fix-redirects.sh: adding forced redirect

Revamp most of the Helm content:
- overview of Helm moved to helm-intro.md
- explanation of chart format in helm-chart-format.md
- the very crude chart example is now in helm-create-basic-chart.md
- the more advanced chart (with templates etc) is now in helm-create-better-chart.md
- deep dive into Helm internals (how it stores it's data) in helm-secrets.md

This is all for Helm 3. Helm 2 is not supported anymore.

.gitignore

@@ -8,6 +8,7 @@ slides/*.yml.html
 slides/autopilot/state.yaml
 slides/index.html
 slides/past.html
+slides/slides.zip
 node_modules
 
 ### macOS ###

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/consul.yaml

@@ -2,8 +2,6 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   name: consul
-  labels:
-    app: consul
 rules:
   - apiGroups: [""]
     resources:
@@ -29,8 +27,6 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: consul
-  labels:
-    app: consul
 ---
 apiVersion: v1
 kind: Service
@@ -72,7 +68,7 @@ spec:
       terminationGracePeriodSeconds: 10
       containers:
         - name: consul
-          image: "consul:1.5"
+          image: "consul:1.6"
           args:
             - "agent"
             - "-bootstrap-expect=3"

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

@@ -3,6 +3,7 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: fluentd
+  namespace: default
 ---
 apiVersion: rbac.authorization.k8s.io/v1beta1
 kind: ClusterRole
@@ -32,13 +33,17 @@ subjects:
   name: fluentd
   namespace: default
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   name: fluentd
+  namespace: default
   labels:
     app: fluentd
 spec:
+  selector:
+    matchLabels:
+      app: fluentd
   template:
     metadata:
       labels:
@@ -86,12 +91,13 @@ spec:
         hostPath:
           path: /var/lib/docker/containers
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   labels:
     app: elasticsearch
   name: elasticsearch
+  namespace: default
 spec:
   selector:
     matchLabels:
@@ -119,6 +125,7 @@ metadata:
   labels:
     app: elasticsearch
   name: elasticsearch
+  namespace: default
 spec:
   ports:
   - port: 9200
@@ -128,12 +135,13 @@ spec:
     app: elasticsearch
   type: ClusterIP
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   labels:
     app: kibana
   name: kibana
+  namespace: default
 spec:
   selector:
     matchLabels:
@@ -157,6 +165,7 @@ metadata:
   labels:
     app: kibana
   name: kibana
+  namespace: default
 spec:
   ports:
   - port: 5601

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: networking.k8s.io/v1beta1
 kind: Ingress
 metadata:
-  name: cheddar
+  name: whatever
 spec:
   rules:
-  - host: px.3.123.33.38.nip.io
+  - host: whatever.A.B.C.D.nip.io
     http:
       paths:
       - path: /
         backend:
-          serviceName: px-lighthouse
-          servicePort: 80
-
+          serviceName: whatever
+          servicePort: 1234

k8s/insecure-dashboard.yaml

@@ -12,19 +12,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# ------------------- Dashboard Secret ------------------- #
-
 apiVersion: v1
-kind: Secret
+kind: Namespace
 metadata:
-  labels:
-    k8s-app: kubernetes-dashboard
-  name: kubernetes-dashboard-certs
-  namespace: kube-system
-type: Opaque
+  name: kubernetes-dashboard
 
 ---
-# ------------------- Dashboard Service Account ------------------- #
 
 apiVersion: v1
 kind: ServiceAccount
@@ -32,62 +25,147 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard
-  namespace: kube-system
+  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
 
 ---
-# ------------------- Dashboard Role & Role Binding ------------------- #
 
 kind: Role
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
-  name: kubernetes-dashboard-minimal
-  namespace: kube-system
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
 rules:
-  # Allow Dashboard to create 'kubernetes-dashboard-key-holder' secret.
-- apiGroups: [""]
-  resources: ["secrets"]
-  verbs: ["create"]
-  # Allow Dashboard to create 'kubernetes-dashboard-settings' config map.
-- apiGroups: [""]
-  resources: ["configmaps"]
-  verbs: ["create"]
   # Allow Dashboard to get, update and delete Dashboard exclusive secrets.
-- apiGroups: [""]
-  resources: ["secrets"]
-  resourceNames: ["kubernetes-dashboard-key-holder", "kubernetes-dashboard-certs"]
-  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 from heapster.
-- apiGroups: [""]
-  resources: ["services"]
-  resourceNames: ["heapster"]
-  verbs: ["proxy"]
-- apiGroups: [""]
-  resources: ["services/proxy"]
-  resourceNames: ["heapster", "http:heapster:", "https:heapster:"]
-  verbs: ["get"]
+  - 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:
-  name: kubernetes-dashboard-minimal
-  namespace: kube-system
+  labels:
+    k8s-app: kubernetes-dashboard
+  name: kubernetes-dashboard
+  namespace: kubernetes-dashboard
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
-  name: kubernetes-dashboard-minimal
-subjects:
-- kind: ServiceAccount
   name: kubernetes-dashboard
-  namespace: kube-system
+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
 
 ---
-# ------------------- Dashboard Deployment ------------------- #
 
 kind: Deployment
 apiVersion: apps/v1
@@ -95,7 +173,7 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard
-  namespace: kube-system
+  namespace: kubernetes-dashboard
 spec:
   replicas: 1
   revisionHistoryLimit: 10
@@ -108,61 +186,125 @@ spec:
         k8s-app: kubernetes-dashboard
     spec:
       containers:
-      - name: kubernetes-dashboard
-        image: k8s.gcr.io/kubernetes-dashboard-amd64:v1.10.1
-        ports:
-        - containerPort: 8443
-          protocol: TCP
-        args:
-          - --auto-generate-certificates
-          - --enable-skip-login
-          # 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
-        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
+        - 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: {}
+        - 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
+        - key: node-role.kubernetes.io/master
+          effect: NoSchedule
 
 ---
-# ------------------- Dashboard Service ------------------- #
 
 kind: Service
 apiVersion: v1
 metadata:
   labels:
-    k8s-app: kubernetes-dashboard
-  name: kubernetes-dashboard
-  namespace: kube-system
+    k8s-app: dashboard-metrics-scraper
+  name: dashboard-metrics-scraper
+  namespace: kubernetes-dashboard
 spec:
   ports:
-    - port: 443
-      targetPort: 8443
+    - port: 8000
+      targetPort: 8000
   selector:
-    k8s-app: kubernetes-dashboard
+    k8s-app: dashboard-metrics-scraper
+
 ---
-apiVersion: extensions/v1beta1
+
+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:
@@ -181,10 +323,12 @@ spec:
       - args:
         - sh
         - -c
-        - apk add --no-cache socat && socat TCP-LISTEN:80,fork,reuseaddr OPENSSL:kubernetes-dashboard.kube-system:443,verify=0
+        - 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:
@@ -199,13 +343,13 @@ spec:
   selector:
     app: dashboard
   type: NodePort
+
 ---
-apiVersion: rbac.authorization.k8s.io/v1beta1
+
+apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
-  name: kubernetes-dashboard
-  labels:
-    k8s-app: kubernetes-dashboard
+  name: insecure-dashboard
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
@@ -213,4 +357,4 @@ roleRef:
 subjects:
 - kind: ServiceAccount
   name: kubernetes-dashboard
-  namespace: kube-system
+  namespace: kubernetes-dashboard

k8s/just-a-pod.yaml

@@ -1,5 +1,5 @@
 apiVersion: v1
-Kind: Pod
+kind: Pod
 metadata:
   name: hello
   namespace: default

k8s/local-path-storage.yaml

@@ -45,7 +45,7 @@ subjects:
   name: local-path-provisioner-service-account
   namespace: local-path-storage
 ---
-apiVersion: apps/v1beta2
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: local-path-provisioner

k8s/metrics-server.yaml

@@ -58,7 +58,7 @@ metadata:
   name: metrics-server
   namespace: kube-system
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: metrics-server

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

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: nginx-with-volume
+  name: nginx-with-git
 spec:
   volumes:
   - name: www

k8s/nginx-4-with-init.yaml

@@ -0,0 +1,20 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx-with-init
+spec:
+  volumes:
+  - name: www
+  containers:
+  - name: nginx
+    image: nginx
+    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/

k8s/persistent-consul.yaml

@@ -1,51 +1,54 @@
 apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
+kind: ClusterRole
 metadata:
-  name: consul
+  name: persistentconsul
 rules:
-  - apiGroups: [ "" ]
-    resources: [ pods ]
-    verbs:     [ get, list ]
+  - apiGroups: [""]
+    resources:
+      - pods
+    verbs:
+      - get
+      - list
 ---
 apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
+kind: ClusterRoleBinding
 metadata:
-  name: consul
+  name: persistentconsul
 roleRef:
   apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: consul
+  kind: ClusterRole
+  name: persistentconsul
 subjects:
   - kind: ServiceAccount
-    name: consul
-    namespace: orange
+    name: persistentconsul
+    namespace: default
 ---
 apiVersion: v1
 kind: ServiceAccount
 metadata:
-  name: consul
+  name: persistentconsul
 ---
 apiVersion: v1
 kind: Service
 metadata:
-  name: consul
+  name: persistentconsul
 spec:
   ports:
   - port: 8500
     name: http
   selector:
-    app: consul
+    app: persistentconsul
 ---
 apiVersion: apps/v1
 kind: StatefulSet
 metadata:
-  name: consul
+  name: persistentconsul
 spec:
-  serviceName: consul
+  serviceName: persistentconsul
   replicas: 3
   selector:
     matchLabels:
-      app: consul
+      app: persistentconsul
   volumeClaimTemplates:
     - metadata:
         name: data
@@ -58,9 +61,9 @@ spec:
   template:
     metadata:
       labels:
-        app: consul
+        app: persistentconsul
     spec:
-      serviceAccountName: consul
+      serviceAccountName: persistentconsul
       affinity:
         podAntiAffinity:
           requiredDuringSchedulingIgnoredDuringExecution:
@@ -69,19 +72,19 @@ spec:
                   - key: app
                     operator: In
                     values:
-                      - consul
+                      - persistentconsul
               topologyKey: kubernetes.io/hostname
       terminationGracePeriodSeconds: 10
       containers:
         - name: consul
-          image: "consul:1.5"
+          image: "consul:1.6"
           volumeMounts:
             - name: data
               mountPath: /consul/data
           args:
             - "agent"
             - "-bootstrap-expect=3"
-            - "-retry-join=provider=k8s namespace=orange label_selector=\"app=consul\""
+            - "-retry-join=provider=k8s label_selector=\"app=persistentconsul\""
             - "-client=0.0.0.0"
             - "-data-dir=/consul/data"
             - "-server"

k8s/portworx.yaml

@@ -1,5 +1,4 @@
-# SOURCE: https://install.portworx.com/?kbver=1.15.2&b=true&s=/dev/loop4&c=px-workshop&stork=true&lh=true&st=k8s&mc=false
-# SOURCE: https://install.portworx.com/?kbver=1.15.2&b=true&s=/dev/loop4&c=px-workshop&stork=true&lh=true&st=k8s&mc=false
+# SOURCE: https://install.portworx.com/?mc=false&kbver=1.17.1&b=true&s=%2Fdev%2Floop4&j=auto&c=px-workshop&stork=true&csi=true&lh=true&st=k8s
 ---
 kind: Service
 apiVersion: v1
@@ -11,7 +10,7 @@ metadata:
 spec:
   selector:
     name: portworx
-  type: NodePort
+  type: ClusterIP
   ports:
     - name: px-api
       protocol: TCP
@@ -51,6 +50,165 @@ spec:
     shortNames:
     - vps
     - vp
+  preserveUnknownFields: false
+  validation:
+    openAPIV3Schema:
+      type: object
+      required:
+      - spec
+      properties:
+        spec:
+          type: object
+          description: The desired spec of the volume placement strategy
+          properties:
+            replicaAffinity:
+              type: array
+              description: Allows you to specify a rule which creates an affinity for replicas within a volume
+              items:
+                type: object
+                properties:
+                  enforcement:
+                    type: string
+                    enum:
+                    - required
+                    - preferred
+                    description: Specifies if the given rule is required (hard) or preferred (soft)
+                  topologyKey:
+                    type: string
+                    minLength: 1
+                    description: Key for the node label that the system uses to denote a topology domain. The key can be for any node label that is present on the Kubernetes node.
+                  matchExpressions:
+                    description: Expression to use for the replica affinity rule
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        key:
+                          type: string
+                          minLength: 1
+                        operator:
+                          type: string
+                          enum:
+                          - In
+                          - NotIn
+                          - Exists
+                          - DoesNotExist
+                          - Lt
+                          - Gt
+                          description: The logical operator to use for comparing the key and values in the match expression
+                        values:
+                          type: array
+                          items:
+                            type: string
+                      required:
+                      - key
+                      - operator
+            replicaAntiAffinity:
+              type: array
+              description: Allows you to specify a rule that creates an anti-affinity for replicas within a volume
+              items:
+                type: object
+                properties:
+                  enforcement:
+                    type: string
+                    enum:
+                    - required
+                    - preferred
+                    description: Specifies if the given rule is required (hard) or preferred (soft)
+                  topologyKey:
+                    type: string
+                    minLength: 1
+                    description: Key for the node label that the system uses to denote a topology domain. The key can be for any node label that is present on the Kubernetes node.
+                required:
+                - topologyKey
+            volumeAffinity:
+              type: array
+              description: Allows you to colocate volumes by specifying rules that place replicas of a volume together with those of another volume for which the specified labels match
+              items:
+                type: object
+                properties:
+                  enforcement:
+                    type: string
+                    enum:
+                    - required
+                    - preferred
+                    description: Specifies if the given rule is required (hard) or preferred (soft)
+                  topologyKey:
+                    type: string
+                    minLength: 1
+                    description: Key for the node label that the system uses to denote a topology domain. The key can be for any node label that is present on the Kubernetes node.
+                  matchExpressions:
+                    description: Expression to use for the volume affinity rule
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        key:
+                          type: string
+                          minLength: 1
+                        operator:
+                          type: string
+                          enum:
+                          - In
+                          - NotIn
+                          - Exists
+                          - DoesNotExist
+                          - Lt
+                          - Gt
+                          description: The logical operator to use for comparing the key and values in the match expression
+                        values:
+                          type: array
+                          items:
+                            type: string
+                      required:
+                      - key
+                      - operator
+                required:
+                - matchExpressions
+            volumeAntiAffinity:
+              type: array
+              description: Allows you to specify dissociation rules between 2 or more volumes that match the given labels
+              items:
+                type: object
+                properties:
+                  enforcement:
+                    type: string
+                    enum:
+                    - required
+                    - preferred
+                    description: Specifies if the given rule is required (hard) or preferred (soft)
+                  topologyKey:
+                    type: string
+                    minLength: 1
+                    description: Key for the node label that the system uses to denote a topology domain. The key can be for any node label that is present on the Kubernetes node.
+                  matchExpressions:
+                    description: Expression to use for the volume anti affinity rule
+                    type: array
+                    items:
+                      type: object
+                      properties:
+                        key:
+                          type: string
+                          minLength: 1
+                        operator:
+                          type: string
+                          enum:
+                          - In
+                          - NotIn
+                          - Exists
+                          - DoesNotExist
+                          - Lt
+                          - Gt
+                          description: The logical operator to use for comparing the key and values in the match expression
+                        values:
+                          type: array
+                          items:
+                            type: string
+                      required:
+                      - key
+                      - operator
+                required:
+                - matchExpressions
 ---
 apiVersion: v1
 kind: ServiceAccount
@@ -85,6 +243,13 @@ rules:
 - apiGroups: ["portworx.io"]
   resources: ["volumeplacementstrategies"]
   verbs: ["get", "list"]
+- apiGroups: ["stork.libopenstorage.org"]
+  resources: ["backuplocations"]
+  verbs: ["get", "list"]
+- apiGroups: [""]
+  resources: ["events"]
+  verbs: ["create"]
+
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
@@ -128,14 +293,19 @@ roleRef:
   name: px-role
   apiGroup: rbac.authorization.k8s.io
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   name: portworx
   namespace: kube-system
+  labels:
+    name: portworx
   annotations:
-    portworx.com/install-source: "https://install.portworx.com/?kbver=1.15.2&b=true&s=/dev/loop4&c=px-workshop&stork=true&lh=true&st=k8s&mc=false"
+    portworx.com/install-source: "https://install.portworx.com/?mc=false&kbver=1.17.1&b=true&s=%2Fdev%2Floop4&j=auto&c=px-workshop&stork=true&csi=true&lh=true&st=k8s"
 spec:
+  selector:
+    matchLabels:
+      name: portworx
   minReadySeconds: 0
   updateStrategy:
     type: RollingUpdate
@@ -159,28 +329,20 @@ spec:
                 operator: DoesNotExist
       hostNetwork: true
       hostPID: false
-      initContainers:
-        - name: checkloop
-          image: alpine
-          command: [ "sh", "-c" ]
-          args:
-            - |
-              if ! grep -q loop4 /proc/partitions; then
-                echo 'Could not find "loop4" in /proc/partitions. Please create it first.'
-                exit 1
-              fi
       containers:
         - name: portworx
-          image: portworx/oci-monitor:2.1.3
+          image: portworx/oci-monitor:2.3.2
           imagePullPolicy: Always
           args:
-            ["-c", "px-workshop", "-s", "/dev/loop4", "-secret_type", "k8s", "-b", 
+            ["-c", "px-workshop", "-s", "/dev/loop4", "-secret_type", "k8s", "-j", "auto", "-b", 
              "-x", "kubernetes"]
           env:
             - name: "AUTO_NODE_RECOVERY_TIMEOUT_IN_SECS"
               value: "1500"
             - name: "PX_TEMPLATE_VERSION"
               value: "v4"
+            - name: CSI_ENDPOINT 
+              value: unix:///var/lib/kubelet/plugins/pxd.portworx.com/csi.sock
             
           livenessProbe:
             periodSeconds: 30
@@ -211,6 +373,10 @@ spec:
               mountPath: /etc/crictl.yaml
             - name: etcpwx
               mountPath: /etc/pwx
+            - name: dev
+              mountPath: /dev
+            - name: csi-driver-path
+              mountPath: /var/lib/kubelet/plugins/pxd.portworx.com
             - name: optpwx
               mountPath: /opt/pwx
             - name: procmount
@@ -225,6 +391,27 @@ spec:
               readOnly: true
             - name: dbusmount
               mountPath: /var/run/dbus
+        - name: csi-node-driver-registrar
+          image: quay.io/k8scsi/csi-node-driver-registrar:v1.1.0
+          args:
+            - "--v=5"
+            - "--csi-address=$(ADDRESS)"
+            - "--kubelet-registration-path=/var/lib/kubelet/plugins/pxd.portworx.com/csi.sock"
+          imagePullPolicy: Always
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+            - name: KUBE_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          securityContext:
+            privileged: true
+          volumeMounts:
+            - name: csi-driver-path
+              mountPath: /csi
+            - name: registration-dir
+              mountPath: /registration
       restartPolicy: Always
       serviceAccountName: px-account
       volumes:
@@ -247,6 +434,17 @@ spec:
         - name: etcpwx
           hostPath:
             path: /etc/pwx
+        - name: dev
+          hostPath:
+            path: /dev
+        - name: registration-dir
+          hostPath:
+            path: /var/lib/kubelet/plugins_registry
+            type: DirectoryOrCreate
+        - name: csi-driver-path
+          hostPath:
+            path: /var/lib/kubelet/plugins/pxd.portworx.com
+            type: DirectoryOrCreate
         - name: optpwx
           hostPath:
             path: /opt/pwx
@@ -266,6 +464,172 @@ spec:
           hostPath:
             path: /var/run/dbus
 ---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: px-csi-account
+  namespace: kube-system
+---
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+   name: px-csi-role
+rules:
+- apiGroups: ["extensions"]
+  resources: ["podsecuritypolicies"]
+  resourceNames: ["privileged"]
+  verbs: ["use"]
+- apiGroups: ["apiextensions.k8s.io"]
+  resources: ["customresourcedefinitions"]
+  verbs: ["*"]
+- apiGroups: [""]
+  resources: ["nodes"]
+  verbs: ["get", "list", "watch"]
+- apiGroups: [""]
+  resources: ["persistentvolumes"]
+  verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]
+- apiGroups: [""]
+  resources: ["persistentvolumeclaims"]
+  verbs: ["get", "list", "watch", "update"]
+- apiGroups: [""]
+  resources: ["persistentvolumeclaims/status"]
+  verbs: ["update", "patch"]
+- apiGroups: ["storage.k8s.io"]
+  resources: ["storageclasses"]
+  verbs: ["get", "list", "watch"]
+- apiGroups: ["storage.k8s.io"]
+  resources: ["volumeattachments"]
+  verbs: ["get", "list", "watch", "update", "patch"]
+- apiGroups: [""]
+  resources: ["events"]
+  verbs: ["list", "watch", "create", "update", "patch"]
+- apiGroups: [""]
+  resources: ["secrets"]
+  verbs: ["get", "list"]
+- apiGroups: ["snapshot.storage.k8s.io"]
+  resources: ["volumesnapshots", "volumesnapshotcontents", "volumesnapshotclasses", "volumesnapshots/status"]
+  verbs: ["create", "get", "list", "watch", "update", "delete"]
+- apiGroups: [""]
+  resources: ["nodes"]
+  verbs: ["get", "list", "watch"]
+- apiGroups: ["storage.k8s.io"]
+  resources: ["csinodes"]
+  verbs: ["get", "list", "watch", "update"]
+- apiGroups: [""]
+  resources: ["nodes"]
+  verbs: ["get", "list", "watch"]
+- apiGroups: ["csi.storage.k8s.io"]
+  resources: ["csidrivers"]
+  verbs: ["create", "delete"]
+- apiGroups: [""]
+  resources: ["endpoints"]
+  verbs: ["get", "watch", "list", "delete", "update", "create"]
+- apiGroups: ["coordination.k8s.io"]
+  resources: ["leases"]
+  verbs: ["*"]
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: px-csi-role-binding
+subjects:
+- kind: ServiceAccount
+  name: px-csi-account
+  namespace: kube-system
+roleRef:
+  kind: ClusterRole
+  name: px-csi-role
+  apiGroup: rbac.authorization.k8s.io
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: px-csi-service
+  namespace: kube-system
+spec:
+  clusterIP: None
+---
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  name: px-csi-ext
+  namespace: kube-system
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: px-csi-driver
+  template:
+    metadata:
+      labels:
+        app: px-csi-driver
+    spec:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+            - matchExpressions:
+              - key: px/enabled
+                operator: NotIn
+                values:
+                - "false"
+              - key: node-role.kubernetes.io/master
+                operator: DoesNotExist
+      serviceAccount: px-csi-account
+      containers:
+        - name: csi-external-provisioner
+          imagePullPolicy: Always
+          image: quay.io/openstorage/csi-provisioner:v1.4.0-1
+          args:
+            - "--v=5"
+            - "--provisioner=pxd.portworx.com"
+            - "--csi-address=$(ADDRESS)"
+            - "--enable-leader-election"
+            - "--leader-election-type=leases"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          securityContext:
+            privileged: true
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+        - name: csi-snapshotter
+          image: quay.io/k8scsi/csi-snapshotter:v2.0.0
+          imagePullPolicy: Always
+          args:
+            - "--v=3"
+            - "--csi-address=$(ADDRESS)"
+            - "--leader-election=true"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          securityContext:
+            privileged: true
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+        - name: csi-resizer
+          imagePullPolicy: Always
+          image: quay.io/k8scsi/csi-resizer:v0.3.0
+          args:
+            - "--v=5"
+            - "--csi-address=$(ADDRESS)"
+            - "--leader-election=true"
+          env:
+            - name: ADDRESS
+              value: /csi/csi.sock
+          securityContext:
+            privileged: true
+          volumeMounts:
+            - name: socket-dir
+              mountPath: /csi
+      volumes:
+        - name: socket-dir
+          hostPath:
+            path: /var/lib/kubelet/plugins/pxd.portworx.com
+            type: DirectoryOrCreate
+---
 kind: Service
 apiVersion: v1
 metadata:
@@ -276,7 +640,7 @@ metadata:
 spec:
   selector:
     name: portworx-api
-  type: NodePort
+  type: ClusterIP
   ports:
     - name: px-api
       protocol: TCP
@@ -291,12 +655,17 @@ spec:
       port: 9021
       targetPort: 9021
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: DaemonSet
 metadata:
   name: portworx-api
   namespace: kube-system
+  labels:
+    name: portworx-api
 spec:
+  selector:
+    matchLabels:
+      name: portworx-api
   minReadySeconds: 0
   updateStrategy:
     type: RollingUpdate
@@ -332,8 +701,14 @@ spec:
               port: 9001
       restartPolicy: Always
       serviceAccountName: px-account
-
-
+---
+apiVersion: storage.k8s.io/v1beta1
+kind: CSIDriver
+metadata:
+  name: pxd.portworx.com
+spec:
+  attachRequired: false
+  podInfoOnMount: false
 ---
 apiVersion: v1
 kind: ConfigMap
@@ -369,48 +744,9 @@ apiVersion: rbac.authorization.k8s.io/v1
 metadata:
    name: stork-role
 rules:
-  - apiGroups: [""]
-    resources: ["pods", "pods/exec"]
-    verbs: ["get", "list", "delete", "create", "watch"]
-  - apiGroups: [""]
-    resources: ["persistentvolumes"]
-    verbs: ["get", "list", "watch", "create", "delete"]
-  - apiGroups: [""]
-    resources: ["persistentvolumeclaims"]
-    verbs: ["get", "list", "watch", "update"]
-  - apiGroups: ["storage.k8s.io"]
-    resources: ["storageclasses"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: [""]
-    resources: ["events"]
-    verbs: ["list", "watch", "create", "update", "patch"]
-  - apiGroups: ["stork.libopenstorage.org"]
-    resources: ["*"]
-    verbs: ["get", "list", "watch", "update", "patch", "create", "delete"]
-  - apiGroups: ["apiextensions.k8s.io"]
-    resources: ["customresourcedefinitions"]
-    verbs: ["create", "get"]
-  - apiGroups: ["volumesnapshot.external-storage.k8s.io"]
-    resources: ["volumesnapshots", "volumesnapshotdatas"]
-    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
-  - apiGroups: [""]
-    resources: ["configmaps"]
-    verbs: ["get", "create", "update"]
-  - apiGroups: [""]
-    resources: ["services"]
-    verbs: ["get"]
-  - apiGroups: [""]
-    resources: ["nodes"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: ["*"]
-    resources: ["deployments", "deployments/extensions"]
-    verbs: ["list", "get", "watch", "patch", "update", "initialize"]
-  - apiGroups: ["*"]
-    resources: ["statefulsets", "statefulsets/extensions"]
-    verbs: ["list", "get", "watch", "patch", "update", "initialize"]
   - apiGroups: ["*"]
     resources: ["*"]
-    verbs: ["list", "get"]
+    verbs: ["*"]
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
@@ -438,7 +774,7 @@ spec:
       port: 8099
       targetPort: 8099
 ---
-apiVersion: extensions/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   annotations:
@@ -448,6 +784,9 @@ metadata:
   name: stork
   namespace: kube-system
 spec:
+  selector:
+    matchLabels:
+      name: stork
   strategy:
     rollingUpdate:
       maxSurge: 1
@@ -470,7 +809,7 @@ spec:
         - --leader-elect=true
         - --health-monitor-interval=120
         imagePullPolicy: Always
-        image: openstorage/stork:2.2.4
+        image: openstorage/stork:2.3.1
         env:
         - name: "PX_SERVICE_NAME"
           value: "portworx-api"
@@ -513,8 +852,8 @@ rules:
     verbs: ["get", "create", "update"]
   - apiGroups: [""]
     resources: ["configmaps"]
-    verbs: ["get"]
-  - apiGroups: [""]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["", "events.k8s.io"]
     resources: ["events"]
     verbs: ["create", "patch", "update"]
   - apiGroups: [""]
@@ -549,8 +888,11 @@ rules:
     resources: ["persistentvolumeclaims", "persistentvolumes"]
     verbs: ["get", "list", "watch"]
   - apiGroups: ["storage.k8s.io"]
-    resources: ["storageclasses"]
+    resources: ["storageclasses", "csinodes"]
     verbs: ["get", "list", "watch"]
+  - apiGroups: ["coordination.k8s.io"]
+    resources: ["leases"]
+    verbs: ["create", "update", "get", "list", "watch"]
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1
@@ -565,7 +907,7 @@ roleRef:
   name: stork-scheduler-role
   apiGroup: rbac.authorization.k8s.io
 ---
-apiVersion: apps/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   labels:
@@ -575,12 +917,16 @@ metadata:
   name: stork-scheduler
   namespace: kube-system
 spec:
+  selector:
+    matchLabels:
+      name: stork-scheduler
   replicas: 3
   template:
     metadata:
       labels:
         component: scheduler
         tier: control-plane
+        name: stork-scheduler
       name: stork-scheduler
     spec:
       containers:
@@ -592,7 +938,7 @@ spec:
         - --policy-configmap=stork-config
         - --policy-configmap-namespace=kube-system
         - --lock-object-name=stork-scheduler
-        image: gcr.io/google_containers/kube-scheduler-amd64:v1.15.2
+        image: gcr.io/google_containers/kube-scheduler-amd64:v1.17.1
         livenessProbe:
           httpGet:
             path: /healthz
@@ -694,7 +1040,7 @@ spec:
   selector:
     tier: px-web-console
 ---
-apiVersion: apps/v1beta1
+apiVersion: apps/v1
 kind: Deployment
 metadata:
   name: px-lighthouse
@@ -702,6 +1048,9 @@ metadata:
   labels:
     tier: px-web-console
 spec:
+  selector:
+    matchLabels:
+      tier: px-web-console
   strategy:
     rollingUpdate:
       maxSurge: 1
@@ -718,7 +1067,7 @@ spec:
     spec:
       initContainers:
       - name: config-init
-        image: portworx/lh-config-sync:0.4
+        image: portworx/lh-config-sync:2.0.5
         imagePullPolicy: Always
         args:
         - "init"
@@ -727,7 +1076,7 @@ spec:
           mountPath: /config/lh
       containers:
       - name: px-lighthouse
-        image: portworx/px-lighthouse:2.0.4
+        image: portworx/px-lighthouse:2.0.6
         imagePullPolicy: Always
         args: [ "-kubernetes", "true" ]
         ports:
@@ -737,7 +1086,7 @@ spec:
         - name: config
           mountPath: /config/lh
       - name: config-sync
-        image: portworx/lh-config-sync:0.4
+        image: portworx/lh-config-sync:2.0.5
         imagePullPolicy: Always
         args:
         - "sync"
@@ -745,9 +1094,23 @@ spec:
         - name: config
           mountPath: /config/lh
       - name: stork-connector
-        image: portworx/lh-stork-connector:0.2
+        image: portworx/lh-stork-connector:2.0.5
         imagePullPolicy: Always
       serviceAccountName: px-lh-account
       volumes:
       - name: config
         emptyDir: {}
+---
+# That one is an extra.
+# Create a default Storage Class to simplify Portworx setup.
+kind: StorageClass
+apiVersion: storage.k8s.io/v1beta1
+metadata:
+  name: portworx-replicated
+  annotations:
+    storageclass.kubernetes.io/is-default-class: "true"
+provisioner: kubernetes.io/portworx-volume
+parameters:
+ repl: "2"
+ priority_io: "high"
+

