➕️ Add chapter about codespaces and dev clusters

- detect which EKS version to use
  (instead of hard-coding it in the TF config)
- do not issue a CSR on EKS
  (because EKS is broken and doesn't support it)
- automatically install a StorageClass on EKS
  (because the EBS CSI addon doesn't install one by default)
- put EKS clusters in the default VPC
  (instead of creating one VPC per cluster,
  since there is a default limit of 5 VPC per region)

.devcontainer/devcontainer.json

@@ -0,0 +1,26 @@
+{
+        "name": "container.training environment to get started with Docker and/or Kubernetes",
+        "image": "ghcr.io/jpetazzo/shpod",
+        "features": {
+                //"ghcr.io/devcontainers/features/common-utils:2": {}
+        },
+
+        // Use 'forwardPorts' to make a list of ports inside the container available locally.
+        "forwardPorts": [],
+
+        //"postCreateCommand": "... install extra packages...",
+        "postStartCommand": "dind.sh",
+
+        // This lets us use "docker-outside-docker".
+        // Unfortunately, minikube, kind, etc. don't work very well that way;
+        // so for now, we'll likely use "docker-in-docker" instead (with a 
+        // privilege dcontainer). But we're still exposing that socket in case
+        // someone wants to do something interesting with it.
+        "mounts": ["source=/var/run/docker.sock,target=/var/run/docker-host.sock,type=bind"],
+
+        // This is for docker-in-docker.
+        "privileged": true,
+
+        // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+        "remoteUser": "k8s"
+}

.gitignore

@@ -9,6 +9,7 @@ prepare-labs/terraform/many-kubernetes/one-kubernetes-config/config.tf
 prepare-labs/terraform/many-kubernetes/one-kubernetes-module/*.tf
 prepare-labs/terraform/tags
 prepare-labs/terraform/virtual-machines/openstack/*.tfvars
+prepare-labs/terraform/virtual-machines/proxmox/*.tfvars
 prepare-labs/www
 
 slides/*.yml.html

dockercoins/hasher/Dockerfile

@@ -1,7 +1,7 @@
 FROM ruby:alpine
 RUN apk add --update build-base curl
 RUN gem install sinatra --version '~> 3'
-RUN gem install thin
+RUN gem install thin --version '~> 1'
 ADD hasher.rb /
 CMD ["ruby", "hasher.rb"]
 EXPOSE 80

dockercoins/webui/Dockerfile

@@ -1,5 +1,5 @@
 FROM node:4-slim
-RUN npm install express
+RUN npm install express@4
 RUN npm install redis@3
 COPY files/ /files/
 COPY webui.js /

k8s/blue.yaml

@@ -0,0 +1,33 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: blue
+  name: blue
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: blue
+  template:
+    metadata:
+      labels:
+        app: blue
+    spec:
+      containers:
+      - image: jpetazzo/color
+        name: color
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: blue
+  name: blue
+spec:
+  ports:
+  - name: "80"
+    port: 80
+  selector:
+    app: blue

k8s/kustomize-examples/ollama-with-sidecar/add-haproxy-sidecar/cleanup/kustomization.yaml

@@ -0,0 +1,12 @@
+# This removes the haproxy Deployment.
+
+apiVersion: kustomize.config.k8s.io/v1alpha1
+kind: Component
+
+patches:
+- patch: |-
+    $patch: delete
+    kind: Deployment
+    apiVersion: apps/v1
+    metadata:
+      name: haproxy

k8s/kustomize-examples/ollama-with-sidecar/add-haproxy-sidecar/kustomization.yaml

@@ -0,0 +1,14 @@
+apiVersion: kustomize.config.k8s.io/v1alpha1
+kind: Component
+
+# Within a Kustomization, it is not possible to specify in which
+# order transformations (patches, replacements, etc) should be
+# executed. If we want to execute transformations in a specific
+# order, one possibility is to put them in individual components,
+# and then invoke these components in the order we want.
+# It works, but it creates an extra level of indirection, which
+# reduces readability and complicates maintenance.
+
+components:
+- setup
+- cleanup

k8s/kustomize-examples/ollama-with-sidecar/add-haproxy-sidecar/setup/haproxy.cfg

@@ -0,0 +1,20 @@
+global
+  #log stdout format raw local0
+  #daemon
+  maxconn 32
+defaults
+  #log global
+  timeout client 1h
+  timeout connect 1h
+  timeout server 1h
+  mode http
+  option abortonclose
+frontend metrics
+  bind :9000
+  http-request use-service prometheus-exporter
+frontend ollama_frontend
+  bind :8000
+  default_backend ollama_backend
+  maxconn 16
+backend ollama_backend
+  server ollama_server localhost:11434 check

k8s/kustomize-examples/ollama-with-sidecar/add-haproxy-sidecar/setup/haproxy.yaml

@@ -0,0 +1,39 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: haproxy
+  name: haproxy
+spec:
+  selector:
+    matchLabels:
+      app: haproxy
+  template:
+    metadata:
+      labels:
+        app: haproxy
+    spec:
+      volumes:
+      - name: haproxy
+        configMap:
+          name: haproxy
+      containers:
+      - image: haproxy:3.0
+        name: haproxy
+        volumeMounts:
+        - name: haproxy
+          mountPath: /usr/local/etc/haproxy
+        readinessProbe:
+          httpGet:
+            port: 9000
+        ports:
+        - name: haproxy
+          containerPort: 8000
+        - name: metrics
+          containerPort: 9000
+        resources:
+          requests:
+            cpu: 0.05
+          limits:
+            cpu: 1

k8s/kustomize-examples/ollama-with-sidecar/add-haproxy-sidecar/setup/kustomization.yaml

@@ -0,0 +1,75 @@
+# This adds a sidecar to the ollama Deployment, by taking
+# the pod template and volumes from the haproxy Deployment.
+# The idea is to allow to run ollama+haproxy in two modes:
+# - separately (each with their own Deployment),
+# - together in the same Pod, sidecar-style.
+# The YAML files define how to run them separetely, and this
+# "replacements" directive fetches a specific volume and
+# a specific container from the haproxy Deployment, to add
+# them to the ollama Deployment.
+#
+# This would be simpler if kustomize allowed to append or
+# merge lists in "replacements"; but it doesn't seem to be
+# possible at the moment.
+#
+# It would be even better if kustomize allowed to perform
+# a strategic merge using a fieldPath as the source, because
+# we could merge both the containers and the volumes in a
+# single operation.
+#
+# Note that technically, it might be possible to layer
+# multiple kustomizations so that one generates the patch
+# to be used in another; but it wouldn't be very readable
+# or maintainable so we decided to not do that right now.
+#
+# However, the current approach (fetching fields one by one)
+# has an advantage: it could let us transform the haproxy
+# container into a real sidecar (i.e. an initContainer with
+# a restartPolicy=Always).
+
+apiVersion: kustomize.config.k8s.io/v1alpha1
+kind: Component
+
+resources:
+- haproxy.yaml
+
+configMapGenerator:
+- name: haproxy
+  files:
+  - haproxy.cfg
+
+replacements:
+- source:
+    kind: Deployment
+    name: haproxy
+    fieldPath: spec.template.spec.volumes.[name=haproxy]
+  targets:
+  - select:
+      kind: Deployment
+      name: ollama
+    fieldPaths:
+    - spec.template.spec.volumes.[name=haproxy]
+    options:
+      create: true
+- source:
+    kind: Deployment
+    name: haproxy
+    fieldPath: spec.template.spec.containers.[name=haproxy]
+  targets:
+  - select:
+      kind: Deployment
+      name: ollama
+    fieldPaths:
+    - spec.template.spec.containers.[name=haproxy]
+    options:
+      create: true
+- source:
+    kind: Deployment
+    name: haproxy
+    fieldPath: spec.template.spec.containers.[name=haproxy].ports.[name=haproxy].containerPort
+  targets:
+  - select:
+      kind: Service
+      name: ollama
+    fieldPaths:
+    - spec.ports.[name=11434].targetPort

k8s/kustomize-examples/ollama-with-sidecar/blue.yaml

@@ -0,0 +1,34 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: blue
+  name: blue
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: blue
+  template:
+    metadata:
+      labels:
+        app: blue
+    spec:
+      containers:
+      - image: jpetazzo/color
+        name: color
+        ports:
+        - containerPort: 80
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: blue
+  name: blue
+spec:
+  ports:
+  - port: 80
+  selector:
+    app: blue

k8s/kustomize-examples/ollama-with-sidecar/kustomization.yaml

@@ -0,0 +1,94 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+# Each of these YAML files contains a Deployment and a Service.
+# The blue.yaml file is here just to demonstrate that the rest
+# of this Kustomization can be precisely scoped to the ollama
+# Deployment (and Service): the blue Deployment and Service
+# shouldn't be affected by our kustomize transformers.
+resources:
+- ollama.yaml
+- blue.yaml
+
+buildMetadata:
+
+# Add a label app.kubernetes.io/managed-by=kustomize-vX.Y.Z
+- managedByLabel
+
+# Add an annotation config.kubernetes.io/origin, indicating:
+# - which file defined that resource;
+# - if it comes from a git repository, which one, and which
+#   ref (tag, branch...) it was.
+- originAnnotations
+
+# Add an annotation alpha.config.kubernetes.io/transformations
+# indicating which patches and other transformers have changed
+# each resource.
+- transformerAnnotations
+
+# Let's generate a ConfigMap with literal values.
+# Note that this will actually add a suffix to the name of the
+# ConfigMaps (e.g.: ollama-8bk8bd8m76) and it will update all
+# references to the ConfigMap (e.g. in Deployment manifests)
+# accordingly. The suffix is a hash of the ConfigMap contents,
+# so that basically, if the ConfigMap is edited, any workload
+# using that ConfigMap will automatically do a rolling update.
+configMapGenerator:
+- name: ollama
+  literals:
+  - "model=gemma3:270m"
+  - "prompt=If you visit Paris, I suggest that you"
+  - "queue=4"
+  name: ollama
+
+patches:
+# The Deployment manifest in ollama.yaml doesn't specify
+# resource requests and limits, so that it can run on any
+# cluster (including resource-constrained local clusters
+# like KiND or minikube). The example belows add CPU
+# requests and limits using a strategic merge patch.
+# The patch is inlined here, but it could also be put
+# in a file and referenced with "path: xxxxxx.yaml".
+- patch: |
+    apiVersion: apps/v1
+    kind: Deployment
+    metadata:
+      name: ollama
+    spec:
+      template:
+        spec:
+          containers:
+          - name: ollama
+            resources:
+              requests:
+                cpu: 1
+              limits:
+                cpu: 2
+# This will have the same effect, with one little detail:
+# JSON patches cannot specify containers by name, so this
+# assumes that the ollama container is the first one in
+# the pod template (whereas the strategic merge patch can
+# use "merge keys" and identify containers by their name).
+#- target:
+#    kind: Deployment
+#    name: ollama
+#  patch: |
+#    - op: add
+#      path: /spec/template/spec/containers/0/resources
+#      value:
+#        requests:
+#          cpu: 1
+#        limits:
+#          cpu: 2
+
+# A "component" is a bit like a "base", in the sense that
+# it lets us define some reusable resources and behaviors.
+# There is a key different, though:
+# - a "base" will be evaluated in isolation: it will
+#   generate+transform some resources, then these resources
+#   will be included in the main Kustomization;
+# - a "component" has access to all the resources that
+#   have been generated by the main Kustomization, which
+#   means that it can transform them (with patches etc).
+components:
+- add-haproxy-sidecar

k8s/kustomize-examples/ollama-with-sidecar/ollama.yaml

@@ -0,0 +1,73 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: ollama
+  name: ollama
+spec:
+  selector:
+    matchLabels:
+      app: ollama
+  template:
+    metadata:
+      labels:
+        app: ollama
+    spec:
+      volumes:
+      - name: ollama
+        hostPath:
+          path: /opt/ollama
+          type: DirectoryOrCreate
+      containers:
+      - image: ollama/ollama
+        name: ollama
+        env:
+        - name: OLLAMA_MAX_QUEUE
+          valueFrom:
+            configMapKeyRef:
+              name: ollama
+              key: queue
+        - name: MODEL
+          valueFrom:
+            configMapKeyRef:
+              name: ollama
+              key: model
+        volumeMounts:
+        - name: ollama
+          mountPath: /root/.ollama
+        lifecycle:
+          postStart:
+            exec:
+              command:
+                - /bin/sh
+                - -c
+                - ollama pull $MODEL
+        livenessProbe:
+          httpGet:
+            port: 11434
+        readinessProbe:
+          exec:
+            command:
+              - /bin/sh
+              - -c
+              - ollama show $MODEL
+        ports:
+        - name: ollama
+          containerPort: 11434
+---
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app: ollama
+  name: ollama
+spec:
+  ports:
+  - name: "11434"
+    port: 11434
+    protocol: TCP
+    targetPort: 11434
+  selector:
+    app: ollama
+  type: ClusterIP

k8s/kustomize-examples/registry-with-prefix-transformer/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- microservices
+- redis

k8s/kustomize-examples/registry-with-prefix-transformer/microservices/kustomization.yaml

@@ -0,0 +1,13 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- microservices.yaml
+transformers:
+- |
+  apiVersion: builtin
+  kind: PrefixSuffixTransformer
+  metadata:
+    name: use-ghcr-io
+  prefix: ghcr.io/
+  fieldSpecs:
+  - path: spec/template/spec/containers/image

k8s/kustomize-examples/registry-with-prefix-transformer/microservices/microservices.yaml

@@ -0,0 +1,125 @@
+---
+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: 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/kustomize-examples/registry-with-prefix-transformer/redis/kustomization.yaml

@@ -0,0 +1,4 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- redis.yaml

k8s/kustomize-examples/registry-with-prefix-transformer/redis/redis.yaml

@@ -0,0 +1,35 @@
+---
+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

k8s/kustomize-examples/registry-with-replacements/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/kustomize-examples/registry-with-replacements/kustomization.yaml

@@ -0,0 +1,30 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- dockercoins.yaml
+replacements:
+- sourceValue: ghcr.io/dockercoins
+  targets:
+  - select:
+      kind: Deployment
+      labelSelector: "app in (hasher,rng,webui,worker)"
+      # It will soon be possible to use regexes in replacement selectors,
+      # meaning that the "labelSelector:" above can be replaced with the
+      # following "name:" selector which is a tiny bit simpler:
+      #name: hasher|rng|webui|worker
+      # Regex support in replacement selectors was added by this PR:
+      # https://github.com/kubernetes-sigs/kustomize/pull/5863
+      # This PR was merged in August 2025, but as of October 2025, the
+      # latest release of Kustomize is 5.7.1, which was released in July.
+      # Hopefully the feature will be available in the next release :)
+    # Another possibility would be to select all Deployments, and then
+    # reject the one(s) for which we don't want to update the registry;
+    # for instance:
+    #reject:
+    #  kind: Deployment
+    #  name: redis
+    fieldPaths:
+    - spec.template.spec.containers.*.image
+    options:
+      delimiter: "/"
+      index: 0

k8s/kyverno-pod-color-1.yaml

@@ -3,7 +3,6 @@ kind: ClusterPolicy
 metadata:
   name: pod-color-policy-1
 spec:
-  validationFailureAction: enforce
   rules:
   - name: ensure-pod-color-is-valid
     match:
@@ -18,5 +17,6 @@ spec:
             operator: NotIn
             values: [ red, green, blue ]
     validate:
+      failureAction: Enforce
       message: "If it exists, the label color must be red, green, or blue."
       deny: {}

k8s/kyverno-pod-color-2.yaml

@@ -3,7 +3,6 @@ kind: ClusterPolicy
 metadata:
   name: pod-color-policy-2
 spec:
-  validationFailureAction: enforce
   background: false
   rules:
   - name: prevent-color-change
@@ -22,6 +21,7 @@ spec:
       operator: NotEquals
       value: ""
     validate:
+      failureAction: Enforce
       message: "Once label color has been added, it cannot be changed."
       deny:
         conditions:

k8s/kyverno-pod-color-3.yaml

@@ -3,7 +3,6 @@ kind: ClusterPolicy
 metadata:
   name: pod-color-policy-3
 spec:
-  validationFailureAction: enforce
   background: false
   rules:
   - name: prevent-color-change
@@ -22,7 +21,6 @@ spec:
       operator: Equals
       value: ""
     validate:
+      failureAction: Enforce
       message: "Once label color has been added, it cannot be removed."
-      deny:
-        conditions:
-
+      deny: {}

prepare-labs/README.md

@@ -66,7 +66,7 @@ Here is where we look for credentials for each provider:
 - Civo: CLI configuration file (`~/.civo.json`)
 - Digital Ocean: CLI configuration file (`~/.config/doctl/config.yaml`)
 - Exoscale: CLI configuration file (`~/.config/exoscale/exoscale.toml`)
-- Google Cloud: FIXME, note that the project name is currently hard-coded to `prepare-tf`
+- Google Cloud: we're using "Application Default Credentials (ADC)"; run `gcloud auth application-default login`; note that we'll use the default "project" set in `gcloud` unless you set the `GOOGLE_PROJECT` environment variable
 - Hetzner: CLI configuration file (`~/.config/hcloud/cli.toml`)
 - Linode: CLI configuration file (`~/.config/linode-cli`)
 - OpenStack: you will need to write a tfvars file (check [that exemple](terraform/virtual-machines/openstack/tfvars.example))

prepare-labs/konk.sh

@@ -5,34 +5,53 @@
 # 10% CPU
 # (See https://docs.google.com/document/d/1n0lwp6rQKQUIuo_A5LQ1dgCzrmjkDjmDtNj1Jn92UrI)
 # PRO2-XS = 4 core, 16 gb
+#
+# With vspod:
+# 800 MB RAM
+# 33% CPU
+#
 
