated on workers, [Calico](https://www.projectcalico.org/) 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/)
+* Ready for Ingress, Dashboards, Metrics, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+
+## Docs
+
+Please see the [official docs](https://typhoon.psdn.io) and the Digital Ocean [tutorial](https://typhoon.psdn.io/digital-ocean/).
+

digital-ocean/container-linux/kubernetes/bootkube.tf

@@ -1,14 +1,13 @@
 # Self-hosted Kubernetes assets (kubeconfig, manifests)
 module "bootkube" {
-  source = "git::https://github.com/poseidon/bootkube-terraform.git?ref=5ffbfec46dc05721eaf9d15c3c9bbedefaead1bc"
+  source = "git::https://github.com/poseidon/terraform-render-bootkube.git?ref=v0.8.1"
 
-  cluster_name                  = "${var.cluster_name}"
-  api_servers                   = ["${format("%s.%s", var.cluster_name, var.dns_zone)}"]
-  etcd_servers                  = ["http://127.0.0.1:2379"]
-  asset_dir                     = "${var.asset_dir}"
-  networking                    = "${var.networking}"
-  network_mtu                   = 1440
-  pod_cidr                      = "${var.pod_cidr}"
-  service_cidr                  = "${var.service_cidr}"
-  experimental_self_hosted_etcd = "true"
+  cluster_name = "${var.cluster_name}"
+  api_servers  = ["${format("%s.%s", var.cluster_name, var.dns_zone)}"]
+  etcd_servers = "${digitalocean_record.etcds.*.fqdn}"
+  asset_dir    = "${var.asset_dir}"
+  networking   = "${var.networking}"
+  network_mtu  = 1440
+  pod_cidr     = "${var.pod_cidr}"
+  service_cidr = "${var.service_cidr}"
 }

digital-ocean/container-linux/kubernetes/cl/controller.yaml.tmpl

@@ -1,10 +1,42 @@
 ---
 systemd:
   units:
+    - name: etcd-member.service
+      enable: true
+      dropins:
+        - name: 40-etcd-cluster.conf
+          contents: |
+            [Service]
+            Environment="ETCD_IMAGE_TAG=v3.2.0"
+            Environment="ETCD_NAME=${etcd_name}"
+            Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379"
+            Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
+            Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
+            Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
+            Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
+            Environment="ETCD_STRICT_RECONFIG_CHECK=true"
+            Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
+            Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
+            Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
+            Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
+            Environment="ETCD_CLIENT_CERT_AUTH=true"
+            Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
+            Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
+            Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
+            Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
     - name: docker.service
       enable: true
     - name: locksmithd.service
       mask: true
+    - name: kubelet.path
+      enable: true
+      contents: |
+        [Unit]
+        Description=Watch for kubeconfig
+        [Path]
+        PathExists=/etc/kubernetes/kubeconfig
+        [Install]
+        WantedBy=multi-user.target
     - name: wait-for-dns.service
       enable: true
       contents: |
@@ -19,46 +51,50 @@ systemd:
         [Install]
         RequiredBy=kubelet.service
     - name: kubelet.service
-      enable: true
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
         Requires=coreos-metadata.service
         After=coreos-metadata.service
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
         EnvironmentFile=/run/metadata/coreos
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
+          --allow-privileged \
           --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${k8s_dns_service_ip} \
+          --cluster_domain=cluster.local \
           --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
           --exit-on-lock-contention \
           --hostname-override=$${COREOS_DIGITALOCEAN_IPV4_PRIVATE_0} \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --allow-privileged \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
           --node-labels=node-role.kubernetes.io/master \
+          --pod-manifest-path=/etc/kubernetes/manifests \
           --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
-          --cluster_dns=${k8s_dns_service_ip} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=10
         [Install]
@@ -78,34 +114,13 @@ systemd:
         WantedBy=multi-user.target
 storage:
   files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          apiVersion: v1
-          kind: Config
-          clusters:
-          - name: local
-            cluster:
-              server: ${kubeconfig_server}
-              certificate-authority-data: ${kubeconfig_ca_cert}
-          users:
-          - name: kubelet
-            user:
-              client-certificate-data: ${kubeconfig_kubelet_cert}
-              client-key-data: ${kubeconfig_kubelet_key}
-          contexts:
-          - context:
-              cluster: local
-              user: kubelet
     - path: /etc/kubernetes/kubelet.env
       filesystem: root
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
       contents:
@@ -128,7 +143,7 @@ storage:
           [ -d /opt/bootkube/assets/experimental/manifests ] && mv /opt/bootkube/assets/experimental/manifests/* /opt/bootkube/assets/manifests && rm -r /opt/bootkube/assets/experimental/manifests
           [ -d /opt/bootkube/assets/experimental/bootstrap-manifests ] && mv /opt/bootkube/assets/experimental/bootstrap-manifests/* /opt/bootkube/assets/bootstrap-manifests && rm -r /opt/bootkube/assets/experimental/bootstrap-manifests
           BOOTKUBE_ACI="$${BOOTKUBE_ACI:-quay.io/coreos/bootkube}"
-          BOOTKUBE_VERSION="$${BOOTKUBE_VERSION:-v0.6.1}"
+          BOOTKUBE_VERSION="$${BOOTKUBE_VERSION:-v0.8.1}"
           BOOTKUBE_ASSETS="$${BOOTKUBE_ASSETS:-/opt/bootkube/assets}"
           exec /usr/bin/rkt run \
             --trust-keys-from-https \

digital-ocean/container-linux/kubernetes/cl/worker.yaml.tmpl

@@ -5,6 +5,15 @@ systemd:
       enable: true
     - name: locksmithd.service
       mask: true
+    - name: kubelet.path
+      enable: true
+      contents: |
+        [Unit]
+        Description=Watch for kubeconfig
+        [Path]
+        PathExists=/etc/kubernetes/kubeconfig
+        [Install]
+        WantedBy=multi-user.target
     - name: wait-for-dns.service
       enable: true
       contents: |
@@ -19,45 +28,49 @@ systemd:
         [Install]
         RequiredBy=kubelet.service
     - name: kubelet.service
-      enable: true
       contents: |
         [Unit]
         Description=Kubelet via Hyperkube ACI
         Requires=coreos-metadata.service
         After=coreos-metadata.service
+        Wants=rpc-statd.service
         [Service]
         EnvironmentFile=/etc/kubernetes/kubelet.env
         EnvironmentFile=/run/metadata/coreos
-        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/run/kubelet-pod.uuid \
+        Environment="RKT_RUN_ARGS=--uuid-file-save=/var/cache/kubelet-pod.uuid \
           --volume=resolv,kind=host,source=/etc/resolv.conf \
           --mount volume=resolv,target=/etc/resolv.conf \
           --volume var-lib-cni,kind=host,source=/var/lib/cni \
           --mount volume=var-lib-cni,target=/var/lib/cni \
+          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
+          --mount volume=opt-cni-bin,target=/opt/cni/bin \
           --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log"
+          --mount volume=var-log,target=/var/log \
+          --insecure-options=image"
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/checkpoint-secrets
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/inactive-manifests
         ExecStartPre=/bin/mkdir -p /var/lib/cni
         ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet-pod.uuid
+        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
         ExecStart=/usr/lib/coreos/kubelet-wrapper \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --require-kubeconfig \
-          --client-ca-file=/etc/kubernetes/ca.crt \
+          --allow-privileged \
           --anonymous-auth=false \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${k8s_dns_service_ip} \
+          --cluster_domain=cluster.local \
           --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --network-plugin=cni \
-          --lock-file=/var/run/lock/kubelet.lock \
           --exit-on-lock-contention \
           --hostname-override=$${COREOS_DIGITALOCEAN_IPV4_PRIVATE_0} \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --allow-privileged \
+          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --lock-file=/var/run/lock/kubelet.lock \
+          --network-plugin=cni \
           --node-labels=node-role.kubernetes.io/node \
-          --cluster_dns=${k8s_dns_service_ip} \
-          --cluster_domain=cluster.local
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet-pod.uuid
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --require-kubeconfig
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
         RestartSec=5
         [Install]
@@ -76,34 +89,13 @@ systemd:
         WantedBy=multi-user.target
 storage:
   files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          apiVersion: v1
-          kind: Config
-          clusters:
-          - name: local
-            cluster:
-              server: ${kubeconfig_server}
-              certificate-authority-data: ${kubeconfig_ca_cert}
-          users:
-          - name: kubelet
-            user:
-              client-certificate-data: ${kubeconfig_kubelet_cert}
-              client-key-data: ${kubeconfig_kubelet_key}
-          contexts:
-          - context:
-              cluster: local
-              user: kubelet
     - path: /etc/kubernetes/kubelet.env
       filesystem: root
       mode: 0644
       contents:
         inline: |
-          KUBELET_IMAGE_URL=quay.io/coreos/hyperkube
-          KUBELET_IMAGE_TAG=v1.7.3_coreos.0
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.8.2
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
       contents:
@@ -120,7 +112,8 @@ storage:
             --trust-keys-from-https \
             --volume config,kind=host,source=/etc/kubernetes \
             --mount volume=config,target=/etc/kubernetes \
-            quay.io/coreos/hyperkube:v1.7.3_coreos.0 \
+            --insecure-options=image \
+            docker://gcr.io/google_containers/hyperkube:v1.8.2 \
             --net=host \
             --dns=host \
             --exec=/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)