k8s/postgres.yaml

@@ -12,7 +12,14 @@ 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:11

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

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
@@ -25,7 +25,7 @@ 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:
@@ -38,6 +38,7 @@ Virtualbox, Vagrant and Ansible
 
 
 ## 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

@@ -10,15 +10,21 @@ These tools can help you to create VMs on:
 
 - [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
 
@@ -87,26 +93,37 @@ You're all set!
 ```
 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 group 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 groups 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 group of VMs
-start        Start a group of VMs
-status       List instance status for a given group
-stop         Stop (terminate, shutdown, kill, remove, destroy...) instances
-test         Run tests (pre-flight checks) on a group 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
@@ -245,3 +262,32 @@ If you don't have `wkhtmltopdf` installed, you will get a warning that it is a m
 
   - 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/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/lib/commands.sh

@@ -127,11 +127,11 @@ _cmd_kubebins() {
     set -e
     cd /usr/local/bin
     if ! [ -x etcd ]; then
-        curl -L https://github.com/etcd-io/etcd/releases/download/v3.3.10/etcd-v3.3.10-linux-amd64.tar.gz \
+        curl -L https://github.com/etcd-io/etcd/releases/download/v3.3.15/etcd-v3.3.15-linux-amd64.tar.gz \
         | sudo tar --strip-components=1 --wildcards -zx '*/etcd' '*/etcdctl'
     fi
     if ! [ -x hyperkube ]; then
-        curl -L https://dl.k8s.io/v1.14.1/kubernetes-server-linux-amd64.tar.gz \
+        curl -L https://dl.k8s.io/v1.16.2/kubernetes-server-linux-amd64.tar.gz \
         | sudo tar --strip-components=3 -zx kubernetes/server/bin/hyperkube
     fi
     if ! [ -x kubelet ]; then
@@ -143,7 +143,7 @@ _cmd_kubebins() {
     sudo mkdir -p /opt/cni/bin
     cd /opt/cni/bin
     if ! [ -x bridge ]; then
-        curl -L https://github.com/containernetworking/plugins/releases/download/v0.7.5/cni-plugins-amd64-v0.7.5.tgz \
+        curl -L https://github.com/containernetworking/plugins/releases/download/v0.7.6/cni-plugins-amd64-v0.7.6.tgz \
         | sudo tar -zx
     fi
     "
@@ -157,10 +157,10 @@ _cmd_kube() {
     # Optional version, e.g. 1.13.5
     KUBEVERSION=$2
     if [ "$KUBEVERSION" ]; then
-        EXTRA_KUBELET="=$KUBEVERSION-00"
+        EXTRA_APTGET="=$KUBEVERSION-00"
         EXTRA_KUBEADM="--kubernetes-version=v$KUBEVERSION"
     else
-        EXTRA_KUBELET=""
+        EXTRA_APTGET=""
         EXTRA_KUBEADM=""
     fi
 
@@ -172,7 +172,7 @@ _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$EXTRA_KUBELET kubeadm kubectl &&
+    sudo apt-get install -qy kubelet$EXTRA_APTGET kubeadm$EXTRA_APTGET kubectl$EXTRA_APTGET &&
     kubectl completion bash | sudo tee /etc/bash_completion.d/kubectl"
 
     # Initialize kube master
@@ -242,7 +242,7 @@ EOF"
     # 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"
 
@@ -323,6 +323,15 @@ _cmd_listall() {
     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
@@ -362,6 +371,16 @@ _cmd_opensg() {
     infra_opensg
 }
 
+_cmd portworx "Prepare the nodes for Portworx deployment"
+_cmd_portworx() {
+    TAG=$1
+    need_tag
+
+    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
@@ -386,6 +405,20 @@ _cmd_pull_images() {
     pull_tag
 }
 
+_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
@@ -441,7 +474,7 @@ _cmd_start() {
     need_infra $INFRA
 
     if [ -z "$TAG" ]; then
-        TAG=$(make_tag)
+        TAG=$(_cmd_maketag)
     fi
     mkdir -p tags/$TAG
     ln -s ../../$INFRA tags/$TAG/infra.sh
@@ -503,20 +536,24 @@ _cmd_test() {
     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=$1
     need_tag
     pssh "
     if i_am_first_node; then
-        kubectl -n kube-system get serviceaccount helm ||
-            kubectl -n kube-system create serviceaccount helm
-        sudo -u docker -H helm init --service-account helm
-        kubectl get clusterrolebinding helm-can-do-everything ||
-            kubectl create clusterrolebinding helm-can-do-everything \
-                --clusterrole=cluster-admin \
-                --serviceaccount=kube-system:helm
-        sudo -u docker -H helm upgrade --install prometheus stable/prometheus \
+        sudo -u docker -H helm repo add stable https://kubernetes-charts.storage.googleapis.com/
+        sudo -u docker -H helm install prometheus stable/prometheus \
             --namespace kube-system \
             --set server.service.type=NodePort \
             --set server.service.nodePort=30090 \
@@ -582,7 +619,7 @@ _cmd_www() {
         echo "http://$IPADDR:8000/$F"
     done
     info "Press Ctrl-C to stop server."
-    python -m http.server
+    python3 -m http.server
 }
 
 greet() {
@@ -703,10 +740,3 @@ sync_keys() {
         info "Using existing key $AWS_KEY_NAME."
     fi
 }
-
-make_tag() {
-    if [ -z $USER ]; then
-        export USER=anonymous
-    fi
-    date +%Y-%m-%d-%H-%M-$USER
-}

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

@@ -4,17 +4,12 @@ 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)))
@@ -30,7 +25,9 @@ while ips:
     ips = ips[clustersize:]
     clusters.append(cluster)
 
-template_file_name = SETTINGS["cards_template"]
+context["clusters"] = clusters
+
+template_file_name = context["cards_template"]
 template_file_path = os.path.join(
     os.path.dirname(__file__),
     "..",
@@ -39,18 +36,19 @@ template_file_path = os.path.join(
     )
 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
     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": context["paper_size"],
+            "margin-top": context["paper_margin"],
+            "margin-bottom": context["paper_margin"],
+            "margin-left": context["paper_margin"],
+            "margin-right": context["paper_margin"],
             })
     print("Generated ips.pdf")
 except ImportError:

prepare-vms/lib/postprep.py

@@ -73,8 +73,29 @@ 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
@@ -85,6 +106,7 @@ 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")
+system("sudo apt-get -qy install emacs-nox joe")
 
 #######################
 ### DOCKER INSTALLS ###

prepare-vms/settings/admin-dmuc.yaml

@@ -26,3 +26,5 @@ machine_version: 0.14.0
 
 # Password used to connect with the "docker user"
 docker_user_password: training
+
+image:

prepare-vms/settings/admin-kubenet.yaml

@@ -26,3 +26,6 @@ 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

@@ -26,3 +26,6 @@ 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

@@ -26,3 +26,5 @@ machine_version: 0.14.0
 
 # Password used to connect with the "docker user"
 docker_user_password: training
+
+image:

prepare-vms/settings/jerome.yaml

@@ -26,4 +26,3 @@ machine_version: 0.14.0
 
 # Password used to connect with the "docker user"
 docker_user_password: training
-

prepare-vms/setup-admin-clusters.sh

@@ -61,6 +61,6 @@ TAG=$PREFIX-$SETTINGS
 	--count $((3*$STUDENTS))
 
 ./workshopctl deploy $TAG
-./workshopctl kube $TAG 1.13.5
+./workshopctl kube $TAG 1.14.6
 ./workshopctl cards $TAG
 

prepare-vms/templates/cards.html

@@ -1,12 +1,23 @@
-{# Feel free to customize or override anything in there! #}
+{#
+   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 = "http://FIXME.container.training/" -%}
-{%- set pagesize = 9 -%}
-{%- set lang = "en" -%}
-{%- set event = "training session" -%}
-{%- set backside = False -%}
-{%- set image = "kube" -%}
-{%- set clusternumber = 100 -%}
+{%- 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) -%}
 
 {%- set image_src = {
 	"docker": "https://s3-us-west-2.amazonaws.com/www.breadware.com/integrations/docker.png",
@@ -161,7 +172,9 @@ img.kube {
     <div>
         <p>{{ intro }}</p>
         <p>
+            {% if image_src %}
             <img src="{{ image_src }}" />
+            {% endif %}
             <table>
             	{% if clusternumber != None %}
 	            <tr><td>cluster:</td></tr>
@@ -187,8 +200,10 @@ img.kube {
         </p>
 
         <p>
+            {% if url %}
         	{{ slides_are_at }}
             <center>{{ url }}</center>
+            {% endif %}
         </p>
     </div>
     {% if loop.index%pagesize==0 or loop.last %}

slides/Dockerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.9
-RUN apk add --no-cache entr py-pip git
+FROM alpine:3.11
+RUN apk add --no-cache entr py3-pip git zip
 COPY requirements.txt .
-RUN pip install -r requirements.txt
+RUN pip3 install -r requirements.txt

slides/_redirects

@@ -1,7 +1,10 @@
 # Uncomment and/or edit one of the the following lines if necessary.
 #/ /kube-halfday.yml.html 200
-/ /intro-fullday.yml.html 200!
-#/ /kube-twodays.yml.html 200
+#/ /kube-fullday.yml.html 200
+/ /kube.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

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 == "/ #":
@@ -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))

slides/build.sh

@@ -14,6 +14,7 @@ once)
       ./appendcheck.py $YAML.html
     done
   fi
+  zip -qr slides.zip . && echo "Created slides.zip archive."
   ;;
 
 forever)

slides/containers/Container_Engines.md

@@ -104,22 +104,6 @@ like Windows, macOS, Solaris, FreeBSD ...
 
 ---
 
-## rkt
-
-* Compares to `runc`.
-
-* No daemon or API.
-
-* Strong emphasis on security (through privilege separation).
-
-* Networking has to be set up separately (e.g. through CNI plugins).
-
-* Partial image management (pull, but no push).
-
-  (Image build is handled by separate tools.)
-
----
-
 ## CRI-O
 
 * Designed to be used with Kubernetes as a simple, basic runtime.

slides/containers/Init_Systems.md

@@ -0,0 +1,137 @@
+# Init systems and PID 1
+
+In this chapter, we will consider:
+
+- the role of PID 1 in the world of Docker,
+
+- how to avoid some common pitfalls due to the misuse of init systems.
+
+---
+
+## What's an init system?
+
+- On UNIX, the "init system" (or "init" in short) is PID 1.
+
+- It is the first process started by the kernel when the system starts.
+
+- It has multiple responsibilities:
+
+  - start every other process on the machine,
+
+  - reap orphaned zombie processes.
+
+---
+
+class: extra-details
+
+## Orphaned zombie processes ?!?
+
+- When a process exits (or "dies"), it becomes a "zombie".
+
+  (Zombie processes show up in `ps` or `top` with the status code `Z`.)
+
+- Its parent process must *reap* the zombie process.
+
+  (This is done by calling `waitpid()` to retrieve the process' exit status.)
+
+- When a process exits, if it has child processes, these processes are "orphaned."
+
+- They are then re-parented to PID 1, init.
+
+- Init therefore needs to take care of these orphaned processes when they exit.
+
+---
+
+## Don't use init systems in containers
+
+- It's often tempting to use an init system or a process manager.
+
+  (Examples: *systemd*, *supervisord*...)
+
+- Our containers are then called "system containers".
+
+  (By contrast with "application containers".)
+
+- "System containers" are similar to lightweight virtual machines.
+
+- They have multiple downsides:
+
+  - when starting multiple processes, their logs get mixed on stdout,
+
+  - if the application process dies, the container engine doesn't see it.
+
+- Overall, they make it harder to operate troubleshoot containerized apps.
+
+---
+
+## Exceptions and workarounds
+
+- Sometimes, it's convenient to run a real init system like *systemd*.
+
+  (Example: a CI system whose goal is precisely to test an init script or unit file.)
+
+- If we need to run multiple processes: can we use multiple containers?
+
+  (Example: [this Compose file](https://github.com/jpetazzo/container.training/blob/master/compose/simple-k8s-control-plane/docker-compose.yaml) runs multiple processes together.)
+
+- When deploying with Kubernetes:
+
+  - a container belong to a pod,
+
+  - a pod can have multiple containers.
+
+---
+
+## What about these zombie processes?
+
+- Our application runs as PID 1 in the container.
+
+- Our application may or may not be designed to reap zombie processes.
+
+- If our application uses subprocesses and doesn't reap them ...
+
+  ... this can lead to PID exhaustion!
+
+  (Or, more realistically, to a confusing herd of zombie processes.)
+
+- How can we solve this?
+
+---
+
+## Tini to the rescue
+
+- Docker can automatically provide a minimal `init` process.
+
+- This is enabled with `docker run --init ...`
+
+- It uses a small init system ([tini](https://github.com/krallin/tini)) as PID 1:
+
+  - it reaps zombies,
+
+  - it forwards signals,
+
+  - it exits when the child exits.
+
+- It is totally transparent to our application.
+
+- We should use it if our application creates subprocess but doesn't reap them.
+
+---
+
+class: extra-details
+
+## What about Kubernetes?
+
+- Kubernetes does not expose that `--init` option.
+
+- However, we can achieve the same result with [Process Namespace Sharing](https://kubernetes.io/docs/tasks/configure-pod-container/share-process-namespace/).
+
+- When Process Namespace Sharing is enabled, PID 1 will be `pause`.
+
+- That `pause` process takes care of reaping zombies.
+
+- Process Namespace Sharing is available since Kubernetes 1.16.
+
+- If you're using an older version of Kubernetes ...
+
+  ... you might have to add `tini` explicitly to your Docker image.

slides/containers/Installing_Docker.md

@@ -102,29 +102,44 @@ class: extra-details
 
 ---
 
-## Docker Desktop for Mac and Docker Desktop for Windows
+## Docker Desktop
 
-* Special Docker Editions that integrate well with their respective host OS
+* Special Docker edition available for Mac and Windows
 
-* Provide user-friendly GUI to edit Docker configuration and settings
+* Integrates well with the host OS:
 
-* Leverage the host OS virtualization subsystem (e.g. the [Hypervisor API](https://developer.apple.com/documentation/hypervisor) on macOS)
+  * installed like normal user applications on the host
 
-* Installed like normal user applications on the host
+  * provides user-friendly GUI to edit Docker configuration and settings
 
-* Under the hood, they both run a tiny VM (transparent to our daily use)
+* Only support running one Docker VM at a time ...
 
-* Access network resources like normal applications
-  <br/>(and therefore, play better with enterprise VPNs and firewalls)
-
-* Support filesystem sharing through volumes (we'll talk about this later)
-
-* They only support running one Docker VM at a time ...
-  <br/>
   ... but we can use `docker-machine`, the Docker Toolbox, VirtualBox, etc. to get a cluster.
 
 ---
 
+class: extra-details
+
+## Docker Desktop internals
+
+* Leverages the host OS virtualization subsystem
+
+  (e.g. the [Hypervisor API](https://developer.apple.com/documentation/hypervisor) on macOS)
+
+* Under the hood, runs a tiny VM
+
+  (transparent to our daily use)
+
+* Accesses network resources like normal applications
+
+  (and therefore, plays better with enterprise VPNs and firewalls)
+
+* Supports filesystem sharing through volumes
+
+  (we'll talk about this later)
+
+---
+
 ## Running Docker on macOS and Windows
 
 When you execute `docker version` from the terminal:

slides/containers/Pods_Anatomy.md

@@ -0,0 +1,47 @@
+# Container Super-structure
+
+- Multiple orchestration platforms support some kind of container super-structure.
+
+  (i.e., a construct or abstraction bigger than a single container.)
+
+- For instance, on Kubernetes, this super-structure is called a *pod*.
+
+- A pod is a group of containers (it could be a single container, too).
+
+- These containers run together, on the same host.
+
+  (A pod cannot straddle multiple hosts.)
+
+- All the containers in a pod have the same IP address.
+
+- How does that map to the Docker world?
+
+---
+
+class: pic
+
+## Anatomy of a Pod
+
+![Pods](images/kubernetes_pods.svg)
+
+---
+
+## Pods in Docker
+
+- The containers inside a pod share the same network namespace.
+
+  (Just like when using `docker run --net=container:<container_id>` with the CLI.)
+
+- As a result, they can communicate together over `localhost`.
+
+- In addition to "our" containers, the pod has a special container, the *sandbox*.
+
+- That container uses a special image: `k8s.gcr.io/pause`.
+
+  (This is visible when listing containers running on a Kubernetes node.)
+
+- Containers within a pod have independent filesystems.
+
+- They can share directories by using a mechanism called *volumes.*
+
+  (Which is similar to the concept of volumes in Docker.)

slides/containers/Publishing_To_Docker_Hub.md

@@ -100,3 +100,25 @@ class: extra-details
 * In "Build rules" block near page bottom, put `/www` in "Build Context" column (or whichever directory the Dockerfile is in).
 * Click "Save and Build" to build the repository immediately (without waiting for a git push).
 * Subsequent builds will happen automatically, thanks to GitHub hooks.
+
+---
+
+## Building on the fly
+
+- Some services can build images on the fly from a repository
+
+- Example: [ctr.run](https://ctr.run/)
+
+.exercise[
+
+- Use ctr.run to automatically build a container image and run it:
+  ```bash
+  docker run ctr.run/github.com/undefinedlabs/hello-world
+  ```
+
+]
+
+There might be a long pause before the first layer is pulled,
+because the API behind `docker pull` doesn't allow to stream build logs, and there is no feedback during the build.
+
+It is possible to view the build logs by setting up an account on [ctr.run](https://ctr.run/).

slides/containers/links.md

@@ -1 +0,0 @@
-../swarm/links.md

slides/containers/links.md

@@ -0,0 +1,12 @@
+# Links and resources
+
+- [Docker Community Slack](https://community.docker.com/registrations/groups/4316)
+- [Docker Community Forums](https://forums.docker.com/)
+- [Docker Hub](https://hub.docker.com)
+- [Docker Blog](https://blog.docker.com/)
+- [Docker documentation](https://docs.docker.com/)
+- [Docker on StackOverflow](https://stackoverflow.com/questions/tagged/docker)
+- [Docker on Twitter](https://twitter.com/docker)
+- [Play With Docker Hands-On Labs](https://training.play-with-docker.com/)
+
+.footnote[These slides (and future updates) are on → https://container.training/]

slides/images/kubernetes_pods.drawio

@@ -0,0 +1 @@
+<mxfile host="www.draw.io" modified="2019-12-06T15:04:22.728Z" agent="Mozilla/5.0 (X11; Linux x86_64; rv:71.0) Gecko/20100101 Firefox/71.0" etag="zsQLtxL9GRXJF3jcROIq" version="12.3.7" type="device" pages="1"><diagram id="hOpsmMj0j3CSse8MyRSQ" name="Page-1">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</diagram></mxfile>

slides/index.py

@@ -1,5 +1,14 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python3
 # coding: utf-8
+
+FLAGS=dict(
+  cz=u"🇨🇿",
+  de=u"🇩🇪",
+  fr=u"🇫🇷",
+  uk=u"🇬🇧",
+  us=u"🇺🇸",
+)
+
 TEMPLATE="""<html>
 <head>
   <title>{{ title }}</title>
@@ -34,7 +43,7 @@ TEMPLATE="""<html>
 
         {% for item in coming_soon %}
           <tr>
-            <td>{{ item.title }}</td>
+            <td>{{ item.flag }} {{ item.title }}</td>
             <td>{% if item.slides %}<a class="slides" href="{{ item.slides }}" />{% endif %}</td>
             <td>{% if item.attend %}<a class="attend" href="{{ item.attend }}" />
             {% else %}
@@ -123,13 +132,13 @@ TEMPLATE="""<html>
     </table>
   </div>
 </body>
-</html>""".decode("utf-8")
+</html>"""
 
 import datetime
 import jinja2
 import yaml
 
-items = yaml.load(open("index.yaml"))
+items = yaml.safe_load(open("index.yaml"))
 
 # Items with a date correspond to scheduled sessions.
 # Items without a date correspond to self-paced content.
@@ -160,6 +169,7 @@ for item in items:
             item["prettydate"] = date_begin.strftime("%B %d{}, %Y").format(suffix)
         item["begin"] = date_begin
         item["end"] = date_end
+    item["flag"] = FLAGS.get(item.get("country"),"")
 
 today = datetime.date.today()
 coming_soon = [i for i in items if i.get("date") and i["end"] >= today]
@@ -177,10 +187,10 @@ with open("index.html", "w") as f:
     	past_workshops=past_workshops,
     	self_paced=self_paced,
     	recorded_workshops=recorded_workshops
-    	).encode("utf-8"))
+    	))
 
 with open("past.html", "w") as f:
 	f.write(template.render(
 		title="Container Training",
 		all_past_workshops=past_workshops
-		).encode("utf-8"))
+		))

slides/index.yaml

@@ -1,3 +1,66 @@
+- date: 2020-03-06
+  country: uk
+  city: London
+  event: QCON
+  speaker: jpetazzo
+  title: Kubernetes Intensive Course
+  attend: https://qconlondon.com/london2020/workshop/kubernetes-intro
+  #slides: https://qconuk2019.container.training/
+
+- date: 2020-03-05
+  country: uk
+  city: London
+  event: QCON
+  speaker: jpetazzo
+  title: Docker Intensive Course
+  attend: https://qconlondon.com/london2020/workshop/docker-intensive-course
+  #slides: https://qconuk2019.container.training/
+
+- date: 2020-02-03
+  country: fr
+  city: Paris
+  event: ENIX SAS
+  speaker: jpetazzo
+  title: Fondamentaux Conteneurs et Docker (in French)
+  lang: fr
+  attend: https://enix.io/fr/services/formation/
+
+- date: 2020-02-04
+  country: fr
+  city: Paris
+  event: ENIX SAS
+  speaker: jpetazzo
+  title: Fondamentaux Orchestration et Kubernetes (in French)
+  lang: fr
+  attend: https://enix.io/fr/services/formation/
+
+- date: 2020-02-05
+  country: fr
+  city: Paris
+  event: ENIX SAS
+  speaker: jpetazzo
+  title: Kubernetes et Méthodologies DevOps (in French)
+  lang: fr
+  attend: https://enix.io/fr/services/formation/
+
+- date: 2020-02-06
+  country: fr
+  city: Paris
+  event: ENIX SAS
+  speaker: jpetazzo
+  title: Kubernetes Avancé (in French)
+  lang: fr
+  attend: https://enix.io/fr/services/formation/
+
+- date: 2020-02-07
+  country: fr
+  city: Paris
+  event: ENIX SAS
+  speaker: jpetazzo
+  title: Opérer Kubernetes (in French)
+  lang: fr
+  attend: https://enix.io/fr/services/formation/
+
 - date: [2019-11-04, 2019-11-05]
   country: de
   city: Berlin
@@ -5,6 +68,7 @@
   speaker: jpetazzo
   title: Deploying and scaling applications with Kubernetes
   attend: https://conferences.oreilly.com/velocity/vl-eu/public/schedule/detail/79109
+  slides: https://velocity-2019-11.container.training/
 
 - date: 2019-11-13
   country: fr
@@ -15,6 +79,38 @@
   lang: fr
   attend: http://2019.devops-dday.com/Workshop.html
 
+- date: 2019-10-30
+  country: us
+  city: Portland, OR
+  event: LISA
+  speaker: jpetazzo
+  title: Deep Dive into Kubernetes Internals for Builders and Operators
+  attend: https://www.usenix.org/conference/lisa19/presentation/petazzoni-tutorial
+
+- date: [2019-10-22, 2019-10-24]
+  country: us
+  city: Charlotte, NC
+  event: Ardan Labs
+  speaker: jpetazzo
+  title: Kubernetes Training
+  attend: https://www.eventbrite.com/e/containers-docker-and-kubernetes-training-for-devs-and-ops-charlotte-nc-november-2019-tickets-73296659281
+
+- date: 2019-10-22
+  country: us
+  city: Charlotte, NC
+  event: Ardan Labs
+  speaker: jpetazzo
+  title: Docker & Containers Training
+  attend: https://www.eventbrite.com/e/containers-docker-and-kubernetes-training-for-devs-and-ops-charlotte-nc-november-2019-tickets-73296659281
+  
+- date: 2019-10-22
+  country: de
+  city: Berlin
+  event: GOTO
+  speaker: bretfisher
+  title: Kubernetes or Swarm? Build Both, Deploy Apps, Learn The Differences
+  attend: https://gotober.com/2019/workshops/194
+
 - date: [2019-09-24, 2019-09-25]
   country: fr
   city: Paris
@@ -23,6 +119,7 @@
   title: Déployer ses applications avec Kubernetes (in French)
   lang: fr
   attend: https://enix.io/fr/services/formation/deployer-ses-applications-avec-kubernetes/
+  slides: https://kube-2019-09.container.training/
 
 - date: 2019-08-27
   country: tr

slides/intro-fullday.yml

@@ -1,83 +0,0 @@
-title: |
-  Introduction
-  to Containers
-
-chat: "[Slack](https://dockercommunity.slack.com/messages/C7GKACWDV)"
-#chat: "[Gitter](https://gitter.im/jpetazzo/workshop-yyyymmdd-city)"
-
-gitrepo: github.com/jpetazzo/container.training
-
-slides: http://container.training/
-
-exclude:
-- self-paced
-
-chapters:
-- shared/title.md
-- logistics.md
-- containers/intro.md
-- shared/about-slides.md
-- shared/toc.md
-- 
-  - containers/Docker_Overview.md
-  #- containers/Docker_History.md
-  - containers/Training_Environment.md
-  #- containers/Installing_Docker.md
-  - containers/First_Containers.md
-  - containers/Background_Containers.md
-  #- containers/Start_And_Attach.md
-  - containers/Initial_Images.md
-  - containers/Building_Images_Interactively.md
-  - containers/Building_Images_With_Dockerfiles.md
-  - containers/Cmd_And_Entrypoint.md
--
-  - containers/Copying_Files_During_Build.md
-  - containers/Exercise_Dockerfile_Basic.md
-  - containers/Multi_Stage_Builds.md
-  #- containers/Publishing_To_Docker_Hub.md
-  - containers/Exercise_Dockerfile_Advanced.md
-  - containers/Dockerfile_Tips.md
--
-  - containers/Naming_And_Inspecting.md
-  #- containers/Labels.md
-  - containers/Getting_Inside.md
-  - containers/Container_Networking_Basics.md
-  #- containers/Network_Drivers.md
-  - containers/Container_Network_Model.md
-  #- containers/Connecting_Containers_With_Links.md
-  #- containers/Ambassadors.md
-  - containers/Local_Development_Workflow.md
-  #- containers/Windows_Containers.md
-  #- containers/Working_With_Volumes.md
-  - containers/Compose_For_Dev_Stacks.md
-  - containers/Exercise_Composefile.md
-- 
-  #- containers/Docker_Machine.md
-  #- containers/Advanced_Dockerfiles.md
-  #- containers/Ecosystem.md
-  - containers/Orchestration_Overview.md
-  - |
-    # (Insert Infinity content here)
-    
-  - shared/thankyou.md
-  - containers/links.md
-- 
-  - |
-    # (Extra material - intermediary)
-
-  - containers/Application_Configuration.md
-  - containers/Labels.md
-  - containers/Logging.md
-  - containers/Resource_Limits.md
-  - containers/Network_Drivers.md
-  - containers/Windows_Containers.md
-  - containers/Working_With_Volumes.md
--
-  - |
-     # (Extra material - advanced)
-
-  - containers/Advanced_Dockerfiles.md
-  - containers/Namespaces_Cgroups.md
-  - containers/Copy_On_Write.md
-  - containers/Containers_From_Scratch.md
-  - containers/Container_Engines.md

slides/intro-selfpaced.yml

@@ -1,63 +0,0 @@
-title: |
-  Introduction
-  to Containers
-
-chat: "[Slack](https://dockercommunity.slack.com/messages/C7GKACWDV)"
-#chat: "[Gitter](https://gitter.im/jpetazzo/workshop-yyyymmdd-city)"
-
-gitrepo: github.com/jpetazzo/container.training
-
-slides: http://container.training/
-
-exclude:
-- in-person
-
-chapters:
-- shared/title.md
-# - shared/logistics.md
-- containers/intro.md
-- shared/about-slides.md
-- shared/toc.md
-- - containers/Docker_Overview.md
-  - containers/Docker_History.md
-  - containers/Training_Environment.md
-  - containers/Installing_Docker.md
-  - containers/First_Containers.md
-  - containers/Background_Containers.md
-  - containers/Start_And_Attach.md
-- - containers/Initial_Images.md
-  - containers/Building_Images_Interactively.md
-  - containers/Building_Images_With_Dockerfiles.md
-  - containers/Cmd_And_Entrypoint.md
-  - containers/Copying_Files_During_Build.md
-  - containers/Exercise_Dockerfile_Basic.md
-- - containers/Multi_Stage_Builds.md
-  - containers/Publishing_To_Docker_Hub.md
-  - containers/Dockerfile_Tips.md
-  - containers/Exercise_Dockerfile_Advanced.md
-- - containers/Naming_And_Inspecting.md
-  - containers/Labels.md
-  - containers/Getting_Inside.md
-- - containers/Container_Networking_Basics.md
-  - containers/Network_Drivers.md
-  - containers/Container_Network_Model.md
-  #- containers/Connecting_Containers_With_Links.md
-  - containers/Ambassadors.md
-- - containers/Local_Development_Workflow.md
-  - containers/Windows_Containers.md
-  - containers/Working_With_Volumes.md
-  - containers/Compose_For_Dev_Stacks.md
-  - containers/Exercise_Composefile.md
-  - containers/Docker_Machine.md
-- - containers/Advanced_Dockerfiles.md
-  - containers/Application_Configuration.md
-  - containers/Logging.md
-  - containers/Resource_Limits.md
-- - containers/Namespaces_Cgroups.md
-  - containers/Copy_On_Write.md
-  #- containers/Containers_From_Scratch.md
-- - containers/Container_Engines.md
-  - containers/Ecosystem.md
-  - containers/Orchestration_Overview.md
-  - shared/thankyou.md
-  - containers/links.md

slides/k8s/accessinternal.md

@@ -118,9 +118,9 @@ installed and set up `kubectl` to communicate with your cluster.
 <!--
 ```wait Connected to localhost```
 ```keys INFO server```
-```keys ^J```
+```key ^J```
 ```keys QUIT```
-```keys ^J```
+```key ^J```
 -->
 