-PROVIDER=scaleway
+set -e
+
+KONKTAG=konk
+PROVIDER=linode
+STUDENTS=5
 
 case "$PROVIDER" in
 linode)
   export TF_VAR_node_size=g6-standard-6
-  export TF_VAR_location=eu-west
+  export TF_VAR_location=fr-par
   ;;
 scaleway)
   export TF_VAR_node_size=PRO2-XS
+  # For tiny testing purposes, these are okay too:
+  #export TF_VAR_node_size=PLAY2-NANO
   export TF_VAR_location=fr-par-2
   ;;
 esac
 
-./labctl create --mode mk8s --settings settings/konk.env --provider $PROVIDER --tag konk
-
 # set kubeconfig file
 export KUBECONFIG=~/kubeconfig
-cp tags/konk/stage2/kubeconfig.101 $KUBECONFIG
+
+if [ "$PROVIDER" = "kind" ]; then
+  kind create cluster --name $KONKTAG
+  ADDRTYPE=InternalIP
+else
+  if ! [ -f tags/$KONKTAG/stage2/kubeconfig.101 ]; then
+    ./labctl create --mode mk8s --settings settings/konk.env --provider $PROVIDER --tag $KONKTAG
+  fi
+  cp tags/$KONKTAG/stage2/kubeconfig.101 $KUBECONFIG
+  ADDRTYPE=ExternalIP
+fi
 
 # set external_ip labels
-kubectl get nodes -o=jsonpath='{range .items[*]}{.metadata.name} {.status.addresses[?(@.type=="ExternalIP")].address}{"\n"}{end}' |
-while read node address; do
+kubectl get nodes -o=jsonpath='{range .items[*]}{.metadata.name} {.status.addresses[?(@.type=="'$ADDRTYPE'")].address}{"\n"}{end}' |
+while read node address ignoredaddresses; do
   kubectl label node $node external_ip=$address
 done
 
 # vcluster all the things
-./labctl create --settings settings/mk8s.env --provider vcluster --mode mk8s --students 50
+./labctl create --settings settings/mk8s.env --provider vcluster --mode mk8s --students $STUDENTS
 
 # install prometheus stack because that's cool
 helm upgrade --install --repo https://prometheus-community.github.io/helm-charts \

prepare-labs/lib/commands.sh

@@ -49,6 +49,41 @@ _cmd_clean() {
 	done	
 }
 
+_cmd codeserver "Install code-server on the clusters"
+_cmd_codeserver() {
+    TAG=$1
+    need_tag
+
+    ARCH=${ARCHITECTURE-amd64}
+    CODESERVER_VERSION=4.96.4
+    CODESERVER_URL=https://github.com/coder/code-server/releases/download/v${CODESERVER_VERSION}/code-server-${CODESERVER_VERSION}-linux-${ARCH}.tar.gz
+    pssh "
+    set -e
+    i_am_first_node || exit 0
+    if ! [ -x /usr/local/bin/code-server ]; then
+        curl -fsSL $CODESERVER_URL | sudo tar zx -C /opt
+        sudo ln -s /opt/code-server-${CODESERVER_VERSION}-linux-${ARCH}/bin/code-server /usr/local/bin/code-server
+        sudo -u $USER_LOGIN -H code-server --install-extension ms-azuretools.vscode-docker
+        sudo -u $USER_LOGIN -H code-server --install-extension ms-kubernetes-tools.vscode-kubernetes-tools
+        sudo -u $USER_LOGIN -H mkdir -p /home/$USER_LOGIN/.local/share/code-server/User
+        echo '{\"workbench.startupEditor\": \"terminal\"}' | sudo -u $USER_LOGIN tee /home/$USER_LOGIN/.local/share/code-server/User/settings.json
+        sudo -u $USER_LOGIN mkdir -p /home/$USER_LOGIN/.config/systemd/user
+        sudo -u $USER_LOGIN tee /home/$USER_LOGIN/.config/systemd/user/code-server.service <<EOF
+[Unit]
+Description=code-server
+
+[Install]
+WantedBy=default.target
+
+[Service]
+ExecStart=/usr/local/bin/code-server --bind-addr [::]:1789
+Restart=always
+EOF
+        sudo systemctl --user -M $USER_LOGIN@ enable code-server.service --now
+        sudo loginctl enable-linger $USER_LOGIN
+    fi"
+}
+
 _cmd createuser "Create the user that students will use"
 _cmd_createuser() {
     TAG=$1
@@ -235,7 +270,27 @@ _cmd_create() {
 
     ln -s ../../$SETTINGS tags/$TAG/settings.env.orig
     cp $SETTINGS tags/$TAG/settings.env
-    . $SETTINGS
+
+    # For Google Cloud, it is necessary to specify which "project" to use.
+    # Unfortunately, the Terraform provider doesn't seem to have a way
+    # to detect which Google Cloud project you want to use; it has to be
+    # specified one way or another. Let's decide that it should be set with
+    # the GOOGLE_PROJECT env var; and if that var is not set, we'll try to
+    # figure it out from gcloud.
+    # (See https://github.com/hashicorp/terraform-provider-google/issues/10907#issuecomment-1015721600)
+    # Since we need that variable to be set each time we'll call Terraform
+    # (e.g. when destroying the environment), let's save it to the settings.env
+    # file.
+    if [ "$PROVIDER" = "googlecloud" ]; then
+        if ! [ "$GOOGLE_PROJECT" ]; then
+            info "PROVIDER=googlecloud but GOOGLE_PROJECT is not set. Detecting it."
+            GOOGLE_PROJECT=$(gcloud config get project)
+            info "GOOGLE_PROJECT will be set to '$GOOGLE_PROJECT'."
+        fi
+        echo "export GOOGLE_PROJECT=$GOOGLE_PROJECT" >> tags/$TAG/settings.env
+    fi
+
+    . tags/$TAG/settings.env
 
     echo $MODE > tags/$TAG/mode
     echo $PROVIDER > tags/$TAG/provider
@@ -262,20 +317,9 @@ _cmd_create() {
         if [ "$CLUSTERSIZE" ]; then
             echo nodes_per_cluster = $CLUSTERSIZE >> terraform.tfvars
         fi
-        for RETRY in 1 2 3; do
-            if terraform apply -auto-approve; then
-                touch terraform.ok
-                break
-            fi
-        done
-        if ! [ -f terraform.ok ]; then
-            die "Terraform failed."
-        fi
     )
 
     sep
-    info "Successfully created $COUNT instances with tag $TAG"
-    echo create_ok > tags/$TAG/status
 
     # If the settings.env file has a "STEPS" field,
     # automatically execute all the actions listed in that field.
@@ -350,9 +394,13 @@ _cmd_clusterize() {
     done < /tmp/cluster
     "
 
-    while read line; do
-        printf '{"login": "%s", "password": "%s", "ipaddrs": "%s"}\n' "$USER_LOGIN" "$USER_PASSWORD" "$line"
-    done < tags/$TAG/clusters.tsv > tags/$TAG/logins.jsonl
+    jq --raw-input --compact-output \
+       --arg USER_LOGIN "$USER_LOGIN" --arg USER_PASSWORD "$USER_PASSWORD" '
+    {
+      "login": $USER_LOGIN,
+      "password": $USER_PASSWORD,
+      "ipaddrs": .
+    }' < tags/$TAG/clusters.tsv > tags/$TAG/logins.jsonl
 
     echo cluster_ok > tags/$TAG/status
 }
@@ -592,7 +640,9 @@ EOF
     # Install weave as the pod network
     pssh "
     if i_am_first_node; then
-        kubectl apply -f https://github.com/weaveworks/weave/releases/download/v2.8.1/weave-daemonset-k8s-1.11.yaml
+        curl -fsSL https://github.com/weaveworks/weave/releases/download/v2.8.1/weave-daemonset-k8s-1.11.yaml |
+        sed s,weaveworks/weave,quay.io/rackspace/weave, |
+        kubectl apply -f-
     fi"
 
     # FIXME this is a gross hack to add the deployment key to our SSH agent,
@@ -948,7 +998,7 @@ _cmd_logins() {
     need_tag $TAG
 
     cat tags/$TAG/logins.jsonl \
-    | jq -r '"\(.password)\tssh -l \(.login)\(if .port then " -p \(.port)" else "" end)\t\(.ipaddrs)"'
+    | jq -r '"\(if .codeServerPort then "\(.codeServerPort)\t" else "" end )\(.password)\tssh -l \(.login)\(if .port then " -p \(.port)" else "" end)\t\(.ipaddrs)"'
 }
 
 _cmd maketag "Generate a quasi-unique tag for a group of instances"
@@ -1090,7 +1140,7 @@ _cmd_tailhist () {
     set -e
     sudo apt-get install unzip -y
     wget -c https://github.com/joewalnes/websocketd/releases/download/v0.3.0/websocketd-0.3.0-linux_$ARCH.zip
-    unzip websocketd-0.3.0-linux_$ARCH.zip websocketd
+    unzip -o websocketd-0.3.0-linux_$ARCH.zip websocketd
     sudo mv websocketd /usr/local/bin/websocketd
     sudo mkdir -p /opt/tailhist
     sudo tee /opt/tailhist.service <<EOF
@@ -1113,14 +1163,35 @@ EOF
     pssh -I sudo tee /opt/tailhist/index.html <lib/tailhist.html
 }
 
+_cmd terraform "Apply Terraform configuration to provision resources."
+_cmd_terraform() {
+    TAG=$1
+    need_tag
+    echo terraforming > tags/$TAG/status
+    (
+        cd tags/$TAG
+        terraform apply -auto-approve
+        # The Terraform provider for Proxmox has a bug; sometimes it fails
+        # to obtain VM address from the QEMU agent. In that case, we put
+        # ERROR in the ips.txt file (instead of the VM IP address). Detect
+        # that so that we run Terraform again (this typically solves the issue).
+        if grep -q ERROR ips.txt; then
+          die "Couldn't obtain IP address of some machines. Try to re-run terraform."
+        fi
+    )
+    echo terraformed > tags/$TAG/status
+
+}
+
 _cmd tools "Install a bunch of useful tools (editors, git, jq...)"
 _cmd_tools() {
     TAG=$1
     need_tag
 
     pssh "
+    set -e
     sudo apt-get -q update
-    sudo apt-get -qy install apache2-utils emacs-nox git httping htop jid joe jq mosh python-setuptools tree unzip
+    sudo apt-get -qy install apache2-utils argon2 emacs-nox git httping htop jid joe jq mosh tree unzip
     # This is for VMs with broken PRNG (symptom: running docker-compose randomly hangs)
     sudo apt-get -qy install haveged
     "
@@ -1167,14 +1238,17 @@ fi
     "
 }
 
-_cmd ssh "Open an SSH session to the first node of a tag"
+_cmd ssh "Open an SSH session to a node (first one by default)"
 _cmd_ssh() {
     TAG=$1
     need_tag
-    IP=$(head -1 tags/$TAG/ips.txt)
-    info "Logging into $IP (default password: $USER_PASSWORD)"
-    ssh $SSHOPTS $USER_LOGIN@$IP
-
+    if [ "$2" ]; then
+        ssh -l ubuntu -i tags/$TAG/id_rsa $2
+    else
+        IP=$(head -1 tags/$TAG/ips.txt)
+        info "Logging into $IP (default password: $USER_PASSWORD)"
+        ssh $SSHOPTS $USER_LOGIN@$IP
+    fi
 }
 
 _cmd tags "List groups of VMs known locally"
@@ -1260,7 +1334,13 @@ _cmd_passwords() {
     $0 ips "$TAG" | paste "$PASSWORDS_FILE" - | while read password nodes; do
         info "Setting password for $nodes..."
         for node in $nodes; do
-            echo $USER_LOGIN:$password | ssh $SSHOPTS -i tags/$TAG/id_rsa ubuntu@$node sudo chpasswd
+            echo $USER_LOGIN $password | ssh $SSHOPTS -i tags/$TAG/id_rsa ubuntu@$node '
+                read login password
+                echo $login:$password | sudo chpasswd
+                hashedpassword=$(echo -n $password | argon2 saltysalt$RANDOM -e)
+                sudo -u $login mkdir -p /home/$login/.config/code-server
+                echo "hashed-password: \"$hashedpassword\"" | sudo -u $login tee /home/$login/.config/code-server/config.yaml >/dev/null
+                '
         done
     done
     info "Done."
@@ -1292,6 +1372,11 @@ _cmd_wait() {
     pssh -l $SSH_USER "
     if [ -d /var/lib/cloud ]; then
         cloud-init status --wait
+        case $? in
+        0) exit 0;; # all is good
+        2) exit 0;; # recoverable error (happens with proxmox deprecated cloud-init payloads)
+        *) exit 1;; # all other problems
+        esac
     fi"
 }
 
@@ -1334,7 +1419,7 @@ WantedBy=multi-user.target
 
 [Service]
 WorkingDirectory=/opt/webssh
-ExecStart=/usr/bin/env python run.py --fbidhttp=false --port=1080 --policy=reject
+ExecStart=/usr/bin/env python3 run.py --fbidhttp=false --port=1080 --policy=reject
 User=nobody
 Group=nogroup
 Restart=always

prepare-labs/lib/pssh.sh

@@ -23,6 +23,14 @@ pssh() {
     # necessary - or down to zero, too.
     sleep ${PSSH_DELAY_PRE-1}
 
+    # When things go wrong, it's convenient to ask pssh to show the output
+    # of the failed command. Let's make that easy with a DEBUG env var.
+    if [ "$DEBUG" ]; then
+        PSSH_I=-i
+    else
+        PSSH_I=""
+    fi
+
     $(which pssh || which parallel-ssh) -h $HOSTFILE -l ubuntu \
         --par ${PSSH_PARALLEL_CONNECTIONS-100} \
         --timeout 300 \
@@ -31,5 +39,6 @@ pssh() {
         -O UserKnownHostsFile=/dev/null \
         -O StrictHostKeyChecking=no \
         -O ForwardAgent=yes \
+        $PSSH_I \
         "$@"
 }

prepare-labs/settings/admin-kubenet.env

@@ -7,6 +7,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-kuberouter.env

@@ -7,6 +7,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-monokube.env

@@ -11,6 +11,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-oldversion.env

@@ -10,6 +10,7 @@ USER_PASSWORD=training
 KUBEVERSION=1.28.9
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-polykube.env

@@ -6,6 +6,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-test.env

@@ -6,6 +6,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/docker.env

@@ -6,6 +6,7 @@ USER_LOGIN=docker
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize
@@ -14,6 +15,5 @@ STEPS="
   createuser
   webssh
   tailhist
-  cards
   ips
-"
+"

prepare-labs/settings/konk.env

@@ -3,4 +3,4 @@ CLUSTERSIZE=5
 USER_LOGIN=k8s
 USER_PASSWORD=
 
-STEPS="stage2"
+STEPS="terraform stage2"

prepare-labs/settings/kubernetes.env

@@ -6,6 +6,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/largekube.env

@@ -7,6 +7,7 @@ USER_LOGIN=k8s
 USER_PASSWORD=training
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/mk8s.env

