Add support for worker pools on AWS

* Allow groups of workers to be defined and joined to
a cluster (i.e. worker pools)
* Move worker resources into a Terraform submodule
* Output variables needed for passing to worker pools
* Add usage docs for AWS worker pools (advanced)

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

@@ -0,0 +1,119 @@
+---
+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
+        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=/bin/mkdir -p /var/lib/kubelet/volumeplugins
+        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_domain_suffix} \
+          --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 \
+          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
+        Restart=always
+        RestartSec=5
+        [Install]
+        WantedBy=multi-user.target
+    - name: delete-node.service
+      enable: true
+      contents: |
+        [Unit]
+        Description=Waiting to delete Kubernetes node on shutdown
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/true
+        ExecStop=/etc/kubernetes/delete-node
+        [Install]
+        WantedBy=multi-user.target
+storage:
+  files:
+    - path: /etc/kubernetes/kubeconfig
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          ${kubeconfig}
+    - path: /etc/kubernetes/kubelet.env
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          KUBELET_IMAGE_URL=docker://gcr.io/google_containers/hyperkube
+          KUBELET_IMAGE_TAG=v1.9.3
+    - path: /etc/sysctl.d/max-user-watches.conf
+      filesystem: root
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+    - path: /etc/kubernetes/delete-node
+      filesystem: root
+      mode: 0744
+      contents:
+        inline: |
+          #!/bin/bash
+          set -e
+          exec /usr/bin/rkt run \
+            --trust-keys-from-https \
+            --volume config,kind=host,source=/etc/kubernetes \
+            --mount volume=config,target=/etc/kubernetes \
+            --insecure-options=image \
+            docker://gcr.io/google_containers/hyperkube:v1.9.3 \
+            --net=host \
+            --dns=host \
+            --exec=/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
+passwd:
+  users:
+    - name: core
+      ssh_authorized_keys:
+        - "${ssh_authorized_key}"

aws/container-linux/kubernetes/workers/ingress.tf

@@ -0,0 +1,80 @@
+# Network Load Balancer for Ingress
+resource "aws_lb" "ingress" {
+  name               = "${var.cluster_name}-ingress"
+  load_balancer_type = "network"
+  internal           = false
+
+  subnets = ["${var.subnet_ids}"]
+}
+
+# Forward HTTP traffic to workers
+resource "aws_lb_listener" "ingress-http" {
+  load_balancer_arn = "${aws_lb.ingress.arn}"
+  protocol          = "TCP"
+  port              = 80
+
+  default_action {
+    type             = "forward"
+    target_group_arn = "${aws_lb_target_group.workers-http.arn}"
+  }
+}
+
+# Forward HTTPS traffic to workers
+resource "aws_lb_listener" "ingress-https" {
+  load_balancer_arn = "${aws_lb.ingress.arn}"
+  protocol          = "TCP"
+  port              = 443
+
+  default_action {
+    type             = "forward"
+    target_group_arn = "${aws_lb_target_group.workers-https.arn}"
+  }
+}
+
+# Network Load Balancer target groups of instances
+
+resource "aws_lb_target_group" "workers-http" {
+  name        = "${var.cluster_name}-workers-http"
+  vpc_id      = "${var.vpc_id}"
+  target_type = "instance"
+
+  protocol = "TCP"
+  port     = 80
+
+  # Ingress Controller HTTP health check
+  health_check {
+    protocol = "HTTP"
+    port     = 10254
+    path     = "/healthz"
+
+    # NLBs required to use same healthy and unhealthy thresholds
+    healthy_threshold   = 3
+    unhealthy_threshold = 3
+
+    # Interval between health checks required to be 10 or 30
+    interval = 10
+  }
+}
+
+resource "aws_lb_target_group" "workers-https" {
+  name        = "${var.cluster_name}-workers-https"
+  vpc_id      = "${var.vpc_id}"
+  target_type = "instance"
+
+  protocol = "TCP"
+  port     = 443
+
+  # Ingress Controller HTTP health check
+  health_check {
+    protocol = "HTTP"
+    port     = 10254
+    path     = "/healthz"
+
+    # NLBs required to use same healthy and unhealthy thresholds
+    healthy_threshold   = 3
+    unhealthy_threshold = 3
+
+    # Interval between health checks required to be 10 or 30
+    interval = 10
+  }
+}

aws/container-linux/kubernetes/workers/outputs.tf

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

aws/container-linux/kubernetes/workers/variables.tf

@@ -0,0 +1,73 @@
+variable "cluster_name" {
+  type        = "string"
+  description = "Unique name"
+}
+
+variable "vpc_id" {
+  type = "string"
+  description = "ID of the VPC for creating instances"
+}
+
+variable "subnet_ids" {
+  type = "list"
+  description = "List of subnet IDs for creating instances"
+}
+
+variable "security_groups" {
+  type = "list"
+  description = "List of security group IDs"
+}
+
+# instances
+
+variable "count" {
+  type        = "string"
+  default     = "1"
+  description = "Number of instances"
+}
+
+variable "instance_type" {
+  type        = "string"
+  default     = "t2.small"
+  description = "EC2 instance type"
+}
+
+variable "os_channel" {
+  type        = "string"
+  default     = "stable"
+  description = "Container Linux AMI channel (stable, beta, alpha)"
+}
+
+variable "disk_size" {
+  type        = "string"
+  default     = "40"
+  description = "Size of the disk in GB"
+}
+
+# configuration
+
+variable "kubeconfig" {
+  type = "string"
+  description = "Generated Kubelet kubeconfig"
+}
+
+variable "ssh_authorized_key" {
+  type        = "string"
+  description = "SSH public key for user 'core'"
+}
+
+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.
+EOD
+
+  type    = "string"
+  default = "10.3.0.0/16"
+}
+
+variable "cluster_domain_suffix" {
+  description = "Queries for domains with the suffix will be answered by kube-dns. Default is cluster.local (e.g. foo.default.svc.cluster.local) "
+  type        = "string"
+  default     = "cluster.local"
+}

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

@@ -0,0 +1,74 @@
+# Workers AutoScaling Group
+resource "aws_autoscaling_group" "workers" {
+  name = "${var.cluster_name}-worker ${aws_launch_configuration.worker.name}"
+
+  # count
+  desired_capacity          = "${var.count}"
+  min_size                  = "${var.count}"
+  max_size                  = "${var.count + 2}"
+  default_cooldown          = 30
+  health_check_grace_period = 30
+
+  # network
+  vpc_zone_identifier = ["${var.subnet_ids}"]
+
+  # template
+  launch_configuration = "${aws_launch_configuration.worker.name}"
+
+  # target groups to which instances should be added
+  target_group_arns = [
+    "${aws_lb_target_group.workers-http.id}",
+    "${aws_lb_target_group.workers-https.id}",
+  ]
+
+  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 = "${var.instance_type}"
+
+  user_data = "${data.ct_config.worker_ign.rendered}"
+
+  # storage
+  root_block_device {
+    volume_type = "standard"
+    volume_size = "${var.disk_size}"
+  }
+
+  # network
+  security_groups = ["${var.security_groups}"]
+
+  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 = {
+    kubeconfig            = "${indent(10, var.kubeconfig)}"
+    ssh_authorized_key    = "${var.ssh_authorized_key}"
+    k8s_dns_service_ip    = "${cidrhost(var.service_cidr, 10)}"
+    cluster_domain_suffix = "${var.cluster_domain_suffix}"
+  }
+}
+
+data "ct_config" "worker_ign" {
+  content      = "${data.template_file.worker_config.rendered}"
+  pretty_print = false
+}