 - Terminate the port forwarder:

slides/k8s/authn-authz.md

@@ -547,7 +547,7 @@ It's important to note a couple of details in these flags...
 
 - Exit the container with `exit` or `^D`
 
-<!-- ```keys ^D``` -->
+<!-- ```key ^D``` -->
 
 ]
 
@@ -667,17 +667,12 @@ class: extra-details
 
 - For auditing purposes, sometimes we want to know who can perform an action
 
-- There is a proof-of-concept tool by Aqua Security which does exactly that:
+- There are a few tools to help us with that
 
-  https://github.com/aquasecurity/kubectl-who-can
+  - [kubectl-who-can](https://github.com/aquasecurity/kubectl-who-can) by Aqua Security
 
-- This is one way to install it:
-  ```bash
-  docker run --rm -v /usr/local/bin:/go/bin golang \
-         go get -v github.com/aquasecurity/kubectl-who-can
-  ```
+  - [Review Access (aka Rakkess)](https://github.com/corneliusweig/rakkess)
 
-- This is one way to use it:
-  ```bash
-  kubectl-who-can create pods
-  ```
+- Both are available as standalone programs, or as plugins for `kubectl`
+
+  (`kubectl` plugins can be installed and managed with `krew`)

slides/k8s/build-with-docker.md

@@ -109,7 +109,7 @@ spec:
 
 <!--
 ```longwait latest: digest: sha256:```
-```keys ^C```
+```key ^C```
 -->
 
 ]

slides/k8s/build-with-kaniko.md

@@ -174,7 +174,7 @@ spec:
 
 <!--
 ```longwait registry:5000/rng-kaniko:latest:```
-```keys ^C```
+```key ^C```
 -->
 
 ]

slides/k8s/buildshiprun-dockerhub.md

@@ -15,26 +15,3 @@
   - `dockercoins/webui:v0.1`
 
   - `dockercoins/worker:v0.1`
-
----
-
-## Setting `$REGISTRY` and `$TAG`
-
-- In the upcoming exercises and labs, we use a couple of environment variables:
-
-  - `$REGISTRY` as a prefix to all image names
-
-  - `$TAG` as the image version tag
-
-- For example, the worker image is `$REGISTRY/worker:$TAG`
-
-- If you copy-paste the commands in these exercises:
-
-  **make sure that you set `$REGISTRY` and `$TAG` first!**
-
-- For example:
-  ```
-  export REGISTRY=dockercoins TAG=v0.1
-  ```
-
-  (this will expand `$REGISTRY/worker:$TAG` to `dockercoins/worker:v0.1`)

slides/k8s/cluster-upgrade.md

@@ -10,6 +10,8 @@
 
 - Components can be upgraded one at a time without problems
 
+<!-- ##VERSION## -->
+
 ---
 
 ## Checking what we're running
@@ -166,7 +168,7 @@
 
 - Upgrade kubelet:
   ```bash
-  apt install kubelet=1.14.2-00
+  sudo apt install kubelet=1.15.3-00
   ```
 
 ]
@@ -226,7 +228,7 @@
   sudo vim /etc/kubernetes/manifests/kube-apiserver.yaml
   ```
 
-- Look for the `image:` line, and update it to e.g. `v1.14.0`
+- Look for the `image:` line, and update it to e.g. `v1.15.0`
 
 ]
 
@@ -260,14 +262,52 @@
   sudo kubeadm upgrade plan
   ```
 
-  (Note: kubeadm is confused by our manual upgrade of the API server.
-  <br/>It thinks the cluster is running 1.14.0!)
+]
 
-<!-- ##VERSION## -->
+Note 1: kubeadm thinks that our cluster is running 1.15.0.
+<br/>It is confused by our manual upgrade of the API server!
+
+Note 2: kubeadm itself is still version 1.14.6.
+<br/>It doesn't know how to upgrade do 1.15.X.
+
+---
+
+## Upgrading kubeadm
+
+- First things first: we need to upgrade kubeadm
+
+.exercise[
+
+- Upgrade kubeadm:
+  ```
+  sudo apt install kubeadm
+  ```
+
+- Check what kubeadm tells us:
+  ```
+  sudo kubeadm upgrade plan
+  ```
+
+]
+
+Note: kubeadm still thinks that our cluster is running 1.15.0.
+<br/>But at least it knows about version 1.15.X now.
+
+---
+
+## Upgrading the cluster with kubeadm
+
+- Ideally, we should revert our `image:` change
+
+  (so that kubeadm executes the right migration steps)
+
+- Or we can try the upgrade anyway
+
+.exercise[
 
 - Perform the upgrade:
   ```bash
-  sudo kubeadm upgrade apply v1.14.2
+  sudo kubeadm upgrade apply v1.15.3
   ```
 
 ]
@@ -287,8 +327,8 @@
 - Download the configuration on each node, and upgrade kubelet:
   ```bash
     for N in 1 2 3; do
-      ssh test$N sudo kubeadm upgrade node config --kubelet-version v1.14.2
-      ssh test$N sudo apt install kubelet=1.14.2-00
+      ssh test$N sudo kubeadm upgrade node config --kubelet-version v1.15.3
+      ssh test$N sudo apt install kubelet=1.15.3-00
     done
   ```
 ]
@@ -297,7 +337,7 @@
 
 ## Checking what we've done
 
-- All our nodes should now be updated to version 1.14.2
+- All our nodes should now be updated to version 1.15.3
 
 .exercise[
 
@@ -307,3 +347,19 @@
   ```
 
 ]
+
+---
+
+class: extra-details
+
+## Skipping versions
+
+- This example worked because we went from 1.14 to 1.15
+
+- If you are upgrading from e.g. 1.13, you will generally have to go through 1.14 first
+
+- This means upgrading kubeadm to 1.14.X, then using it to upgrade the cluster
+
+- Then upgrading kubeadm to 1.15.X, etc.
+
+- **Make sure to read the release notes before upgrading!**

slides/k8s/concepts-k8s.md

@@ -44,21 +44,37 @@
 
 ## Other things that Kubernetes can do for us
 
-- Basic autoscaling
+- Autoscaling
 
-- Blue/green deployment, canary deployment
+  (straightforward on CPU; more complex on other metrics)
 
-- Long running services, but also batch (one-off) jobs
+- Ressource management and scheduling
 
-- Overcommit our cluster and *evict* low-priority jobs
+  (reserve CPU/RAM for containers; placement constraints)
 
-- Run services with *stateful* data (databases etc.)
+- Advanced rollout patterns
 
-- Fine-grained access control defining *what* can be done by *whom* on *which* resources
+  (blue/green deployment, canary deployment)
 
-- Integrating third party services (*service catalog*)
+---
 
-- Automating complex tasks (*operators*)
+## More things that Kubernetes can do for us
+
+- Batch jobs
+
+  (one-off; parallel; also cron-style periodic execution)
+
+- Fine-grained access control
+
+  (defining *what* can be done by *whom* on *which* resources)
+
+- Stateful services
+
+  (databases, message queues, etc.)
+
+- Automating complex tasks with *operators*
+
+  (e.g. database replication, failover, etc.)
 
 ---
 
@@ -183,6 +199,30 @@ class: extra-details
 
 class: extra-details
 
+## How many nodes should a cluster have?
+
+- There is no particular constraint
+
+  (no need to have an odd number of nodes for quorum)
+
+- A cluster can have zero node
+
+  (but then it won't be able to start any pods)
+
+- For testing and development, having a single node is fine
+
+- For production, make sure that you have extra capacity
+
+  (so that your workload still fits if you lose a node or a group of nodes)
+
+- Kubernetes is tested with [up to 5000 nodes](https://kubernetes.io/docs/setup/best-practices/cluster-large/)
+
+  (however, running a cluster of that size requires a lot of tuning)
+
+---
+
+class: extra-details
+
 ## Do we need to run Docker at all?
 
 No!
@@ -191,11 +231,29 @@ No!
 
 - By default, Kubernetes uses the Docker Engine to run containers
 
-- We could also use `rkt` ("Rocket") from CoreOS
+- We can leverage other pluggable runtimes through the *Container Runtime Interface*
 
-- Or leverage other pluggable runtimes through the *Container Runtime Interface*
+- <del>We could also use `rkt` ("Rocket") from CoreOS</del> (deprecated)
 
-  (like CRI-O, or containerd)
+---
+
+class: extra-details
+
+## Some runtimes available through CRI
+
+- [containerd](https://github.com/containerd/containerd/blob/master/README.md)
+
+  - maintained by Docker, IBM, and community
+  - used by Docker Engine, microk8s, k3s, GKE; also standalone
+  - comes with its own CLI, `ctr`
+
+- [CRI-O](https://github.com/cri-o/cri-o/blob/master/README.md):
+
+  - maintained by Red Hat, SUSE, and community
+  - used by OpenShift and Kubic
+  - designed specifically as a minimal runtime for Kubernetes
+
+- [And more](https://kubernetes.io/docs/setup/production-environment/container-runtimes/)
 
 ---
 
@@ -265,6 +323,48 @@ class: pic
 
 ---
 
+## Scaling
+
+- How would we scale the pod shown on the previous slide?
+
+- **Do** create additional pods
+
+  - each pod can be on a different node
+
+  - each pod will have its own IP address
+
+- **Do not** add more NGINX containers in the pod
+
+  - all the NGINX containers would be on the same node
+
+  - they would all have the same IP address
+    <br/>(resulting in `Address alreading in use` errors)
+
+---
+
+## Together or separate
+
+- Should we put e.g. a web application server and a cache together?
+  <br/>
+  ("cache" being something like e.g. Memcached or Redis)
+
+- Putting them **in the same pod** means:
+
+  - they have to be scaled together
+
+  - they can communicate very efficiently over `localhost`
+
+- Putting them **in different pods** means:
+
+  - they can be scaled separately
+
+  - they must communicate over remote IP addresses
+    <br/>(incurring more latency, lower performance)
+
+- Both scenarios can make sense, depending on our goals
+
+---
+
 ## Credits
 
 - The first diagram is courtesy of Lucas Käldström, in [this presentation](https://speakerdeck.com/luxas/kubeadm-cluster-creation-internals-from-self-hosting-to-upgradability-and-ha)

slides/k8s/configuration.md

@@ -193,7 +193,12 @@
 
 - Best practice: set a memory limit, and pass it to the runtime
 
-  (see [this blog post](https://very-serio.us/2017/12/05/running-jvms-in-kubernetes/) for a detailed example)
+- Note: recent versions of the JVM can do this automatically
+
+  (see [JDK-8146115](https://bugs.java.com/bugdatabase/view_bug.do?bug_id=JDK-8146115))
+  and
+  [this blog post](https://very-serio.us/2017/12/05/running-jvms-in-kubernetes/)
+  for detailed examples)
 
 ---
 

slides/k8s/create-chart.md

@@ -1,114 +0,0 @@
-## Creating a chart
-
-- We are going to show a way to create a *very simplified* chart
-
-- In a real chart, *lots of things* would be templatized
-
-  (Resource names, service types, number of replicas...)
-
-.exercise[
-
-- Create a sample chart:
-  ```bash
-  helm create dockercoins
-  ```
-
-- Move away the sample templates and create an empty template directory:
-  ```bash
-  mv dockercoins/templates dockercoins/default-templates
-  mkdir dockercoins/templates
-  ```
-
-]
-
----
-
-## Exporting the YAML for our application
-
-- The following section assumes that DockerCoins is currently running
-
-.exercise[
-
-- Create one YAML file for each resource that we need:
-  .small[
-  ```bash
-
-	while read kind name; do
-	  kubectl get -o yaml $kind $name > dockercoins/templates/$name-$kind.yaml
-	done <<EOF
-	deployment worker
-	deployment hasher
-	daemonset rng
-	deployment webui
-	deployment redis
-	service hasher
-	service rng
-	service webui
-	service redis
-	EOF
-  ```
-  ]
-
-]
-
----
-
-## Testing our helm chart
-
-.exercise[
-
-- Let's install our helm chart! (`dockercoins` is the path to the chart)
-  ```
-  helm install dockercoins
-  ```
-]
-
---
-
-- Since the application is already deployed, this will fail:<br>
-`Error: release loitering-otter failed: services "hasher" already exists`
-
-- To avoid naming conflicts, we will deploy the application in another *namespace*
-
----
-
-## Switching to another namespace
-
-- We can create a new namespace and switch to it
-
-  (Helm will automatically use the namespace specified in our context)
-
-- We can also tell Helm which namespace to use
-
-.exercise[
-
-- Tell Helm to use a specific namespace:
-  ```bash
-  helm install dockercoins --namespace=magenta
-  ```
-
-]
-
----
-
-## Checking our new copy of DockerCoins
-
-- We can check the worker logs, or the web UI
-
-.exercise[
-
-- Retrieve the NodePort number of the web UI:
-  ```bash
-  kubectl get service webui --namespace=magenta
-  ```
-
-- Open it in a web browser
-
-- Look at the worker logs:
-  ```bash
-  kubectl logs deploy/worker --tail=10 --follow --namespace=magenta
-  ```
-
-]
-
-Note: it might take a minute or two for the worker to start.

slides/k8s/create-more-charts.md

@@ -1,367 +0,0 @@
-# Creating Helm charts
-
-- We are going to create a generic Helm chart
-
-- We will use that Helm chart to deploy DockerCoins
-
-- Each component of DockerCoins will have its own *release*
-
-- In other words, we will "install" that Helm chart multiple times
-
-  (one time per component of DockerCoins)
-
----
-
-## Creating a generic chart
-
-- Rather than starting from scratch, we will use `helm create`
-
-- This will give us a basic chart that we will customize
-
-.exercise[
-
-- Create a basic chart:
-  ```bash
-  cd ~
-  helm create helmcoins
-  ```
-
-]
-
-This creates a basic chart in the directory `helmcoins`.
-
----
-
-## What's in the basic chart?
-
-- The basic chart will create a Deployment and a Service
-
-- Optionally, it will also include an Ingress
-
-- If we don't pass any values, it will deploy the `nginx` image
-
-- We can override many things in that chart
-
-- Let's try to deploy DockerCoins components with that chart!
-
----
-
-## Writing `values.yaml` for our components
-
-- We need to write one `values.yaml` file for each component
-
-  (hasher, redis, rng, webui, worker)
-
-- We will start with the `values.yaml` of the chart, and remove what we don't need
-
-- We will create 5 files:
-
-  hasher.yaml, redis.yaml, rng.yaml, webui.yaml, worker.yaml
-
----
-
-## Getting started
-
-- For component X, we want to use the image dockercoins/X:v0.1
-
-  (for instance, for rng, we want to use the image dockercoins/rng:v0.1)
-
-- Exception: for redis, we want to use the official image redis:latest
-
-.exercise[
-
-- Write minimal YAML files for the 5 components, specifying only the image
-
-]
-
---
-
-*Hint: our YAML files should look like this.*
-
-```yaml
-### rng.yaml
-image:
-  repository: dockercoins/`rng`
-  tag: v0.1
-```
-
----
-
-## Deploying DockerCoins components
-
-- For convenience, let's work in a separate namespace
-
-.exercise[
-
-- Create a new namespace:
-  ```bash
-  kubectl create namespace helmcoins
-  ```
-
-- Switch to that namespace:
-  ```bash
-  kns helmcoins
-  ```
-
-]
-
----
-
-## Deploying the chart
-
-- To install a chart, we can use the following command:
-  ```bash
-  helm install [--name `X`] <chart>
-  ```
-
-- We can also use the following command, which is idempotent:
-  ```bash
-  helm upgrade --install `X` chart
-  ```
-
-.exercise[
-
-- Install the 5 components of DockerCoins:
-  ```bash
-    for COMPONENT in hasher redis rng webui worker; do
-      helm upgrade --install $COMPONENT helmcoins/ --values=$COMPONENT.yaml
-    done
-  ```
-
-]
-
----
-
-## Checking what we've done
-
-- Let's see if DockerCoins is working!
-
-.exercise[
-
-- Check the logs of the worker:
-  ```bash
-  stern worker
-  ```
-
-- Look at the resources that were created:
-  ```bash
-  kubectl get all
-  ```
-
-]
-
-There are *many* issues to fix!
-
----
-
-## Service names
-
-- Our services should be named `rng`, `hasher`, etc., but they are named differently
-
-- Look at the YAML template used for the services
-
-- Does it look like we can override the name of the services?
-
---
-
-- *Yes*, we can use `.Values.nameOverride`
-
-- This means setting `nameOverride` in the values YAML file
-
----
-
-## Setting service names
-
-- Let's add `nameOverride: X` in each values YAML file!
-
-  (where X is hasher, redis, rng, etc.)
-
-.exercise[
-
-- Edit the 5 YAML files to add `nameOverride: X`
-
-- Deploy the updated Chart:
-  ```bash
-    for COMPONENT in hasher redis rng webui worker; do
-      helm upgrade --install $COMPONENT helmcoins/ --values=$COMPONENT.yaml
-    done
-  ```
-  (Yes, this is exactly the same command as before!)
-
-]
-
----
-
-## Checking what we've done
-
-.exercise[
-
-- Check the service names:
-  ```bash
-  kubectl get services
-  ```
-  Great! (We have a useless service for `worker`, but let's ignore it for now.)
-
-- Check the state of the pods:
-  ```bash
-  kubectl get pods
-  ```
-  Not so great... Some pods are *not ready.*
-
-]
-
----
-
-## Troubleshooting pods
-
-- The easiest way to troubleshoot pods is to look at *events*
-
-- We can look at all the events on the cluster (with `kubectl get events`)
-
-- Or we can use `kubectl describe` on the objects that have problems
-
-  (`kubectl describe` will retrieve the events related to the object)
-
-.exercise[
-
-- Check the events for the redis pods:
-  ```bash
-  kubectl describe pod -l app.kubernetes.io/name=redis
-  ```
-
-]
-
-What's going on?
-
----
-
-## Healthchecks
-
-- The default chart defines healthchecks doing HTTP requests on port 80
-
-- That won't work for redis and worker
-
-  (redis is not HTTP, and not on port 80; worker doesn't even listen)
-
---
-
-- We could comment out the healthchecks
-
-- We could also make them conditional
-
-- This sounds more interesting, let's do that!
-
----
-
-## Conditionals
-
-- We need to enclose the healthcheck block with:
-
-  `{{ if CONDITION }}` at the beginning
-
-  `{{ end }}` at the end
-
-- For the condition, we will use `.Values.healthcheck`
-
----
-
-## Updating the deployment template
-
-.exercise[
-
-- Edit `helmcoins/templates/deployment.yaml`
-
-- Before the healthchecks section (it starts with `livenessProbe:`), add:
-
-  `{{ if .Values.healthcheck }}`
-
-- After the healthchecks section (just before `resources:`), add:
-
-  `{{ end }}`
-
-- Edit `hasher.yaml`, `rng.yaml`, `webui.yaml` to add:
-
-  `healthcheck: true`
-
-]
-
----
-
-## Update the deployed charts
-
-- We can now apply the new templates (and the new values)
-
-.exercise[
-
-- Use the same command as earlier to upgrade all five components
-
-- Use `kubectl describe` to confirm that `redis` starts correctly
-
-- Use `kubectl describe` to confirm that `hasher` still has healthchecks
-
-]
-
----
-
-## Is it working now?
-
-- If we look at the worker logs, it appears that the worker is still stuck
-
-- What could be happening?
-
---
-
-- The redis service is not on port 80!
-
-- We need to update the port number in redis.yaml
-
-- We also need to update the port number in deployment.yaml
-
-  (it is hard-coded to 80 there)
-
----
-
-## Setting the redis port
-
-.exercise[
-
-- Edit `redis.yaml` to add:
-  ```yaml
-    service:
-      port: 6379
-  ```
-
-- Edit `helmcoins/templates/deployment.yaml`
-
-- The line with `containerPort` should be:
-  ```yaml
-  containerPort: {{ .Values.service.port }}
-  ```
-
-]
-
----
-
-## Apply changes
-
-- Re-run the for loop to execute `helm upgrade` one more time
-
-- Check the worker logs
-
-- This time, it should be working!
-
----
-
-## Extra steps
-
-- We don't need to create a service for the worker
-
-- We can put the whole service block in a conditional
-
-  (this will require additional changes in other files referencing the service)
-
-- We can set the webui to be a NodePort service
-
-- We can change the number of workers with `replicaCount`
-
-- And much more!

slides/k8s/daemonset.md

@@ -110,20 +110,22 @@
 ```bash vim rng.yml```
 ```wait kind: Deployment```
 ```keys /Deployment```
-```keys ^J```
+```key ^J```
 ```keys cwDaemonSet```
-```keys ^[``` ]
+```key ^[``` ]
 ```keys :wq```
-```keys ^J```
+```key ^J```
 -->
 