@@ -1,4 +1,4 @@
 USER_LOGIN=k8s
 USER_PASSWORD=
 
-STEPS="stage2"
+STEPS="terraform stage2"

prepare-labs/settings/portal.env

@@ -1,4 +1,4 @@
-#export TF_VAR_node_size=GP2.4
+#export TF_VAR_node_size=GP4.4
 #export TF_VAR_node_size=g6-standard-6
 #export TF_VAR_node_size=m7i.xlarge
 
@@ -11,6 +11,7 @@ USER_LOGIN=portal
 USER_PASSWORD=CHANGEME
 
 STEPS="
+  terraform
   wait
   standardize
   clusterize

prepare-labs/templates/cards.html

@@ -69,7 +69,7 @@ body {
 body {
     width: 6.75in; /* two cards wide */
     margin-left: 0.875in; /* (8.5in - 6.75in)/2 */
-    margin-top: 0; /* NOTE: we have to manually specify a top margin of e.g. 0.1875in when printing */
+    margin-top: 0.1875in; /* (11in - 5 cards)/2 */
 }
 {% endif %}
 

prepare-labs/templates/cards.yaml

@@ -8,11 +8,12 @@ backside: |
     Thanks for attending the Asynchronous Architecture Patterns workshop at QCON!
   </p>
   <p>
-    If you'd like me to send you a copy of the recording of the workshop
-    and of the training materials,
-    please scan that QR code to leave me your
-    contact information. Thank you!
+    <b>This QR code will give you my contact info</b> as well as a link to a feedback form.
   </p>
-qrcode: https://2024-11-qconsf.container.training/q
+  <p>
+    If you liked this workshop, I can train your team, in person or online, with custom
+    courses of any length and any level, on Docker, Kubernetes, and MLops.
+  </p>
+qrcode: https://2024-11-qconsf.container.training/#contact
 thing: Kubernetes cluster
-image: logo-bento.svg
+image: logo-kubernetes.png

prepare-labs/terraform/many-kubernetes/stage2.tmpl

@@ -2,7 +2,11 @@ terraform {
   required_providers {
     kubernetes = {
       source  = "hashicorp/kubernetes"
-      version = "2.16.1"
+      version = "~> 2.38.0"
+    }
+    helm = {
+      source = "hashicorp/helm"
+      version = "~> 3.0"
     }
   }
 }
@@ -14,6 +18,20 @@ provider "kubernetes" {
   config_path = "./kubeconfig.${index}"
 }
 
+provider "helm" {
+  alias = "cluster_${index}"
+  kubernetes = {
+    config_path = "./kubeconfig.${index}"
+  }
+}
+
+# Password used for SSH and code-server access
+resource "random_string" "shpod_${index}" {
+  length  = 6
+  special = false
+  upper   = false
+}
+
 resource "kubernetes_namespace" "shpod_${index}" {
   provider = kubernetes.cluster_${index}
   metadata {
@@ -21,121 +39,53 @@ resource "kubernetes_namespace" "shpod_${index}" {
   }
 }
 
-resource "kubernetes_deployment" "shpod_${index}" {
+data "kubernetes_service" "shpod_${index}" {
+  depends_on = [ helm_release.shpod_${index} ]
   provider = kubernetes.cluster_${index}
   metadata {
     name = "shpod"
-    namespace = kubernetes_namespace.shpod_${index}.metadata.0.name
-  }
-  spec {
-    selector {
-      match_labels = {
-        app = "shpod"
-      }
-    }
-    template {
-      metadata {
-        labels = {
-          app = "shpod"
-        }
-      }
-      spec {
-        service_account_name = "shpod"
-        container {
-          image = "jpetazzo/shpod"
-          name = "shpod"
-          env {
-            name = "PASSWORD"
-            value = random_string.shpod_${index}.result
-          }
-          lifecycle {
-            post_start {
-              exec {
-                command = [ "sh", "-c", "curl http://myip.enix.org/REMOTE_ADDR > /etc/HOSTIP || true" ]
-              }
-            }
-          }
-          resources {
-            limits = {
-              cpu    = "2"
-              memory = "500M"
-            }
-            requests = {
-              cpu    = "100m"
-              memory = "250M"
-            }
-          }
-        }
-      }
-    }
-  }
-}
-
-resource "kubernetes_service" "shpod_${index}" {
-  provider = kubernetes.cluster_${index}
-  lifecycle {
-    # Folks might alter their shpod Service to expose extra ports.
-    # Don't reset their changes.
-    ignore_changes = [ spec ]
-  }
-  metadata {
-    name = "shpod"
-    namespace = kubernetes_namespace.shpod_${index}.metadata.0.name
-  }
-  spec {
-    selector = {
-      app = "shpod"
-    }
-    port {
-      name = "ssh"
-      port = 22
-      target_port = 22
-    }
-    type = "NodePort"
-  }
-}
-
-resource "kubernetes_service_account" "shpod_${index}" {
-  provider = kubernetes.cluster_${index}
-  metadata {
-    name = "shpod"
-    namespace = kubernetes_namespace.shpod_${index}.metadata.0.name
-  }
-}
-
-resource "kubernetes_cluster_role_binding" "shpod_${index}" {
-  provider = kubernetes.cluster_${index}
-  metadata {
-    name = "shpod"
-  }
-  role_ref {
-    api_group = "rbac.authorization.k8s.io"
-    kind      = "ClusterRole"
-    name      = "cluster-admin"
-  }
-  subject {
-    kind      = "ServiceAccount"
-    name      = "shpod"
     namespace = "shpod"
   }
-  subject {
-    api_group = "rbac.authorization.k8s.io"
-    kind      = "Group"
-    name      = "shpod-cluster-admins"
-  }
 }
 
-resource "random_string" "shpod_${index}" {
-  length  = 6
-  special = false
-  upper   = false
-}
-
-provider "helm" {
-  alias = "cluster_${index}"
-  kubernetes {
-    config_path = "./kubeconfig.${index}"
-  }
+resource "helm_release" "shpod_${index}" {
+  provider = helm.cluster_${index}
+  repository = "https://shpod.in"
+  chart = "shpod"
+  name = "shpod"
+  namespace = "shpod"
+  create_namespace = false
+  values = [
+    yamlencode({
+      service = {
+        type = "NodePort"
+      }
+      resources = {
+        requests = {
+          cpu = "100m"
+          memory = "500M"
+        }
+        limits = {
+          cpu = "1"
+          memory = "1000M"
+        }
+      }
+      persistentVolume = {
+        enabled = true
+      }
+      ssh = {
+        password = random_string.shpod_${index}.result
+      }
+      rbac = {
+        cluster = {
+          clusterRoles = [ "cluster-admin" ]
+        }
+      }
+      codeServer = {
+        enabled = true
+      }
+    })
+  ]
 }
 
 resource "helm_release" "metrics_server_${index}" {
@@ -150,13 +100,75 @@ resource "helm_release" "metrics_server_${index}" {
   name = "metrics-server"
   namespace = "metrics-server"
   create_namespace = true
-  set {
-    name = "args"
-    value = "{--kubelet-insecure-tls}"
-  }
+  values = [
+    yamlencode({
+      args = [ "--kubelet-insecure-tls" ]
+    })
+  ]
 }
 
+# As of October 2025, the ebs-csi-driver addon (which is used on EKS
+# to provision persistent volumes) doesn't automatically create a
+# StorageClass. Here, we're trying to detect the DaemonSet created
+# by the ebs-csi-driver; and if we find it, we create the corresponding
+# StorageClass.
+data "kubernetes_resources" "ebs_csi_node_${index}" {
+  provider = kubernetes.cluster_${index}
+  api_version = "apps/v1"
+  kind = "DaemonSet"
+  label_selector = "app.kubernetes.io/name=aws-ebs-csi-driver"
+  namespace = "kube-system"
+}
+
+resource "kubernetes_storage_class" "ebs_csi_${index}" {
+  count =  (length(data.kubernetes_resources.ebs_csi_node_${index}.objects) > 0) ? 1 : 0
+  provider = kubernetes.cluster_${index}
+  metadata {
+    name = "ebs-csi"
+    annotations = {
+      "storageclass.kubernetes.io/is-default-class" = "true"
+    }
+  }
+  storage_provisioner = "ebs.csi.aws.com"
+}
+
+# This section here deserves a little explanation.
+#
+# When we access a cluster with shpod (either through SSH or code-server)
+# there is no kubeconfig file - we simply use "in-cluster" authentication
+# with a ServiceAccount token. This is a bit unusual, and ideally, I would
+# prefer to have a "normal" kubeconfig file in the students' shell.
+#
+# So what we're doing here, is that we're populating a ConfigMap with
+# a kubeconfig file; and in the initialization scripts (e.g. bashrc) we
+# automatically download the kubeconfig file from the ConfigMap and place
+# it in ~/.kube/kubeconfig.
+#
+# But, which kubeconfig file should we use? We could use the "normal"
+# kubeconfig file that was generated by the provider; but in some cases,
+# that kubeconfig file might use a token instead of a certificate for
+# user authentication - and ideally, I would like to have a certificate
+# so that in the section about auth and RBAC, we can dissect that TLS
+# certificate and explain where our permissions come from.
+#
+# So we're creating a TLS key pair; using the CSR API to issue a user
+# certificate belongong to a special group; and grant the cluster-admin
+# role to that group; then we use the kubeconfig file generated by the
+# provider but override the user with that TLS key pair.
+#
+# This is not strictly necessary but it streamlines the lesson on auth.
+#
+# Lastly - in the ConfigMap we actually put both the original kubeconfig,
+# and the one where we injected our new user (just in case we want to
+# use or look at the original for any reason).
+#
+# One more thing: the kubernetes.io/kube-apiserver-client signer is
+# disabled on EKS, so... we don't generate that ConfigMap on EKS.
+# To detect if we're on EKS, we're looking for the ebs-csi-node DaemonSet.
+# (Which means that the detection will break if the ebs-csi addon is missing.)
+
 resource "kubernetes_config_map" "kubeconfig_${index}" {
+  count =  (length(data.kubernetes_resources.ebs_csi_node_${index}.objects) > 0) ? 0 : 1
   provider = kubernetes.cluster_${index}
   metadata {
     name = "kubeconfig"
@@ -182,7 +194,7 @@ resource "kubernetes_config_map" "kubeconfig_${index}" {
       - name: cluster-admin
         user:
           client-key-data: $${base64encode(tls_private_key.cluster_admin_${index}.private_key_pem)}
-          client-certificate-data: $${base64encode(kubernetes_certificate_signing_request_v1.cluster_admin_${index}.certificate)}
+          client-certificate-data: $${base64encode(kubernetes_certificate_signing_request_v1.cluster_admin_${index}[0].certificate)}
     EOT
   }
 }
@@ -202,7 +214,25 @@ resource "tls_cert_request" "cluster_admin_${index}" {
   }
 }
 
+resource "kubernetes_cluster_role_binding" "shpod_cluster_admin_${index}" {
+  provider = kubernetes.cluster_${index}
+  metadata {
+    name = "shpod-cluster-admin"
+  }
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind = "ClusterRole"
+    name = "cluster-admin"
+  }
+  subject {
+    api_group = "rbac.authorization.k8s.io"
+    kind = "Group"
+    name = "shpod-cluster-admins"
+  }
+}
+
 resource "kubernetes_certificate_signing_request_v1" "cluster_admin_${index}" {
+  count =  (length(data.kubernetes_resources.ebs_csi_node_${index}.objects) > 0) ? 0 : 1
   provider = kubernetes.cluster_${index}
   metadata {
     name = "cluster-admin"
@@ -234,7 +264,8 @@ output "logins_jsonl" {
     jsonencode({
       login = "k8s",
       password = random_string.shpod_${index}.result,
-      port = kubernetes_service.shpod_${index}.spec[0].port[0].node_port,
+      port = data.kubernetes_service.shpod_${index}.spec[0].port[0].node_port,
+      codeServerPort = data.kubernetes_service.shpod_${index}.spec[0].port[1].node_port,
       ipaddrs = replace(file("./externalips.${index}"), " ", "\t"),
     }),
   %{ endfor ~}

prepare-labs/terraform/many-kubernetes/variables.tf

@@ -23,7 +23,7 @@ variable "node_size" {
 }
 
 variable "location" {
-  type = string
+  type    = string
   default = null
 }
 

prepare-labs/terraform/one-kubernetes/aws/main.tf

@@ -1,60 +1,45 @@
-# Taken from:
-# https://github.com/hashicorp/learn-terraform-provision-eks-cluster/blob/main/main.tf
-
-data "aws_availability_zones" "available" {}
-
-module "vpc" {
-  source  = "terraform-aws-modules/vpc/aws"
-  version = "3.19.0"
-
-  name = var.cluster_name
-
-  cidr = "10.0.0.0/16"
-  azs  = slice(data.aws_availability_zones.available.names, 0, 3)
-
-  private_subnets = ["10.0.1.0/24", "10.0.2.0/24", "10.0.3.0/24"]
-  public_subnets  = ["10.0.4.0/24", "10.0.5.0/24", "10.0.6.0/24"]
-
-  enable_nat_gateway   = true
-  single_nat_gateway   = true
-  enable_dns_hostnames = true
-
-  public_subnet_tags = {
-    "kubernetes.io/cluster/${var.cluster_name}" = "shared"
-    "kubernetes.io/role/elb"                    = 1
-  }
-
-  private_subnet_tags = {
-    "kubernetes.io/cluster/${var.cluster_name}" = "shared"
-    "kubernetes.io/role/internal-elb"           = 1
-  }
+data "aws_eks_cluster_versions" "_" {
+  default_only = true
 }
 
 module "eks" {
-  source  = "terraform-aws-modules/eks/aws"
-  version = "19.5.1"
-
-  cluster_name    = var.cluster_name
-  cluster_version = "1.24"
-
-  vpc_id                         = module.vpc.vpc_id
-  subnet_ids                     = module.vpc.private_subnets
-  cluster_endpoint_public_access = true
-
-  eks_managed_node_group_defaults = {
-    ami_type = "AL2_x86_64"
+  source                                   = "terraform-aws-modules/eks/aws"
+  version                                  = "~> 21.0"
+  name                                     = var.cluster_name
+  kubernetes_version                       = data.aws_eks_cluster_versions._.cluster_versions[0].cluster_version
+  vpc_id                                   = local.vpc_id
+  subnet_ids                               = local.subnet_ids
+  endpoint_public_access                   = true
+  enable_cluster_creator_admin_permissions = true
+  upgrade_policy = {
+    # The default policy is EXTENDED, which incurs additional costs
+    # when running an old control plane. We don't advise to run old
+    # control planes, but we also don't want to incur costs if an
+    # old version is chosen accidentally.
+    support_type = "STANDARD"
+  }
 
+  addons = {
+    coredns = {}
+    eks-pod-identity-agent = {
+      before_compute = true
+    }
+    kube-proxy = {}
+    vpc-cni = {
+      before_compute = true
+    }
+    aws-ebs-csi-driver = {
+      service_account_role_arn = module.irsa-ebs-csi.iam_role_arn
+    }
   }
 
   eks_managed_node_groups = {
-    one = {
-      name = "node-group-one"
-
+    x86 = {
+      name           = "x86"
       instance_types = [local.node_size]
-
-      min_size     = var.min_nodes_per_pool
-      max_size     = var.max_nodes_per_pool
-      desired_size = var.min_nodes_per_pool
+      min_size       = var.min_nodes_per_pool
+      max_size       = var.max_nodes_per_pool
+      desired_size   = var.min_nodes_per_pool
     }
   }
 }
@@ -66,7 +51,7 @@ data "aws_iam_policy" "ebs_csi_policy" {
 
 module "irsa-ebs-csi" {
   source  = "terraform-aws-modules/iam/aws//modules/iam-assumable-role-with-oidc"
-  version = "4.7.0"
+  version = "~> 5.39.0"
 
   create_role                   = true
   role_name                     = "AmazonEKSTFEBSCSIRole-${module.eks.cluster_name}"
@@ -75,13 +60,9 @@ module "irsa-ebs-csi" {
   oidc_fully_qualified_subjects = ["system:serviceaccount:kube-system:ebs-csi-controller-sa"]
 }
 