digital-ocean/container-linux/kubernetes/controllers.tf

@@ -14,6 +14,21 @@ resource "digitalocean_record" "controllers" {
   value = "${element(digitalocean_droplet.controllers.*.ipv4_address, count.index)}"
 }
 
+resource "digitalocean_record" "etcds" {
+  count = "${var.controller_count}"
+
+  # DNS zone where record should be created
+  domain = "${var.dns_zone}"
+
+  # DNS record (will be prepended to domain)
+  name = "${var.cluster_name}-etcd${count.index}"
+  type = "A"
+  ttl  = 300
+
+  # IPv4 addresses of controllers
+  value = "${element(digitalocean_droplet.controllers.*.ipv4_address_private, count.index)}"
+}
+
 # Controller droplet instances
 resource "digitalocean_droplet" "controllers" {
   count = "${var.controller_count}"
@@ -28,7 +43,7 @@ resource "digitalocean_droplet" "controllers" {
   ipv6               = true
   private_networking = true
 
-  user_data = "${data.ct_config.controller_ign.rendered}"
+  user_data = "${element(data.ct_config.controller_ign.*.rendered, count.index)}"
   ssh_keys  = "${var.ssh_fingerprints}"
 
   tags = [
@@ -43,19 +58,34 @@ resource "digitalocean_tag" "controllers" {
 
 # Controller Container Linux Config
 data "template_file" "controller_config" {
+  count = "${var.controller_count}"
+
   template = "${file("${path.module}/cl/controller.yaml.tmpl")}"
 
   vars = {
-    k8s_dns_service_ip      = "${cidrhost(var.service_cidr, 10)}"
-    k8s_etcd_service_ip     = "${cidrhost(var.service_cidr, 15)}"
-    kubeconfig_ca_cert      = "${module.bootkube.ca_cert}"
-    kubeconfig_kubelet_cert = "${module.bootkube.kubelet_cert}"
-    kubeconfig_kubelet_key  = "${module.bootkube.kubelet_key}"
-    kubeconfig_server       = "${module.bootkube.server}"
+    # 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 = "${join(",", formatlist("%s=https://%s:2380", null_resource.repeat.*.triggers.name, null_resource.repeat.*.triggers.domain))}"
+    k8s_dns_service_ip   = "${cidrhost(var.service_cidr, 10)}"
+  }
+}
+
+# Horrible hack to generate a Terraform list of a desired length without dependencies.
+# Ideal ${repeat("etcd", 3) -> ["etcd", "etcd", "etcd"]}
+resource null_resource "repeat" {
+  count = "${var.controller_count}"
+
+  triggers {
+    name   = "etcd${count.index}"
+    domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
   }
 }
 
 data "ct_config" "controller_ign" {
-  content      = "${data.template_file.controller_config.rendered}"
+  count        = "${var.controller_count}"
+  content      = "${element(data.template_file.controller_config.*.rendered, count.index)}"
   pretty_print = false
 }

digital-ocean/container-linux/kubernetes/require.tf

@@ -0,0 +1,25 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.10.4"
+}
+
+provider "digitalocean" {
+  version = "0.1.2"
+}
+
+provider "local" {
+  version = "~> 1.0"
+}
+
+provider "null" {
+  version = "~> 1.0"
+}
+
+provider "template" {
+  version = "~> 1.0"
+}
+
+provider "tls" {
+  version = "~> 1.0"
+}

digital-ocean/container-linux/kubernetes/ssh.tf

@@ -1,7 +1,75 @@
+# Secure copy kubeconfig to all nodes. Activates kubelet.service
+resource "null_resource" "copy-secrets" {
+  count = "${var.controller_count + var.worker_count}"
+
+  connection {
+    type    = "ssh"
+    host    = "${element(concat(digitalocean_droplet.controllers.*.ipv4_address, digitalocean_droplet.workers.*.ipv4_address), count.index)}"
+    user    = "core"
+    timeout = "15m"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.kubeconfig}"
+    destination = "$HOME/kubeconfig"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_ca_cert}"
+    destination = "$HOME/etcd-client-ca.crt"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_client_cert}"
+    destination = "$HOME/etcd-client.crt"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_client_key}"
+    destination = "$HOME/etcd-client.key"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_server_cert}"
+    destination = "$HOME/etcd-server.crt"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_server_key}"
+    destination = "$HOME/etcd-server.key"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_peer_cert}"
+    destination = "$HOME/etcd-peer.crt"
+  }
+
+  provisioner "file" {
+    content     = "${module.bootkube.etcd_peer_key}"
+    destination = "$HOME/etcd-peer.key"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "sudo mkdir -p /etc/ssl/etcd/etcd",
+      "sudo mv etcd-client* /etc/ssl/etcd/",
+      "sudo cp /etc/ssl/etcd/etcd-client-ca.crt /etc/ssl/etcd/etcd/server-ca.crt",
+      "sudo mv etcd-server.crt /etc/ssl/etcd/etcd/server.crt",
+      "sudo mv etcd-server.key /etc/ssl/etcd/etcd/server.key",
+      "sudo cp /etc/ssl/etcd/etcd-client-ca.crt /etc/ssl/etcd/etcd/peer-ca.crt",
+      "sudo mv etcd-peer.crt /etc/ssl/etcd/etcd/peer.crt",
+      "sudo mv etcd-peer.key /etc/ssl/etcd/etcd/peer.key",
+      "sudo chown -R etcd:etcd /etc/ssl/etcd",
+      "sudo chmod -R 500 /etc/ssl/etcd",
+      "sudo mv /home/core/kubeconfig /etc/kubernetes/kubeconfig",
+    ]
+  }
+}
+
 # Secure copy bootkube assets to ONE controller and start bootkube to perform
 # one-time self-hosted cluster bootstrapping.
 resource "null_resource" "bootkube-start" {
-  depends_on = ["module.bootkube", "digitalocean_droplet.controllers"]
+  depends_on = ["module.bootkube", "null_resource.copy-secrets", "digitalocean_droplet.controllers"]
 