 - Save, quit
 
 - Try to create our new resource:
-  ```
+  ```bash
   kubectl apply -f rng.yml
   ```
 
+<!-- ```wait error:``` -->
+
 ]
 
 --
@@ -501,11 +503,11 @@ be any interruption.*
 <!--
 ```wait Please edit the object below```
 ```keys /app: rng```
-```keys ^J```
+```key ^J```
 ```keys noenabled: yes```
-```keys ^[``` ]
+```key ^[``` ]
 ```keys :wq```
-```keys ^J```
+```key ^J```
 -->
 
 ]
@@ -538,19 +540,18 @@ be any interruption.*
 
 .exercise[
 
-- Update the service to add `enabled: "yes"` to its selector:
-  ```bash
-  kubectl edit service rng
-  ```
+- Update the YAML manifest of the service
+
+- Add `enabled: "yes"` to its selector
 
 <!--
 ```wait Please edit the object below```
-```keys /app: rng```
-```keys ^J```
-```keys noenabled: "yes"```
-```keys ^[``` ]
+```keys /yes```
+```key ^J```
+```keys cw"yes"```
+```key ^[``` ]
 ```keys :wq```
-```keys ^J```
+```key ^J```
 -->
 
 ]
@@ -589,16 +590,25 @@ If we did everything correctly, the web UI shouldn't show any change.
   ```bash
   POD=$(kubectl get pod -l app=rng,pod-template-hash -o name)
   kubectl logs --tail 1 --follow $POD
-
   ```
   (We should see a steady stream of HTTP logs)
 
+<!--
+```wait HTTP/1.1```
+```tmux split-pane -v```
+-->
+
 - In another window, remove the label from the pod:
   ```bash
   kubectl label pod -l app=rng,pod-template-hash enabled-
   ```
   (The stream of HTTP logs should stop immediately)
 
+<!--
+```key ^D```
+```key ^C```
+-->
+
 ]
 
 There might be a slight change in the web UI (since we removed a bit

slides/k8s/dashboard.md

@@ -105,6 +105,22 @@ The dashboard will then ask you which authentication you want to use.
 
 ---
 
+## Other dashboards
+
+- [Kube Web View](https://codeberg.org/hjacobs/kube-web-view)
+
+  - read-only dashboard
+
+  - optimized for "troubleshooting and incident response"
+
+  - see [vision and goals](https://kube-web-view.readthedocs.io/en/latest/vision.html#vision) for details
+
+- [Kube Ops View](https://github.com/hjacobs/kube-ops-view)
+
+  - "provides a common operational picture for multiple Kubernetes clusters"
+
+---
+
 # Security implications of `kubectl apply`
 
 - When we do `kubectl apply -f <URL>`, we create arbitrary resources
@@ -156,4 +172,3 @@ The dashboard will then ask you which authentication you want to use.
 - It introduces new failure modes
 
   (for instance, if you try to apply YAML from a link that's no longer valid)
-

slides/k8s/dmuc.md

@@ -481,13 +481,13 @@ docker run alpine echo hello world
 
 .exercise[
 
-- Create the file `kubeconfig.kubelet` with `kubectl`:
+- Create the file `~/.kube/config` with `kubectl`:
   ```bash
-    kubectl --kubeconfig kubeconfig.kubelet config \
+    kubectl config \
             set-cluster localhost --server http://localhost:8080
-    kubectl --kubeconfig kubeconfig.kubelet config \
+    kubectl config \
             set-context localhost --cluster localhost
-    kubectl --kubeconfig kubeconfig.kubelet config \
+    kubectl config \
             use-context localhost
   ```
 
@@ -495,19 +495,7 @@ docker run alpine echo hello world
 
 ---
 
-## All Kubernetes clients can use `kubeconfig`
-
-- The `kubeconfig.kubelet` file has the same format as e.g. `~/.kubeconfig`
-
-- All Kubernetes clients can use a similar file
-
-- The `kubectl config` commands can be used to manipulate these files
-
-- This highlights that kubelet is a "normal" client of the API server
-
----
-
-## Our `kubeconfig.kubelet` file
+## Our `~/.kube/config` file
 
 The file that we generated looks like the one below.
 
@@ -533,9 +521,9 @@ clusters:
 
 .exercise[
 
-- Start kubelet with that `kubeconfig.kubelet` file:
+- Start kubelet with that kubeconfig file:
   ```bash
-  kubelet --kubeconfig kubeconfig.kubelet
+  kubelet --kubeconfig ~/.kube/config
   ```
 
 ]

slides/k8s/dryrun.md

@@ -0,0 +1,211 @@
+# Authoring YAML
+
+- There are various ways to generate YAML with Kubernetes, e.g.:
+
+  - `kubectl run`
+
+  - `kubectl create deployment` (and a few other `kubectl create` variants)
+
+  - `kubectl expose`
+
+- When and why do we need to write our own YAML?
+
+- How do we write YAML from scratch?
+
+---
+
+## The limits of generated YAML
+
+- Many advanced (and even not-so-advanced) features require to write YAML:
+
+  - pods with multiple containers
+
+  - resource limits
+
+  - healthchecks
+
+  - DaemonSets, StatefulSets
+
+  - and more!
+
+- How do we access these features?
+
+---
+
+## We don't have to start from scratch
+
+- Create a resource (e.g. Deployment)
+
+- Dump its YAML with `kubectl get -o yaml ...`
+
+- Edit the YAML
+
+- Use `kubectl apply -f ...` with the YAML file to:
+
+  - update the resource (if it's the same kind)
+
+  - create a new resource (if it's a different kind)
+
+- Or: Use The Docs, Luke
+
+  (the documentation almost always has YAML examples)
+
+---
+
+## Generating YAML without creating resources
+
+- We can use the `--dry-run` option
+
+.exercise[
+
+- Generate the YAML for a Deployment without creating it:
+  ```bash
+  kubectl create deployment web --image nginx --dry-run
+  ```
+
+]
+
+- We can clean up that YAML even more if we want
+
+  (for instance, we can remove the `creationTimestamp` and empty dicts)
+
+---
+
+## Using `--dry-run` with `kubectl apply`
+
+- The `--dry-run` option can also be used with `kubectl apply`
+
+- However, it can be misleading (it doesn't do a "real" dry run)
+
+- Let's see what happens in the following scenario:
+
+  - generate the YAML for a Deployment
+
+  - tweak the YAML to transform it into a DaemonSet
+
+  - apply that YAML to see what would actually be created
+
+---
+
+## The limits of `kubectl apply --dry-run`
+
+.exercise[
+
+- Generate the YAML for a deployment:
+  ```bash
+  kubectl create deployment web --image=nginx -o yaml > web.yaml
+  ```
+
+- Change the `kind` in the YAML to make it a `DaemonSet`:
+  ```bash
+  sed -i s/Deployment/DaemonSet/ web.yaml
+  ```
+
+- Ask `kubectl` what would be applied:
+  ```bash
+  kubectl apply -f web.yaml --dry-run --validate=false -o yaml
+  ```
+
+]
+
+The resulting YAML doesn't represent a valid DaemonSet.
+
+---
+
+## Server-side dry run
+
+- Since Kubernetes 1.13, we can use [server-side dry run and diffs](https://kubernetes.io/blog/2019/01/14/apiserver-dry-run-and-kubectl-diff/)
+
+- Server-side dry run will do all the work, but *not* persist to etcd
+
+  (all validation and mutation hooks will be executed)
+
+.exercise[
+
+- Try the same YAML file as earlier, with server-side dry run:
+  ```bash
+  kubectl apply -f web.yaml --server-dry-run --validate=false -o yaml
+  ```
+
+]
+
+The resulting YAML doesn't have the `replicas` field anymore.
+
+Instead, it has the fields expected in a DaemonSet.
+
+---
+
+## Advantages of server-side dry run
+
+- The YAML is verified much more extensively
+
+- The only step that is skipped is "write to etcd"
+
+- YAML that passes server-side dry run *should* apply successfully
+
+  (unless the cluster state changes by the time the YAML is actually applied)
+
+- Validating or mutating hooks that have side effects can also be an issue
+
+---
+
+## `kubectl diff`
+
+- Kubernetes 1.13 also introduced `kubectl diff`
+
+- `kubectl diff` does a server-side dry run, *and* shows differences
+
+.exercise[
+
+- Try `kubectl diff` on the YAML that we tweaked earlier:
+  ```bash
+  kubectl diff -f web.yaml
+  ```
+
+<!-- ```wait status:``` -->
+
+]
+
+Note: we don't need to specify `--validate=false` here.
+
+---
+
+## Advantage of YAML
+
+- Using YAML (instead of `kubectl run`/`create`/etc.) allows to be *declarative*
+
+- The YAML describes the desired state of our cluster and applications
+
+- YAML can be stored, versioned, archived (e.g. in git repositories)
+
+- To change resources, change the YAML files
+
+  (instead of using `kubectl edit`/`scale`/`label`/etc.)
+
+- Changes can be reviewed before being applied
+
+  (with code reviews, pull requests ...)
+
+- This workflow is sometimes called "GitOps"
+
+  (there are tools like Weave Flux or GitKube to facilitate it)
+
+---
+
+## YAML in practice
+
+- Get started with `kubectl run`/`create`/`expose`/etc.
+
+- Dump the YAML with `kubectl get -o yaml`
+
+- Tweak that YAML and `kubectl apply` it back
+
+- Store that YAML for reference (for further deployments)
+
+- Feel free to clean up the YAML:
+
+  - remove fields you don't know
+
+  - check that it still works!
+
+- That YAML will be useful later when using e.g. Kustomize or Helm

slides/k8s/healthchecks-more.md

@@ -1,41 +1,3 @@
-## Questions to ask before adding healthchecks
-
-- Do we want liveness, readiness, both?
-
-  (sometimes, we can use the same check, but with different failure thresholds)
-
-- Do we have existing HTTP endpoints that we can use?
-
-- Do we need to add new endpoints, or perhaps use something else?
-
-- Are our healthchecks likely to use resources and/or slow down the app?
-
-- Do they depend on additional services?
-
-  (this can be particularly tricky, see next slide)
-
----
-
-## Healthchecks and dependencies
-
-- A good healthcheck should always indicate the health of the service itself
-
-- It should not be affected by the state of the service's dependencies
-
-- Example: a web server requiring a database connection to operate
-
-  (make sure that the healthcheck can report "OK" even if the database is down;
-  <br/>
-  because it won't help us to restart the web server if the issue is with the DB!)
-
-- Example: a microservice calling other microservices
-
-- Example: a worker process
-
-  (these will generally require minor code changes to report health)
-
----
-
 ## Adding healthchecks to an app
 
 - Let's add healthchecks to DockerCoins!
@@ -370,24 +332,4 @@ class: extra-details
 
   (and have gcr.io/pause take care of the reaping)
 
----
-
-## Healthchecks for worker
-
-- Readiness isn't useful
-
-  (because worker isn't a backend for a service)
-
-- Liveness may help us restart a broken worker, but how can we check it?
-
-- Embedding an HTTP server is an option
-
-  (but it has a high potential for unwanted side effects and false positives)
-
-- Using a "lease" file can be relatively easy:
-
-  - touch a file during each iteration of the main loop
-
-  - check the timestamp of that file from an exec probe
-
-- Writing logs (and checking them from the probe) also works
+- Discussion of this in [Video - 10 Ways to Shoot Yourself in the Foot with Kubernetes, #9 Will Surprise You](https://www.youtube.com/watch?v=QKI-JRs2RIE)

slides/k8s/healthchecks.md

@@ -42,9 +42,11 @@
 
   - internal corruption (causing all requests to error)
 
-- If the liveness probe fails *N* consecutive times, the container is killed
+- Anything where our incident response would be "just restart/reboot it"
 
-- *N* is the `failureThreshold` (3 by default)
+.warning[**Do not** use liveness probes for problems that can't be fixed by a restart]
+
+- Otherwise we just restart our pods for no reason, creating useless load
 
 ---
 
@@ -52,7 +54,7 @@
 
 - Indicates if the container is ready to serve traffic
 
-- If a container becomes "unready" (let's say busy!) it might be ready again soon
+- If a container becomes "unready" it might be ready again soon
 
 - If the readiness probe fails:
 
@@ -66,19 +68,79 @@
 
 ## When to use a readiness probe
 
-- To indicate temporary failures
+- To indicate failure due to an external cause
 
-  - the application can only service *N* parallel connections
+  - database is down or unreachable
 
-  - the runtime is busy doing garbage collection or initial data load
+  - mandatory auth or other backend service unavailable
 
-- The container is marked as "not ready" after `failureThreshold` failed attempts
+- To indicate temporary failure or unavailability
 
-  (3 by default)
+  - application can only service *N* parallel connections
 
-- It is marked again as "ready" after `successThreshold` successful attempts
+  - runtime is busy doing garbage collection or initial data load
 
-  (1 by default)
+- For processes that take a long time to start
+
+  (more on that later)
+
+---
+
+## Dependencies
+
+- If a web server depends on a database to function, and the database is down:
+
+  - the web server's liveness probe should succeed
+
+  - the web server's readiness probe should fail
+
+- Same thing for any hard dependency (without which the container can't work)
+
+.warning[**Do not** fail liveness probes for problems that are external to the container]
+
+---
+
+## Timing and thresholds
+
+- Probes are executed at intervals of `periodSeconds` (default: 10)
+
+- The timeout for a probe is set with `timeoutSeconds` (default: 1)
+
+.warning[If a probe takes longer than that, it is considered as a FAIL]
+
+- A probe is considered successful after `successThreshold` successes (default: 1)
+
+- A probe is considered failing after `failureThreshold` failures (default: 3)
+
+- A probe can have an `initialDelaySeconds` parameter (default: 0)
+
+- Kubernetes will wait that amount of time before running the probe for the first time
+
+  (this is important to avoid killing services that take a long time to start)
+
+---
+
+class: extra-details
+
+## Startup probe
+
+- Kubernetes 1.16 introduces a third type of probe: `startupProbe`
+
+  (it is in `alpha` in Kubernetes 1.16)
+
+- It can be used to indicate "container not ready *yet*"
+
+  - process is still starting
+
+  - loading external data, priming caches
+
+- Before Kubernetes 1.16, we had to use the `initialDelaySeconds` parameter
+
+  (available for both liveness and readiness probes)
+
+- `initialDelaySeconds` is a rigid delay (always wait X before running probes)
+
+- `startupProbe` works better when a container start time can vary a lot
 
 ---
 
@@ -112,10 +174,12 @@
 
   (instead of serving errors or timeouts)
 
-- Overloaded backends get removed from load balancer rotation
+- Unavailable backends get removed from load balancer rotation
 
   (thus improving response times across the board)
 
+- If a probe is not defined, it's as if there was an "always successful" probe
+
 ---
 
 ## Example: HTTP probe
@@ -165,14 +229,56 @@ If the Redis process becomes unresponsive, it will be killed.
 
 ---
 
-## Details about liveness and readiness probes
+## Questions to ask before adding healthchecks
 
-- Probes are executed at intervals of `periodSeconds` (default: 10)
+- Do we want liveness, readiness, both?
 
-- The timeout for a probe is set with `timeoutSeconds` (default: 1)
+  (sometimes, we can use the same check, but with different failure thresholds)
 
-- A probe is considered successful after `successThreshold` successes (default: 1)
+- Do we have existing HTTP endpoints that we can use?
 
-- A probe is considered failing after `failureThreshold` failures (default: 3)
+- Do we need to add new endpoints, or perhaps use something else?
 
-- If a probe is not defined, it's as if there was an "always successful" probe
+- Are our healthchecks likely to use resources and/or slow down the app?
+
+- Do they depend on additional services?
+
+  (this can be particularly tricky, see next slide)
+
+---
+
+## Healthchecks and dependencies
+
+- Liveness checks should not be influenced by the state of external services
+
+- All checks should reply quickly (by default, less than 1 second)
+
+- Otherwise, they are considered to fail
+
+- This might require to check the health of dependencies asynchronously
+
+  (e.g. if a database or API might be healthy but still take more than
+  1 second to reply, we should check the status asynchronously and report
+  a cached status)
+
+---
+
+## Healthchecks for workers
+
+(In that context, worker = process that doesn't accept connections)
+
+- Readiness isn't useful
+
+  (because workers aren't backends for a service)
+
+- Liveness may help us restart a broken worker, but how can we check it?
+
+- Embedding an HTTP server is a (potentially expensive) option
+
+- Using a "lease" file can be relatively easy:
+
+  - touch a file during each iteration of the main loop
+
+  - check the timestamp of that file from an exec probe
+
+- Writing logs (and checking them from the probe) also works

slides/k8s/helm-chart-format.md

@@ -0,0 +1,239 @@
+# Helm chart format
+
+- What exactly is a chart?
+
+- What's in it?
+
+- What would be involved in creating a chart?
+
+  (we won't create a chart, but we'll see the required steps)
+
+---
+
+## What is a chart
+
+- A chart is a set of files
+
+- Some of these files are mandatory for the chart to be viable
+
+  (more on that later)
+
+- These files are typically packed in a tarball
+
+- These tarballs are stored in "repos"
+
+  (which can be static HTTP servers)
+
+- We can install from a repo, from a local tarball, or an unpacked tarball
+
+  (the latter option is preferred when developing a chart)
+
+---
+
+## What's in a chart
+
+- A chart must have at least:
+
+  - a `templates` directory, with YAML manifests for Kubernetes resources
+
+  - a `values.yaml` file, containing (tunable) parameters for the chart
+
+  - a `Chart.yaml` file, containing metadata (name, version, description ...)
+
+- Let's look at a simple chart, `stable/tomcat`
+
+---
+
+## Downloading a chart
+
+- We can use `helm pull` to download a chart from a repo
+
+.exercise[
+
+- Download the tarball for `stable/tomcat`:
+  ```bash
+  helm pull stable/tomcat
+  ```
+  (This will create a file named `tomcat-X.Y.Z.tgz`.)
+
+- Or, download + untar `stable/tomcat`:
+  ```bash
+  helm pull stable/tomcat --untar
+  ```
+  (This will create a directory named `tomcat`.)
+
+]
+
+---
+
+## Looking at the chart's content
+
+- Let's look at the files and directories in the `tomcat` chart
+
+.exercise[
+
+- Display the tree structure of the chart we just downloaded:
+  ```bash
+  tree tomcat
+  ```
+
+]
+
+We see the components mentioned above: `Chart.yaml`, `templates/`, `values.yaml`.
+
+---
+
+## Templates
+
+- The `templates/` directory contains YAML manifests for Kubernetes resources
+
+  (Deployments, Services, etc.)
+
+- These manifests can contain template tags
+
+  (using the standard Go template library)
+
+
+.exercise[
+
+- Look at the template file for the tomcat Service resource:
+  ```bash
+  cat tomcat/templates/appsrv-svc.yaml
+  ```
+
+]
+
+---
+
+## Analyzing the template file
+
+- Tags are identified by `{{ ... }}`
+
+- `{{ template "x.y" }}` expands a [named template](https://helm.sh/docs/chart_template_guide/named_templates/#declaring-and-using-templates-with-define-and-template)
+
+  (previously defined with `{{ define "x.y "}}...stuff...{{ end }}`)
+
+- The `.` in `{{ template "x.y" . }}` is the *context* for that named template
+
+  (so that the named template block can access variables from the local context)
+
+- `{{ .Release.xyz }}` refers to [built-in variables](https://helm.sh/docs/chart_template_guide/builtin_objects/) initialized by Helm
+
+  (indicating the chart name, version, whether we are installing or upgrading ...)
+
+- `{{ .Values.xyz }}` refers to tunable/settable [values](https://helm.sh/docs/chart_template_guide/values_files/)