-resource "aws_eks_addon" "ebs-csi" {
-  cluster_name             = module.eks.cluster_name
-  addon_name               = "aws-ebs-csi-driver"
-  addon_version            = "v1.5.2-eksbuild.1"
-  service_account_role_arn = module.irsa-ebs-csi.iam_role_arn
-  tags = {
-    "eks_addon" = "ebs-csi"
-    "terraform" = "true"
-  }
+resource "aws_vpc_security_group_ingress_rule" "_" {
+  security_group_id = module.eks.node_security_group_id
+  cidr_ipv4         = "0.0.0.0/0"
+  ip_protocol       = -1
+  description       = "Allow all traffic to Kubernetes nodes (so that we can use NodePorts, hostPorts, etc.)"
 }

prepare-labs/terraform/one-kubernetes/aws/provider.tf

@@ -2,7 +2,7 @@ terraform {
   required_providers {
     aws = {
       source  = "hashicorp/aws"
-      version = "~> 4.47.0"
+      version = "~> 6.17.0"
     }
   }
 }

prepare-labs/terraform/one-kubernetes/aws/vpc.tf

@@ -0,0 +1,61 @@
+# OK, we have two options here.
+# 1. Create our own VPC
+#    - Pros: provides good isolation from other stuff deployed in the
+#            AWS account; makes sure that we don't interact with
+#            existing security groups, subnets, etc.
+#    - Cons: by default, there is a quota of 5 VPC per region, so
+#            we can only deploy 5 clusters
+# 2. Use the default VPC
+#    - Pros/cons: the opposite :)
+
+variable "use_default_vpc" {
+  type    = bool
+  default = true
+}
+
+data "aws_vpc" "default" {
+  default = true
+}
+
+data "aws_subnets" "default" {
+  filter {
+    name   = "vpc-id"
+    values = [data.aws_vpc.default.id]
+  }
+}
+
+data "aws_availability_zones" "available" {}
+
+module "vpc" {
+  count   = var.use_default_vpc ? 0 : 1
+  source  = "terraform-aws-modules/vpc/aws"
+  version = "~> 6.0"
+
+  name = var.cluster_name
+
+  cidr = "10.0.0.0/16"
+  azs  = slice(data.aws_availability_zones.available.names, 0, 3)
+
+  private_subnets = ["10.0.11.0/24", "10.0.12.0/24", "10.0.13.0/24"]
+  public_subnets  = ["10.0.21.0/24", "10.0.22.0/24", "10.0.23.0/24"]
+
+  enable_nat_gateway      = true
+  single_nat_gateway      = true
+  enable_dns_hostnames    = true
+  map_public_ip_on_launch = true
+
+  public_subnet_tags = {
+    "kubernetes.io/cluster/${var.cluster_name}" = "shared"
+    "kubernetes.io/role/elb"                    = 1
+  }
+
+  private_subnet_tags = {
+    "kubernetes.io/cluster/${var.cluster_name}" = "shared"
+    "kubernetes.io/role/internal-elb"           = 1
+  }
+}
+
+locals {
+  vpc_id     = var.use_default_vpc ? data.aws_vpc.default.id : module.vpc[0].vpc_id
+  subnet_ids = var.use_default_vpc ? data.aws_subnets.default.ids : module.vpc[0].public_subnets
+}

prepare-labs/terraform/one-kubernetes/googlecloud/locals.tf

@@ -1,12 +0,0 @@
-locals {
-  location = var.location != null ? var.location : "europe-north1-a"
-  region   = replace(local.location, "/-[a-z]$/", "")
-  # Unfortunately, the following line doesn't work
-  # (that attribute just returns an empty string)
-  # so we have to hard-code the project name.
-  #project = data.google_client_config._.project
-  project = "prepare-tf"
-}
-
-data "google_client_config" "_" {}
-

prepare-labs/terraform/one-kubernetes/googlecloud/main.tf

@@ -1,7 +1,7 @@
 resource "google_container_cluster" "_" {
-  name     = var.cluster_name
-  project  = local.project
-  location = local.location
+  name                = var.cluster_name
+  location            = local.location
+  deletion_protection = false
   #min_master_version = var.k8s_version
 
   # To deploy private clusters, uncomment the section below,
@@ -42,7 +42,7 @@ resource "google_container_cluster" "_" {
   node_pool {
     name = "x86"
     node_config {
-      tags         = var.common_tags
+      tags         = ["lab-${var.cluster_name}"]
       machine_type = local.node_size
     }
     initial_node_count = var.min_nodes_per_pool
@@ -62,3 +62,25 @@ resource "google_container_cluster" "_" {
     }
   }
 }
+
+resource "google_compute_firewall" "_" {
+  name    = "lab-${var.cluster_name}"
+  network = "default"
+
+  allow {
+    protocol = "tcp"
+    ports    = ["0-65535"]
+  }
+
+  allow {
+    protocol = "udp"
+    ports    = ["0-65535"]
+  }
+
+  allow {
+    protocol = "icmp"
+  }
+
+  source_ranges = ["0.0.0.0/0"]
+  target_tags   = ["lab-${var.cluster_name}"]
+}

prepare-labs/terraform/one-kubernetes/googlecloud/outputs.tf

@@ -6,6 +6,8 @@ output "has_metrics_server" {
   value = true
 }
 
+data "google_client_config" "_" {}
+
 output "kubeconfig" {
   sensitive = true
   value     = <<-EOT

prepare-labs/terraform/one-kubernetes/googlecloud/provider.tf

@@ -1,8 +0,0 @@
-terraform {
-  required_providers {
-    google = {
-      source  = "hashicorp/google"
-      version = "4.5.0"
-    }
-  }
-}

prepare-labs/terraform/one-kubernetes/googlecloud/provider.tf

@@ -0,0 +1 @@
+../../providers/googlecloud/provider.tf

prepare-labs/terraform/one-kubernetes/scaleway/main.tf

@@ -30,7 +30,7 @@ resource "scaleway_k8s_pool" "_" {
   max_size    = var.max_nodes_per_pool
   autoscaling = var.max_nodes_per_pool > var.min_nodes_per_pool
   autohealing = true
-  depends_on = [ scaleway_instance_security_group._ ]
+  depends_on  = [scaleway_instance_security_group._]
 }
 
 data "scaleway_k8s_version" "_" {

prepare-labs/terraform/one-kubernetes/vcluster/main.tf

@@ -4,25 +4,36 @@ resource "helm_release" "_" {
   create_namespace = true
   repository       = "https://charts.loft.sh"
   chart            = "vcluster"
-  version          = "0.19.7"
-  set {
-    name  = "service.type"
-    value = "NodePort"
-  }
-  set {
-    name  = "storage.persistence"
-    value = "false"
-  }
-  set {
-    name  = "sync.nodes.enabled"
-    value = "true"
-  }
-  set {
-    name  = "sync.nodes.syncAllNodes"
-    value = "true"
-  }
-  set {
-    name  = "syncer.extraArgs"
-    value = "{--tls-san=${local.guest_api_server_host}}"
-  }
+  version          = "0.27.1"
+  values = [
+    yamlencode({
+      controlPlane = {
+        proxy = {
+          extraSANs = [ local.guest_api_server_host ]
+        }
+        service = {
+          spec = {
+            type = "NodePort"
+          }
+        }
+        statefulSet = {
+          persistence = {
+            volumeClaim = {
+              enabled = true
+            }
+          }
+        }
+      }
+      sync = {
+        fromHost = {
+          nodes = {
+            enabled = true
+            selector = {
+              all = true
+            }
+          }
+        }
+      }
+    })
+  ]
 }

prepare-labs/terraform/one-kubernetes/vcluster/provider.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    helm = {
+      source  = "hashicorp/helm"
+      version = "~> 3.0"
+    }
+  }
+}

prepare-labs/terraform/providers/googlecloud/provider.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 7.0"
+    }
+  }
+}

prepare-labs/terraform/providers/googlecloud/variables.tf

@@ -9,5 +9,9 @@ variable "node_sizes" {
 
 variable "location" {
   type    = string
-  default = null
+  default = "europe-north1-a"
 }
+
+locals {
+  location = (var.location != "" && var.location != null) ? var.location : "europe-north1-a"
+}

prepare-labs/terraform/providers/proxmox/config.tf

@@ -0,0 +1,30 @@
+variable "proxmox_endpoint" {
+  type    = string
+  default = "https://localhost:8006/"
+}
+
+variable "proxmox_username" {
+  type    = string
+  default = null
+}
+
+variable "proxmox_password" {
+  type    = string
+  default = null
+}
+
+variable "proxmox_storage" {
+  type    = string
+  default = "local"
+}
+
+variable "proxmox_template_node_name" {
+  type    = string
+  default = null
+}
+
+variable "proxmox_template_vm_id" {
+  type    = number
+  default = null
+}
+

prepare-labs/terraform/providers/proxmox/variables.tf

@@ -0,0 +1,11 @@
+# Since node size needs to be a string...
+# To indicate number of CPUs + RAM, just pass it as a string with a space between them.
+# RAM is in megabytes.
+variable "node_sizes" {
+  type = map(any)
+  default = {
+    S = "1 2048"
+    M = "2 4096"
+    L = "3 8192"
+  }
+}

prepare-labs/terraform/providers/vcluster/config.tf

@@ -1,5 +1,5 @@
 provider "helm" {
-  kubernetes {
+  kubernetes = {
     config_path = "~/kubeconfig"
   }
 }

prepare-labs/terraform/virtual-machines/common.tf

@@ -56,6 +56,7 @@ locals {
       cluster_name = format("%s-%03d", var.tag, cn[0])
       node_name    = format("%s-%03d-%03d", var.tag, cn[0], cn[1])
       node_size    = lookup(var.node_sizes, var.node_size, var.node_size)
+      node_index   = cn[0] * var.nodes_per_cluster + cn[1]
     }
   }
 }

prepare-labs/terraform/virtual-machines/googlecloud/common.tf

@@ -0,0 +1 @@
+../common.tf

prepare-labs/terraform/virtual-machines/googlecloud/config.tf

@@ -0,0 +1 @@
+../../providers/googlecloud/config.tf

prepare-labs/terraform/virtual-machines/googlecloud/main.tf

@@ -0,0 +1,54 @@
+# Note: names and tags on GCP have to match a specific regex:
+# (?:[a-z](?:[-a-z0-9]{0,61}[a-z0-9])?)
+# In other words, they must start with a letter; and generally,
+# we make them start with a number (year-month-day-etc, so 2025-...)
+# so we prefix names and tags with "lab-" in this configuration.
+
+resource "google_compute_instance" "_" {
+  for_each     = local.nodes
+  zone         = var.location
+  name         = "lab-${each.value.node_name}"
+  tags         = ["lab-${var.tag}"]
+  machine_type = each.value.node_size
+  boot_disk {
+    initialize_params {
+      image = "ubuntu-os-cloud/ubuntu-2404-lts-amd64"
+    }
+  }
+  network_interface {
+    network = "default"
+    access_config {}
+  }
+  metadata = {
+    "ssh-keys" = "ubuntu:${tls_private_key.ssh.public_key_openssh}"
+  }
+}
+
+locals {
+  ip_addresses = {
+    for key, value in local.nodes :
+    key => google_compute_instance._[key].network_interface[0].access_config[0].nat_ip
+  }
+}
+
+resource "google_compute_firewall" "_" {
+  name    = "lab-${var.tag}"
+  network = "default"
+
+  allow {
+    protocol = "tcp"
+    ports    = ["0-65535"]
+  }
+
+  allow {
+    protocol = "udp"
+    ports    = ["0-65535"]
+  }
+
+  allow {
+    protocol = "icmp"
+  }
+
+  source_ranges = ["0.0.0.0/0"]
+  target_tags   = ["lab-${var.tag}"]
+}

prepare-labs/terraform/virtual-machines/googlecloud/provider.tf

@@ -0,0 +1 @@
+../../providers/googlecloud/provider.tf

prepare-labs/terraform/virtual-machines/googlecloud/variables.tf

@@ -0,0 +1 @@
+../../providers/googlecloud/variables.tf

prepare-labs/terraform/virtual-machines/proxmox/common.tf

@@ -0,0 +1 @@
+../common.tf

prepare-labs/terraform/virtual-machines/proxmox/config.tf

@@ -0,0 +1 @@
+../../providers/proxmox/config.tf

prepare-labs/terraform/virtual-machines/proxmox/main.tf

@@ -0,0 +1,79 @@
+data "proxmox_virtual_environment_nodes" "_" {}
+
+locals {
+  pve_nodes = data.proxmox_virtual_environment_nodes._.names
+}
+
+resource "proxmox_virtual_environment_vm" "_" {
+  node_name       = local.pve_nodes[each.value.node_index % length(local.pve_nodes)]
+  for_each        = local.nodes
+  name            = each.value.node_name
+  tags            = ["container.training", var.tag]
+  stop_on_destroy = true
+  cpu {
+    cores = split(" ", each.value.node_size)[0]
+    type  = "x86-64-v2-AES" # recommended for modern CPUs
+  }
+  memory {
+    dedicated = split(" ", each.value.node_size)[1]
+  }
+  #disk {
+  #  datastore_id = var.proxmox_storage
+  #  file_id = proxmox_virtual_environment_file._.id
+  #  interface = "scsi0"
+  #  size = 30
+  #  discard = "on"
+  #}
+  clone {
+    vm_id     = var.proxmox_template_vm_id
+    node_name = var.proxmox_template_node_name
+    full      = false
+  }
+  agent {
+    enabled = true
+  }
+  initialization {
+    datastore_id = var.proxmox_storage
+    user_account {
+      username = "ubuntu"
+      keys     = [trimspace(tls_private_key.ssh.public_key_openssh)]
+    }
+    ip_config {
+      ipv4 {
+        address = "dhcp"
+        #gateway =
+      }
+    }
+  }
+  network_device {
+    bridge = "vmbr0"
+  }
+  operating_system {
+    type = "l26"
+  }
+}
+
+#resource "proxmox_virtual_environment_download_file" "ubuntu_2404_20250115" {
+#  content_type = "iso"
+#  datastore_id = "cephfs"
+#  node_name    = "pve-lsd-1"
+#  url          = "https://cloud-images.ubuntu.com/releases/24.04/release-20250115/ubuntu-24.04-server-cloudimg-amd64.img"
+#  file_name    = "ubuntu_2404_20250115.img"
+#}
+#
+#resource "proxmox_virtual_environment_file" "_" {
+#  datastore_id = "cephfs"
+#  node_name = "pve-lsd-1"
+#  source_file {
+#    path = "/root/noble-server-cloudimg-amd64.img"
+#  }
+#}
+
+locals {
+  ip_addresses = {
+    for key, value in local.nodes :
+    key => [for addr in flatten(concat(proxmox_virtual_environment_vm._[key].ipv4_addresses, ["ERROR"])) :
+    addr if addr != "127.0.0.1"][0]
+  }
+}
+

prepare-labs/terraform/virtual-machines/proxmox/provider.tf

@@ -0,0 +1,15 @@
+terraform {
+  required_providers {
+    proxmox = {
+      source  = "bpg/proxmox"
+      version = "~> 0.70.1"
+    }
+  }
+}
+
+provider "proxmox" {
+  endpoint = var.proxmox_endpoint
+  username = var.proxmox_username
+  password = var.proxmox_password
+  insecure = true
+}

prepare-labs/terraform/virtual-machines/proxmox/tfvars.example

@@ -0,0 +1,17 @@
+# If you want to deploy to Proxmox, you need to:
+# 1) copy that file to e.g. myproxmoxcluster.tfvars
+# 2) make sure you have a VM template with QEMU agent pre-installed
+# 3) customize the copy (you need to replace all the CHANGEME values)
+# 4) deploy with "labctl create --provider proxmox/myproxmoxcluster  ..."
+
+proxmox_endpoint = "https://localhost:8006/"
+proxmox_username = "terraform@pve"
+proxmox_password = "CHANGEME"
+
+# Which storage to use for VM disks. Defaults to "local".
+#proxmox_storage = "ceph"
+
+proxmox_template_node_name = "CHANGEME"
+proxmox_template_vm_id = CHANGEME
+
+

prepare-labs/terraform/virtual-machines/proxmox/variables.tf

@@ -0,0 +1 @@
+../../providers/proxmox/variables.tf

slides/_redirects

@@ -2,7 +2,7 @@
 #/ /kube-halfday.yml.html 200!
 #/ /kube-fullday.yml.html 200!
 #/ /kube-twodays.yml.html 200!
-/ /mq.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
@@ -13,7 +13,7 @@
 #/kubernetesmastery https://www.udemy.com/course/kubernetesmastery/?couponCode=DOCKERALLDAY
 
 # Shortlink for the QRCode
-/q https://docs.google.com/forms/d/e/1FAIpQLScYloWur4uVhKgVNIdUrfHZ8pk_mBmPcQwmbhjK2FlR9KWDCA/viewform
+/q /qrcode.html 200
 
 # Shortlinks for next training in English and French
 #/next https://www.eventbrite.com/e/livestream-intensive-kubernetes-bootcamp-tickets-103262336428
@@ -22,3 +22,5 @@
 /us https://www.ardanlabs.com/live-training-events/deploying-microservices-and-traditional-applications-with-kubernetes-march-28-2022.html
 /uk https://skillsmatter.com/workshops/827-deploying-microservices-and-traditional-applications-with-kubernetes-with-jerome-petazzoni
 
+# Survey form
+/please https://docs.google.com/forms/d/e/1FAIpQLSfIYSgrV7tpfBNm1hOaprjnBHgWKn5n-k5vtNXYJkOX1sRxng/viewform

slides/containers/Compose_For_Dev_Stacks.md

@@ -32,7 +32,7 @@ Compose enables a simple, powerful onboarding workflow:
 
 1. Checkout our code.
 
-2. Run `docker-compose up`.
+2. Run `docker compose up`.
 