   connection {
     type    = "ssh"

digital-ocean/container-linux/kubernetes/workers.tf

@@ -43,12 +43,8 @@ data "template_file" "worker_config" {
   template = "${file("${path.module}/cl/worker.yaml.tmpl")}"
 
   vars = {
-    k8s_dns_service_ip      = "${cidrhost(var.service_cidr, 10)}"
-    k8s_etcd_service_ip     = "${cidrhost(var.service_cidr, 15)}"
-    kubeconfig_ca_cert      = "${module.bootkube.ca_cert}"
-    kubeconfig_kubelet_cert = "${module.bootkube.kubelet_cert}"
-    kubeconfig_kubelet_key  = "${module.bootkube.kubelet_key}"
-    kubeconfig_server       = "${module.bootkube.server}"
+    k8s_dns_service_ip  = "${cidrhost(var.service_cidr, 10)}"
+    k8s_etcd_service_ip = "${cidrhost(var.service_cidr, 15)}"
   }
 }
 

docs/addons/calico.md

@@ -1,4 +0,0 @@
-# Calico Policy
-
-!!! bug "In Progress"
-    These docs haven't been moved over yet.

docs/addons/ingress.md

@@ -1,4 +1,121 @@
-# Ingress Controller
+# Nginx Ingress Controller
 
-!!! bug "In Progress"
-    These docs haven't been moved over yet.
+Nginx Ingress controller pods accept and demultiplex HTTP, HTTPS, TCP, or UDP traffic to backend services. Ingress controllers watch the Kubernetes API for Ingress resources and update their configuration accordingly. Ingress resources for HTTP(S) applications support virtual hosts (FQDNs), path rules, TLS termination, and SNI.
+
+## AWS
+
+On AWS, an elastic load balancer distributes traffic across worker nodes (i.e. an auto-scaling group) running an Ingress controller deployment on host ports 80 and 443. Firewall rules allow traffic to ports 80 and 443. Health check rules ensure only workers with a health Ingress controller receive traffic.
+
+Create the Ingress controller deployment, service, RBAC roles, RBAC bindings, default backend, and namespace.
+
+```
+kubectl apply -R -f addons/nginx-ingress/aws
+```
+
+For each application, add a DNS CNAME resolving to the ELB's DNS record.
+
+```
+app1.example.com -> tempest-ingress.123456.us-west2.elb.amazonaws.com
+aap2.example.com -> tempest-ingress.123456.us-west2.elb.amazonaws.com
+app3.example.com -> tempest-ingress.123456.us-west2.elb.amazonaws.com
+```
+
+Find the ELB's DNS name through the console or use the Typhoon module's output `ingress_dns_name`. For example, you might use Terraform to manage a Google Cloud DNS record:
+
+```tf
+resource "google_dns_record_set" "some-application" {
+  # DNS zone name
+  managed_zone = "example-zone"
+
+  # DNS record
+  name    = "app.example.com."
+  type    = "CNAME"
+  ttl     = 300
+  rrdatas = ["${module.aws-tempest.ingress_dns_name}."]
+}
+```
+
+## Digital Ocean
+
+On Digital Ocean, a DNS A record (e.g. `nemo-workers.example.com`) resolves to each worker[^1] running an Ingress controller DaemonSet on host ports 80 and 443. Firewall rules allow IPv4 and IPv6 traffic to ports 80 and 443.
+
+Create the Ingress controller daemonset, service, RBAC roles, RBAC bindings, default backend, and namespace.
+
+```
+kubectl apply -R -f addons/nginx-ingress/digital-ocean
+```
+
+For each application, add a CNAME record resolving to the worker(s) DNS record. Use the Typhoon module's output `workers_dns` to find the worker DNS value. For example, you might use Terraform to manage a Google Cloud DNS record:
+
+```tf
+resource "google_dns_record_set" "some-application" {
+  # DNS zone name
+  managed_zone = "example-zone"
+
+  # DNS record
+  name    = "app.example.com."
+  type    = "CNAME"
+  ttl     = 300
+  rrdatas = ["${module.digital-ocean-nemo.workers_dns}."]
+}
+```
+
+[^1]: Digital Ocean does offers load balancers. We've opted not to use them to keep the Digital Ocean setup simple and cheap for developers.
+
+## Google Cloud
+
+On Google Cloud, a network load balancer distributes traffic across worker nodes (i.e. a target pool of backends) running an Ingress controller deployment on host ports 80 and 443. Firewall rules allow traffic to ports 80 and 443. Health check rules ensure the target pool only includes worker nodes with a healthy Nginx Ingress controller.
+
+Create the Ingress controller deployment, service, RBAC roles, RBAC bindings, default backend, and namespace.
+
+```
+kubectl apply -R -f addons/nginx-ingress/google-cloud
+```
+
+For each application, add a DNS record resolving to the network load balancer's IPv4 address.
+
+```
+app1.example.com -> 11.22.33.44
+aap2.example.com -> 11.22.33.44
+app3.example.com -> 11.22.33.44
+```
+
+Find the IPv4 address with `gcloud compute addresses list` or use the Typhoon module's output `ingress_static_ip`. For example, you might use Terraform to manage a Google Cloud DNS record:
+
+```tf
+resource "google_dns_record_set" "some-application" {
+  # DNS zone name
+  managed_zone = "example-zone"
+
+  # DNS record
+  name    = "app.example.com."
+  type    = "A"
+  ttl     = 300
+  rrdatas = ["${module.google-cloud-yavin.ingress_static_ip}"]
+}
+```
+
+## Bare-Metal
+
+On bare-metal, routing traffic to Ingress controller pods can be done in number of ways.
+
+### Equal-Cost Multi-Path
+
+Deploy the Nginx Ingress Controller as a deployment. Deploy the service with a fixed ClusterIP (e.g. 10.3.0.12) in the Kubernetes service IPv4 CIDR range. There is no need for a NodePort or for pods to bind host ports. Any node can proxy packets destined for the service's ClusterIP to a node which has a pod endpoint.
+
+Configure the network router or load balancer with a static route for the Kubernetes service range and set the next hop to a node. Repeat for each node and set the metric (i.e. cost) of each. Finally, DNAT traffic destined for the WAN on ports 80 or 443 to the service's fixed ClusterIP.
+
+Add a DNS record resolving to the WAN for each application.
+
+```tf
+resource "google_dns_record_set" "some-application" {
+  # Managed DNS Zone name
+  managed_zone = "dghubble-io"
+
+  # Name of the DNS record
+  name    = "app.example.com."
+  type    = "A"
+  ttl     = 300
+  rrdatas = ["SOME-WAN-IP"]
+}
+```

docs/addons/overview.md

@@ -2,11 +2,10 @@
 
 Every Typhoon cluster is verified to work well with several post-install addons.
 