+
+  (more on that in a minute)
+
+---
+
+## Values
+
+- Each chart comes with a
+  [values file](https://helm.sh/docs/chart_template_guide/values_files/)
+
+- It's a YAML file containing a set of default parameters for the chart
+
+- The values can be accessed in templates with e.g. `{{ .Values.x.y }}`
+
+  (corresponding to field `y` in map `x` in the values file)
+
+- The values can be set or overridden when installing or ugprading a chart:
+
+  - with `--set x.y=z` (can be used multiple times to set multiple values)
+
+  - with `--values some-yaml-file.yaml` (set a bunch of values from a file)
+
+- Charts following best practices will have values following specific patterns
+
+  (e.g. having a `service` map allowing to set `service.type` etc.)
+
+---
+
+## Other useful tags
+
+- `{{ if x }} y {{ end }}` allows to include `y` if `x` evaluates to `true`
+
+  (can be used for e.g. healthchecks, annotations, or even an entire resource)
+
+- `{{ range x }} y {{ end }}` iterates over `x`, evaluating `y` each time
+
+  (the elements of `x` are assigned to `.` in the range scope)
+
+- `{{- x }}`/`{{ x -}}` will remove whitespace on the left/right
+
+- The whole [Sprig](http://masterminds.github.io/sprig/) library, with additions:
+
+  `lower` `upper` `quote` `trim` `default` `b64enc` `b64dec` `sha256sum` `indent` `toYaml` ...
+
+---
+
+## Pipelines
+
+- `{{ quote blah }}` can also be expressed as `{{ blah | quote }}`
+
+- With multiple arguments, `{{ x y z }}` can be expressed as `{{ z | x y }}`)
+
+- Example: `{{ .Values.annotations | toYaml | indent 4 }}`
+
+  - transforms the map under `annotations` into a YAML string
+
+  - indents it with 4 spaces (to match the surrounding context)
+
+- Pipelines are not specific to Helm, but a feature of Go templates
+
+  (check the [Go text/template documentation](https://golang.org/pkg/text/template/) for more details and examples)
+
+---
+
+## README and NOTES.txt
+
+- At the top-level of the chart, it's a good idea to have a README
+
+- It will be viewable with e.g. `helm show readme stable/tomcat`
+
+- In the `templates/` directory, we can also have a `NOTES.txt` file
+
+- When the template is installed (or upgraded), `NOTES.txt` is processed too
+
+  (i.e. its `{{ ... }}` tags are evaluated)
+
+- It gets displayed after the install or upgrade
+
+- It's a great place to generate messages to tell the user:
+
+  - how to connect to the release they just deployed
+
+  - any passwords or other thing that we generated for them
+
+---
+
+## Additional files
+
+- We can place arbitrary files in the chart (outside of the `templates/` directory)
+
+- They can be accessed in templates with `.Files`
+
+- They can be transformed into ConfigMaps or Secrets with `AsConfig` and `AsSecrets`
+
+  (see [this example](https://helm.sh/docs/chart_template_guide/accessing_files/#configmap-and-secrets-utility-functions) in the Helm docs)
+
+---
+
+## Hooks and tests
+
+- We can define *hooks* in our templates
+
+- Hooks are resources annotated with `"helm.sh/hook": NAME-OF-HOOK`
+
+- Hook names include `pre-install`, `post-install`, `test`, [and much more](https://helm.sh/docs/topics/charts_hooks/#the-available-hooks)
+
+- The resources defined in hooks are loaded at a specific time
+
+- Hook execution is *synchronous*
+
+  (if the resource is a Job or Pod, Helm will wait for its completion)
+
+- This can be use for database migrations, backups, notifications, smoke tests ...
+
+- Hooks named `test` are executed only when running `helm test RELEASE-NAME`

slides/k8s/helm-create-basic-chart.md

@@ -0,0 +1,220 @@
+# Creating a basic chart
+
+- We are going to show a way to create a *very simplified* chart
+
+- In a real chart, *lots of things* would be templatized
+
+  (Resource names, service types, number of replicas...)
+
+.exercise[
+
+- Create a sample chart:
+  ```bash
+  helm create dockercoins
+  ```
+
+- Move away the sample templates and create an empty template directory:
+  ```bash
+  mv dockercoins/templates dockercoins/default-templates
+  mkdir dockercoins/templates
+  ```
+
+]
+
+---
+
+## Exporting the YAML for our application
+
+- The following section assumes that DockerCoins is currently running
+
+- If DockerCoins is not running, see next slide
+
+.exercise[
+
+- Create one YAML file for each resource that we need:
+  .small[
+  ```bash
+
+	while read kind name; do
+	  kubectl get -o yaml $kind $name > dockercoins/templates/$name-$kind.yaml
+	done <<EOF
+	deployment worker
+	deployment hasher
+	daemonset rng
+	deployment webui
+	deployment redis
+	service hasher
+	service rng
+	service webui
+	service redis
+	EOF
+  ```
+  ]
+
+]
+
+---
+
+## Obtaining DockerCoins YAML
+
+- If DockerCoins is not running, we can also obtain the YAML from a public repository
+
+.exercise[
+
+- Clone the kubercoins repository:
+  ```bash
+  git clone https://github.com/jpetazzo/kubercoins
+  ```
+
+- Copy the YAML files to the `templates/` directory:
+  ```bash
+  cp kubercoins/*.yaml dockercoins/templates/
+  ```
+
+]
+
+---
+
+## Testing our helm chart
+
+.exercise[
+
+- Let's install our helm chart!
+  ```
+  helm install helmcoins dockercoins
+  ```
+  (`helmcoins` is the name of the release; `dockercoins` is the local path of the chart)
+
+]
+
+--
+
+- Since the application is already deployed, this will fail:
+```
+Error: rendered manifests contain a resource that already exists.
+Unable to continue with install: existing resource conflict:
+kind: Service, namespace: default, name: hasher
+```
+
+- To avoid naming conflicts, we will deploy the application in another *namespace*
+
+---
+
+## Switching to another namespace
+
+- We need create a new namespace
+
+  (Helm 2 creates namespaces automatically; Helm 3 doesn't anymore)
+
+- We need to tell Helm which namespace to use
+
+.exercise[
+
+- Create a new namespace:
+  ```bash
+  kubectl create namespace helmcoins
+  ```
+
+- Deploy our chart in that namespace:
+  ```bash
+  helm install helmcoins dockercoins --namespace=helmcoins
+  ```
+
+]
+
+---
+
+## Helm releases are namespaced
+
+- Let's try to see the release that we just deployed
+
+.exercise[
+
+- List Helm releases:
+  ```bash
+  helm list
+  ```
+
+]
+
+Our release doesn't show up!
+
+We have to specify its namespace (or switch to that namespace).
+
+---
+
+## Specifying the namespace
+
+- Try again, with the correct namespace
+
+.exercise[
+
+- List Helm releases in `helmcoins`:
+  ```bash
+  helm list --namespace=helmcoins
+  ```
+
+]
+
+---
+
+## Checking our new copy of DockerCoins
+
+- We can check the worker logs, or the web UI
+
+.exercise[
+
+- Retrieve the NodePort number of the web UI:
+  ```bash
+  kubectl get service webui --namespace=helmcoins
+  ```
+
+- Open it in a web browser
+
+- Look at the worker logs:
+  ```bash
+  kubectl logs deploy/worker --tail=10 --follow --namespace=helmcoins
+  ```
+
+]
+
+Note: it might take a minute or two for the worker to start.
+
+---
+
+## Discussion, shortcomings
+
+- Helm (and Kubernetes) best practices recommend to add a number of annotations
+
+  (e.g. `app.kubernetes.io/name`, `helm.sh/chart`, `app.kubernetes.io/instance` ...)
+
+- Our basic chart doesn't have any of these
+
+- Our basic chart doesn't use any template tag
+
+- Does it make sense to use Helm in that case?
+
+- *Yes,* because Helm will:
+
+  - track the resources created by the chart
+
+  - save successive revisions, allowing us to rollback
+
+[Helm docs](https://helm.sh/docs/topics/chart_best_practices/labels/)
+and [Kubernetes docs](https://kubernetes.io/docs/concepts/overview/working-with-objects/common-labels/)
+have details about recommended annotations and labels.
+
+---
+
+## Cleaning up
+
+- Let's remove that chart before moving on
+
+.exercise[
+
+- Delete the release (don't forget to specify the namespace):
+  ```bash
+  helm delete helmcoins --namespace=helmcoins
+  ```
+
+]

slides/k8s/helm-create-better-chart.md

@@ -0,0 +1,579 @@
+# Creating better Helm charts
+
+- We are going to create a chart with the helper `helm create`
+
+- This will give us a chart implementing lots of Helm best practices
+
+  (labels, annotations, structure of the `values.yaml` file ...)
+
+- We will use that chart as a generic Helm chart
+
+- We will use it to deploy DockerCoins
+
+- Each component of DockerCoins will have its own *release*
+
+- In other words, we will "install" that Helm chart multiple times
+
+  (one time per component of DockerCoins)
+
+---
+
+## Creating a generic chart
+
+- Rather than starting from scratch, we will use `helm create`
+
+- This will give us a basic chart that we will customize
+
+.exercise[
+
+- Create a basic chart:
+  ```bash
+  cd ~
+  helm create helmcoins
+  ```
+
+]
+
+This creates a basic chart in the directory `helmcoins`.
+
+---
+
+## What's in the basic chart?
+
+- The basic chart will create a Deployment and a Service
+
+- Optionally, it will also include an Ingress
+
+- If we don't pass any values, it will deploy the `nginx` image
+
+- We can override many things in that chart
+
+- Let's try to deploy DockerCoins components with that chart!
+
+---
+
+## Writing `values.yaml` for our components
+
+- We need to write one `values.yaml` file for each component
+
+  (hasher, redis, rng, webui, worker)
+
+- We will start with the `values.yaml` of the chart, and remove what we don't need
+
+- We will create 5 files:
+
+  hasher.yaml, redis.yaml, rng.yaml, webui.yaml, worker.yaml
+
+- In each file, we want to have:
+  ```yaml
+    image:
+      repository: IMAGE-REPOSITORY-NAME
+      tag: IMAGE-TAG
+  ```
+
+---
+
+## Getting started
+
+- For component X, we want to use the image dockercoins/X:v0.1
+
+  (for instance, for rng, we want to use the image dockercoins/rng:v0.1)
+
+- Exception: for redis, we want to use the official image redis:latest
+
+.exercise[
+
+- Write YAML files for the 5 components, with the following model:
+  ```yaml
+    image:
+      repository: `IMAGE-REPOSITORY-NAME` (e.g. dockercoins/worker)
+      tag: `IMAGE-TAG` (e.g. v0.1)
+  ```
+
+]
+
+---
+
+## Deploying DockerCoins components
+
+- For convenience, let's work in a separate namespace
+
+.exercise[
+
+- Create a new namespace (if it doesn't already exist):
+  ```bash
+  kubectl create namespace helmcoins
+  ```
+
+- Switch to that namespace:
+  ```bash
+  kns helmcoins
+  ```
+
+]
+
+---
+
+## Deploying the chart
+
+- To install a chart, we can use the following command:
+  ```bash
+  helm install COMPONENT-NAME CHART-DIRECTORY
+  ```
+
+- We can also use the following command, which is idempotent:
+  ```bash
+  helm upgrade COMPONENT-NAME CHART-DIRECTORY --install
+  ```
+
+.exercise[
+
+- Install the 5 components of DockerCoins:
+  ```bash
+    for COMPONENT in hasher redis rng webui worker; do
+      helm upgrade $COMPONENT helmcoins --install --values=$COMPONENT.yaml
+    done
+  ```
+
+]
+
+---
+
+## Checking what we've done
+
+- Let's see if DockerCoins is working!
+
+.exercise[
+
+- Check the logs of the worker:
+  ```bash
+  stern worker
+  ```
+
+- Look at the resources that were created:
+  ```bash
+  kubectl get all
+  ```
+
+]
+
+There are *many* issues to fix!
+
+---
+
+## Can't pull image
+
+- It looks like our images can't be found
+
+.exercise[
+
+- Use `kubectl describe` on any of the pods in error
+
+]
+
+- We're trying to pull `rng:1.16.0` instead of `rng:v0.1`!
+
+- Where does that `1.16.0` tag come from?
+
+---
+
+## Inspecting our template
+
+- Let's look at the `templates/` directory
+
+  (and try to find the one generating the Deployment resource)
+
+.exercise[
+
+- Show the structure of the `helmcoins` chart that Helm generated:
+  ```bash
+  tree helmcoins
+  ```
+
+- Check the file `helmcoins/templates/deployment.yaml`
+
+- Look for the `image:` parameter
+
+]
+
+*The image tag references `{{ .Chart.AppVersion }}`. Where does that come from?*
+
+---
+
+## The `.Chart` variable
+
+- `.Chart` is a map corresponding to the values in `Chart.yaml`
+
+- Let's look for `AppVersion` there!
+
+.exercise[
+
+- Check the file `helmcoins/Chart.yaml`
+
+- Look for the `appVersion:` parameter
+
+]
+
+(Yes, the case is different between the template and the Chart file.)
+
+---
+
+## Using the correct tags
+
+- If we change `AppVersion` to `v0.1`, it will change for *all* deployments
+
+  (including redis)
+
+- Instead, let's change the *template* to use `{{ .Values.image.tag }}`
+
+  (to match what we've specified in our values YAML files)
+
+.exercise[
+
+- Edit `helmcoins/templates/deployment.yaml`
+
+- Replace `{{ .Chart.AppVersion }}` with `{{ .Values.image.tag }}`
+
+]
+
+---
+
+## Upgrading to use the new template
+
+- Technically, we just made a new version of the *chart*
+
+- To use the new template, we need to *upgrade* the release to use that chart
+
+.exercise[
+
+- Upgrade all components:
+  ```bash
+    for COMPONENT in hasher redis rng webui worker; do
+      helm upgrade $COMPONENT helmcoins
+    done
+  ```
+
+- Check how our pods are doing:
+  ```bash
+  kubectl get pods
+  ```
+
+]
+
+We should see all pods "Running". But ... not all of them are READY.
+
+---
+
+## Troubleshooting readiness
+
+- `hasher`, `rng`, `webui` should show up as `1/1 READY`
+
+- But `redis` and `worker` should show up as `0/1 READY`
+
+- Why?
+
+---
+
+## Troubleshooting pods
+
+- The easiest way to troubleshoot pods is to look at *events*
+
+- We can look at all the events on the cluster (with `kubectl get events`)
+
+- Or we can use `kubectl describe` on the objects that have problems
+
+  (`kubectl describe` will retrieve the events related to the object)
+
+.exercise[
+
+- Check the events for the redis pods:
+  ```bash
+  kubectl describe pod -l app.kubernetes.io/name=redis
+  ```
+
+]
+
+It's failing both its liveness and readiness probes!
+
+---
+
+## Healthchecks
+
+- The default chart defines healthchecks doing HTTP requests on port 80
+
+- That won't work for redis and worker
+
+  (redis is not HTTP, and not on port 80; worker doesn't even listen)
+
+--
+
+- We could remove or comment out the healthchecks
+
+- We could also make them conditional
+
+- This sounds more interesting, let's do that!
+
+---
+
+## Conditionals
+
+- We need to enclose the healthcheck block with:
+
+  `{{ if false }}` at the beginning (we can change the condition later)
+
+  `{{ end }}` at the end
+
+.exercise[
+
+- Edit `helmcoins/templates/deployment.yaml`
+
+- Add `{{ if false }}` on the line before `livenessProbe`
+
+- Add `{{ end }}` after the `readinessProbe` section
+
+  (see next slide for details)
+
+]
+
+---
+
+This is what the new YAML should look like (added lines in yellow):
+
+```yaml
+        ports:
+          - name: http
+            containerPort: 80
+            protocol: TCP
+        `{{ if false }}`
+        livenessProbe:
+          httpGet:
+            path: /
+            port: http
+        readinessProbe:
+          httpGet:
+            path: /
+            port: http
+        `{{ end }}`
+        resources:
+          {{- toYaml .Values.resources | nindent 12 }}
+```
+
+---
+
+## Testing the new chart
+
+- We need to upgrade all the services again to use the new chart
+
+.exercise[
+
+- Upgrade all components:
+  ```bash
+    for COMPONENT in hasher redis rng webui worker; do
+      helm upgrade $COMPONENT helmcoins
+    done
+  ```
+
+- Check how our pods are doing:
+  ```bash
+  kubectl get pods
+  ```
+
+]
+
+Everything should now be running!
+
+---
+
+## What's next?
+
+- Is this working now?
+
+.exercise[
+
+- Let's check the logs of the worker:
+  ```bash
+  stern worker
+  ```
+
+]
+
+This error might look familiar ... The worker can't resolve `redis`.
+
+Typically, that error means that the `redis` service doesn't exist.
+
+---
+
+## Checking services
+
+- What about the services created by our chart?
+
+.exercise[
+
+- Check the list of services:
+  ```bash
+  kubectl get services
+  ```
+
+]
+
+They are named `COMPONENT-helmcoins` instead of just `COMPONENT`.
+
+We need to change that!
+
+---
+
+## Where do the service names come from?
+
+- Look at the YAML template used for the services
+
+- It should be using `{{ include "helmcoins.fullname" }}`
+
+- `include` indicates a *template block* defined somewhere else
+
+.exercise[
+
+- Find where that `fullname` thing is defined:
+  ```bash
+  grep define.*fullname helmcoins/templates/*
+  ```
+
+]
+
+It should be in `_helpers.tpl`.
+
+We can look at the definition, but it's fairly complex ...
+
+---
+
+## Changing service names
+
+- Instead of that `{{ include }}` tag, let's use the name of the release
+
+- The name of the release is available as `{{ .Release.Name }}`
+
+.exercise[
+
+- Edit `helmcoins/templates/service.yaml`
+
+- Replace the service name with `{{ .Release.Name }}`
+
+- Upgrade all the releases to use the new chart
+
+- Confirm that the services now have the right names
+
+]
+
+---
+
+## Is it working now?
+
+- If we look at the worker logs, it appears that the worker is still stuck
+
+- What could be happening?
+
+--
+
+- The redis service is not on port 80!
+
+- Let's see how the port number is set
+
+- We need to look at both the *deployment* template and the *service* template
+
+---
+
+## Service template
+
+- In the service template, we have the following section:
+  ```yaml
+    ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  ```
+
+- `port` is the port on which the service is "listening"
+
+  (i.e. to which our code needs to connect)
+
+- `targetPort` is the port on which the pods are listening
+
+- The `name` is not important (it's OK if it's `http` even for non-HTTP traffic)
+
+---
+
+## Setting the redis port
+
+- Let's add a `service.port` value to the redis release
+
+.exercise[
+
+- Edit `redis.yaml` to add:
+  ```yaml
+    service:
+      port: 6379
+  ```
+
+- Apply the new values file:
+  ```bash
+  helm upgrade redis helmcoins --values=redis.yaml
+  ```
+
+]
+
+---
+
+## Deployment template
+
+- If we look at the deployment template, we see this section:
+  ```yaml
+          ports:
+            - name: http
+              containerPort: 80
+              protocol: TCP
+  ```
+
+- The container port is hard-coded to 80
+
+- We'll change it to use the port number specified in the values
+
+---
+
+## Changing the deployment template
+
+.exercise[  
+
+- Edit `helmcoins/templates/deployment.yaml`
+
+- The line with `containerPort` should be:
+  ```yaml
+  containerPort: {{ .Values.service.port }}
+  ```
+
+]
+
+---
+
+## Apply changes
+
+- Re-run the for loop to execute `helm upgrade` one more time
+
+- Check the worker logs
+
+- This time, it should be working!
+
+---
+
+## Extra steps
+
+- We don't need to create a service for the worker
+
+- We can put the whole service block in a conditional
+
+  (this will require additional changes in other files referencing the service)
+
+- We can set the webui to be a NodePort service
+
+- We can change the number of workers with `replicaCount`
+
+- And much more!