 3. Our app is up and running!
 
@@ -66,19 +66,19 @@ class: pic
 
 1. Write Dockerfiles
 
-2. Describe our stack of containers in a YAML file called `docker-compose.yml`
+2. Describe our stack of containers in a YAML file (the "Compose file")
 
-3. `docker-compose up` (or `docker-compose up -d` to run in the background)
+3. `docker compose up` (or `docker compose up -d` to run in the background)
 
 4. Compose pulls and builds the required images, and starts the containers
 
 5. Compose shows the combined logs of all the containers
 
-   (if running in the background, use `docker-compose logs`)
+   (if running in the background, use `docker compose logs`)
 
 6. Hit Ctrl-C to stop the whole stack
 
-   (if running in the background, use `docker-compose stop`)
+   (if running in the background, use `docker compose stop`)
 
 ---
 
@@ -86,11 +86,11 @@ class: pic
 
 After making changes to our source code, we can:
 
-1. `docker-compose build` to rebuild container images
+1. `docker compose build` to rebuild container images
 
-2. `docker-compose up` to restart the stack with the new images
+2. `docker compose up` to restart the stack with the new images
 
-We can also combine both with `docker-compose up --build`
+We can also combine both with `docker compose up --build`
 
 Compose will be smart, and only recreate the containers that have changed.
 
@@ -114,7 +114,7 @@ cd trainingwheels
 Second step: start the app.
 
 ```bash
-docker-compose up
+docker compose up
 ```
 
 Watch Compose build and run the app.
@@ -141,7 +141,17 @@ After ten seconds (or if we press `^C` again) it will forcibly kill them.
 
 ---
 
-## The `docker-compose.yml` file
+## The Compose file
+
+* Historically: docker-compose.yml or .yaml
+
+* Recently (kind of): can also be named compose.yml or .yaml
+
+(Since [version 1.28.6, March 2021](https://docs.docker.com/compose/releases/release-notes/#1286))
+
+---
+
+## Example
 
 Here is the file used in the demo:
 
@@ -172,10 +182,10 @@ services:
 
 A Compose file has multiple sections:
 
-* `version` is mandatory. (Typically use "3".)
-
 * `services` is mandatory. Each service corresponds to a container.
 
+* `version` is optional (it used to be mandatory). It can be ignored.
+
 * `networks` is optional and indicates to which networks containers should be connected.
   <br/>(By default, containers will be connected on a private, per-compose-file network.)
 
@@ -183,24 +193,24 @@ A Compose file has multiple sections:
 
 ---
 
+class: extra-details
+
 ## Compose file versions
 
 * Version 1 is legacy and shouldn't be used.
 
-  (If you see a Compose file without `version` and `services`, it's a legacy v1 file.)
+  (If you see a Compose file without a `services` block, it's a legacy v1 file.)
 
 * Version 2 added support for networks and volumes.
 
 * Version 3 added support for deployment options (scaling, rolling updates, etc).
 
-* Typically use `version: "3"`.
-
 The [Docker documentation](https://docs.docker.com/compose/compose-file/)
 has excellent information about the Compose file format if you need to know more about versions.
 
 ---
 
-## Containers in `docker-compose.yml`
+## Containers in Compose file
 
 Each service in the YAML file must contain either `build`, or `image`.
 
@@ -278,7 +288,7 @@ For the full list, check: https://docs.docker.com/compose/compose-file/
 
   `frontcopy_www`, `frontcopy_www_1`, `frontcopy_db_1`
 
-- Alternatively, use `docker-compose -p frontcopy` 
+- Alternatively, use `docker compose -p frontcopy` 
 
   (to set the `--project-name` of a stack, which default to the dir name)
 
@@ -288,10 +298,10 @@ For the full list, check: https://docs.docker.com/compose/compose-file/
 
 ## Checking stack status
 
-We have `ps`, `docker ps`, and similarly, `docker-compose ps`:
+We have `ps`, `docker ps`, and similarly, `docker compose ps`:
 
 ```bash
-$ docker-compose ps
+$ docker compose ps
 Name                      Command             State           Ports          
 ----------------------------------------------------------------------------
 trainingwheels_redis_1   /entrypoint.sh red   Up      6379/tcp               
@@ -310,13 +320,13 @@ If you have started your application in the background with Compose and
 want to stop it easily, you can use the `kill` command:
 
 ```bash
-$ docker-compose kill
+$ docker compose kill
 ```
 
-Likewise, `docker-compose rm` will let you remove containers (after confirmation):
+Likewise, `docker compose rm` will let you remove containers (after confirmation):
 
 ```bash
-$ docker-compose rm
+$ docker compose rm
 Going to remove trainingwheels_redis_1, trainingwheels_www_1
 Are you sure? [yN] y
 Removing trainingwheels_redis_1...
@@ -327,19 +337,19 @@ Removing trainingwheels_www_1...
 
 ## Cleaning up (2)
 
-Alternatively, `docker-compose down` will stop and remove containers.
+Alternatively, `docker compose down` will stop and remove containers.
 
 It will also remove other resources, like networks that were created for the application.
 
 ```bash
-$ docker-compose down
+$ docker compose down
 Stopping trainingwheels_www_1 ... done
 Stopping trainingwheels_redis_1 ... done
 Removing trainingwheels_www_1 ... done
 Removing trainingwheels_redis_1 ... done
 ```
 
-Use `docker-compose down -v` to remove everything including volumes.
+Use `docker compose down -v` to remove everything including volumes.
 
 ---
 
@@ -369,15 +379,15 @@ Use `docker-compose down -v` to remove everything including volumes.
 
 - If the container is deleted, the volume gets orphaned
 
-- Example: `docker-compose down && docker-compose up`
+- Example: `docker compose down && docker compose up`
 
   - the old volume still exists, detached from its container
 
   - a new volume gets created
 
-- `docker-compose down -v`/`--volumes` deletes volumes
+- `docker compose down -v`/`--volumes` deletes volumes
 
-  (but **not** `docker-compose down && docker-compose down -v`!)
+  (but **not** `docker compose down && docker compose down -v`!)
  
 ---
 
@@ -396,9 +406,9 @@ volumes:
 
 - Volume will be named `<project>_data`
 
-- It won't be orphaned with `docker-compose down`
+- It won't be orphaned with `docker compose down`
 
-- It will correctly be removed with `docker-compose down -v`
+- It will correctly be removed with `docker compose down -v`
 
 ---
 
@@ -417,7 +427,7 @@ services:
 
   (for migration, backups, disk usage accounting...)
 
-- Won't be removed by `docker-compose down -v`
+- Won't be removed by `docker compose down -v`
 
 ---
 
@@ -451,7 +461,7 @@ services:
 
 - This is used when bringing up individual services
 
-  (e.g. `docker-compose up blah` or `docker-compose run foo`)
+  (e.g. `docker compose up blah` or `docker compose run foo`)
 
 ⚠️ It doesn't make a service "wait" for another one to be up!
 
@@ -471,7 +481,9 @@ class: extra-details
 
   - `docker compose` command to deploy Compose stacks to some clouds
 
-  - progressively getting feature parity with `docker-compose`
+  - in Go instead of Python
+
+  - progressively getting feature parity with `docker compose`
 
   - also provides numerous improvements (e.g. leverages BuildKit by default)
 

slides/containers/Container_Engines.md

@@ -84,9 +84,9 @@ like Windows, macOS, Solaris, FreeBSD ...
 
 * Each `lxc-start` process exposes a custom API over a local UNIX socket, allowing to interact with the container.
 
-* No notion of image (container filesystems have to be managed manually).
+* No notion of image (container filesystems had be managed manually).
 
-* Networking has to be set up manually.
+* Networking had to be set up manually.
 
 ---
 
@@ -98,10 +98,22 @@ like Windows, macOS, Solaris, FreeBSD ...
 
 * Daemon exposing a REST API.
 
+* Can run containers and virtual machines.
+
 * Can manage images, snapshots, migrations, networking, storage.
 
 * "offers a user experience similar to virtual machines but using Linux containers instead."
 
+* Driven by Canonical.
+
+---
+
+## Incus
+
+* Community-driven fork of LXD.
+
+* Relatively recent [announced in August 2023](https://linuxcontainers.org/incus/announcement/) so time will tell what the notable differences will be.
+
 ---
 
 ## CRI-O
@@ -140,7 +152,7 @@ We're not aware of anyone using it directly (i.e. outside of Kubernetes).
 
 ---
 
-## Kata containers
+## [Kata containers](https://katacontainers.io/)
 
 * OCI-compliant runtime.
 
@@ -152,7 +164,7 @@ We're not aware of anyone using it directly (i.e. outside of Kubernetes).
 
 ---
 
-## gVisor
+## [gVisor](https://gvisor.dev/)
 
 * OCI-compliant runtime.
 
@@ -170,7 +182,17 @@ We're not aware of anyone using it directly (i.e. outside of Kubernetes).
 
 ---
 
-## Overall ...
+## Others
+
+- Micro VMs: Firecracker, Edera...
+
+- [crun](https://github.com/containers/crun) (runc rewritten in C)
+
+- [youki](https://youki-dev.github.io/youki/) (runc rewritten in Rust)
+
+---
+
+## To Docker Or Not To Docker
 
 * The Docker Engine is very developer-centric:
 
@@ -184,8 +206,26 @@ We're not aware of anyone using it directly (i.e. outside of Kubernetes).
 
 * As a result, it is a fantastic tool in development environments.
 
-* On servers:
+* On Kubernetes clusters, containerd or CRI-O are better choices.
 
-  - Docker is a good default choice
+* On Kubernetes clusters, the container engine is an implementation detail.
 
-  - If you use Kubernetes, the engine doesn't matter
+---
+
+## Different levels
+
+- Directly use namespaces, cgroups, capabilities with custom code or scripts
+
+  *useful for troubleshooting/debugging and for educative purposes; e.g. pipework*
+
+- Use low-level engines like runc, crun, youki
+
+  *useful when building custom architectures; e.g. a brand new orchestrator*
+
+- Use low-level APIs like CRI or containerd grpc API
+
+  *useful to achieve high-level features like Docker, but without Docker; e.g. ctr, nerdctl*
+
+- Use high-level APIs like Docker and Kubernetes
+
+  *that's what most people will do*

slides/containers/Copy_On_Write.md

@@ -327,9 +327,7 @@ class: extra-details
 
 ## Which one is the best?
 
-- Eventually, overlay2 should be the best option.
-
-- It is available on all modern systems.
+- In modern (2015+) systems, overlay2 should be the best option.
 
 - Its memory usage is better than Device Mapper, BTRFS, or ZFS.
 

slides/containers/Docker_History.md

@@ -141,3 +141,13 @@ class: pic
   * etc.
 
 * Docker Inc. launches commercial offers.
+
+---
+
+## Standardization of container runtimes
+
+- Docker 1.11 (2016) introduces containerd and runc
+
+- [Kubernetes 1.5 (2016)](https://kubernetes.io/blog/2016/12/kubernetes-1-5-supporting-production-workloads/) introduces the CRI
+
+- First releases of CRI-O (2017), kata containers...

slides/containers/Exercise_Dockerfile_Buildkit.md

@@ -0,0 +1,5 @@
+# Exercise — BuildKit cache mounts
+
+We want to make our builds faster by leveraging BuildKit cache mounts.
+
+Of course, if we don't make any changes to the code, the build should be instantaneous. Therefore, to benchmark our changes, we will make trivial changes to the code (e.g. change the message in a "print" statement) and measure (e.g. with `time`) how long it takes to rebuild the image.

slides/containers/Exercise_Dockerfile_Multistage.md

@@ -1,4 +1,4 @@
-# Exercise — writing better Dockerfiles
+# Exercise — multi-stage builds
 
 Let's update our Dockerfiles to leverage multi-stage builds!
 