+* [CLUO](cluo.md) (Container Linux only)
 * Nginx [Ingress Controller](ingress.md)
-* Calico [Network Policy](calico.md)
 * [Heapster](heapster.md)
 * Kubernetes [Dashboard](dashboard.md)
-* [CLUO](cluo.md) (Container Linux only)
-* Prometheus
+* [Prometheus](prometheus.md)
 * Grafana
 

docs/addons/prometheus.md

@@ -0,0 +1,50 @@
+# Prometheus
+
+Prometheus collects metrics (e.g. `node_memory_usage_bytes`) from *targets* by scraping their HTTP metrics endpoints. Targets are organized into *jobs*, defined in the Prometheus config. Targets may expose counter, gauge, histogram, or summary metrics.
+
+Here's a simple config from the Prometheus [tutorial](https://prometheus.io/docs/introduction/getting_started/).
+
+```
+global:
+  scrape_interval: 15s
+scrape_configs:
+  - job_name: 'prometheus'
+    scrape_interval: 5s
+    static_configs:
+      - targets: ['localhost:9090']
+```
+
+On Kubernetes clusters, Prometheus is run as a Deployment, configured with a ConfigMap, and accessed via a Service or Ingress.
+
+```
+kubectl apply -f addons/prometheus -R
+```
+
+The ConfigMap configures Prometheus to target apiserver endpoints, node metrics, cAdvisor metrics, and exporters. By default, data is kept in an `emptyDir` so it is persisted until the pod is rescheduled.
+
+### Exporters
+
+Exporters expose metrics for 3rd-party systems that don't natively expose Prometheus metrics.
+
+* [node_exporter](https://github.com/prometheus/node_exporter) - DaemonSet that exposes a machine's hardware and OS metrics
+* [kube-state-metrics](https://github.com/kubernetes/kube-state-metrics) - Deployment that exposes Kubernetes object metrics
+* [blackbox_exporter](https://github.com/prometheus/blackbox_exporter) - Scrapes HTTP, HTTPS, DNS, TCP, or ICMP endpoints and exposes availability as metrics
+
+### Queries and Graphs
+
+Prometheus provides a simplistic UI for querying and graphing metrics. Use `kubectl` to authenticate to the apiserver and create a local port-forward to the Prometheus pod.
+
+```
+kubectl get pods -n monitoring
+kubectl port-forward prometheus-POD-ID 9090 -n monitoring
+```
+
+Visit [127.0.0.1:9090](http://127.0.0.1:9090) to query [expressions](http://127.0.0.1:9090/graph), view [targets](http://127.0.0.1:9090/targets), or check [alerts](http://127.0.0.1:9090/alerts).
+
+![Prometheus Graph](/img/prometheus-graph.png)
+<br/>
+![Prometheus Targets](/img/prometheus-targets.png)
+
+### Visualization
+
+Grafana can be used to build dashboards and rich visualizations that use Prometheus as the datasource. Favor Grafana for these use cases and use the Prometheus for debugging or quickly checking available metrics.