slides/k8s/helm-intro.md

@@ -0,0 +1,419 @@
+# Managing stacks with Helm
+
+- We created our first resources with `kubectl run`, `kubectl expose` ...
+
+- We have also created resources by loading YAML files with `kubectl apply -f`
+
+- For larger stacks, managing thousands of lines of YAML is unreasonable
+
+- These YAML bundles need to be customized with variable parameters
+
+  (E.g.: number of replicas, image version to use ...)
+
+- It would be nice to have an organized, versioned collection of bundles
+
+- It would be nice to be able to upgrade/rollback these bundles carefully
+
+- [Helm](https://helm.sh/) is an open source project offering all these things!
+
+---
+
+## Helm concepts
+
+- `helm` is a CLI tool
+
+- It is used to find, install, upgrade *charts*
+
+- A chart is an archive containing templatized YAML bundles
+
+- Charts are versioned
+
+- Charts can be stored on private or public repositories
+
+---
+
+## Differences between charts and packages
+
+- A package (deb, rpm...) contains binaries, libraries, etc.
+
+- A chart contains YAML manifests
+
+  (the binaries, libraries, etc. are in the images referenced by the chart)
+
+- On most distributions, a package can only be installed once
+
+  (installing another version replaces the installed one)
+
+- A chart can be installed multiple times
+
+- Each installation is called a *release*
+
+- This allows to install e.g. 10 instances of MongoDB
+
+  (with potentially different versions and configurations)
+
+---
+
+class: extra-details
+
+## Wait a minute ...
+
+*But, on my Debian system, I have Python 2 **and** Python 3.
+<br/>
+Also, I have multiple versions of the Postgres database engine!*
+
+Yes!
+
+But they have different package names:
+
+- `python2.7`, `python3.8`
+
+- `postgresql-10`, `postgresql-11`
+
+Good to know: the Postgres package in Debian includes
+provisions to deploy multiple Postgres servers on the
+same system, but it's an exception (and it's a lot of
+work done by the package maintainer, not by the `dpkg`
+or `apt` tools).
+
+---
+
+## Helm 2 vs Helm 3
+
+- Helm 3 was released [November 13, 2019](https://helm.sh/blog/helm-3-released/)
+
+- Charts remain compatible between Helm 2 and Helm 3
+
+- The CLI is very similar (with minor changes to some commands)
+
+- The main difference is that Helm 2 uses `tiller`, a server-side component
+
+- Helm 3 doesn't use `tiller` at all, making it simpler (yay!)
+
+---
+
+class: extra-details
+
+## With or without `tiller`
+
+- With Helm 3:
+
+  - the `helm` CLI communicates directly with the Kubernetes API
+
+  - it creates resources (deployments, services...) with our credentials
+
+- With Helm 2:
+
+  - the `helm` CLI communicates with `tiller`, telling `tiller` what to do
+
+  - `tiller` then communicates with the Kubernetes API, using its own credentials
+
+- This indirect model caused significant permissions headaches
+
+  (`tiller` required very broad permissions to function)
+
+- `tiller` was removed in Helm 3 to simplify the security aspects
+
+---
+
+## Installing Helm
+
+- If the `helm` CLI is not installed in your environment, install it
+
+.exercise[
+
+- Check if `helm` is installed:
+  ```bash
+  helm
+  ```
+
+- If it's not installed, run the following command:
+  ```bash
+  curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get-helm-3 \
+  | bash
+  ```
+
+]
+
+(To install Helm 2, replace `get-helm-3` with `get`.)
+
+---
+
+class: extra-details
+
+## Only if using Helm 2 ...
+
+- We need to install Tiller and give it some permissions
+
+- Tiller is composed of a *service* and a *deployment* in the `kube-system` namespace
+
+- They can be managed (installed, upgraded...) with the `helm` CLI
+
+.exercise[
+
+- Deploy Tiller:
+  ```bash
+  helm init
+  ```
+
+]
+
+At the end of the install process, you will see:
+
+```
+Happy Helming!
+```
+
+---
+
+class: extra-details
+
+## Only if using Helm 2 ...
+
+- Tiller needs permissions to create Kubernetes resources
+
+- In a more realistic deployment, you might create per-user or per-team
+  service accounts, roles, and role bindings
+
+.exercise[
+
+- Grant `cluster-admin` role to `kube-system:default` service account:
+  ```bash
+  kubectl create clusterrolebinding add-on-cluster-admin \
+      --clusterrole=cluster-admin --serviceaccount=kube-system:default
+  ```
+
+
+]
+
+(Defining the exact roles and permissions on your cluster requires
+a deeper knowledge of Kubernetes' RBAC model. The command above is
+fine for personal and development clusters.)
+
+---
+
+## Charts and repositories
+
+- A *repository* (or repo in short) is a collection of charts
+
+- It's just a bunch of files
+
+  (they can be hosted by a static HTTP server, or on a local directory)
+
+- We can add "repos" to Helm, giving them a nickname
+
+- The nickname is used when referring to charts on that repo
+
+  (for instance, if we try to install `hello/world`, that
+  means the chart `world` on the repo `hello`; and that repo
+  `hello` might be something like https://blahblah.hello.io/charts/)
+
+---
+
+## Managing repositories
+
+- Let's check what repositories we have, and add the `stable` repo
+
+  (the `stable` repo contains a set of official-ish charts)
+
+.exercise[
+
+- List our repos:
+  ```bash
+  helm repo list
+  ```
+
+- Add the `stable` repo:
+  ```bash
+  helm repo add stable https://kubernetes-charts.storage.googleapis.com/
+  ```
+
+]
+
+Adding a repo can take a few seconds (it downloads the list of charts from the repo).
+
+It's OK to add a repo that already exists (it will merely update it).
+
+---
+
+## Search available charts
+
+- We can search available charts with `helm search`
+
+- We need to specify where to search (only our repos, or Helm Hub)
+
+- Let's search for all charts mentioning tomcat!
+
+.exercise[
+
+- Search for tomcat in the repo that we added earlier:
+  ```bash
+  helm search repo tomcat
+  ```
+
+- Search for tomcat on the Helm Hub:
+  ```bash
+  helm search hub tomcat
+  ```
+
+]
+
+[Helm Hub](https://hub.helm.sh/) indexes many repos, using the [Monocular](https://github.com/helm/monocular) server.
+
+---
+
+## Charts and releases
+
+- "Installing a chart" means creating a *release*
+
+- We need to name that release
+
+  (or use the `--generate-name` to get Helm to generate one for us)
+
+.exercise[
+
+- Install the tomcat chart that we found earlier:
+  ```bash
+  helm install java4ever stable/tomcat
+  ```
+
+- List the releases:
+  ```bash
+  helm list
+  ```
+
+]
+
+---
+
+class: extra-details
+
+## Searching and installing with Helm 2
+
+- Helm 2 doesn't have support for the Helm Hub
+
+- The `helm search` command only takes a search string argument
+
+  (e.g. `helm search tomcat`)
+
+- With Helm 2, the name is optional:
+
+  `helm install stable/tomcat` will automatically generate a name
+
+  `helm install --name java4ever stable/tomcat` will specify a name
+
+---
+
+## Viewing resources of a release
+
+- This specific chart labels all its resources with a `release` label
+
+- We can use a selector to see these resources
+
+.exercise[
+
+- List all the resources created by this release:
+  ```bash
+  kuectl get all --selector=release=java4ever
+  ```
+
+]
+
+Note: this `release` label wasn't added automatically by Helm.
+<br/>
+It is defined in that chart. In other words, not all charts will provide this label.
+
+---
+
+## Configuring a release
+
+- By default, `stable/tomcat` creates a service of type `LoadBalancer`
+
+- We would like to change that to a `NodePort`
+
+- We could use `kubectl edit service java4ever-tomcat`, but ...
+
+  ... our changes would get overwritten next time we update that chart!
+
+- Instead, we are going to *set a value*
+
+- Values are parameters that the chart can use to change its behavior
+
+- Values have default values
+
+- Each chart is free to define its own values and their defaults
+
+---
+
+## Checking possible values
+
+- We can inspect a chart with `helm show` or `helm inspect`
+
+.exercise[
+
+- Look at the README for tomcat:
+  ```bash
+  helm show readme stable/tomcat
+  ```
+
+- Look at the values and their defaults:
+  ```bash
+  helm show values stable/tomcat
+  ```
+
+]
+
+The `values` may or may not have useful comments.
+
+The `readme` may or may not have (accurate) explanations for the values.
+
+(If we're unlucky, there won't be any indication about how to use the values!)
+
+---
+
+## Setting values
+
+- Values can be set when installing a chart, or when upgrading it
+
+- We are going to update `java4ever` to change the type of the service
+
+.exercise[
+
+- Update `java4ever`:
+  ```bash
+  helm upgrade java4ever stable/tomcat --set service.type=NodePort
+  ```
+
+]
+
+Note that we have to specify the chart that we use (`stable/tomcat`),
+even if we just want to update some values.
+
+We can set multiple values. If we want to set many values, we can use `-f`/`--values` and pass a YAML file with all the values.
+
+All unspecified values will take the default values defined in the chart.
+
+---
+
+## Connecting to tomcat
+
+- Let's check the tomcat server that we just installed
+
+- Note: its readiness probe has a 60s delay
+
+  (so it will take 60s after the initial deployment before the service works)
+
+.exercise[
+
+- Check the node port allocated to the service:
+  ```bash
+  kubectl get service java4ever-tomcat
+  PORT=$(kubectl get service java4ever-tomcat -o jsonpath={..nodePort})
+  ```
+
+- Connect to it, checking the demo app on `/sample/`:
+  ```bash
+  curl localhost:$PORT/sample/
+  ```
+
+]

slides/k8s/helm-secrets.md

@@ -0,0 +1,234 @@
+# Helm secrets
+
+- Helm can do *rollbacks*:
+
+  - to previously installed charts
+
+  - to previous sets of values
+
+- How and where does it store the data needed to do that?
+
+- Let's investigate!
+
+---
+
+## We need a release
+
+- We need to install something with Helm
+
+- Let's use the `stable/tomcat` chart as an example
+
+.exercise[
+
+- Install a release called `tomcat` with the chart `stable/tomcat`:
+  ```bash
+  helm upgrade tomcat stable/tomcat --install
+  ```
+
+- Let's upgrade that release, and change a value:
+  ```bash
+  helm upgrade tomcat stable/tomcat --set ingress.enabled=true
+  ```
+
+]
+
+---
+
+## Release history
+
+- Helm stores successive revisions of each release
+
+.exercise[
+
+- View the history for that release:
+  ```bash
+  helm history tomcat
+  ```
+
+]
+
+Where does that come from?
+
+---
+
+## Investigate
+
+- Possible options:
+
+  - local filesystem (no, because history is visible from other machines)
+
+  - persistent volumes (no, Helm works even without them)
+
+  - ConfigMaps, Secrets?
+
+.exercise[
+
+- Look for ConfigMaps and Secrets:
+  ```bash
+  kuebectl get configmaps,secrets
+  ```
+
+]
+
+--
+
+We should see a number of secrets with TYPE `helm.sh/release.v1`.
+
+---
+
+## Unpacking a secret
+
+- Let's find out what is in these Helm secrets
+
+.exercise[
+
+- Examine the secret corresponding to the second release of `tomcat`:
+  ```bash
+  kubectl describe secret sh.helm.release.v1.tomcat.v2
+  ```
+  (`v1` is the secret format; `v2` means revision 2 of the `tomcat` release)
+
+]
+
+There is a key named `release`.
+
+---
+
+## Unpacking the release data
+
+- Let's see what's in this `release` thing!
+
+.exercise[
+
+- Dump the secret:
+  ```bash
+  kubectl get secret sh.helm.release.v1.tomcat.v2 \
+      -o go-template='{{ .data.release }}'
+  ```
+
+]
+
+Secrets are encoded in base64. We need to decode that!
+
+---
+
+## Decoding base64
+
+- We can pipe the output through `base64 -d` or use go-template's `base64decode`
+
+.exercise[
+
+- Decode the secret:
+  ```bash
+  kubectl get secret sh.helm.release.v1.tomcat.v2 \
+      -o go-template='{{ .data.release | base64decode }}'
+  ```
+
+]
+
+--
+
+... Wait, this *still* looks like base64. What's going on?
+
+--
+
+Let's try one more round of decoding!
+
+---
+
+## Decoding harder
+
+- Just add one more base64 decode filter
+
+.exercise[
+
+- Decode it twice:
+  ```bash
+  kubectl get secret sh.helm.release.v1.tomcat.v2 \
+      -o go-template='{{ .data.release | base64decode | base64decode }}'
+  ```
+
+]
+
+--
+
+... OK, that was *a lot* of binary data. What sould we do with it?
+
+---
+
+## Guessing data type
+
+- We could use `file` to figure out the data type
+
+.exercise[
+
+- Pipe the decoded release through `file -`:
+  ```bash
+  kubectl get secret sh.helm.release.v1.tomcat.v2 \
+      -o go-template='{{ .data.release | base64decode | base64decode }}' \
+      | file -
+  ```
+
+]
+
+--
+
+Gzipped data! It can be decoded with `gunzip -c`.
+
+---
+
+## Uncompressing the data
+
+- Let's uncompress the data and save it to a file
+
+.exercise[
+
+- Rerun the previous command, but with `| gunzip -c > release-info` :
+  ```bash
+  kubectl get secret sh.helm.release.v1.tomcat.v2 \
+      -o go-template='{{ .data.release | base64decode | base64decode }}' \
+      | gunzip -c > release-info
+  ```
+
+- Look at `release-info`:
+  ```bash
+  cat release-info
+  ```
+
+]
+
+--
+
+It's a bundle of ~~YAML~~ JSON.
+
+---
+
+## Looking at the JSON
+
+If we inspect that JSON (e.g. with `jq keys release-info`), we see:
+
+- `chart` (contains the entire chart used for that release)
+- `config` (contains the values that we've set)
+- `info` (date of deployment, status messages)
+- `manifest` (YAML generated from the templates)
+- `name` (name of the release, so `tomcat`)
+- `namespace` (namespace where we deployed the release)
+- `version` (revision number within that release; starts at 1)
+
+The chart is in a structured format, but it's entirely captured in this JSON.
+
+---
+
+## Conclusions
+
+- Helm stores each release information in a Secret in the namespace of the release
+
+- The secret is JSON object (gzipped and encoded in base64)
+
+- It contains the manifests generated for that release
+
+- ... And everything needed to rebuild these manifests
+
+  (including the full source of the chart, and the values used)
+
+- This allows arbitrary rollbacks, as well as tweaking values even without having access to the source of the chart (or the chart repo) used for deployment

slides/k8s/helm.md

@@ -1,178 +0,0 @@
-# Managing stacks with Helm
-
-- We created our first resources with `kubectl run`, `kubectl expose` ...
-
-- We have also created resources by loading YAML files with `kubectl apply -f`
-
-- For larger stacks, managing thousands of lines of YAML is unreasonable
-
-- These YAML bundles need to be customized with variable parameters
-
-  (E.g.: number of replicas, image version to use ...)
-
-- It would be nice to have an organized, versioned collection of bundles
-
-- It would be nice to be able to upgrade/rollback these bundles carefully
-
-- [Helm](https://helm.sh/) is an open source project offering all these things!
-
----
-
-## Helm concepts
-
-- `helm` is a CLI tool
-
-- `tiller` is its companion server-side component
-
-- A "chart" is an archive containing templatized YAML bundles
-
-- Charts are versioned
-
-- Charts can be stored on private or public repositories
-
----
-
-## Installing Helm
-
-- If the `helm` CLI is not installed in your environment, install it
-
-.exercise[
-
-- Check if `helm` is installed:
-  ```bash
-  helm
-  ```
-
-- If it's not installed, run the following command:
-  ```bash
-  curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get | bash
-  ```
-
-]
-
----
-
-## Installing Tiller
-
-- Tiller is composed of a *service* and a *deployment* in the `kube-system` namespace
-
-- They can be managed (installed, upgraded...) with the `helm` CLI
-
-.exercise[
-
-- Deploy Tiller:
-  ```bash
-  helm init
-  ```
-
-]
-
-If Tiller was already installed, don't worry: this won't break it.
-
-At the end of the install process, you will see:
-
-```
-Happy Helming!
-```
-
----
-
-## Fix account permissions
-
-- Helm permission model requires us to tweak permissions
-
-- In a more realistic deployment, you might create per-user or per-team
-  service accounts, roles, and role bindings
-
-.exercise[
-
-- Grant `cluster-admin` role to `kube-system:default` service account:
-  ```bash
-  kubectl create clusterrolebinding add-on-cluster-admin \
-      --clusterrole=cluster-admin --serviceaccount=kube-system:default
-  ```
-
-]
-
-(Defining the exact roles and permissions on your cluster requires
-a deeper knowledge of Kubernetes' RBAC model. The command above is
-fine for personal and development clusters.)
-
----
-
-## View available charts
-
-- A public repo is pre-configured when installing Helm
-
-- We can view available charts with `helm search` (and an optional keyword)
-
-.exercise[
-
-- View all available charts:
-  ```bash
-  helm search
-  ```
-
-- View charts related to `prometheus`:
-  ```bash
-  helm search prometheus
-  ```
-
-]
-
----
-
-## Install a chart
-
-- Most charts use `LoadBalancer` service types by default
-
-- Most charts require persistent volumes to store data
-
-- We need to relax these requirements a bit
-
-.exercise[
-
-- Install the Prometheus metrics collector on our cluster:
-  ```bash
-  helm install stable/prometheus \
-         --set server.service.type=NodePort \
-         --set server.persistentVolume.enabled=false
-  ```
-
-]
-
-Where do these `--set` options come from?
-
----
-
-## Inspecting a chart
-
-- `helm inspect` shows details about a chart (including available options)
-
-.exercise[
-
-- See the metadata and all available options for `stable/prometheus`:
-  ```bash
-  helm inspect stable/prometheus
-  ```
-
-]
-
-The chart's metadata includes a URL to the project's home page.
-
-(Sometimes it conveniently points to the documentation for the chart.)
-
----
-
-## Viewing installed charts
-
-- Helm keeps track of what we've installed
-
-.exercise[
-
-- List installed Helm charts:
-  ```bash
-  helm list
-  ```
-
-]

slides/k8s/horizontal-pod-autoscaler.md

@@ -105,19 +105,36 @@
 
 - Monitor pod CPU usage:
   ```bash
-  watch kubectl top pods
+  watch kubectl top pods -l app=busyhttp
   ```
 
+<!--
+```wait NAME```
+```tmux split-pane -v```
+```bash CLUSTERIP=$(kubectl get svc busyhttp -o jsonpath={.spec.clusterIP})```
+-->
+
 - Monitor service latency:
   ```bash
-  httping http://`ClusterIP`/
+  httping http://`$CLUSTERIP`/
   ```
 
+<!--
+```wait connected to```
+```tmux split-pane -v```
+-->
+
 - Monitor cluster events:
   ```bash
   kubectl get events -w
   ```
 
+<!--
+```wait Normal```
+```tmux split-pane -v```
+```bash CLUSTERIP=$(kubectl get svc busyhttp -o jsonpath={.spec.clusterIP})```
+-->
+
 ]
 
 ---
@@ -130,9 +147,15 @@
 
 - Send a lot of requests to the service, with a concurrency level of 3:
   ```bash
-  ab -c 3 -n 100000 http://`ClusterIP`/
+  ab -c 3 -n 100000 http://`$CLUSTERIP`/
   ```
 
+<!--
+```wait be patient```
+```tmux split-pane -v```
+```tmux selectl even-vertical```
+-->
+
 ]
 
 The latency (reported by `httping`) should increase above 3s.
@@ -193,6 +216,20 @@ This can also be set with `--cpu-percent=`.
   kubectl edit deployment busyhttp
   ```
 
+<!--
+```wait Please edit```
+```keys /resources```
+```key ^J```
+```keys $xxxo  requests:```
+```key ^J```
+```key Space```
+```key Space```
+```keys cpu: "1"```
+```key Escape```
+```keys :wq```
+```key ^J```
+-->
+
 - In the `containers` list, add the following block:
   ```yaml
     resources:
@@ -243,3 +280,29 @@ This can also be set with `--cpu-percent=`.
 - The metrics provided by metrics server are standard; everything else is custom
 
 - For more details, see [this great blog post](https://medium.com/uptime-99/kubernetes-hpa-autoscaling-with-custom-and-external-metrics-da7f41ff7846) or [this talk](https://www.youtube.com/watch?v=gSiGFH4ZnS8)
+
+---
+
+## Cleanup
+
+- Since `busyhttp` uses CPU cycles, let's stop it before moving on
+
+.exercise[
+
+- Delete the `busyhttp` Deployment:
+  ```bash
+  kubectl delete deployment busyhttp
+  ```
+
+<!--
+```key ^D```
+```key ^C```
+```key ^D```
+```key ^C```
+```key ^D```
+```key ^C```
+```key ^D```
+```key ^C```
+-->
+
+]

slides/k8s/ingress.md

@@ -524,3 +524,183 @@ spec:
 - This should eventually stabilize
 
   (remember that ingresses are currently `apiVersion: networking.k8s.io/v1beta1`)
+
+---
+
+## A special feature in action
+
+- We're going to see how to implement *canary releases* with Traefik
+
+- This feature is available on multiple ingress controllers
+
+- ... But it is configured very differently on each of them
+
+---
+
+## Canary releases
+
+- A *canary release* (or canary launch or canary deployment) is a release that will process only a small fraction of the workload
+
+- After deploying the canary, we compare its metrics to the normal release
+
+- If the metrics look good, the canary will progressively receive more traffic
+
+  (until it gets 100% and becomes the new normal release)
+
+- If the metrics aren't good, the canary is automatically removed
+
+- When we deploy a bad release, only a tiny fraction of traffic is affected
+
+---
+
+## Various ways to implement canary
+
+- Example 1: canary for a microservice
+
+  - 1% of all requests (sampled randomly) are sent to the canary
+  - the remaining 99% are sent to the normal release
+
+- Example 2: canary for a web app
+
+  - 1% of users are sent to the canary web site
+  - the remaining 99% are sent to the normal release
+
+- Example 3: canary for shipping physical goods
+
+  - 1% of orders are shipped with the canary process
+  - the reamining 99% are shipped with the normal process
+
+- We're going to implement example 1 (per-request routing)
+
+---
+
+## Canary releases with Traefik
+
+- We need to deploy the canary and expose it with a separate service
+
+- Then, in the Ingress resource, we need:
+
+  - multiple `paths` entries (one for each service, canary and normal)
+
+  - an extra annotation indicating the weight of each service
+
+- If we want, we can send requests to more than 2 services
+
+- Let's send requests to our 3 cheesy services!
+
+.exercise[
+
+- Create the resource shown on the next slide
+
+]
+
+---
+
+## The Ingress resource
+
+.small[
+```yaml
+apiVersion: networking.k8s.io/v1beta1
+kind: Ingress
+metadata:
+  name: cheeseplate
+  annotations:
+    traefik.ingress.kubernetes.io/service-weights: |
+      cheddar: 50%
+      wensleydale: 25%
+      stilton: 25%
+spec:
+  rules:
+  - host: cheeseplate.`A.B.C.D`.nip.io
+    http:
+      paths:
+      - path: /
+        backend:
+          serviceName: cheddar
+          servicePort: 80
+      - path: /
+        backend:
+          serviceName: wensledale
+          servicePort: 80
+      - path: /
+        backend:
+          serviceName: stilton
+          servicePort: 80
+```
+]
+
+---
+
+## Testing the canary
+
+- Let's check the percentage of requests going to each service
+
+.exercise[
+
+- Continuously send HTTP requests to the new ingress:
+  ```bash
+    while sleep 0.1; do
+      curl -s http://cheeseplate.A.B.C.D.nip.io/
+    done
+  ```
+
+]
+
+We should see a 50/25/25 request mix.
+
+---
+
+class: extra-details
+
+## Load balancing fairness
+
+Note: if we use odd request ratios, the load balancing algorithm might appear to be broken on a small scale (when sending a small number of requests), but on a large scale (with many requests) it will be fair.
+
+For instance, with a 11%/89% ratio, we can see 79 requests going to the 89%-weighted service, and then requests alternating between the two services; then 79 requests again, etc. 
+
+---
+
+class: extra-details
+
+## Other ingress controllers
+
+*Just to illustrate how different things are ...*
+
+- With the NGINX ingress controller:
+
+  - define two ingress ressources
+    <br/>
+    (specifying rules with the same host+path)
+
+  - add `nginx.ingress.kubernetes.io/canary` annotations on each
+
+
+- With Linkerd2:
+
+  - define two services
+
+  - define an extra service for the weighted aggregate of the two
+
+  - define a TrafficSplit (this is a CRD introduced by the SMI spec)
+
+---
+
+class: extra-details
+
+## We need more than that
+
+What we saw is just one of the multiple building blocks that we need to achieve a canary release.
+
+We also need:
+
+- metrics (latency, performance ...) for our releases
+
+- automation to alter canary weights
+
+  (increase canary weight if metrics look good; decrease otherwise)
+
+- a mechanism to manage the lifecycle of the canary releases
+
+  (create them, promote them, delete them ...)
+
+For inspiration, check [flagger by Weave](https://github.com/weaveworks/flagger).

slides/k8s/kubectlexpose.md

@@ -14,42 +14,80 @@
 
   `ClusterIP`, `NodePort`, `LoadBalancer`, `ExternalName`
 
----
-
-## Basic service types
-
-- `ClusterIP` (default type)
-
-  - a virtual IP address is allocated for the service (in an internal, private range)
-  - this IP address is reachable only from within the cluster (nodes and pods)
-  - our code can connect to the service using the original port number
-
-- `NodePort`
-
-  - a port is allocated for the service (by default, in the 30000-32768 range)
-  - that port is made available *on all our nodes* and anybody can connect to it
-  - our code must be changed to connect to that new port number
-
-These service types are always available.
-
-Under the hood: `kube-proxy` is using a userland proxy and a bunch of `iptables` rules.
+- HTTP services can also use `Ingress` resources (more on that later)
 
 ---
 
-## More service types
+## `ClusterIP`
 
-- `LoadBalancer`
+- It's the default service type
 
-  - an external load balancer is allocated for the service
-  - the load balancer is configured accordingly
-    <br/>(e.g.: a `NodePort` service is created, and the load balancer sends traffic to that port)
-  - available only when the underlying infrastructure provides some "load balancer as a service"
-    <br/>(e.g. AWS, Azure, GCE, OpenStack...)
+- A virtual IP address is allocated for the service
 
-- `ExternalName`
+  (in an internal, private range; e.g. 10.96.0.0/12)
 
-  - the DNS entry managed by CoreDNS will just be a `CNAME` to a provided record
-  - no port, no IP address, no nothing else is allocated
+- This IP address is reachable only from within the cluster (nodes and pods)
+
+- Our code can connect to the service using the original port number
+
+- Perfect for internal communication, within the cluster
+
+---
+
+## `LoadBalancer`
+
+- An external load balancer is allocated for the service
+
+  (typically a cloud load balancer, e.g. ELB on AWS, GLB on GCE ...)
+
+- This is available only when the underlying infrastructure provides some kind of
+  "load balancer as a service"
+
+- Each service of that type will typically cost a little bit of money
+
+  (e.g. a few cents per hour on AWS or GCE)
+
+- Ideally, traffic would flow directly from the load balancer to the pods
+
+- In practice, it will often flow through a `NodePort` first
+
+---
+
+## `NodePort`
+
+- A port number is allocated for the service
+
+  (by default, in the 30000-32767 range)
+
+- That port is made available *on all our nodes* and anybody can connect to it
+
+  (we can connect to any node on that port to reach the service)
+
+- Our code needs to be changed to connect to that new port number
+
+- Under the hood: `kube-proxy` sets up a bunch of `iptables` rules on our nodes
+
+- Sometimes, it's the only available option for external traffic
+
+  (e.g. most clusters deployed with kubeadm or on-premises)
+
+---
+
+class: extra-details
+
+## `ExternalName`
+
+- No load balancer (internal or external) is created
+
+- Only a DNS entry gets added to the DNS managed by Kubernetes
+
+- That DNS entry will just be a `CNAME` to a provided record
+
+Example:
+```bash
+kubectl create service externalname k8s --external-name kubernetes.io
+```
+*Creates a CNAME `k8s` pointing to `kubernetes.io`*
 