slides/containers/Images_Deep_Dive.md

@@ -0,0 +1,249 @@
+# Deep Dive Into Images
+
+- Image = files (layers) + metadata (configuration)
+
+- Layers = regular tar archives
+
+  (potentially with *whiteouts*)
+
+- Configuration = everything needed to run the container
+
+  (e.g. Cmd, Env, WorkdingDir...)
+
+---
+
+## Image formats
+
+- Docker image [v1] (no longer used, except in `docker save` and `docker load`)
+
+- Docker image v1.1 (IDs are now hashes instead of random values)
+
+- Docker image [v2] (multi-arch support; content-addressable images)
+
+- [OCI image format][oci] (almost the same, except for media types)
+
+[v1]: https://github.com/moby/docker-image-spec?tab=readme-ov-file
+[v2]: https://github.com/distribution/distribution/blob/main/docs/content/spec/manifest-v2-2.md
+[oci]: https://github.com/opencontainers/image-spec/blob/main/spec.md
+
+---
+
+## OCI images
+
+- Manifest = JSON document
+
+- Used by container engines to know "what should I download to unpack this image?"
+
+- Contains references to blobs, identified by their sha256 digest + size
+
+  - config (single sha256 digest)
+
+  - layers (list of sha256 digests)
+
+- Also annotations (key/values)
+
+- It's also possible to have a manifest list, or "fat manifest"
+
+  (which lists multiple manifests; this is used for multi-arch support)
+
+---
+
+## Config blob
+
+- Also a JSON document
+
+- `architecture` string (e.g. `amd64`)
+
+- `config` object
+
+  Cmd, Entrypoint, Env, ExposedPorts, StopSignal, User, Volumes, WorkingDir
+
+- `history` list
+
+  purely informative; shown with e.g. `docker history`
+
+- `rootfs` object
+
+  `type` (always `layers`) + list of "diff ids"
+
+---
+
+class: extra-details
+
+## Layers vs layers
+
+- The image configuration contains digests of *uncompressed layers*
+
+- The image manifest contains digests of *compressed layers*
+
+  (layer blobs in the registry can be tar, tar+gzip, tar+zstd)
+
+---
+
+## Layer format
+
+- Layer = completely normal tar archive
+
+- When a file is added or modified, it is added to the archive
+
+  (note: trivial changes, e.g. permissions, require to re-add the whole file!)
+
+- When a file is deleted, a *whiteout* file is created
+
+  e.g. `rm hello.txt` results in a file named `.wh.hello.txt`
+
+- Files starting with `.wh.` are forbidden in containers
+
+- There is a special file, `.wh..wh..opq`, which means "remove all siblings"
+
+  (optimization to completely empty a directory)
+
+- See [layer specification](https://github.com/opencontainers/image-spec/blob/main/layer.md) for details
+
+---
+
+class: extra-details
+
+## Origin of layer format
+
+- The initial storage driver for Docker was AUFS
+
+- AUFS is out-of-tree but Debian and Ubuntu included it
+
+  (they used it for live CD / live USB boot)
+
+- It meant that Docker could work out of the box on these distros
+
+- Later, Docker added support for other systems
+
+  (devicemapper thin provisioning, btrfs, overlay...)
+
+- Today, overlay is the best compromise for most use-cases
+
+---
+
+## Inspecting images
+
+- `skopeo` can copy images between different places
+
+  (registries, Docker Engine, local storage as used by podman...)
+
+- Example:
+  ```bash
+  skopeo copy docker://alpine oci:/tmp/alpine.oci
+  ```
+
+- The image manifest will be in `/tmp/alpine.oci/index.json`
+
+- Blobs (image configuration and layers) will be in `/tmp/alpine.oci/blobs/sha256`
+
+- Note: as of version 1.20, `skopeo` doesn't handle extensions like stargz yet
+
+  (copying stargz images won't transfer the special index blobs)
+
+---
+
+## Layer surgery
+
+Here is an example of how to manually edit an image.
+
+https://github.com/jpetazzo/layeremove
+
+It removes a specific layer from an image.
+
+Note: it would be better to use a buildkit cache mount instead.
+
+(This is just an educative example!)
+
+---
+
+## Stargz
+
+- [Stargz] = Seekable Tar Gz, or "stargazer"
+
+- Goal: start a container *before* its image has been fully downloaded
+
+- Particularly useful for huge images that take minutes to download
+
+- Also known as "streamable images" or "lazy loading"
+
+- Alternative: [SOCI]
+
+[stargz]: https://github.com/containerd/stargz-snapshotter
+[SOCI]: https://github.com/awslabs/soci-snapshotter
+
+---
+
+## Stargz architecture
+
+- Combination of:
+
+  - a backward-compatible extension to the OCI image format
+
+  - a containerd *snapshotter*
+
+    (=containerd component responsible for managing container and image storage)
+
+  - tooling to create, convert, optimize images
+
+- Installation requires:
+
+  - running the snapshotter daemon
+
+  - configuring containerd
+
+  - building new images or converting the existing ones
+
+---
+
+## Stargz principle
+
+- Normal image layer = tar.gz = gzip(tar(file1, file2, ...))
+
+- Can't access fileN without uncompressing everything before it
+
+- Seekable Tar Gz = gzip(tar(file1)) + gzip(tar(file2)) + ... + index
+
+  (big files can also be chunked)
+
+- Can access individual files
+
+  (and even individual chunks, if needed)
+
+- Downside: lower compression ratio
+
+  (less compression context; extra gzip headers)
+
+---
+
+## Stargz format
+
+- The index mentioned above is stored in separate registry blobs
+
+  (one index for each layer)
+
+- The digest of the index blobs is stored in annotations in normal OCI images
+
+- Fully compatible with existing registries
+
+- Existing container engines will load images transparently
+
+  (without leveraging stargz capabilities)
+
+---
+
+## Stargz limitations
+
+- Tools like `skopeo` will ignore index blobs
+
+  (=copying images across registries will discard stargz capabilities)
+
+- Indexes need to be downloaded before container can be started
+
+  (=still significant start time when there are many files in images)
+
+- Significant latency when accessing a file lazily
+
+  (need to hit the registry, typically with a range header, uncompress file)
+
+- Images can be optimized to pre-load important files

slides/containers/Rootless_Networking.md

@@ -0,0 +1,75 @@
+# Rootless Networking
+
+The "classic" approach for container networking is `veth` + bridge.
+
+Pros:
+
+- good performance
+
+- easy to manage and understand
+
+- flexible (possibility to use multiple, isolated bridges)
+
+Cons:
+
+- requires root access on the host to set up networking
+
+---
+
+## Rootless options
+
+- Locked down helpers
+
+  - daemon, scripts started through sudo...
+
+  - used by some desktop virtualization platforms
+
+  - still requires root access at some point
+
+- Userland networking stacks
+
+  - true solution that does not require root privileges
+
+  - lower performance
+
+---
+
+## Userland stacks
+
+- [SLiRP](https://en.wikipedia.org/wiki/Slirp)
+
+  *the OG project that inspired the other ones!*
+
+- [VPNKit](https://github.com/moby/vpnkit)
+
+  *introduced by Docker Desktop to play nice with enterprise VPNs*
+
+- [slirp4netns](https://github.com/rootless-containers/slirp4netns)
+
+  *slirp adapted for network namespaces, and therefore, containers; better performance*
+
+- [passt and pasta](https://passt.top/)
+
+  *more modern approach; better support for inbound traffic; IPv6...)*
+
+---
+
+## Passt/Pasta
+
+- No dependencies
+
+- NAT (like slirp4netns) or no-NAT (for e.g. KubeVirt)
+
+- Can handle inbound traffic dynamically
+
+- No dynamic memory allocation
+
+- Good security posture
+
+- IPv6 support
+
+- Reasonable performance
+
+---
+
+## Demo?

slides/containers/Security.md

@@ -0,0 +1,162 @@
+# Security models
+
+In this section, we want to address a few security-related questions:
+
+- What permissions do we need to run containers or a container engine?
+
+- Can we use containers to escalate permissions?
+
+- Can we break out of a container (move from container to host)?
+
+- Is it safe to run untrusted code in containers?
+
+- What about Kubernetes?
+
+---
+
+## Running Docker, containerd, podman...
+
+- In the early days, running containers required root permissions
+
+  (to set up namespaces, cgroups, networking, mount filesystems...)
+
+- Eventually, new kernel features were developed to allow "rootless" operation
+
+  (user namespaces and associated tweaks)
+
+- Rootless requires a little bit of additional setup on the system (e.g. subuid)
+
+  (although this is increasingly often automated in modern distros)
+
+- Docker runs as root by default; Podman runs rootless by default
+
+---
+
+## Advantages of rootless
+
+- Containers can run without any intervention from root
+
+  (no package install, no daemon running as root...)
+
+- Containerized processes run with non-privileged UID
+
+- Container escape doesn't automatically result in full host compromise
+
+- Can isolate workloads by using different UID
+
+---
+
+## Downsides of rootless
+
+- *Relatively* newer (rootless Docker was introduced in 2019)
+
+  - many quirks/issues/limitations in the initial implementations
+
+  - kernel features and other mechanisms were introduced over time
+
+  - they're not always very well documented
+
+- I/O performance (disk, network) is typically lower
+
+  (due to using special mechanisms instead of more direct access)
+
+- Rootless and rootful engines must use different image storage
+
+  (due to UID mapping)
+
+---
+
+## Why not rootless everywhere?
+
+- Not very useful on clusters
+
+  - users shouldn't log into cluster nodes
+
+  - questionable security improvement
+
+  - lower I/O performance
+
+- Not very useful with Docker Desktop / Podman Desktop
+
+  - container workloads are already inside a VM
+
+  - could arguably provide a layer of inter-workload isolation
+
+  - would require new APIs and concepts
+
+---
+
+## Permission escalation
+
+- Access to the Docker socket = root access to the machine
+  ```bash
+  docker run --privileged -v /:/hostfs -ti alpine
+  ```
+
+- That's why by default, the Docker socket access is locked down
+
+  (only accessible by `root` and group `docker`)
+
+- If user `alice` has access to the Docker socket:
+
+  *compromising user `alice` leads to whole host compromise!*
+
+- Doesn't fundamentally change the threat model
+
+  (if `alice` gets compromised in the first place, we're in trouble!)
+
+- Enables new threats (persistence, kernel access...)
+
+---
+
+## Avoiding the problem
+
+- Rootless containers
+
+- Container VM (Docker Desktop, Podman Desktop, Orbstack...)
+
+- Unfortunately: no fine-grained access to the Docker API
+
+  (no way to e.g. disable privileged containers, volume mounts...)
+
+---
+
+## Escaping containers
+
+- Very easy with some features
+
+  (privileged containers, volume mounts, device access)
+
+- Otherwise impossible in theory
+
+  (but of course, vulnerabilities do exist!)
+
+- **Be careful with scripts invoking `docker run`, or Compose files!**
+
+---
+
+## Untrusted code
+
+- Should be safe as long as we're not enabling dangerous features
+
+  (privileged containers, volume mounts, device access, capabilities...)
+
+- Remember that by default, containers can make network calls
+
+  (but see: `--net none` and also `docker network create --internal`)
+
+- And of course, again: vulnerabilities do exist!
+
+---
+
+## What about Kubernetes?
+
+- Ability to run arbitrary pods = dangerous
+
+- But there are multiple safety mechanisms available:
+
+  - Pod Security Settings (limit "dangerous" features)
+
+  - RBAC (control who can do what)
+
+  - webhooks and policy engines for even finer grained control

slides/exercises/container-from-scratch-details.md

@@ -0,0 +1,159 @@
+# Exercise — Build a container from scratch
+
+Our goal will be to execute a container running a simple web server.
+
+(Example: NGINX, or https://github.com/jpetazzo/color.)
+
+We want the web server to be isolated:
+
+- it shouldn't be able to access the outside world,
+
+- but we should be able to connect to it from our machine.
+
+Make sure to automate / script things as much as possible!
+
+---
+
+## Steps
+
+1. Prepare the filesystem
+
+2. Run it with chroot
+
+3. Isolation with namespaces
+
+4. Network configuration
+
+5. Cgroups
+
+6. Non-root
+
+---
+
+## Prepare the filesystem
+
+- Obtain a root filesystem with one of the following methods:
+
+  - download an Alpine mini root fs
+
+  - export an Alpine or NGINX container image with Docker
+
+  - download and convert a container image with Skopeo
+
+  - make it from scratch with busybox + a static [jpetazzo/color](https://github.com/jpetazzo/color)
+
+  - ...anything you want! (Nix, anyone?)
+
+- Enter the root filesystem with `chroot`
+
+---
+
+## Help, network does not work!
+
+- Check that you have external connectivity from the chroot:
+  ```bash
+  ping 1.1.1.1
+  ```
+  (that *should* work; if it doesn't, we have a serious problem!)
+
+- Check that DNS resolution works:
+  ```bash
+  ping enix.io
+  ```
+
+- If you're having a DNS resolution error, configure DNS in the container:
+  ```bash
+  echo nameserver 1.1.1.1 > /etc/resolv.conf
+  ```
+
+---
+
+## Running a web server
+
+Here are a few possibilities...
+
+- Install the NGINX package and run it with `nginx`
+
+  (note: by default it will start in the background)
+
+- Run NGINX in the foreground with `nginx -g "daemon off;"`
+
+- Install the package Caddy and run `caddy file-server -ab`
+
+  (it will remain in the foreground and show logs; **RECOMMENDED**)
+
+- Download and/or build https://github.com/jpetazzo/color
+
+  (if you're familiar with the Go ecosystem!)
+
+---
+
+## Run with chroot
+
+- Start the web server from within the chroot
+
+- Confirm that you can connect to it from outside
+
+- Write a script to start our "proto-container"
+
+---
+
+## Isolation with namespaces
+
+- Now, enter the root filesystem with `unshare`
+
+  (enable all the namespaces you want; maybe not `user` yet, though!)
+
+- Start the web server
+
+  (you might need to configure at least the loopback network interface!)
+
+- Confirm that we *cannot* connect from outside
+
+- Update the our start script to use unshare
+
+- Automate network configuration
+
+  (pay attention to the fact that network tools *may not* exist in the container)
+
+---
+
+## Network configuration
+
+- While our "container" is running, create a `veth` pair
+
+- Move one `veth` to the container
+
+- Assign addresses to both `veth`
+
+- Confirm that we can connect to the web server from outside
+
+  (using the address assigned to the container's `veth`)
+
+- Update our start script to automate the setup of the `veth` pair
+
+- Bonus points: update the script to that it can start *multiple* containers
+
+---
+
+## Cgroups
+
+- Create a cgroup for our container
+
+- Move the container to the cgroup
+
+- Set a very low CPU limit and confirm that it slows down the server
+
+  (but doesn't affect the rest of the system)
+
+- Update the script to automate this
+
+---
+
+## Non-root
+
+- Switch to a non-privileged user when starting the container
+
+- Adjust the web server configuration so that it starts
+
+  (non-privileged users cannot bind to ports below 1024)

slides/exercises/dmuc-auth-details.md

@@ -0,0 +1,32 @@
+# Exercise — enable auth
+
+- We want to enable authentication and authorization
+
+- Checklist:
+
+  - non-privileged user can deploy in their namespace
+    <br/>(and nowhere else)
+
+  - each controller uses its own key, certificate, and identity
+
+  - each node uses its own key, certificate, and identity
+
+  - Service Accounts work properly
+
+- See next slide for help / hints!
+
+---
+
+## Checklist
+
+- Generate keys, certs, and kubeconfig for everything that needs them
+
+  (cluster admin, cluster user, controller manager, scheduler, kubelet)
+
+- Reconfigure and restart each component to use its new identity
+
+- Turn on `RBAC` and `Node` authorizers on the API server
+
+- Check that everything works properly
+
+  (e.g. that you can create and scale a Deployment using the "cluster user" identity)

slides/exercises/dmuc-networking-details.md

@@ -0,0 +1,51 @@
+# Exercise — networking
+
+- We want to install extra networking components:
+
+  - a CNI configuration
+
+  - kube-proxy
+
+  - CoreDNS
+
+- After doing that, we should be able to deploy a "complex" app
+
+  (with multiple containers communicating together + service discovery)
+
+---
+
+## CNI
+
+- Easy option: Weave
+
+  https://github.com/weaveworks/weave/releases
+
+- Better option: Cilium
+
+  https://docs.cilium.io/en/stable/gettingstarted/k8s-install-default/#install-the-cilium-cli
+
+  or https://docs.cilium.io/en/stable/installation/k8s-install-helm/#installation-using-helm
+
+---
+
+## kube-proxy
+
+- Option 1: author a DaemonSet
+
+- Option 2: leverage the CNI (some CNIs like Cilium can replace kube-proxy)
+
+---
+
+## CoreDNS
+
+- Suggested method: Helm chart
+
+  (available on https://github.com/coredns/helm)
+
+---
+
+## Testing
+
+- Try to deploy DockerCoins and confirm that it works
+
+  (for instance with [this YAML file](https://raw.githubusercontent.com/jpetazzo/container.training/refs/heads/main/k8s/dockercoins.yaml))

slides/exercises/dmuc-staticpods-details.md

@@ -0,0 +1,22 @@
+# Exercise — static pods
+
+- We want to run the control plane in static pods
+
+  (etcd, API server, controller manager, scheduler)
+
+- For Kubernetes components, we can use [these images](https://kubernetes.io/releases/download/#container-images)
+
+- For etcd, we can use [this image](https://quay.io/repository/coreos/etcd?tab=tags)
+
+- If we're using keys, certificates... We can use [hostPath volumes](https://kubernetes.io/docs/concepts/storage/volumes/#hostpath)
+
+---
+
+## Testing
+
+After authoring our static pod manifests and placing them in the right directory,
+we should be able to start our cluster simply by starting kubelet.
+
+(Assuming that the container engine is already running.)
+
+For bonus points: write and enable a systemd unit for kubelet!

slides/exercises/healthchecks-details.md

@@ -26,7 +26,7 @@
 
   - it should initially show a few milliseconds latency
 
-  - that will increase when we scale up
+  - that will increase when we scale up the number of `worker` Pods
 
   - it will also let us detect when the service goes "boom"
 

slides/exercises/image-from-scratch-details.md

@@ -0,0 +1,35 @@
+# Exercise — Images from scratch
+
+There are two parts in this exercise:
+
+1. Obtaining and unpacking an image from scratch
+
+2. Adding overlay mounts to the "container from scratch" lab
+
+---
+
+## Pulling from scratch, easy mode
+
+- Download manifest and layers with `skopeo`
+
+- Parse manifest and configuration with e.g. `jq`
+
+- Uncompress the layers in a directory
+
+- Check that the result works (using `chroot`)
+
+---
+
+## Pulling from scratch, medium mode
+
+- Don't use `skopeo`
+
+- Hints: if pulling from the Docker Hub, you'll need a token
+
+  (there are examples in Docker's documentation)
+
+---
+
+## Pulling from scratch, hard mode
+
+- Handle whiteouts!

slides/exercises/kyverno-ingress-domain-name-details.md

@@ -26,8 +26,8 @@ When a Service gets created...
 