docs/aws.md

@@ -0,0 +1,248 @@
+# AWS
+
+In this tutorial, we'll create a Kubernetes v1.8.2 cluster on AWS.
+
+We'll declare a Kubernetes cluster in Terraform using the Typhoon Terraform module. On apply, a VPC, gateway, subnets, auto-scaling groups of controllers and workers, network load balancers for controllers and workers, and security groups will be created.
+
+Controllers and workers are provisioned to run a `kubelet`. A one-time [bootkube](https://github.com/kubernetes-incubator/bootkube) bootstrap schedules `etcd`, `apiserver`, `scheduler`, `controller-manager`, and `kube-dns` on controllers and runs `kube-proxy` and `flannel` or `calico` on each node. A generated `kubeconfig` provides `kubectl` access to the cluster.
+
+!!! warning "Alpha"
+    Typhoon Kubernetes clusters on AWS are marked as "alpha".
+
+!!! warning "Disabled"
+    Clusters do not use EC2 instances with elevated IAM roles. Kubernetes AWS integrations are not enabled.
+
+## Requirements
+
+* AWS Account and IAM credentials
+* AWS Route53 DNS Zone (registered Domain Name or delegated subdomain)
+* Terraform v0.10.4+ and [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) installed locally
+
+## Terraform Setup
+
+Install [Terraform](https://www.terraform.io/downloads.html) v0.10.1 on your system.
+
+```sh
+$ terraform version
+Terraform v0.10.7
+```
+
+Add the [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) plugin binary for your system.
+
+```sh
+wget https://github.com/coreos/terraform-provider-ct/releases/download/v0.2.0/terraform-provider-ct-v0.2.0-linux-amd64.tar.gz
+tar xzf terraform-provider-ct-v0.2.0-linux-amd64.tar.gz
+sudo mv terraform-provider-ct-v0.2.0-linux-amd64/terraform-provider-ct /usr/local/bin/
+```
+
+Add the plugin to your `~/.terraformrc`.
+
+```
+providers {
+  ct = "/usr/local/bin/terraform-provider-ct"
+}
+```
+
+Read [concepts](concepts.md) to learn about Terraform, modules, and organizing resources. Change to your infrastructure repository (e.g. `infra`).
+
+```
+cd infra/clusters
+```
+
+## Provider
+
+Login to your AWS IAM dashboard and find your IAM user. Select "Security Credentials" and create an access key. Save the id and secret to a file that can be referenced in configs.
+
+```
+[default]
+aws_access_key_id = xxx
+aws_secret_access_key = yyy
+```
+
+Configure the AWS provider to use your access key credentials in a `providers.tf` file.
+
+```tf
+provider "aws" {
+  region                  = "eu-central-1"
+  shared_credentials_file = "/home/user/.config/aws/credentials"
+}
+```
+
+Additional configuration options are described in the `aws` provider [docs](https://www.terraform.io/docs/providers/aws/).
+
+!!! tip
+    Regions are listed in [docs](http://docs.aws.amazon.com/general/latest/gr/rande.html#ec2_region) or with `aws ec2 describe-regions`.
+
+## Cluster
+
+Define a Kubernetes cluster using the module `aws/container-linux/kubernetes`.
+
+```tf
+module "aws-tempest" {
+  source = "git::https://github.com/poseidon/typhoon//aws/container-linux/kubernetes"
+
+  cluster_name = "tempest"
+
+  # AWS
+  dns_zone           = "aws.example.com"
+  dns_zone_id        = "Z3PAABBCFAKEC0"
+  controller_count   = 1
+  controller_type    = "t2.small"
+  worker_count       = 2
+  worker_type        = "t2.small"
+  ssh_authorized_key = "ssh-rsa AAAAB3Nz..."
+
+  # bootkube
+  asset_dir  = "/home/user/.secrets/clusters/tempest"
+}
+```
+
+Reference the [variables docs](#variables) or the [variables.tf](https://github.com/poseidon/typhoon/blob/master/aws/container-linux/kubernetes/variables.tf) source.
+
+## ssh-agent
+
+Initial bootstrapping requires `bootkube.service` be started on one controller node. Terraform uses `ssh-agent` to automate this step. Add your SSH private key to `ssh-agent`.
+
+```sh
+ssh-add ~/.ssh/id_rsa
+ssh-add -L
+```
+
+!!! warning
+    `terrafrom apply` will hang connecting to a controller if `ssh-agent` does not contain the SSH key.
+
+## Apply
+
+Initialize the config directory if this is the first use with Terraform.
+
+```sh
+terraform init
+```
+
+Get or update Terraform modules.
+
+```sh
+$ terraform get            # downloads missing modules
+$ terraform get --update   # updates all modules
+Get: git::https://github.com/poseidon/typhoon (update)
+Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.8.1 (update)
+```
+
+Plan the resources to be created.
+
+```sh
+$ terraform plan
+Plan: 98 to add, 0 to change, 0 to destroy.
+```
+
+Apply the changes to create the cluster.
+
+```sh
+$ terraform apply
+...
+module.aws-tempest.null_resource.bootkube-start: Still creating... (10m50s elapsed)
+module.aws-tempest.null_resource.bootkube-start: Still creating... (11m0s elapsed)
+module.aws-tempest.null_resource.bootkube-start: Creation complete after 11m8s (ID: 3961816482286168143)
+
+Apply complete! Resources: 98 added, 0 changed, 0 destroyed.
+```
+
+In 10-20 minutes, the Kubernetes cluster will be ready.
+
+!!! bug ""
+    Typhoon clusters on AWS take much longer to create than clusters on other platforms. This is related to DNS resolution time to the ASG, which will be resolved in a future version that uses static controllers.
+
+## Verify
+
+[Install kubectl](https://coreos.com/kubernetes/docs/latest/configure-kubectl.html) on your system. Use the generated `kubeconfig` credentials to access the Kubernetes cluster and list nodes.
+
+```
+$ KUBECONFIG=/home/user/.secrets/clusters/tempest/auth/kubeconfig
+$ kubectl get nodes
+NAME             STATUS    AGE       VERSION        
+ip-10-0-12-221   Ready     34m       v1.8.2
+ip-10-0-19-112   Ready     34m       v1.8.2
+ip-10-0-4-22     Ready     34m       v1.8.2
+```
+
+List the pods.
+
+```
+$ kubectl get pods --all-namespaces
+NAMESPACE     NAME                                      READY  STATUS    RESTARTS  AGE              
+kube-system   calico-node-1m5bf                         2/2    Running   0         34m              
+kube-system   calico-node-7jmr1                         2/2    Running   0         34m              
+kube-system   calico-node-bknc8                         2/2    Running   0         34m              
+kube-system   etcd-operator-2287495111-br512            1/1    Running   1         34m              
+kube-system   kube-apiserver-4mjbk                      1/1    Running   0         34m              
+kube-system   kube-controller-manager-3597210155-j2jbt  1/1    Running   1         34m              
+kube-system   kube-controller-manager-3597210155-j7g7x  1/1    Running   0         34m              
+kube-system   kube-dns-1187388186-wx1lg                 3/3    Running   0         34m              
+kube-system   kube-etcd-0000                            1/1    Running   0         32m              
+kube-system   kube-etcd-network-checkpointer-dt5pt      1/1    Running   0         34m              
+kube-system   kube-proxy-14wxv                          1/1    Running   0         34m              
+kube-system   kube-proxy-9vxh2                          1/1    Running   0         34m              
+kube-system   kube-proxy-sbbsh                          1/1    Running   0         34m              
+kube-system   kube-scheduler-3359497473-5plhf           1/1    Running   0         34m              
+kube-system   kube-scheduler-3359497473-r7zg7           1/1    Running   1         34m              
+kube-system   pod-checkpointer-4kxtl                    1/1    Running   0         34m              
+kube-system   pod-checkpointer-4kxtl-ip-10-0-12-221     1/1    Running   0         33m
+```
+
+## Going Further
+
+Learn about [version pinning](concepts.md#versioning), maintenance, and [addons](addons/overview.md).
+
+!!! note
+    On Container Linux clusters, install the `container-linux-update-operator` addon to coordinate reboots and drains when nodes auto-update. Otherwise, updates may not be applied until the next reboot.
+
+## Variables
+
+### Required
+
+| Name | Description | Example |
+|:-----|:------------|:--------|
+| cluster_name | Unique cluster name (prepended to dns_zone) | "tempest" |
+| dns_zone | AWS Route53 DNS zone | "aws.example.com" |
+| dns_zone_id | AWS Route53 DNS zone id | "Z3PAABBCFAKEC0" |
+| ssh_authorized_key | SSH public key for ~/.ssh_authorized_keys | "ssh-rsa AAAAB3NZ..." |
+| os_channel | Container Linux AMI channel | stable, beta, alpha |
+| asset_dir | Path to a directory where generated assets should be placed (contains secrets) | "/home/user/.secrets/clusters/tempest" |
+
+#### DNS Zone
+
+Clusters create a DNS A record `${cluster_name}.${dns_zone}` to resolve a network load balancer backed by controller instances. This FQDN is used by workers and `kubectl` to access the apiserver. In this example, the cluster's apiserver would be accessible at `tempest.aws.example.com`.
+
+You'll need a registered domain name or subdomain registered in a AWS Route53 DNS zone. You can set this up once and create many clusters with unqiue names.
+
+```tf
+resource "aws_route53_zone" "zone-for-clusters" {
+  name = "aws.example.com."
+}
+```
+
+Reference the DNS zone id with `"${aws_route53_zone.zone-for-clusters.zone_id}"`.
+
+!!! tip ""
+    If you have an existing domain name with a zone file elsewhere, just carve out a subdomain that can be managed on Route53 (e.g. aws.mydomain.com) and [update nameservers](http://docs.aws.amazon.com/Route53/latest/DeveloperGuide/SOA-NSrecords.html).
+
+### Optional
+
+| Name | Description | Default | Example |
+|:-----|:------------|:--------|:--------|
+| controller_count | Number of controllers (i.e. masters) | 1 | 1 |
+| controller_type | Controller EC2 instance type | "t2.small" | "t2.medium" |
+| worker_count | Number of workers | 1 | 3 |
+| worker_type | Worker EC2 instance type | "t2.small" | "t2.medium" |
+| disk_size | Size of the EBS volume in GB | "40" | "100" |
+| networking | Choice of networking provider | "calico" | "calico" or "flannel" |
+| network_mtu | CNI interface MTU (calico only) | 1480 | 8981 |
+| host_cidr | CIDR range to assign to EC2 instances | "10.0.0.0/16" | "10.1.0.0/16" |
+| pod_cidr | CIDR range to assign to Kubernetes pods | "10.2.0.0/16" | "10.22.0.0/16" |
+| service_cidr | CIDR range to assgin to Kubernetes services | "10.3.0.0/16" | "10.3.0.0/24" |
+
+Check the list of valid [instance types](https://aws.amazon.com/ec2/instance-types/).
+
+!!! tip "MTU"
+    If your EC2 instance type supports [Jumbo frames](http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/network_mtu.html#jumbo_frame_instances) (most do), we recommend you change the `network_mtu` to 8991! You will get better pod-to-pod bandwidth.
+

docs/bare-metal.md

@@ -1,10 +1,10 @@
 # Bare-Metal
 
-In this tutorial, we'll network boot and provison a Kubernetes v1.7.3 cluster on bare-metal.
+In this tutorial, we'll network boot and provison a Kubernetes v1.8.2 cluster on bare-metal.
 
 First, we'll deploy a [Matchbox](https://github.com/coreos/matchbox) service and setup a network boot environment. Then, we'll declare a Kubernetes cluster in Terraform using the Typhoon Terraform module and power on machines. On PXE boot, machines will install Container Linux to disk, reboot into the disk install, and provision themselves as Kubernetes controllers or workers.
 
-Controllers are provisioned as etcd peers and run `etcd-member` (etcd3) and `kubelet`. Workers are provisioned to run a `kubelet`. A one-time [bootkube](https://github.com/kubernetes-incubator/bootkube) bootstrap schedules an `apiserver`, `scheduler`, `controller-manager`, and `kube-dns` on controllers and runs `kube-proxy` and `flannel` on each node. A generated `kubeconfig` provides `kubectl` access to the cluster.
+Controllers are provisioned as etcd peers and run `etcd-member` (etcd3) and `kubelet`. Workers are provisioned to run a `kubelet`. A one-time [bootkube](https://github.com/kubernetes-incubator/bootkube) bootstrap schedules an `apiserver`, `scheduler`, `controller-manager`, and `kube-dns` on controllers and runs `kube-proxy` and `flannel` or `calico` on each node. A generated `kubeconfig` provides `kubectl` access to the cluster.
 