 ---
 
@@ -86,7 +124,10 @@ Under the hood: `kube-proxy` is using a userland proxy and a bunch of `iptables`
   kubectl get pods -w
   ```
 
-<!-- ```keys ^C``` -->
+<!--
+```wait NAME```
+```tmux split-pane -h```
+-->
 
 - Create a deployment for this very lightweight HTTP server:
   ```bash
@@ -153,6 +194,8 @@ Under the hood: `kube-proxy` is using a userland proxy and a bunch of `iptables`
 
 <!--
 ```hide kubectl wait deploy httpenv --for condition=available```
+```key ^D```
+```key ^C```
 -->
 
 - Send a few requests:
@@ -279,18 +322,28 @@ error: the server doesn't have a resource type "endpoint"
 
 ---
 
-## Exposing services to the outside world
+class: extra-details
 
-- The default type (ClusterIP) only works for internal traffic
+## `ExternalIP`
 
-- If we want to accept external traffic, we can use one of these:
+- When creating a servivce, we can also specify an `ExternalIP`
 
-  - NodePort (expose a service on a TCP port between 30000-32768)
+  (this is not a type, but an extra attribute to the service)
 
-  - LoadBalancer (provision a cloud load balancer for our service)
+- It will make the service availableon this IP address
 
-  - ExternalIP (use one node's external IP address)
+  (if the IP address belongs to a node of the cluster)
 
-  - Ingress (a special mechanism for HTTP services)
+---
 
-*We'll see NodePorts and Ingresses more in detail later.*
+## `Ingress`
+
+- Ingresses are another type (kind) of resource
+
+- They are specifically for HTTP services
+
+  (not TCP or UDP)
+
+- They can also handle TLS certificates, URL rewriting ...
+
+- They require an *Ingress Controller* to function

slides/k8s/kubectlget.md

@@ -20,6 +20,50 @@
 
 ---
 
+class: extra-details
+
+## `kubectl` is the new SSH
+
+- We often start managing servers with SSH
+
+  (installing packages, troubleshooting ...)
+
+- At scale, it becomes tedious, repetitive, error-prone
+
+- Instead, we use config management, central logging, etc.
+
+- In many cases, we still need SSH:
+
+  - as the underlying access method (e.g. Ansible)
+
+  - to debug tricky scenarios
+
+  - to inspect and poke at things
+
+---
+
+class: extra-details
+
+## The parallel with `kubectl`
+
+- We often start managing Kubernetes clusters with `kubectl`
+
+  (deploying applications, troubleshooting ...)
+
+- At scale (with many applications or clusters), it becomes tedious, repetitive, error-prone
+
+- Instead, we use automated pipelines, observability tooling, etc.
+
+- In many cases, we still need `kubectl`:
+
+  - to debug tricky scenarios
+
+  - to inspect and poke at things
+
+- The Kubernetes API is always the underlying access method
+
+---
+
 ## `kubectl get`
 
 - Let's look at our `Node` resources with `kubectl get`!
@@ -71,7 +115,7 @@
 
 - Show the capacity of all our nodes as a stream of JSON objects:
   ```bash
-    kubectl get nodes -o json | 
+    kubectl get nodes -o json |
             jq ".items[] | {name:.metadata.name} + .status.capacity"
   ```
 
@@ -182,53 +226,6 @@ class: extra-details
 
 ---
 
-## Services
-
-- A *service* is a stable endpoint to connect to "something"
-
-  (In the initial proposal, they were called "portals")
-
-.exercise[
-
-- List the services on our cluster with one of these commands:
-  ```bash
-  kubectl get services
-  kubectl get svc
-  ```
-
-]
-
---
-
-There is already one service on our cluster: the Kubernetes API itself.
-
----
-
-## ClusterIP services
-
-- A `ClusterIP` service is internal, available from the cluster only
-
-- This is useful for introspection from within containers
-
-.exercise[
-
-- Try to connect to the API:
-  ```bash
-  curl -k https://`10.96.0.1`
-  ```
-  
-  - `-k` is used to skip certificate verification
-
-  - Make sure to replace 10.96.0.1 with the CLUSTER-IP shown by `kubectl get svc`
-
-]
-
---
-
-The error that we see is expected: the Kubernetes API requires authentication.
-
----
-
 ## Listing running containers
 
 - Containers are manipulated through *pods*
@@ -467,3 +464,117 @@ class: extra-details
 
 [KEP-0009]: https://github.com/kubernetes/enhancements/blob/master/keps/sig-node/0009-node-heartbeat.md
 [node controller documentation]: https://kubernetes.io/docs/concepts/architecture/nodes/#node-controller
+
+---
+
+## Services
+
+- A *service* is a stable endpoint to connect to "something"
+
+  (In the initial proposal, they were called "portals")
+
+.exercise[
+
+- List the services on our cluster with one of these commands:
+  ```bash
+  kubectl get services
+  kubectl get svc
+  ```
+
+]
+
+--
+
+There is already one service on our cluster: the Kubernetes API itself.
+
+---
+
+## ClusterIP services
+
+- A `ClusterIP` service is internal, available from the cluster only
+
+- This is useful for introspection from within containers
+
+.exercise[
+
+- Try to connect to the API:
+  ```bash
+  curl -k https://`10.96.0.1`
+  ```
+
+  - `-k` is used to skip certificate verification
+
+  - Make sure to replace 10.96.0.1 with the CLUSTER-IP shown by `kubectl get svc`
+
+]
+
+The command above should either time out, or show an authentication error. Why?
+
+---
+
+## Time out
+
+- Connections to ClusterIP services only work *from within the cluster*
+
+- If we are outside the cluster, the `curl` command will probably time out
+
+  (Because the IP address, e.g. 10.96.0.1, isn't routed properly outside the cluster)
+
+- This is the case with most "real" Kubernetes clusters
+
+- To try the connection from within the cluster, we can use [shpod](https://github.com/jpetazzo/shpod)
+
+---
+
+## Authentication error
+
+This is what we should see when connecting from within the cluster:
+```json
+$ curl -k https://10.96.0.1
+{
+  "kind": "Status",
+  "apiVersion": "v1",
+  "metadata": {
+
+  },
+  "status": "Failure",
+  "message": "forbidden: User \"system:anonymous\" cannot get path \"/\"",
+  "reason": "Forbidden",
+  "details": {
+
+  },
+  "code": 403
+}
+```
+
+---
+
+## Explanations
+
+- We can see `kind`, `apiVersion`, `metadata`
+
+- These are typical of a Kubernetes API reply
+
+- Because we *are* talking to the Kubernetes API
+
+- The Kubernetes API tells us "Forbidden"
+
+  (because it requires authentication)
+
+- The Kubernetes API is reachable from within the cluster
+
+  (many apps integrating with Kubernetes will use this)
+
+---
+
+## DNS integration
+
+- Each service also gets a DNS record
+
+- The Kubernetes DNS resolver is available *from within pods*
+
+  (and sometimes, from within nodes, depending on configuration)
+
+- Code running in pods can connect to services using their name
+
+  (e.g. https://kubernetes/...)

slides/k8s/kubectlproxy.md

@@ -101,7 +101,7 @@ If we wanted to talk to the API, we would need to:
 
 <!--
 ```wait /version```
-```keys ^J```
+```key ^J```
 -->
 
 - Terminate the proxy:

slides/k8s/kubectlrun.md

@@ -20,10 +20,9 @@
 
 .exercise[
 
-- Let's ping `1.1.1.1`, Cloudflare's 
-  [public DNS resolver](https://blog.cloudflare.com/announcing-1111/):
+- Let's ping the address of `localhost`, the loopback interface:
   ```bash
-  kubectl run pingpong --image alpine ping 1.1.1.1
+  kubectl run pingpong --image alpine ping 127.0.0.1
   ```
 
 <!-- ```hide kubectl wait deploy/pingpong --for condition=available``` -->
@@ -153,9 +152,11 @@ pod/pingpong-7c8bbcd9bc-6c9qz   1/1       Running   0          10m
   kubectl logs deploy/pingpong --tail 1 --follow
   ```
 
+- Leave that command running, so that we can keep an eye on these logs
+
 <!--
 ```wait seq=3```
-```keys ^C```
+```tmux split-pane -h```
 -->
 
 ]
@@ -186,6 +187,54 @@ We could! But the *deployment* would notice it right away, and scale back to the
 
 ---
 
+## Log streaming
+
+- Let's look again at the output of `kubectl logs`
+
+  (the one we started before scaling up)
+
+- `kubectl logs` shows us one line per second
+
+- We could expect 3 lines per second
+
+  (since we should now have 3 pods running `ping`)
+
+- Let's try to figure out what's happening!
+
+---
+
+## Streaming logs of multiple pods
+
+- What happens if we restart `kubectl logs`?
+
+.exercise[
+
+- Interrupt `kubectl logs` (with Ctrl-C)
+
+<!--
+```tmux last-pane```
+```key ^C```
+-->
+
+- Restart it:
+  ```bash
+  kubectl logs deploy/pingpong --tail 1 --follow
+  ```
+
+<!--
+```wait using pod/pingpong-```
+```tmux last-pane```
+-->
+
+]
+
+`kubectl logs` will warn us that multiple pods were found, and that it's showing us only one of them.
+
+Let's leave `kubectl logs` running while we keep exploring.
+
+---
+
+
 ## Resilience
 
 - The *deployment* `pingpong` watches its *replica set*
@@ -196,27 +245,56 @@ We could! But the *deployment* would notice it right away, and scale back to the
 
 .exercise[
 
-- In a separate window, list pods, and keep watching them:
+- In a separate window, watch the list of pods:
   ```bash
-  kubectl get pods -w
+  watch kubectl get pods
   ```
 
 <!--
-```wait Running```
-```keys ^C```
-```hide kubectl wait deploy pingpong --for condition=available```
-```keys kubectl delete pod ping```
-```copypaste pong-..........-.....```
+```wait Every 2.0s```
+```tmux split-pane -v```
 -->
 
-- Destroy a pod:
+- Destroy the pod currently shown by `kubectl logs`:
   ```
   kubectl delete pod pingpong-xxxxxxxxxx-yyyyy
   ```
+
+<!--
+```tmux select-pane -t 0```
+```copy pingpong-[^-]*-.....```
+```tmux last-pane```
+```keys kubectl delete pod ```
+```paste```
+```key ^J```
+```check```
+```key ^D```
+```tmux select-pane -t 1```
+```key ^C```
+```key ^D```
+-->
+
 ]
 
 ---
 
+## What happened?
+
+- `kubectl delete pod` terminates the pod gracefully
+
+  (sending it the TERM signal and waiting for it to shutdown)
+
+- As soon as the pod is in "Terminating" state, the Replica Set replaces it
+
+- But we can still see the output of the "Terminating" pod in `kubectl logs`
+
+- Until 30 seconds later, when the grace period expires
+
+- The pod is then killed, and `kubectl logs` exits
+
+---
+
+
 ## What if we wanted something different?
 
 - What if we wanted to start a "one-shot" container that *doesn't* get restarted?
@@ -234,6 +312,73 @@ We could! But the *deployment* would notice it right away, and scale back to the
 
 ---
 
+## Scheduling periodic background work
+
+- A Cron Job is a job that will be executed at specific intervals
+
+  (the name comes from the traditional cronjobs executed by the UNIX crond)
+
+- It requires a *schedule*, represented as five space-separated fields:
+
+  - minute [0,59]
+  - hour [0,23]
+  - day of the month [1,31]
+  - month of the year [1,12]
+  - day of the week ([0,6] with 0=Sunday)
+
+- `*` means "all valid values"; `/N` means "every N"
+
+- Example: `*/3 * * * *` means "every three minutes"
+
+---
+
+## Creating a Cron Job
+
+- Let's create a simple job to be executed every three minutes
+
+- Cron Jobs need to terminate, otherwise they'd run forever
+
+.exercise[
+
+- Create the Cron Job:
+  ```bash
+  kubectl run every3mins --schedule="*/3 * * * *" --restart=OnFailure \
+      --image=alpine sleep 10
+  ```
+
+- Check the resource that was created:
+  ```bash
+  kubectl get cronjobs
+  ```
+
+]
+
+---
+
+## Cron Jobs in action
+
+- At the specified schedule, the Cron Job will create a Job
+
+- The Job will create a Pod
+
+- The Job will make sure that the Pod completes
+
+  (re-creating another one if it fails, for instance if its node fails)
+
+.exercise[
+
+- Check the Jobs that are created:
+  ```bash
+  kubectl get jobs
+  ```
+
+]
+
+(It will take a few minutes before the first job is scheduled.)
+
+---
+
+
 ## What about that deprecation warning?
 
 - As we can see from the previous slide, `kubectl run` can do many things
@@ -257,12 +402,12 @@ We could! But the *deployment* would notice it right away, and scale back to the
 
 ## Various ways of creating resources
 
-- `kubectl run` 
+- `kubectl run`
 
   - easy way to get started
   - versatile
 
-- `kubectl create <resource>` 
+- `kubectl create <resource>`
 
   - explicit, but lacks some features
   - can't create a CronJob before Kubernetes 1.14
@@ -309,7 +454,7 @@ We could! But the *deployment* would notice it right away, and scale back to the
 
 <!--
 ```wait seq=```
-```keys ^C```
+```key ^C```
 -->
 
 ]
@@ -338,6 +483,8 @@ class: extra-details
   kubectl logs -l run=pingpong --tail 1 -f
   ```
 
+<!-- ```wait error:``` -->
+
 ]
 
 We see a message like the following one:
@@ -406,15 +553,36 @@ class: extra-details
 
 ---
 
-## Aren't we flooding 1.1.1.1?
+class: extra-details
 
-- If you're wondering this, good question!
+## Party tricks involving IP addresses
 
-- Don't worry, though:
+- It is possible to specify an IP address with less than 4 bytes
 
-  *APNIC's research group held the IP addresses 1.1.1.1 and 1.0.0.1. While the addresses were valid, so many people had entered them into various random systems that they were continuously overwhelmed by a flood of garbage traffic. APNIC wanted to study this garbage traffic but any time they'd tried to announce the IPs, the flood would overwhelm any conventional network.*
+  (example: `127.1`)
 
-  (Source: https://blog.cloudflare.com/announcing-1111/)
+- Zeroes are then inserted in the middle
 
-- It's very unlikely that our concerted pings manage to produce
-  even a modest blip at Cloudflare's NOC!
+- As a result, `127.1` expands to `127.0.0.1`
+
+- So we can `ping 127.1` to ping `localhost`!
+
+(See [this blog post](https://ma.ttias.be/theres-more-than-one-way-to-write-an-ip-address/
+) for more details.)
+
+---
+
+class: extra-details
+
+## More party tricks with IP addresses
+
+- We can also ping `1.1`
+
+- `1.1` will expand to `1.0.0.1`
+
+- This is one of the addresses of Cloudflare's
+  [public DNS resolver](https://blog.cloudflare.com/announcing-1111/)
+
+- This is a quick way to check connectivity
+
+  (if we can reach 1.1, we probably have internet access)

slides/k8s/kubectlscale.md

@@ -12,9 +12,9 @@
 
 <!--
 ```wait RESTARTS```
-```keys ^C```
+```key ^C```
 ```wait AVAILABLE```
-```keys ^C```
+```key ^C```
 -->
 
 - Now, create more `worker` replicas:

slides/k8s/kustomize.md

@@ -97,6 +97,8 @@
   ship init https://github.com/jpetazzo/kubercoins
   ```
 
+<!-- ```wait Open browser``` -->
+
 ]
 
 ---
@@ -189,6 +191,11 @@
   kubectl logs deploy/worker --tail=10 --follow --namespace=kustomcoins
   ```
 
+<!--
+```wait units of work done``` 
+```key ^C```
+-->
+
 ]
 
 Note: it might take a minute or two for the worker to start.

slides/k8s/local-persistent-volumes.md

@@ -56,28 +56,6 @@
 
 ---
 
-## Work in a separate namespace
-
-- To avoid conflicts with existing resources, let's create and use a new namespace
-
-.exercise[
-
-- Create a new namespace:
-  ```bash
-  kubectl create namespace orange
-  ```
-
-- Switch to that namespace:
-  ```bash
-  kns orange
-  ```
-
-]
-
-.warning[Make sure to call that namespace `orange`: it is hardcoded in the YAML files.]
-
----
-
 ## Deploying Consul
 
 - We will use a slightly different YAML file
@@ -88,7 +66,9 @@
 
   - the corresponding `volumeMounts` in the Pod spec
 
-  - the namespace `orange` used for discovery of Pods
+  - the label `consul` has been changed to `persistentconsul`
+    <br/>
+    (to avoid conflicts with the other Stateful Set)
 
 .exercise[
 
@@ -117,7 +97,7 @@
   kubectl get pv
   ```
 
-- The Pod `consul-0` is not scheduled yet:
+- The Pod `persistentconsul-0` is not scheduled yet:
   ```bash
   kubectl get pods -o wide
   ```
@@ -132,9 +112,9 @@
 
 - In a Stateful Set, the Pods are started one by one
 
-- `consul-1` won't be created until `consul-0` is running
+- `persistentconsul-1` won't be created until `persistentconsul-0` is running
 
-- `consul-0` has a dependency on an unbound Persistent Volume Claim
+- `persistentconsul-0` has a dependency on an unbound Persistent Volume Claim
 
 - The scheduler won't schedule the Pod until the PVC is bound
 
@@ -172,7 +152,7 @@
 
 - Once a PVC is bound, its pod can start normally
 
-- Once the pod `consul-0` has started, `consul-1` can be created, etc.
+- Once the pod `persistentconsul-0` has started, `persistentconsul-1` can be created, etc.
 
 - Eventually, our Consul cluster is up, and backend by "persistent" volumes
 
@@ -180,7 +160,7 @@
 
 - Check that our Consul clusters has 3 members indeed:
   ```bash
-  kubectl exec consul-0 consul members
+  kubectl exec persistentconsul-0 consul members
   ```
 
 ]

slides/k8s/localkubeconfig.md

@@ -34,11 +34,11 @@
 
 - Download the `kubectl` binary from one of these links:
 
-  [Linux](https://storage.googleapis.com/kubernetes-release/release/v1.15.2/bin/linux/amd64/kubectl)
+  [Linux](https://storage.googleapis.com/kubernetes-release/release/v1.15.3/bin/linux/amd64/kubectl)
   |
-  [macOS](https://storage.googleapis.com/kubernetes-release/release/v1.15.2/bin/darwin/amd64/kubectl)
+  [macOS](https://storage.googleapis.com/kubernetes-release/release/v1.15.3/bin/darwin/amd64/kubectl)
   |
-  [Windows](https://storage.googleapis.com/kubernetes-release/release/v1.15.2/bin/windows/amd64/kubectl.exe)
+  [Windows](https://storage.googleapis.com/kubernetes-release/release/v1.15.3/bin/windows/amd64/kubectl.exe)
 
 - On Linux and macOS, make the binary executable with `chmod +x kubectl`
 

slides/k8s/logs-cli.md

@@ -66,6 +66,8 @@ Exactly what we need!
   sudo chmod +x /usr/local/bin/stern
   ```
 
+- On OS X, just `brew install stern`
+
 <!-- ##VERSION## -->
 
 ---
@@ -82,14 +84,14 @@ Exactly what we need!
 
 .exercise[
 
-- View the logs for all the rng containers:
+- View the logs for all the pingpong containers:
   ```bash
-  stern rng
+  stern pingpong
   ```
 
 <!--
-```wait HTTP/1.1```
-```keys ^C```
+```wait seq=```
+```key ^C```
 -->
 
 ]
@@ -115,7 +117,7 @@ Exactly what we need!
 
 <!--
 ```wait weave-npc```
-```keys ^C```
+```key ^C```
 -->
 
 ]
@@ -136,14 +138,14 @@ Exactly what we need!
 
 .exercise[
 
-- View the logs for all the things started with `kubectl create deployment`:
+- View the logs for all the things started with `kubectl run`:
   ```bash
-  stern -l app
+  stern -l run
   ```
 
 <!--
-```wait units of work```
-```keys ^C```
+```wait seq=```
+```key ^C```
 -->
 
 ]

slides/k8s/multinode.md

@@ -218,6 +218,18 @@ class: extra-details
 
 ## What's going on?
 
+- Without the `--network-plugin` flag, kubelet defaults to "no-op" networking
+
+- It lets the container engine use a default network
+
+  (in that case, we end up with the default Docker bridge)
+
+- Our pods are running on independent, disconnected, host-local networks
+
+---
+
+## What do we need to do?
+
 - On a normal cluster, kubelet is configured to set up pod networking with CNI plugins
 
 - This requires:
@@ -228,14 +240,6 @@ class: extra-details
 
   - running kubelet with `--network-plugin=cni`
 
-- Without the `--network-plugin` flag, kubelet defaults to "no-op" networking
-
-- It lets the container engine use a default network
-
-  (in that case, we end up with the default Docker bridge)
-
-- Our pods are running on independent, disconnected, host-local networks
-
 ---
 
 ## Using network plugins
@@ -394,7 +398,7 @@ class: extra-details
 
 - Start kube-proxy:
   ```bash
-  sudo kube-proxy --kubeconfig ~/kubeconfig
+  sudo kube-proxy --kubeconfig ~/.kube/config
   ```
 
 - Expose our Deployment:

slides/k8s/netpol.md

@@ -120,6 +120,12 @@ This is our game plan:
   kubectl create deployment testweb --image=nginx
   ```
 
+<!--
+```bash
+kubectl wait deployment testweb --for condition=available
+```
+-->
+
 - Find out the IP address of the pod with one of these two commands:
   ```bash
   kubectl get pods -o wide -l app=testweb
@@ -154,6 +160,11 @@ The `curl` command should show us the "Welcome to nginx!" page.
   curl $IP
   ```
 
+<!--
+```wait curl```
+```key ^C```
+-->
+
 ]
 
 The `curl` command should now time out.

slides/k8s/operators.md

@@ -121,7 +121,7 @@ Examples:
 
 ## One operator in action
 
-- We will install the UPMC Enterprises ElasticSearch operator
+- We will install [Elastic Cloud on Kubernetes](https://www.elastic.co/guide/en/cloud-on-k8s/current/k8s-quickstart.html), an ElasticSearch operator
 
 - This operator requires PersistentVolumes
 
@@ -206,51 +206,92 @@ Now, the StorageClass should have `(default)` next to its name.
 
 ## Install the ElasticSearch operator
 
-- The operator needs:
+- The operator provides:
 
-  - a Deployment for its controller
+  - a few CustomResourceDefinitions
+  - a Namespace for its other resources
+  - a ValidatingWebhookConfiguration for type checking
+  - a StatefulSet for its controller and webhook code
   - a ServiceAccount, ClusterRole, ClusterRoleBinding for permissions
-  - a Namespace
 
-- We have grouped all the definitions for these resources in a YAML file
+- All these resources are grouped in a convenient YAML file
 
 .exercise[
 
 - Install the operator:
   ```bash
-  kubectl apply -f ~/container.training/k8s/elasticsearch-operator.yaml
+  kubectl apply -f ~/container.training/k8s/eck-operator.yaml
   ```
 
 ]
 
 ---
 
-## Wait for the operator to be ready
+## Check our new custom resources
 
-- Some operators require to create their CRDs separately
-
-- This operator will create its CRD itself
-
-  (i.e. the CRD is not listed in the YAML that we applied earlier)
+- Let's see which CRDs were created
 
 .exercise[
 
-- Wait until the `elasticsearchclusters` CRD shows up:
+- List all CRDs:
   ```bash
   kubectl get crds
   ```
 
 ]
 
+This operator supports ElasticSearch, but also Kibana and APM. Cool!
+
+---
+
+## Create the `eck-demo` namespace
+
+- For clarity, we will create everything in a new namespace, `eck-demo`
+
+- This namespace is hard-coded in the YAML files that we are going to use
+
+- We need to create that namespace
+
+.exercise[
+
+- Create the `eck-demo` namespace:
+  ```bash
+  kubectl create namespace eck-demo
+  ```
+
+- Switch to that namespace:
+  ```bash
+  kns eck-demo
+  ```
+
+]
+
+---
+
+class: extra-details
+
+## Can we use a different namespace?
+
+Yes, but then we need to update all the YAML manifests that we
+are going to apply in the next slides.
+
+The `eck-demo` namespace is hard-coded in these YAML manifests.
+
+Why?
+
+Because when defining a ClusterRoleBinding that references a
+ServiceAccount, we have to indicate in which namespace the
+ServiceAccount is located.
+
 ---
 
 ## Create an ElasticSearch resource
 
-- We can now create a resource with `kind: ElasticsearchCluster`
+- We can now create a resource with `kind: ElasticSearch`
 
 - The YAML for that resource will specify all the desired parameters:
 
-  - how many nodes do we want of each type (client, master, data)
+  - how many nodes we want
   - image to use
   - add-ons (kibana, cerebro, ...)
   - whether to use TLS or not
@@ -260,7 +301,7 @@ Now, the StorageClass should have `(default)` next to its name.
 