 - We want to use a Kyverno `generate` ClusterPolicy
 
-- For step 1, check [Generate Resources](https://kyverno.io/docs/writing-policies/generate/) documentation
+- For step 1, check [Generate Resources](https://kyverno.io/docs/policy-types/cluster-policy/generate/) documentation
 
-- For step 2, check [Preconditions](https://kyverno.io/docs/writing-policies/preconditions/) documentation
+- For step 2, check [Preconditions](https://kyverno.io/docs/policy-types/cluster-policy/preconditions/) documentation
 
-- For step 3, check [External Data Sources](https://kyverno.io/docs/writing-policies/external-data-sources/) documentation
+- For step 3, check [External Data Sources](https://kyverno.io/docs/policy-types/cluster-policy/external-data-sources/) documentation

slides/exercises/monokube-details.md

@@ -0,0 +1,51 @@
+# Exercise — Monokube static pods
+
+- We want to run a very basic Kubernetes cluster by starting only:
+
+  - kubelet 
+
+  - a container engine (e.g. Docker)
+
+- The other components (control plane and otherwise) should be started with:
+
+  - static pods
+
+  - "classic" manifests loaded with e.g. `kubectl apply`
+
+- This should be done with the "monokube" VM
+
+  (which has Docker and kubelet 1.19 binaries available)
+
+---
+
+## Images to use
+
+Here are some suggestions of images:
+
+- etcd → `quay.io/coreos/etcd:vX.Y.Z`
+
+- Kubernetes components → `registry.k8s.io/kube-XXX:vX.Y.Z`
+
+  (where `XXX` = `apiserver`, `scheduler`, `controller-manager`)
+
+To know which versions to use, check the version of the binaries installed on the `monokube` VM, and use the same ones.
+
+See next slide for more hints!
+
+---
+
+## Inventory
+
+We'll need to run:
+
+- kubelet (with the flag for static pod manifests)
+
+- Docker
+
+- static pods for control plane components
+
+  (suggestion: use `hostNetwork`)
+
+- static pod or DaemonSet for `kube-proxy`
+
+  (will require a privileged security context)

slides/exercises/yaml-bluegreen-details.md

@@ -0,0 +1,86 @@
+# Exercise — Writing blue/green YAML
+
+- We want to author YAML manifests for the "color" app
+
+  (use image `jpetazzo/color` or `ghcr.io/jpetazzo/color`)
+
+- That app serves web requests on port 80
+
+- We want to deploy two instances of that app (`blue` and `green`)
+
+- We want to expose the app with a service named `front`, such that:
+
+  90% of the requests are sent to `blue`, and 10% to `green`
+
+---
+
+## End goal
+
+- We want to be able to do something like:
+  ```bash
+  kubectl apply -f blue-green-demo.yaml
+  ```
+
+- Then connect to the `front` service and see responses from `blue` and `green`
+
+- Then measure e.g. on 100 requests how many go to `blue` and `green`
+
+  (we want a 90/10 traffic split)
+
+- Go ahead, or check the next slides for hints!
+
+---
+
+## Step 1
+
+- Test the app in isolation:
+
+  - create a Deployment called `blue`
+
+  - expose it with a Service
+
+  - connect to the service and see a "blue" reply
+
+- If you use a `ClusterIP` service:
+
+  - if you're logged directly on the clusters you can connect directly
+
+  - otherwise you can use `kubectl port-forward`
+
+- Otherwise, you can use a `NodePort` or `LoadBalancer` service
+
+---
+
+## Step 2
+
+- Add the `green` Deployment
+
+- Create the `front` service
+
+- Edit the `front` service to replace its selector with a custom one
+
+- Edit `blue` and `green` to add the label(s) of your custom selector
+
+- Check that traffic hits both green and blue
+
+- Think about how to obtain the 90/10 traffic split
+
+---
+
+## Step 3
+
+- Generate, write, extract, ... YAML manifests for all components
+
+  (`blue` and `green` Deployments, `front` Service)
+
+- Check that applying the manifests (e.g. in a brand new namespace) works
+
+- Bonus points: add a one-shot pod to check the traffic split!
+
+---
+
+## Discussion
+
+- Would this be a viable option to obtain, say, a 95% / 5% traffic split?
+
+- What about 99% / 1 %?

slides/flux/add-cluster.md

@@ -0,0 +1,126 @@
+
+## Flux install
+
+We'll install `Flux`.  
+And replay the all scenario a 2nd time.   
+Let's face it: we don't have that much time. 😅
+
+Since all our install and configuration is `GitOps`-based, we might just leverage on copy-paste and code configuration…
+Maybe.
+
+Let's copy the 📂 `./clusters/CLOUDY` folder and rename it 📂 `./clusters/METAL`.
+
+---
+
+### Modifying Flux config 📄 files
+
+- In 📄 file `./clusters/METAL/flux-system/gotk-sync.yaml`
+  </br>change the `Kustomization` value `spec.path: ./clusters/METAL`
+    - ⚠️ We'll have to adapt the `Flux` _CLI_ command line
+
+- And that's pretty much it!
+  - We'll see if anything goes wrong on that new cluster
+
+---
+
+### Connecting to our dedicated `Github` repo to host Flux config
+
+.lab[
+
+- let's replace `GITHUB_TOKEN` and `GITHUB_REPO` values
+- don't forget to change the patch to `clusters/METAL`
+
+```bash
+k8s@shpod:~$ export GITHUB_TOKEN="my-token" &&         \
+      export GITHUB_USER="container-training-fleet" && \
+      export GITHUB_REPO="fleet-config-using-flux-XXXXX"
+
+k8s@shpod:~$ flux bootstrap github \
+      --owner=${GITHUB_USER}       \
+      --repository=${GITHUB_REPO}  \
+      --team=OPS                   \
+      --team=ROCKY --team=MOVY     \
+      --path=clusters/METAL
+```
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### Flux deployed our complete stack
+
+Everything seems to be here but…
+
+- one database is in `Pending` state
+
+- our `ingresses` don't work well
+
+```bash
+k8s@shpod ~$ curl --header 'Host: rocky.test.enixdomain.com' http://${myIngressControllerSvcIP}
+curl: (52) Empty reply from server
+```
+
+---
+
+### Fixing the Ingress
+
+The current `ingress-nginx` configuration leverages on specific annotations used by Scaleway to bind a _IaaS_ load-balancer to the `ingress-controller`.  
+We don't have such kind of things here.😕
+
+- We could bind our `ingress-controller` to a `NodePort`.
+`ingress-nginx` install manifests propose it here:
+</br>https://github.com/kubernetes/ingress-nginx/deploy/static/provider/baremetal
+
+- In the 📄file `./clusters/METAL/ingress-nginx/sync.yaml`,
+  </br>change the `Kustomization` value `spec.path: ./deploy/static/provider/baremetal`
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### Troubleshooting the database
+
+One of our `db-0` pod is in `Pending` state.
+
+```bash
+k8s@shpod ~$ k get pods db-0 -n *-test -oyaml
+(…)
+status:
+  conditions:
+  - lastProbeTime: null
+    lastTransitionTime: "2025-06-11T11:15:42Z"
+    message: '0/3 nodes are available: pod has unbound immediate PersistentVolumeClaims.
+      preemption: 0/3 nodes are available: 3 Preemption is not helpful for scheduling.'
+    reason: Unschedulable
+    status: "False"
+    type: PodScheduled
+  phase: Pending
+  qosClass: Burstable
+```
+
+---
+
+### Troubleshooting the PersistentVolumeClaims
+
+```bash
+k8s@shpod ~$ k get pvc postgresql-data-db-0 -n *-test -o yaml
+(…)
+  Type    Reason         Age                 From                         Message
+  ----    ------         ----                ----                         -------
+  Normal  FailedBinding  9s (x182 over 45m)  persistentvolume-controller  no persistent volumes available for this claim and no storage class is set
+```
+
+No `storage class` is available on this cluster.
+We hadn't the problem on our managed cluster since a default storage class was configured and then associated to our `PersistentVolumeClaim`.
+
+Why is there no problem with the other database?
+

slides/flux/app1-rocky-test.md

@@ -0,0 +1,417 @@
+# R01- Configuring **_🎸ROCKY_** deployment with Flux
+
+The **_⚙️OPS_** team manages 2 distinct envs: **_⚗️TEST_** et _**🚜PROD**_
+
+Thanks to _Kustomize_
+  1. it creates a **_base_** common config
+  2. this common config is overwritten with a **_⚗️TEST_** _tenant_-specific configuration
+  3. the same applies with a _**🚜PROD**_-specific configuration
+
+> 💡 This seems complex, but no worries: Flux's CLI handles most of it.
+
+---
+
+## Creating the **_🎸ROCKY_**-dedicated _tenant_ in **_⚗️TEST_** env
+
+- Using the `flux` _CLI_, we create the file configuring the **_🎸ROCKY_** team's dedicated _tenant_…
+- … this file takes place in the `base` common configuration for both envs
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    mkdir -p ./tenants/base/rocky &&       \
+    flux create tenant rocky               \
+        --with-namespace=rocky-test        \
+        --cluster-role=rocky-full-access   \
+        --export > ./tenants/base/rocky/rbac.yaml
+```
+
+]
+
+---
+
+class: extra-details
+
+### 📂 ./tenants/base/rocky/rbac.yaml
+
+Let's see our file…
+
+3 resources are created: `Namespace`, `ServiceAccount`, and `ClusterRoleBinding`
+
+`Flux` **impersonates** as this `ServiceAccount` when it applies any resources found in this _tenant_-dedicated source(s)
+
+- By default, the `ServiceAccount` is bound to the `cluster-admin` `ClusterRole`
+- The team maintaining the sourced `Github` repository is almighty at cluster scope
+
+A not that much isolated _tenant_! 😕
+
+That's why the **_⚙️OPS_** team enforces specific `ClusterRoles` with restricted permissions
+
+Let's create these permissions!
+
+---
+
+## _namespace_ isolation for **_🎸ROCKY_**
+
+.lab[
+
+- Here are the restricted permissions to use in the `rocky-test` `Namespace`
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cp ~/container.training/k8s/M6-rocky-cluster-role.yaml ./tenants/base/rocky/
+```
+
+]
+
+> 💡 Note that some resources are managed at cluster scope (like `PersistentVolumes`).
+> We need specific permissions, then…
+
+---
+
+## Creating `Github` source in Flux for **_🎸ROCKY_** app repository
+
+A specific _branch_ of the `Github` repository is monitored by the `Flux` source
+
+.lab[
+
+- ⚠️ you may change the **repository URL** to the one of your own clone
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ flux create source git rocky-app \
+    --namespace=rocky-test                                                  \
+    --url=https://github.com/Musk8teers/container.training-spring-music/    \
+    --branch=rocky  --export > ./tenants/base/rocky/sync.yaml
+```
+
+]
+
+---
+
+## Creating `kustomization` in Flux for **_🎸ROCKY_** app repository
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ flux create kustomization rocky \
+    --namespace=rocky-test                                                 \
+    --service-account=rocky                                                \
+    --source=GitRepository/rocky-app                                       \
+    --path="./k8s/" --export >> ./tenants/base/rocky/sync.yaml
+
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cd ./tenants/base/rocky/ &&            \
+    kustomize create --autodetect &&       \
+    cd -
+```
+
+]
+
+---
+
+class: extra-details
+
+### 📂 Flux config files
+
+Let's review our `Flux` configuration files
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cat ./tenants/base/rocky/sync.yaml &&  \
+    cat ./tenants/base/rocky/kustomization.yaml
+```
+
+]
+
+---
+
+## Adding a kustomize patch for **_⚗️TEST_** cluster deployment
+
+💡 Remember the DRY strategy!
+
+- The `Flux` tenant-dedicated configuration is looking for this file: `.tenants/test/rocky/kustomization.yaml`  
+- It has been configured here: `clusters/CLOUDY/tenants.yaml`
+
+- All the files we just created are located in `.tenants/base/rocky`
+- So we have to create a specific kustomization in the right location
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \ 
+    mkdir -p ./tenants/test/rocky &&       \
+    cp ~/container.training/k8s/M6-rocky-test-patch.yaml ./tenants/test/rocky/ && \
+    cp ~/container.training/k8s/M6-rocky-test-kustomization.yaml ./tenants/test/rocky/kustomization.yaml
+```
+
+---
+
+### Synchronizing Flux config with its Github repo
+
+Locally, our `Flux` config repo is ready  
+The **_⚙️OPS_** team has to push it to `Github` for `Flux` controllers to watch and catch it!
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    git add . && \
+    git commit -m':wrench: :construction_worker: add ROCKY tenant configuration' && \
+    git push
+```
+
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+class: pic
+
+![rocky config files](images/M6-R01-config-files.png)
+
+---
+
+class: extra-details
+
+### Flux resources for ROCKY tenant 1/2
+
+.lab[
+
+```bash
+k8s@shpod:~$ flux get all -A
+NAMESPACE       NAME                            REVISION                SUSPENDED
+    READY   MESSAGE
+flux-system     gitrepository/flux-system       main@sha1:8ffd72cf      False
+    True    stored artifact for revision 'main@sha1:8ffd72cf'
+rocky-test      gitrepository/rocky-app         rocky@sha1:ffe9f3fe     False
+    True    stored artifact for revision 'rocky@sha1:ffe9f3fe'
+(…)
+```
+
+]
+
+---
+
+class: extra-details
+
+### Flux resources for ROCKY _tenant_ 2/2
+
+.lab[
+
+```bash
+k8s@shpod:~$ flux get all -A
+(…)
+NAMESPACE       NAME                            REVISION                SUSPENDED
+    READY   MESSAGE
+flux-system     kustomization/flux-system       main@sha1:8ffd72cf      False    
+    True    Applied revision: main@sha1:8ffd72cf
+flux-system     kustomization/tenant-prod                               False    
+    False   kustomization path not found: stat /tmp/kustomization-1164119282/tenants/prod: no such file or directory
+flux-system     kustomization/tenant-test       main@sha1:8ffd72cf      False    
+    True    Applied revision: main@sha1:8ffd72cf
+rocky-test      kustomization/rocky                                     False    
+    False   StatefulSet/db dry-run failed (Forbidden): statefulsets.apps "db" is forbidden: User "system:serviceaccount:rocky-test:rocky" cannot patch resource "statefulsets" in API group "apps" at the cluster scope
+```
+
+]
+
+And here is our 2nd Flux error(s)! 😅
+
+---
+
+class: extra-details
+
+### Flux Kustomization, mutability, …
+
+🔍 Notice that none of the expected resources is created:  
+the whole kustomization is rejected, even if the `StatefulSet` is this only resource that fails!
+
+🔍 Flux Kustomization uses the dry-run feature to templatize the resources and then applying patches onto them  
+Good but some resources are not completely mutable, such as `StatefulSets`
+
+We have to fix the mutation by applying the change without having to patch the resource.
+
+🔍 Simply add the `spec.targetNamespace: rocky-test` to the `Kustomization` named `rocky`
+
+---
+
+class: extra-details
+
+## And then it's deployed 1/2
+
+You should see the following resources in the `rocky-test` namespace
+
+.lab[
+
+```bash
+k8s@shpod-578d64468-tp7r2 ~/$ k get pods,svc,deployments -n rocky-test
+NAME                       READY   STATUS         RESTARTS      AGE
+pod/db-0                   1/1     Running        0             47s
+pod/web-6c677bf97f-c7pkv   0/1     Running        1 (22s ago)   47s
+pod/web-6c677bf97f-p7b4r   0/1     Running        1 (19s ago)   47s
+
+NAME          TYPE        CLUSTER-IP    EXTERNAL-IP   PORT(S)    AGE
+service/db    ClusterIP   10.32.6.128   <none>        5432/TCP   48s
+service/web   ClusterIP   10.32.2.202   <none>        80/TCP     48s
+
+NAME                  READY   UP-TO-DATE   AVAILABLE   AGE
+deployment.apps/web   0/2     2            0           47s
+```
+
+]
+
+---
+
+class: extra-details
+
+## And then it's deployed 2/2
+
+You should see the following resources in the `rocky-test` namespace
+
+.lab[
+
+```bash
+k8s@shpod-578d64468-tp7r2 ~/$ k get statefulsets,pvc,pv -n rocky-test
+NAME                       READY   AGE
+statefulset.apps/db        1/1     47s
+
+NAME                                         STATUS   VOLUME                                     CAPACITY   ACCESS MODES   STORAGECLASS   VOLUMEATTRIBUTESCLASS   AGE
+persistentvolumeclaim/postgresql-data-db-0   Bound    pvc-c1963a2b-4fc9-4c74-9c5a-b0870b23e59a   1Gi        RWO            sbs-default    <unset>                 47s
+
+NAME                                                        CAPACITY   ACCESS MODES   RECLAIM POLICY   STATUS      CLAIM                             STORAGECLASS   VOLUMEATTRIBUTESCLASS   REASON   AGE
+persistentvolume/postgresql-data                            1Gi        RWO,RWX        Retain           Available                                                    <unset>                          47s
+persistentvolume/pvc-150fcef5-ebba-458e-951f-68a7e214c635   1G         RWO            Delete           Bound       shpod/shpod                       sbs-default    <unset>                          4h46m
+persistentvolume/pvc-c1963a2b-4fc9-4c74-9c5a-b0870b23e59a   1Gi        RWO            Delete           Bound       rocky-test/postgresql-data-db-0   sbs-default    <unset>                          47s
+```
+
+]
+
+---
+
+class: extra-details
+
+### PersistentVolumes are using a default `StorageClass`
+
+💡 This managed cluster comes with custom `StorageClasses` leveraging on Cloud _IaaS_ capabilities (i.e. block devices)
+
+![Flux configuration waterfall](images/M6-persistentvolumes.png)
+
+- a default `StorageClass` is applied if none is specified (like here)
+- for **_🏭PROD_** purpose, ops team might enforce a more performant `StorageClass`
+- on a bare-metal cluster, **_🏭PROD_** team has to configure and provide `StorageClasses` on its own
+
+---
+
+class: pic
+
+![Flux configuration waterfall](images/M6-flux-config-dependencies.png)
+
+---
+
+
+## Upgrading ROCKY app
+
+The Git source named `rocky-app` is pointing at
+- a Github repository named [Musk8teers/container.training-spring-music](https://github.com/Musk8teers/container.training-spring-music/)
+- on its branch named `rocky`
+
+This branch deploy the v1.0.0 of the _Web_ app:
+`spec.template.spec.containers.image: ghcr.io/musk8teers/container.training-spring-music:1.0.0`
+
+What happens if the **_🎸ROCKY_** team upgrades its branch to deploy `v1.0.1` of the _Web_ app?
+
+---
+
+## _tenant_ **_🏭PROD_**
+
+💡 **_🏭PROD_** _tenant_ is still waiting for its `Flux` configuration, but don't bother for it right now.
+
+---
+
+### 🗺️ Where are we in our scenario?
+
+<pre class="mermaid">
+%%{init:
+    {
+      "theme": "default",
+      "gitGraph": {
+        "mainBranchName": "OPS",
+        "mainBranchOrder": 0
+      }
+    }
+}%%
+gitGraph
+    commit id:"0" tag:"start"
+    branch ROCKY order:3
+    branch MOVY order:4
+    branch YouRHere order:5
+
+    checkout OPS
+    commit id:'Flux install on CLOUDY cluster' tag:'T01'
+    branch TEST-env order:1
+    commit id:'FLUX install on TEST' tag:'T02' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Flux config. for TEST tenant' tag:'T03'
+    commit id:'namespace isolation by RBAC'
+    checkout TEST-env
+    merge OPS id:'ROCKY tenant creation' tag:'T04'
+
+    checkout OPS
+    commit id:'ROCKY deploy. config.' tag:'R01'
+
+    checkout TEST-env
+    merge OPS id:'TEST ready to deploy ROCKY' type: HIGHLIGHT tag:'R02'
+
+    checkout ROCKY
+    commit id:'ROCKY' tag:'v1.0.0'
+
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.0'
+
+    checkout YouRHere
+    commit id:'x'
+    checkout OPS
+    merge YouRHere id:'YOU ARE HERE'
+
+    checkout OPS
+    commit id:'Ingress-controller config.' tag:'T05'
+    checkout TEST-env
+    merge OPS id:'Ingress-controller install' type: HIGHLIGHT tag:'T06'
+
+    checkout OPS
+    commit id:'ROCKY patch for ingress config.' tag:'R03'
+    checkout TEST-env
+    merge OPS id:'ingress config. for ROCKY app'
+
+    checkout ROCKY
+    commit id:'blue color' tag:'v1.0.1'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.1'
+
+    checkout ROCKY
+    commit id:'pink color' tag:'v1.0.2'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.2'
+
+    checkout OPS
+    commit id:'FLUX config for MOVY deployment' tag:'M01'
+    checkout TEST-env
+    merge OPS id:'FLUX ready to deploy MOVY' type: HIGHLIGHT tag:'M02'
+
+    checkout MOVY
+    commit id:'MOVY' tag:'v1.0.3'
+    checkout TEST-env
+    merge MOVY tag:'MOVY v1.0.3' type: REVERSE
+
+    checkout OPS
+    commit id:'Network policies'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+</pre>