 ## Requirements
 
@@ -12,7 +12,7 @@ Controllers are provisioned as etcd peers and run `etcd-member` (etcd3) and `kub
 * PXE-enabled [network boot](https://coreos.com/matchbox/docs/latest/network-setup.html) environment
 * Matchbox v0.6+ deployment with API enabled
 * Matchbox credentials `client.crt`, `client.key`, `ca.crt`
-* Terraform v0.9.2+ and [terraform-provider-matchbox](https://github.com/coreos/terraform-provider-matchbox) installed locally
+* Terraform v0.10.4+ and [terraform-provider-matchbox](https://github.com/coreos/terraform-provider-matchbox) installed locally
 
 ## Machines
 
@@ -94,7 +94,7 @@ For networks already supporting iPXE clients, you can add a `default.ipxe` confi
 chain http://matchbox.foo:8080/boot.ipxe
 ```
 
-For networks with Ubiquiti Routers, you can [configure the router](TODO) itself to chainload machines to iPXE and Matchbox.
+For networks with Ubiquiti Routers, you can [configure the router](/topics/hardware.md#ubiquiti) itself to chainload machines to iPXE and Matchbox.
 
 For a small lab, you may wish to checkout the [quay.io/coreos/dnsmasq](https://quay.io/repository/coreos/dnsmasq) container image and [copy-paste examples](https://github.com/coreos/matchbox/blob/master/Documentation/network-setup.md#coreosdnsmasq).
 
@@ -113,7 +113,7 @@ Install [Terraform](https://www.terraform.io/downloads.html) v0.9.2+ on your sys
 
 ```sh
 $ terraform version
-Terraform v0.10.1
+Terraform v0.10.7
 ```
 
 Add the [terraform-provider-matchbox](https://github.com/coreos/terraform-provider-matchbox) plugin binary for your system.
@@ -128,7 +128,7 @@ Add the plugin to your `~/.terraformrc`.
 
 ```
 providers {
-  ct = "/usr/local/bin/terraform-provider-matchbox"
+  matchbox = "/usr/local/bin/terraform-provider-matchbox"
 }
 ```
 
@@ -140,7 +140,7 @@ cd infra/clusters
 
 ## Provider
 
-Configure the Matchbox provider to use your Matchbox API endpoint and client certificate.
+Configure the Matchbox provider to use your Matchbox API endpoint and client certificate in a `providers.tf` file.
 
 ```tf
 provider "matchbox" {
@@ -162,7 +162,7 @@ module "bare-metal-mercury" {
   # install
   matchbox_http_endpoint  = "http://matchbox.example.com"
   container_linux_channel = "stable"
-  container_linux_version = "1465.6.0"
+  container_linux_version = "1520.6.0"
   ssh_authorized_key      = "ssh-rsa AAAAB3Nz..."
 
   # cluster
@@ -219,7 +219,7 @@ Get or update Terraform modules.
 $ terraform get            # downloads missing modules
 $ terraform get --update   # updates all modules
 Get: git::https://github.com/poseidon/typhoon (update)
-Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.6.1 (update)
+Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.8.1 (update)
 ```
 
 Plan the resources to be created.
@@ -232,20 +232,15 @@ Plan: 55 to add, 0 to change, 0 to destroy.
 Apply the changes. Terraform will generate bootkube assets to `asset_dir` and create Matchbox profiles (e.g. controller, worker) and matching rules via the Matchbox API.
 
 ```sh
-module.bare-metal-mercury.null_resource.copy-secrets.0: Provisioning with 'file'...
-module.bare-metal-mercury.null_resource.copy-secrets.2: Provisioning with 'file'...
-module.bare-metal-mercury.null_resource.copy-secrets.1: Provisioning with 'file'...    
-module.bare-metal-mercury.null_resource.copy-secrets.0: Still creating... (10s elapsed)
-module.bare-metal-mercury.null_resource.copy-secrets.2: Still creating... (10s elapsed)
-module.bare-metal-mercury.null_resource.copy-secrets.1: Still creating... (10s elapsed)
+module.bare-metal-mercury.null_resource.copy-kubeconfig.0: Provisioning with 'file'...
+module.bare-metal-mercury.null_resource.copy-etcd-secrets.0: Provisioning with 'file'...
+module.bare-metal-mercury.null_resource.copy-kubeconfig.0: Still creating... (10s elapsed)
+module.bare-metal-mercury.null_resource.copy-etcd-secrets.0: Still creating... (10s elapsed)
 ...
 ```
 
 Apply will then loop until it can successfully copy credentials to each machine and start the one-time Kubernetes bootstrap service. Proceed to the next step while this loops.
 
-!!! note ""
-    You may see `terraform apply` fail to `copy-secrets` if it connects before the disk install has completed. Run terraform apply until it reconciles successfully.
-
 ### Power
 
 Power on each machine with the boot device set to `pxe` for the next boot only.
@@ -295,9 +290,9 @@ bootkube[5]: Tearing down temporary bootstrap control plane...
 $ KUBECONFIG=/home/user/.secrets/clusters/mercury/auth/kubeconfig
 $ kubectl get nodes
 NAME                STATUS    AGE       VERSION
-node1.example.com   Ready     11m       v1.7.3+coreos.0
-node2.example.com   Ready     11m       v1.7.3+coreos.0
-node3.example.com   Ready     11m       v1.7.3+coreos.0
+node1.example.com   Ready     11m       v1.8.2
+node2.example.com   Ready     11m       v1.8.2
+node3.example.com   Ready     11m       v1.8.2
 ```
 