 - Create our ElasticSearch cluster:
   ```bash
-  kubectl apply -f ~/container.training/k8s/elasticsearch-cluster.yaml
+  kubectl apply -f ~/container.training/k8s/eck-elasticsearch.yaml
   ```
 
 ]
@@ -269,49 +310,88 @@ Now, the StorageClass should have `(default)` next to its name.
 
 ## Operator in action
 
-- Over the next minutes, the operator will create:
+- Over the next minutes, the operator will create our ES cluster
 
-  - StatefulSets (one for master nodes, one for data nodes)
-
-  - Deployments (for client nodes; and for add-ons like cerebro and kibana)
-
-  - Services (for all these pods)
+- It will report our cluster status through the CRD
 
 .exercise[
 
-- Wait for all the StatefulSets to be fully up and running:
+- Check the logs of the operator:
   ```bash
-  kubectl get statefulsets -w
+  stern --namespace=elastic-system operator
   ```
 
+<!--
+```wait elastic-operator-0```
+```tmux split-pane -v```
+--->
+
+- Watch the status of the cluster through the CRD:
+  ```bash
+  kubectl get es -w
+  ```
+
+<!--
+```longwait green```
+```key ^C```
+```key ^D```
+```key ^C```
+-->
+
 ]
 
 ---
 
 ## Connecting to our cluster
 
-- Since connecting directly to the ElasticSearch API is a bit raw,
-  <br/>we'll connect to the cerebro frontend instead
+- It's not easy to use the ElasticSearch API from the shell
+
+- But let's check at least if ElasticSearch is up!
 
 .exercise[
 
-- Edit the cerebro service to change its type from ClusterIP to NodePort:
+- Get the ClusterIP of our ES instance:
   ```bash
-  kubectl patch svc cerebro-es -p "spec: { type: NodePort }"
+  kubectl get services
   ```
 
-- Retrieve the NodePort that was allocated:
+- Issue a request with `curl`:
   ```bash
-  kubectl get svc cerebro-es
+  curl http://`CLUSTERIP`:9200
   ```
 
-- Connect to that port with a browser
-
 ]
 
+We get an authentication error. Our cluster is protected!
+
 ---
 
-## (Bonus) Setup filebeat
+## Obtaining the credentials
+
+- The operator creates a user named `elastic`
+
+- It generates a random password and stores it in a Secret
+
+.exercise[
+
+- Extract the password:
+  ```bash
+    kubectl get secret demo-es-elastic-user \
+            -o go-template="{{ .data.elastic | base64decode }} "
+  ```
+
+- Use it to connect to the API:
+  ```bash
+  curl -u elastic:`PASSWORD` http://`CLUSTERIP`:9200
+  ```
+
+]
+
+We should see a JSON payload with the `"You Know, for Search"` tagline.
+
+---
+
+## Sending data to the cluster
 
 - Let's send some data to our brand new ElasticSearch cluster!
 
@@ -321,22 +401,170 @@ Now, the StorageClass should have `(default)` next to its name.
 
 - Deploy filebeat:
   ```bash
-  kubectl apply -f ~/container.training/k8s/filebeat.yaml
+  kubectl apply -f ~/container.training/k8s/eck-filebeat.yaml
+  ```
+
+- Wait until some pods are up:
+  ```bash
+  watch kubectl get pods -l k8s-app=filebeat
+  ```
+
+<!--
+```wait Running```
+```key ^C```
+-->
+
+- Check that a filebeat index was created:
+  ```bash
+  curl -u elastic:`PASSWORD` http://`CLUSTERIP`:9200/_cat/indices
   ```
 
 ]
 
-We should see at least one index being created in cerebro.
+---
+
+## Deploying an instance of Kibana
+
+- Kibana can visualize the logs injected by filebeat
+
+- The ECK operator can also manage Kibana
+
+- Let's give it a try!
+
+.exercise[
+
+- Deploy a Kibana instance:
+  ```bash
+  kubectl apply -f ~/container.training/k8s/eck-kibana.yaml
+  ```
+
+- Wait for it to be ready:
+  ```bash
+  kubectl get kibana -w
+  ```
+
+<!--
+```longwait green```
+```key ^C```
+-->
+
+]
 
 ---
 
-## (Bonus) Access log data with kibana
+## Connecting to Kibana
 
-- Let's expose kibana (by making kibana-es a NodePort too)
+- Kibana is automatically set up to conect to ElasticSearch
 
-- Then access kibana
+  (this is arranged by the YAML that we're using)
 
-- We'll need to configure kibana indexes
+- However, it will ask for authentication
+
+- It's using the same user/password as ElasticSearch
+
+.exercise[
+
+- Get the NodePort allocated to Kibana:
+  ```bash
+  kubectl get services
+  ```
+
+- Connect to it with a web browser
+
+- Use the same user/password as before
+
+]
+
+---
+
+## Setting up Kibana
+
+After the Kibana UI loads, we need to click around a bit
+
+.exercise[
+
+- Pick "explore on my own"
+
+- Click on Use Elasticsearch data / Connect to your Elasticsearch index"
+
+- Enter `filebeat-*` for the index pattern and click "Next step"
+
+- Select `@timestamp` as time filter field name
+
+- Click on "discover" (the small icon looking like a compass on the left bar)
+
+- Play around!
+
+]
+
+---
+
+## Scaling up the cluster
+
+- At this point, we have only one node
+
+- We are going to scale up
+
+- But first, we'll deploy Cerebro, an UI for ElasticSearch
+
+- This will let us see the state of the cluster, how indexes are sharded, etc.
+
+---
+
+## Deploying Cerebro
+
+- Cerebro is stateless, so it's fairly easy to deploy
+
+  (one Deployment + one Service)
+
+- However, it needs the address and credentials for ElasticSearch
+
+- We prepared yet another manifest for that!
+
+.exercise[
+
+- Deploy Cerebro:
+  ```bash
+  kubectl apply -f ~/container.training/k8s/eck-cerebro.yaml
+  ```
+
+- Lookup the NodePort number and connect to it:
+  ```bash
+  kuebctl get services
+  ```
+
+]
+
+---
+
+## Scaling up the cluster
+
+- We can see on Cerebro that the cluster is "yellow"
+
+  (because our index is not replicated)
+
+- Let's change that!
+
+.exercise[
+
+- Edit the ElasticSearch cluster manifest:
+  ```bash
+  kubectl edit es demo
+  ```
+
+- Find the field `count: 1` and change it to 3
+
+- Save and quit
+
+<!--
+```wait Please edit```
+```keys /count:```
+```key ^J```
+```keys $r3:x```
+```key ^J```
+-->
+
+]
 
 ---
 
@@ -376,13 +604,11 @@ We should see at least one index being created in cerebro.
 
 - Look at the ElasticSearch resource definition
 
-  (`~/container.training/k8s/elasticsearch-cluster.yaml`)
+  (`~/container.training/k8s/eck-elasticsearch.yaml`)
 
-- What should happen if we flip the `use-tls` flag? Twice?
+- What should happen if we flip the TLS flag? Twice?
 
-- What should happen if we remove / re-add the kibana or cerebro sections?
-
-- What should happen if we change the number of nodes?
+- What should happen if we add another group of nodes?
 
 - What if we want different images or parameters for the different nodes?
 

slides/k8s/ourapponkube.md

@@ -11,16 +11,36 @@
 
 - Deploy everything else:
   ```bash
-    set -u
-    for SERVICE in hasher rng webui worker; do
-      kubectl create deployment $SERVICE --image=$REGISTRY/$SERVICE:$TAG
-    done
+  kubectl create deployment hasher --image=dockercoins/hasher:v0.1
+  kubectl create deployment rng --image=dockercoins/rng:v0.1
+  kubectl create deployment webui --image=dockercoins/webui:v0.1
+  kubectl create deployment worker --image=dockercoins/worker:v0.1
   ```
 
 ]
 
 ---
 
+class: extra-details
+
+## Deploying other images
+
+- If we wanted to deploy images from another registry ...
+
+- ... Or with a different tag ...
+
+- ... We could use the following snippet:
+
+```bash
+  REGISTRY=dockercoins
+  TAG=v0.1
+  for SERVICE in hasher rng webui worker; do
+    kubectl create deployment $SERVICE --image=$REGISTRY/$SERVICE:$TAG
+  done
+```
+
+---
+
 ## Is this working?
 
 - After waiting for the deployment to complete, let's look at the logs!
@@ -88,7 +108,7 @@ kubectl wait deploy/worker --for condition=available
 
 <!--
 ```wait units of work done, updating hash counter```
-```keys ^C```
+```key ^C```
 -->
 
 ]

slides/k8s/podsecuritypolicy.md

@@ -220,6 +220,8 @@
   sudo vim /etc/kubernetes/manifests/kube-apiserver.yaml
   ```
 
+<!-- ```wait apiVersion``` -->
+
 ]
 
 ---
@@ -240,6 +242,16 @@
 
 - Save, quit
 
+<!--
+```keys /--enable-admission-plugins=```
+```key ^J```
+```key $```
+```keys a,PodSecurityPolicy```
+```key Escape```
+```keys :wq```
+```key ^J```
+-->
+
 ]
 
 ---
@@ -271,6 +283,8 @@
   kubectl run testpsp1 --image=nginx --restart=Never
   ```
 
+<!-- ```wait forbidden: no providers available``` -->
+
 - Try to create a Deployment:
   ```bash
   kubectl run testpsp2 --image=nginx
@@ -498,3 +512,22 @@ class: extra-details
   - bind `psp:restricted` to the group `system:authenticated`
 
   - bind `psp:privileged` to the ServiceAccount `kube-system:default`
+
+---
+
+## Fixing the cluster
+
+- Let's disable the PSP admission plugin
+
+.exercise[
+
+- Edit the Kubernetes API server static pod manifest
+
+- Remove the PSP admission plugin
+
+- This can be done with this one-liner:
+  ```bash
+  sudo sed -i s/,PodSecurityPolicy// /etc/kubernetes/manifests/kube-apiserver.yaml
+  ```
+
+]

slides/k8s/portworx.md

@@ -197,7 +197,7 @@ If you want to use an external key/value store, add one of the following:
 
 <!--
 ```longwait PX node status reports portworx service is healthy```
-```keys ^C```
+```key ^C```
 -->
 
 ]
@@ -240,6 +240,25 @@ If you want to use an external key/value store, add one of the following:
 
 ---
 
+## Check our default Storage Class
+
+- The YAML manifest applied earlier should define a default storage class
+
+.exercise[
+
+- Check that we have a default storage class:
+  ```bash
+  kubectl get storageclass
+  ```
+
+]
+
+There should be a storage class showing as `portworx-replicated (default)`.
+
+---
+
+class: extra-details
+
 ## Our default Storage Class
 
 This is our Storage Class (in `k8s/storage-class.yaml`):
@@ -265,28 +284,6 @@ parameters:
 
 ---
 
-## Creating our Storage Class
-
-- Let's apply that YAML file!
-
-.exercise[
-
-- Create the Storage Class:
-  ```bash
-  kubectl apply -f ~/container.training/k8s/storage-class.yaml
-  ```
-
-- Check that it is now available:
-  ```bash
-  kubectl get sc
-  ```
-
-]
-
-It should show as `portworx-replicated (default)`.
-
----
-
 ## Our Postgres Stateful set
 
 - The next slide shows `k8s/postgres.yaml`
@@ -326,7 +323,7 @@ spec:
       schedulerName: stork
       containers:
       - name: postgres
-        image: postgres:10.5
+        image: postgres:11
         volumeMounts:
         - mountPath: /var/lib/postgresql/data
           name: postgres
@@ -377,7 +374,7 @@ spec:
 autopilot prompt detection expects $ or # at the beginning of the line.
 ```wait postgres@postgres```
 ```keys PS1="\u@\h:\w\n\$ "```
-```keys ^J```
+```key ^J```
 -->
 
 - Check that default databases have been created correctly:
@@ -431,7 +428,7 @@ autopilot prompt detection expects $ or # at the beginning of the line.
   psql demo -c "select count(*) from pgbench_accounts"
   ```
 
-<!-- ```keys ^D``` -->
+<!-- ```key ^D``` -->
 
 ]
 
@@ -494,7 +491,7 @@ By "disrupt" we mean: "disconnect it from the network".
 
 - Logout to go back on `node1`
 
-<!-- ```keys ^D``` -->
+<!-- ```key ^D``` -->
 
 - Watch the events unfolding with `kubectl get events -w` and `kubectl get pods -w`
 
@@ -522,7 +519,7 @@ By "disrupt" we mean: "disconnect it from the network".
 <!--
 ```wait postgres@postgres```
 ```keys PS1="\u@\h:\w\n\$ "```
-```keys ^J```
+```key ^J```
 -->
 
 - Check the number of rows in the `pgbench_accounts` table:
@@ -530,7 +527,7 @@ By "disrupt" we mean: "disconnect it from the network".
   psql demo -c "select count(*) from pgbench_accounts"
   ```
 
-<!-- ```keys ^D``` -->
+<!-- ```key ^D``` -->
 
 ]
 

slides/k8s/prometheus.md

@@ -60,10 +60,12 @@
 
   (by default: every minute; can be more/less frequent)
 
-- If you're worried about parsing overhead: exporters can also use protobuf
-
 - The list of URLs to scrape (the *scrape targets*) is defined in configuration
 
+.footnote[Worried about the overhead of parsing a text format?
+<br/>
+Check this [comparison](https://github.com/RichiH/OpenMetrics/blob/master/markdown/protobuf_vs_text.md) of the text format with the (now deprecated) protobuf format!]
+
 ---
 
 ## Defining scrape targets
@@ -202,32 +204,46 @@ We need to:
 
 ## Step 1: install Helm
 
-- If we already installed Helm earlier, these commands won't break anything
+- If we already installed Helm earlier, this command won't break anything
 
-.exercice[
+.exercise[
 
-- Install Tiller (Helm's server-side component) on our cluster:
+- Install the Helm CLI:
   ```bash
-  helm init
-  ```
-
-- Give Tiller permission to deploy things on our cluster:
-  ```bash
-  kubectl create clusterrolebinding add-on-cluster-admin \
-      --clusterrole=cluster-admin --serviceaccount=kube-system:default
+  curl https://raw.githubusercontent.com/kubernetes/helm/master/scripts/get-helm-3 \
+  | bash
   ```
 
 ]
 
 ---
 
-## Step 2: install Prometheus
+## Step 2: add the `stable` repo
 
-- Skip this if we already installed Prometheus earlier
+- This will add the repository containing the chart for Prometheus
 
-  (in doubt, check with `helm list`)
+- This command is idempotent
 
-.exercice[
+  (it won't break anything if the repository was already added)
+
+.exercise[
+
+- Add the repository:
+  ```bash
+  helm repo add stable https://kubernetes-charts.storage.googleapis.com/
+  ```
+
+]
+
+---
+
+## Step 3: install Prometheus
+
+- The following command, just like the previous ones, is idempotent
+
+  (it won't error out if Prometheus is already installed)
+
+.exercise[
 
 - Install Prometheus on our cluster:
   ```bash

slides/k8s/resource-limits.md

@@ -515,3 +515,24 @@ services.nodeports               0     0
   (with `kubectl describe resourcequota ...`)
 
 - Rinse and repeat regularly
+
+---
+
+## Additional resources
+
+- [A Practical Guide to Setting Kubernetes Requests and Limits](http://blog.kubecost.com/blog/requests-and-limits/)
+
+  - explains what requests and limits are
+
+  - provides guidelines to set requests and limits
+
+  - gives PromQL expressions to compute good values
+    <br/>(our app needs to be running for a while)
+
+- [Kube Resource Report](https://github.com/hjacobs/kube-resource-report/)
+
+  - generates web reports on resource usage
+
+  - [static demo](https://hjacobs.github.io/kube-resource-report/sample-report/output/index.html)
+    |
+    [live demo](https://kube-resource-report.demo.j-serv.de/applications.html)

slides/k8s/rollout.md

@@ -14,7 +14,27 @@
 
 ## Rolling updates
 
-- With rolling updates, when a resource is updated, it happens progressively
+- With rolling updates, when a Deployment is updated, it happens progressively
+
+- The Deployment controls multiple Replica Sets
+
+- Each Replica Set is a group of identical Pods
+
+  (with the same image, arguments, parameters ...)
+
+- During the rolling update, we have at least two Replica Sets:
+
+  - the "new" set (corresponding to the "target" version)
+
+  - at least one "old" set
+
+- We can have multiple "old" sets
+
+  (if we start another update before the first one is done)
+
+---
+
+## Update strategy
 
 - Two parameters determine the pace of the rollout: `maxUnavailable` and `maxSurge`
 
@@ -61,32 +81,6 @@
 
 ---
 
-## Building a new version of the `worker` service
-
-.warning[
-Only run these commands if you have built and pushed DockerCoins to a local registry.
-<br/>
-If you are using images from the Docker Hub (`dockercoins/worker:v0.1`), skip this.
-]
-
-.exercise[
-
-- Go to the `stacks` directory (`~/container.training/stacks`)
-
-- Edit `dockercoins/worker/worker.py`; update the first `sleep` line to sleep 1 second
-
-- Build a new tag and push it to the registry:
-  ```bash
-  #export REGISTRY=localhost:3xxxx
-  export TAG=v0.2
-  docker-compose -f dockercoins.yml build
-  docker-compose -f dockercoins.yml push
-  ```
-
-]
-
----
-
 ## Rolling out the new `worker` service
 
 .exercise[
@@ -100,12 +94,12 @@ If you are using images from the Docker Hub (`dockercoins/worker:v0.1`), skip th
 
 <!--
 ```wait NAME```
-```keys ^C```
+```key ^C```
 -->
 
 - Update `worker` either with `kubectl edit`, or by running:
   ```bash
-  kubectl set image deploy worker worker=$REGISTRY/worker:$TAG
+  kubectl set image deploy worker worker=dockercoins/worker:v0.2
   ```
 
 ]
@@ -146,8 +140,7 @@ That rollout should be pretty quick. What shows in the web UI?
 
 - Update `worker` by specifying a non-existent image:
   ```bash
-  export TAG=v0.3
-  kubectl set image deploy worker worker=$REGISTRY/worker:$TAG
+  kubectl set image deploy worker worker=dockercoins/worker:v0.3
   ```
 
 - Check what's going on:
@@ -157,7 +150,7 @@ That rollout should be pretty quick. What shows in the web UI?
 
 <!--
 ```wait Waiting for deployment```
-```keys ^C```
+```key ^C```
 -->
 
 ]
@@ -216,27 +209,14 @@ If you didn't deploy the Kubernetes dashboard earlier, just skip this slide.
 
 .exercise[
 
-- Check which port the dashboard is on:
-  ```bash
-  kubectl -n kube-system get svc socat
-  ```
+- Connect to the dashboard that we deployed earlier
+
+- Check that we have failures in Deployments, Pods, and Replica Sets
+
+- Can we see the reason for the failure?
 
 ]
 
-Note the `3xxxx` port.
-
-.exercise[
-
-- Connect to http://oneofournodes:3xxxx/
-
-<!-- ```open https://node1:3xxxx/``` -->
-
-]
-
---
-
-- We have failures in Deployments, Pods, and Replica Sets
-
 ---
 
 ## Recovering from a bad rollout
@@ -249,11 +229,7 @@ Note the `3xxxx` port.
 
 .exercise[
 
-<!--
-```keys
-^C
-```
--->
+<!-- ```key ^C``` -->
 
 - Cancel the deployment and wait for the dust to settle:
   ```bash
@@ -265,6 +241,137 @@ Note the `3xxxx` port.
 
 ---
 
+## Rolling back to an older version
+
+- We reverted to `v0.2`
+
+- But this version still has a performance problem
+
+- How can we get back to the previous version?
+
+---
+
+## Multiple "undos"
+
+- What happens if we try `kubectl rollout undo` again?
+
+.exercise[
+
+- Try it:
+  ```bash
+  kubectl rollout undo deployment worker
+  ```
+
+- Check the web UI, the list of pods ...
+
+]
+
+🤔 That didn't work.
+
+---
+
+## Multiple "undos" don't work
+
+- If we see successive versions as a stack:
+
+  - `kubectl rollout undo` doesn't "pop" the last element from the stack
+
+  - it copies the N-1th element to the top
+
+- Multiple "undos" just swap back and forth between the last two versions!
+
+.exercise[
+
+- Go back to v0.2 again:
+  ```bash
+  kubectl rollout undo deployment worker
+  ```
+
+]
+
+---
+
+## In this specific scenario
+
+- Our version numbers are easy to guess
+
+- What if we had used git hashes?
+
+- What if we had changed other parameters in the Pod spec?
+
+---
+
+## Listing versions
+
+- We can list successive versions of a Deployment with `kubectl rollout history`
+
+.exercise[
+
+- Look at our successive versions:
+  ```bash
+  kubectl rollout history deployment worker
+  ```
+
+]
+
+We don't see *all* revisions.
+
+We might see something like 1, 4, 5.
+
+(Depending on how many "undos" we did before.)
+
+---
+
+## Explaining deployment revisions
+
+- These revisions correspond to our Replica Sets
+
+- This information is stored in the Replica Set annotations
+
+.exercise[
+
+- Check the annotations for our replica sets:
+  ```bash
+  kubectl describe replicasets -l app=worker | grep -A3 ^Annotations
+  ```
+
+]
+
+---
+
+class: extra-details
+
+## What about the missing revisions?
+
+- The missing revisions are stored in another annotation:
+
+  `deployment.kubernetes.io/revision-history`
+
+- These are not shown in `kubectl rollout history`
+
+- We could easily reconstruct the full list with a script
+
+  (if we wanted to!)
+
+---
+
+## Rolling back to an older version
+
+- `kubectl rollout undo` can work with a revision number
+
+.exercise[
+
+- Roll back to the "known good" deployment version:
+  ```bash
+  kubectl rollout undo deployment worker --to-revision=1
+  ```
+
+- Check the web UI or the list of pods
+
+]
+
+---
+
 class: extra-details
 
 ## Changing rollout parameters
@@ -285,7 +392,7 @@ spec:
     spec:
       containers:
       - name: worker
-        image: $REGISTRY/worker:v0.1
+        image: dockercoins/worker:v0.1
   strategy:
     rollingUpdate:
       maxUnavailable: 0
@@ -316,7 +423,7 @@ class: extra-details
         spec:
           containers:
           - name: worker
-            image: $REGISTRY/worker:v0.1
+            image: dockercoins/worker:v0.1
       strategy:
         rollingUpdate:
           maxUnavailable: 0

slides/k8s/scalingdockercoins.md

@@ -19,17 +19,14 @@
 
 .exercise[
 
-- Open two new terminals to check what's going on with pods and deployments:
+- Open a new terminal to keep an eye on our pods:
   ```bash
   kubectl get pods -w
-  kubectl get deployments -w
   ```
 
 <!--
 ```wait RESTARTS```
-```keys ^C```
-```wait AVAILABLE```
-```keys ^C```
+```tmux split-pane -h```
 -->
 
 - Now, create more `worker` replicas:
@@ -73,6 +70,11 @@ The graph in the web UI should go up again.
   kubectl scale deployment worker --replicas=10
   ```
 
+<!--
+```key ^D```
+```key ^C```
+-->
+
 ]
 
 --

slides/k8s/setup-k8s.md

@@ -61,7 +61,8 @@
 
 - [minikube](https://kubernetes.io/docs/setup/minikube/),
   [kubespawn](https://github.com/kinvolk/kube-spawn),
-  [Docker Desktop](https://docs.docker.com/docker-for-mac/kubernetes/):
+  [Docker Desktop](https://docs.docker.com/docker-for-mac/kubernetes/),
+  [kind](https://kind.sigs.k8s.io):
   for local development
 
 - [kubicorn](https://github.com/kubicorn/kubicorn),

slides/k8s/setup-managed.md

@@ -18,7 +18,7 @@ with a cloud provider
 
 ---
 
-## EKS (the hard way)
+## EKS (the old way)
 
 - [Read the doc](https://docs.aws.amazon.com/eks/latest/userguide/getting-started-console.html)
 
@@ -36,7 +36,7 @@ with a cloud provider
 
 ---
 
-## EKS (the easy way)
+## EKS (the new way)
 
 - Install `eksctl`
 

slides/k8s/shippingimages.md

@@ -89,3 +89,30 @@
 - When picking a registry, pay attention to its build system
 
   (when it has one)
+
+---
+
+## Building on the fly
+
+- Some services can build images on the fly from a repository
+
+- Example: [ctr.run](https://ctr.run/)
+
+.exercise[
+
+- Use ctr.run to automatically build a container image and run it:
+  ```bash
+  docker run ctr.run/github.com/jpetazzo/container.training/dockercoins/hasher
+  ```
+
+<!--
+```longwait Sinatra```
+```key ^C```
+-->
+
+]
+
+There might be a long pause before the first layer is pulled,
+because the API behind `docker pull` doesn't allow to stream build logs, and there is no feedback during the build.
+
+It is possible to view the build logs by setting up an account on [ctr.run](https://ctr.run/).