 List the pods.
@@ -305,14 +300,14 @@ List the pods.
 ```
 $ kubectl get pods --all-namespaces
 NAMESPACE     NAME                                       READY     STATUS    RESTARTS   AGE
+kube-system   calico-node-6qp7f                          2/2       Running   1          11m
+kube-system   calico-node-gnjrm                          2/2       Running   0          11m
+kube-system   calico-node-llbgt                          2/2       Running   0          11m
 kube-system   kube-apiserver-7336w                       1/1       Running   0          11m
 kube-system   kube-controller-manager-3271970485-b9chx   1/1       Running   0          11m
 kube-system   kube-controller-manager-3271970485-v30js   1/1       Running   1          11m
 kube-system   kube-dns-1187388186-mx9rt                  3/3       Running   0          11m
 kube-system   kube-etcd-network-checkpointer-q24f7       1/1       Running   0          11m
-kube-system   kube-flannel-6qp7f                         2/2       Running   1          11m
-kube-system   kube-flannel-gnjrm                         2/2       Running   0          11m
-kube-system   kube-flannel-llbgt                         2/2       Running   0          11m
 kube-system   kube-proxy-50sd4                           1/1       Running   0          11m
 kube-system   kube-proxy-bczhp                           1/1       Running   0          11m
 kube-system   kube-proxy-mp2fw                           1/1       Running   0          11m
@@ -353,12 +348,12 @@ Learn about [version pinning](concepts.md#versioning), maintenance, and [addons]
 
 | Name | Description | Default | Example |
 |:-----|:------------|:--------|:--------|
-| cached_install | Whether machines should PXE boot from the Matchbox `/assets` cache. Admin MUST have downloaded Container Linux images into the cache to use this | false | true |
+| cached_install | Whether machines should PXE boot and install from the Matchbox `/assets` cache. Admin MUST have downloaded Container Linux images into the cache to use this | false | true |
 | install_disk | Disk device where Container Linux should be installed | "/dev/sda" | "/dev/sdb" |
 | container_linux_oem | Specify alternative OEM image ids for the disk install | "" | "vmware_raw", "xen" |
-| experimental_self_hosted_etcd | Self-host etcd as pods on Kubernetes (not recommended) | false | true |
-| networking | Choice of networking provider | "flannel" | "flannel" or "calico" |
+| networking | Choice of networking provider | "calico" | "calico" or "flannel" |
 | network_mtu | CNI interface MTU (calico-only) | 1480 | - | 
 | pod_cidr | CIDR range to assign to Kubernetes pods | "10.2.0.0/16" | "10.22.0.0/16" |
 | service_cidr | CIDR range to assgin to Kubernetes services | "10.3.0.0/16" | "10.3.0.0/24" |
+| kernel_args | Additional kernel args to provide at PXE boot | [] | "kvm-intel.nested=1" |
 

docs/concepts.md

@@ -8,7 +8,7 @@ Let's cover the concepts you'll need to get started.
 
 #### Nodes
 
-Cluster nodes provision themselves from a declarative configuration upfront. Nodes run a `kubelet` service and register themselves with the control plane to join the higher order cluster.
+Cluster nodes provision themselves from a declarative configuration upfront. Nodes run a `kubelet` service and register themselves with the control plane to join the higher order cluster. All nodes run `kube-proxy` and `calico` or `flannel` pods.
 
 #### Controllers
 
@@ -16,7 +16,7 @@ Controller nodes are scheduled to run the Kubernetes `apiserver`, `scheduler`, `
 
 #### Workers
 
-Worker nodes register with the control plane and run application workloads. Workers, like all nodes, run `kube-proxy` and `flannel` pods.
+Worker nodes register with the control plane and run application workloads.
 
 ## Terraform
 
@@ -60,7 +60,7 @@ Modules are updated regularly, set the version to a [release tag](https://github
 
 ```tf
 ...
-source = "git:https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes?ref=v1.7.3"
+source = "git:https://github.com/poseidon/typhoon//google-cloud/container-linux/kubernetes?ref=hash"
 ```
 
 Module versioning ensures `terraform get --update` only fetches the desired version, so plan and apply don't change cluster resources, unless the version is altered.
@@ -69,14 +69,15 @@ Module versioning ensures `terraform get --update` only fetches the desired vers
 
 Maintain Terraform configs for "live" infrastructure in a versioned repository. Seek to organize configs to reflect resources that should be managed together in a `terraform apply` invocation.
 
-You may choose to organize resources all together, by team, by project, or some other scheme. Here's an example that manages three clusters together:
+You may choose to organize resources all together, by team, by project, or some other scheme. Here's an example that manages four clusters together:
 
 ```sh
 .git/
 infra/
 └── terraform
     └── clusters
-        ├── bare-metal-tungsten.tf
+        ├── aws-tempest.tf
+        ├── bare-metal-mercury.tf
         ├── google-cloud-yavin.tf
         ├── digital-ocean-nemo.tf
         ├── providers.tf

docs/digital-ocean.md

@@ -1,16 +1,16 @@
 # Digital Ocean
 
-In this tutorial, we'll create a Kubernetes v1.7.3 cluster on Digital Ocean.
+In this tutorial, we'll create a Kubernetes v1.8.2 cluster on Digital Ocean.
 
 We'll declare a Kubernetes cluster in Terraform using the Typhoon Terraform module. On apply, firewall rules, DNS records, tags, and droplets for Kubernetes controllers and workers will be created.
 
-Controllers and workers are provisioned to run a `kubelet`. A one-time [bootkube](https://github.com/kubernetes-incubator/bootkube) bootstrap schedules `etcd`, `apiserver`, `scheduler`, `controller-manager`, and `kube-dns` on controllers and runs `kube-proxy` and `flannel` on each node. A generated `kubeconfig` provides `kubectl` access to the cluster.
+Controllers and workers are provisioned to run a `kubelet`. A one-time [bootkube](https://github.com/kubernetes-incubator/bootkube) bootstrap schedules an `apiserver`, `scheduler`, `controller-manager`, and `kube-dns` on controllers and runs `kube-proxy` and `flannel` on each node. A generated `kubeconfig` provides `kubectl` access to the cluster.
 
 ## Requirements
 
 * Digital Ocean Account and Token
 * Digital Ocean Domain (registered Domain Name or delegated subdomain)
-* Terraform v0.10.1+ and [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) installed locally
+* Terraform v0.10.4+ and [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) installed locally
 
 ## Terraform Setup
 
@@ -18,7 +18,7 @@ Install [Terraform](https://www.terraform.io/downloads.html) v0.10.1+ on your sy
 
 ```sh
 $ terraform version
-Terraform v0.10.1
+Terraform v0.10.7
 ```
 
 Add the [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) plugin binary for your system.
@@ -114,7 +114,7 @@ Get or update Terraform modules.
 $ terraform get            # downloads missing modules
 $ terraform get --update   # updates all modules
 Get: git::https://github.com/poseidon/typhoon (update)
-Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.6.1 (update)
+Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.8.1 (update)
 ```
 
 Plan the resources to be created.
@@ -137,7 +137,7 @@ module.digital-ocean-nemo.null_resource.bootkube-start: Creation complete (ID: 7
 Apply complete! Resources: 54 added, 0 changed, 0 destroyed.
 ```
 
-In 5-10 minutes, the Kubernetes cluster will be ready.
+In 3-6 minutes, the Kubernetes cluster will be ready.
 
 ## Verify
 
@@ -147,22 +147,19 @@ In 5-10 minutes, the Kubernetes cluster will be ready.
 $ KUBECONFIG=/home/user/.secrets/clusters/nemo/auth/kubeconfig
 $ kubectl get nodes
 NAME             STATUS    AGE       VERSION
-10.132.110.130   Ready     10m       v1.7.3+coreos.0
-10.132.115.81    Ready     10m       v1.7.3+coreos.0
-10.132.124.107   Ready     10m       v1.7.3+coreos.0
+10.132.110.130   Ready     10m       v1.8.2
+10.132.115.81    Ready     10m       v1.8.2
+10.132.124.107   Ready     10m       v1.8.2
 ```
 
 List the pods.
 
 ```
 NAMESPACE     NAME                                       READY     STATUS    RESTARTS   AGE
-kube-system   etcd-operator-3329263108-sgsbl             1/1       Running   1          11m
 kube-system   kube-apiserver-n10qr                       1/1       Running   0          11m
 kube-system   kube-controller-manager-3271970485-37gtw   1/1       Running   1          11m
 kube-system   kube-controller-manager-3271970485-p52t5   1/1       Running   0          11m
 kube-system   kube-dns-1187388186-ld1j7                  3/3       Running   0          11m
-kube-system   kube-etcd-0000                             1/1       Running   0          9m
-kube-system   kube-etcd-network-checkpointer-n9xsk       1/1       Running   0          11m
 kube-system   kube-flannel-1cq1v                         2/2       Running   0          11m
 kube-system   kube-flannel-hq9t0                         2/2       Running   1          11m
 kube-system   kube-flannel-v0g9w                         2/2       Running   0          11m

docs/faq.md

@@ -1,6 +1,6 @@
 # FAQ
 
-## Terraform?
+## Terraform
 
 Typhoon provides a Terraform Module for each supported operating system and platform. Terraform is considered a *format* detail, much like a Linux distro might provide images in the qcow2 or ISO format. It is a mechanism for sharing Typhoon in a way that works for many users.
 
@@ -8,12 +8,12 @@ Formats rise and evolve. Typhoon may choose to adapt the format over time (with
 
 ## Self-hosted etcd
 
-Typhoon clusters on cloud providers run etcd as "self-hosted" pods, managed by the [etcd-operator](https://github.com/coreos/etcd-operator). By contrast, Typhoon bare-metal runs an etcd peer as a systemd `etcd-member.service` on each controller (i.e. on-host).
+AWS and Google Cloud clusters run etcd as "self-hosted" pods, managed by the [etcd-operator](https://github.com/coreos/etcd-operator). By contrast, Typhoon bare-metal and Digital Ocean run an etcd peer as a systemd `etcd-member.service` on each controller (i.e. on-host).
 
-In practice, self-hosted etcd has proven to be *ok*, but not ideal. Running the apiserver's etcd atop Kubernetes itself is inherently complex, but works suitably in most cases. It can be opaque to debug if complex edge cases with upstream Kubernetes bugs arise.
+In practice, self-hosted etcd has proven to be *ok*, but not ideal. Running the apiserver's etcd atop Kubernetes itself is inherently complex, but works in most cases. It can be opaque to debug if complex edge cases with upstream Kubernetes bugs arise.
 
 !!! note ""
-    Typhoon clusters and their defaults power the maintainers' clusters. The edge cases are sufficiently rare that self-hosted etcd is not a pressing issue, but cloud clusters may switch back to on-host etcd in the future.
+    Over time, we plan to deprecate self-hosted etcd and revert to running etcd on-host.
 
 ## Operating Systems
 
@@ -21,9 +21,17 @@ Only Container Linux is supported currently. This just due to operational famili
 
 Fedora Cloud will likely be next. 
 
+## Get Help
+
+Ask questions on the IRC #typhoon channel on [freenode.net](http://freenode.net/).
+
+## Security Issues
+
+If you find security issues, please see [security disclosures](/topics/security).
+
 ## Maintainers
 
-Typhoon clusters are Kubernetes configurations the maintainers use in real-world, production clusters.
+Typhoon clusters are Kubernetes clusters the maintainers use in real-world, production clusters.
 
 * Maintainers must personally operate a bare-metal and cloud provider cluster and strive to exercise it in real-world scenarios
 

docs/google-cloud.md

@@ -1,6 +1,6 @@
 # Google Cloud
 
-In this tutorial, we'll create a Kubernetes v1.7.3 cluster on Google Compute Engine (not GKE).
+In this tutorial, we'll create a Kubernetes v1.8.2 cluster on Google Compute Engine (not GKE).
 
 We'll declare a Kubernetes cluster in Terraform using the Typhoon Terraform module. On apply, a network, firewall rules, managed instance groups of Kubernetes controllers and workers, network load balancers for controllers and workers, and health checks will be created.
 
@@ -10,7 +10,7 @@ Controllers and workers are provisioned to run a `kubelet`. A one-time [bootkube
 
 * Google Cloud Account and Service Account
 * Google Cloud DNS Zone (registered Domain Name or delegated subdomain)
-* Terraform v0.9.2+ and [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) installed locally
+* Terraform v0.10.4+ and [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) installed locally
 
 ## Terraform Setup
 
@@ -18,7 +18,7 @@ Install [Terraform](https://www.terraform.io/downloads.html) v0.9.2+ on your sys
 
 ```sh
 $ terraform version
-Terraform v0.10.1
+Terraform v0.10.7
 ```
 
 Add the [terraform-provider-ct](https://github.com/coreos/terraform-provider-ct) plugin binary for your system.
@@ -80,7 +80,7 @@ module "google-cloud-yavin" {
   zone          = "us-central1-c"
   dns_zone      = "example.com"
   dns_zone_name = "example-zone"
-  os_image      = "coreos-stable-1465-6-0-v20170817"
+  os_image      = "coreos-stable-1520-6-0-v20171012"
 
   cluster_name       = "yavin"
   controller_count   = 1
@@ -120,7 +120,7 @@ Get or update Terraform modules.
 $ terraform get            # downloads missing modules
 $ terraform get --update   # updates all modules
 Get: git::https://github.com/poseidon/typhoon (update)
-Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.6.1 (update)
+Get: git::https://github.com/poseidon/bootkube-terraform.git?ref=v0.8.1 (update)
 ```
 
 Plan the resources to be created.
@@ -154,9 +154,9 @@ In 5-10 minutes, the Kubernetes cluster will be ready.
 $ KUBECONFIG=/home/user/.secrets/clusters/yavin/auth/kubeconfig
 $ kubectl get nodes
 NAME                                          STATUS   AGE    VERSION
-yavin-controller-1682.c.example-com.internal  Ready    6m     v1.7.3+coreos.0
-yavin-worker-jrbf.c.example-com.internal      Ready    5m     v1.7.3+coreos.0
-yavin-worker-mzdm.c.example-com.internal      Ready    5m     v1.7.3+coreos.0
+yavin-controller-1682.c.example-com.internal  Ready    6m     v1.8.2
+yavin-worker-jrbf.c.example-com.internal      Ready    5m     v1.8.2
+yavin-worker-mzdm.c.example-com.internal      Ready    5m     v1.8.2
 ```
 
 List the pods.
@@ -164,6 +164,9 @@ List the pods.
 ```
 $ kubectl get pods --all-namespaces
 NAMESPACE     NAME                                      READY  STATUS    RESTARTS  AGE
+kube-system   calico-node-1cs8z                         2/2    Running   0         6m
+kube-system   calico-node-d1l5b                         2/2    Running   0         6m
+kube-system   calico-node-sp9ps                         2/2    Running   0         6m
 kube-system   etcd-operator-3329263108-f443m            1/1    Running   1         6m
 kube-system   kube-apiserver-zppls                      1/1    Running   0         6m
 kube-system   kube-controller-manager-3271970485-gh9kt  1/1    Running   0         6m
@@ -171,9 +174,6 @@ kube-system   kube-controller-manager-3271970485-h90v8  1/1    Running   1
 kube-system   kube-dns-1187388186-zj5dl                 3/3    Running   0         6m
 kube-system   kube-etcd-0000                            1/1    Running   0         5m
 kube-system   kube-etcd-network-checkpointer-crznb      1/1    Running   0         6m
-kube-system   kube-flannel-1cs8z                        2/2    Running   0         6m
-kube-system   kube-flannel-d1l5b                        2/2    Running   0         6m
-kube-system   kube-flannel-sp9ps                        2/2    Running   0         6m
 kube-system   kube-proxy-117v6                          1/1    Running   0         6m
 kube-system   kube-proxy-9886n                          1/1    Running   0         6m
 kube-system   kube-proxy-njn47                          1/1    Running   0         6m
@@ -230,7 +230,7 @@ resource "google_dns_managed_zone" "zone-for-clusters" {
 | controller_count | Number of controllers (i.e. masters) | 1 | 1 |
 | worker_count | Number of workers | 1 | 3 |
 | worker_preemptible | If enabled, Compute Engine will terminate controllers randomly within 24 hours | false | true |
-| networking | Choice of networking provider | "flannel" | "flannel" or "calico" |
+| networking | Choice of networking provider | "calico" | "calico" or "flannel" |
 | pod_cidr | CIDR range to assign to Kubernetes pods | "10.2.0.0/16" | "10.22.0.0/16" |
 | service_cidr | CIDR range to assgin to Kubernetes services | "10.3.0.0/16" | "10.3.0.0/24" |