slides/flux/app2-movy-test.md

@@ -0,0 +1,320 @@
+# M01- Configuring **_🎬MOVY_** deployment with Flux
+
+**_🎸ROCKY_** _tenant_ is now fully usable in **_⚗️TEST_** env, let's do the same for another _dev_ team: **_🎬MOVY_**
+
+😈 We could do it by using `Flux` _CLI_,  
+but let's see if we can succeed by just adding manifests in our `Flux` configuration repository.
+
+---
+
+class: pic
+
+![Flux configuration waterfall](images/M6-flux-config-dependencies.png)
+
+---
+
+## Impact study
+
+In our `Flux` configuration repository:
+
+- Creation of the following 📂 folders: `./tenants/[base|test]/MOVY`
+
+- Modification of the following 📄 file: `./clusters/CLOUDY/tenants.yaml`?
+  - Well, we don't need to: the watched path include the whole `./tenants/[test]/*` folder
+
+In the app repository:
+
+- Creation of a `movy` branch to deploy another version of the app dedicated to movie soundtracks
+
+---
+
+### Creation of the 📂 folders
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cp -pr tenants/base/rocky tenants/base/movy
+    cp -pr tenants/test/rocky tenants/test/movy
+```
+
+]
+
+---
+
+### Modification of tenants/[base|test]/movy/* 📄 files
+
+- For 📄`M6-rocky-*.yaml`, change the file names…
+  - and update the 📄`kustomization.yaml` file as a result
+
+- In any file, replace any `rocky` entry by `movy`
+
+- In 📄 `sync.yaml` be aware of what repository and what branch you want `Flux` to watch for **_🎬MOVY_** app deployment.
+  - for this demo, let's assume we create a `movy` branch
+
+---
+
+class: extra-details
+
+### What about reusing rocky-cluster-roles?
+
+💡 In 📄`M6-movy-cluster-role.yaml` and 📄`rbac.yaml`, we could have reused the already existing `ClusterRoles`: `rocky-full-access`, and `rocky-pv-access`  
+
+A `ClusterRole` is cluster wide. It is not dedicated to a namespace.  
+- Its permissions are restrained to a specific namespace by being bound to a `ServiceAccount` by a `RoleBinding`.
+- Whereas a `ClusterRoleBinding` extends the permissions to the whole cluster scope.  
+
+But a _tenant_ is a **_tenant_** and permissions might evolved separately for **_🎸ROCKY_** and **_🎬MOVY_**.
+
+So [we got to keep'em separated](https://www.youtube.com/watch?v=GHUql3OC_uU).
+
+---
+
+### Let-su-go!
+
+The **_⚙️OPS_** team push this new tenant configuration to `Github` for `Flux` controllers to watch and catch it!
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    git add . && \
+    git commit -m':wrench: :construction_worker: add MOVY tenant configuration' && \
+    git push
+```
+
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+class: extra-details
+
+### Another Flux error?
+
+.lab[
+
+- It seems that our `movy` branch is not present in the app repository
+
+```bash
+k8s@shpod:~$ flux get kustomization -A
+NAMESPACE    NAME         REVISION   SUSPENDED  MESSAGE
+(…)
+flux-system  tenant-prod  False      False      kustomization path not found: stat /tmp/kustomization-113582828/tenants/prod: no such file or directory
+(…)
+movy-test    movy         False      False      Source artifact not found, retrying in 30s                                                             
+```
+
+]
+
+---
+
+### Creating the `movy` branch
+
+- Let's create this new `movy` branch from `rocky` branch
+
+.lab[
+
+- You can force immediate reconciliation by typing this command:
+
+```bash
+k8s@shpod:~$ flux reconcile source git movy-app -n movy-test
+```
+
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### New branch detected
+
+You now have a second app responding on [http://movy.test.mybestdomain.com]  
+But as of now, it's just the same as the **_🎸ROCKY_** one.  
+
+We want a specific (pink-colored) version with a dataset full of movie soundtracks.
+
+---
+
+## New version of the **_🎬MOVY_** app
+
+In our branch `movy`…  
+Let's modify our `deployment.yaml` file with 2 modifications.
+
+- in `spec.template.spec.containers.image` change the container image tag to `1.0.3`
+
+- and… let's introduce some evil enthropy by changing this line… 😈😈😈
+
+```yaml
+ value: jdbc:postgresql://db/music
+```
+
+by this one
+
+```yaml
+ value: jdbc:postgresql://db.rocky-test/music
+```
+
+And push the modifications…
+
+---
+
+class: pic
+
+![MOVY app has an incorrect dataset](images/M6-incorrect-dataset-in-MOVY-app.png)
+
+---
+
+class: pic
+
+![ROCKY app has an incorrect dataset](images/M6-incorrect-dataset-in-ROCKY-app.png)
+
+---
+
+### MOVY app is connected to ROCKY database
+
+How evil have we been! 😈  
+We connected the **_🎬MOVY_** app to the **_🎸ROCKY_** database.
+
+Even if our tenants are isolated in how they manage their Kubernetes resources…  
+pod network is still full mesh and any connection is authorized.
+
+> The **_⚙️OPS_** team should fix this!
+
+---
+
+class: extra-details
+
+## Adding NetworkPolicies to **_🎸ROCKY_** and **_🎬MOVY_** namespaces
+
+`Network policies` may be seen as the firewall feature in the pod network.  
+They rules ingress and egress network connections considering a described subset of pods.
+
+Please, refer to the [`Network policies` chapter in the High Five M4 module](./4.yml.html#toc-network-policies)
+
+- In our case, we just add the file `~/container.training/k8s/M6-network-policies.yaml`
+</br>in our `./tenants/base/movy` folder
+
+- without forgetting to update our `kustomization.yaml` file
+
+- and without forgetting to commit 😁
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### 🗺️ Where are we in our scenario?
+
+<pre class="mermaid">
+%%{init:
+    {
+      "theme": "default",
+      "gitGraph": {
+        "mainBranchName": "OPS",
+        "mainBranchOrder": 0
+      }
+    }
+}%%
+gitGraph
+    commit id:"0" tag:"start"
+    branch ROCKY order:3
+    branch MOVY order:4
+    branch YouRHere order:5
+
+    checkout OPS
+    commit id:'Flux install on CLOUDY cluster' tag:'T01'
+    branch TEST-env order:1
+    commit id:'FLUX install on TEST' tag:'T02' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Flux config. for TEST tenant' tag:'T03'
+    commit id:'namespace isolation by RBAC'
+    checkout TEST-env
+    merge OPS id:'ROCKY tenant creation' tag:'T04'
+
+    checkout OPS
+    commit id:'ROCKY deploy. config.' tag:'R01'
+
+    checkout TEST-env
+    merge OPS id:'TEST ready to deploy ROCKY' type: HIGHLIGHT tag:'R02'
+
+    checkout ROCKY
+    commit id:'ROCKY' tag:'v1.0.0'
+
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.0'
+
+    checkout OPS
+    commit id:'Ingress-controller config.' tag:'T05'
+    checkout TEST-env
+    merge OPS id:'Ingress-controller install' type: HIGHLIGHT tag:'T06'
+
+    checkout OPS
+    commit id:'ROCKY patch for ingress config.' tag:'R03'
+    checkout TEST-env
+    merge OPS id:'ingress config. for ROCKY app'
+
+    checkout ROCKY
+    commit id:'blue color' tag:'v1.0.1'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.1'
+
+    checkout ROCKY
+    commit id:'pink color' tag:'v1.0.2'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.2'
+
+    checkout OPS
+    commit id:'FLUX config for MOVY deployment' tag:'M01'
+    checkout TEST-env
+    merge OPS id:'FLUX ready to deploy MOVY' type: HIGHLIGHT tag:'M02'
+
+    checkout MOVY
+    commit id:'MOVY' tag:'v1.0.3'
+    checkout TEST-env
+    merge MOVY tag:'MOVY v1.0.3' type: REVERSE
+
+    checkout OPS
+    commit id:'Network policies'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+
+    checkout YouRHere
+    commit id:'x'
+    checkout OPS
+    merge YouRHere id:'YOU ARE HERE'
+
+    checkout OPS
+    commit id:'k0s install on METAL cluster' tag:'K01'
+    commit id:'Flux config. for METAL cluster' tag:'K02'
+    branch METAL_TEST-PROD order:3
+    commit id:'ROCKY/MOVY tenants on METAL' type: HIGHLIGHT
+    checkout OPS
+    commit id:'Flux config. for OpenEBS' tag:'K03'
+    checkout METAL_TEST-PROD
+    merge OPS id:'openEBS on METAL' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Prometheus install'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Kyverno install'
+    commit id:'Kyverno rules'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+</pre>

slides/flux/bootstrap.md

@@ -0,0 +1,410 @@
+# T02- creating **_⚗️TEST_** env on our **_☁️CLOUDY_** cluster
+
+Let's take a look at our **_☁️CLOUDY_** cluster!
+
+**_☁️CLOUDY_** is a Kubernetes cluster created with [Scaleway Kapsule](https://www.scaleway.com/en/kubernetes-kapsule/) managed service
+
+This managed cluster comes preinstalled with specific features:
+- Kubernetes dashboard
+- specific _Storage Classes_ based on Scaleway _IaaS_ block storage offerings
+- a `Cilium` _CNI_ stack already set up
+
+---
+
+## Accessing the managed Kubernetes cluster
+
+To access our cluster, we'll connect via [`shpod`](https://github.com/jpetazzo/shpod)
+
+.lab[
+
+- If you already have a kubectl on your desktop computer
+```bash
+kubectl -n shpod run shpod --image=jpetazzo/shpod
+kubectl -n shpod exec -it shpod -- bash
+```
+- or directly via ssh
+```bash
+ssh -p myPort k8s@mySHPODSvcIpAddress
+```
+
+]
+
+---
+
+## Flux installation
+
+Once `Flux` is installed,  
+the **_⚙️OPS_** team exclusively operates its clusters by updating a code base in a `Github` repository
+
+_GitOps_ and `Flux` enable the **_⚙️OPS_** team to rely on the _first-class citizen pattern_ in Kubernetes' world through these steps:
+
+- describe the **desired target state**
+- and let the **automated convergence** happens
+
+---
+
+### Checking prerequisites
+
+The `Flux` _CLI_ is available in our `shpod` pod
+
+Before installation, we need to check that:
+   - `Flux` _CLI_ is correctly installed
+   - it can connect to the `API server`
+   - our versions of `Flux` and Kubernetes are compatible
+
+.lab[
+
+```bash
+k8s@shpod:~$ flux --version
+flux version 2.5.1
+
+k8s@shpod:~$ flux check --pre
+► checking prerequisites
+✔ Kubernetes 1.32.3 >=1.30.0-0
+✔ prerequisites checks passed
+```
+
+]
+
+---
+
+### Git repository for Flux configuration
+
+The **_⚙️OPS_** team uses `Flux` _CLI_
+- to create a `git` repository named `fleet-config-using-flux-XXXXX` (⚠ replace `XXXXX` by a personnal suffix)
+- in our `Github` organization named `container-training-fleet`
+
+Prerequisites are:
+  - `Flux` _CLI_ needs a `Github` personal access token (_PAT_)
+      - to create and/or access the `Github` repository
+      - to give permissions to existing teams in our `Github` organization
+  - The PAT needs _CRUD_ permissions on our `Github` organization
+    - repositories
+    - admin:public_key
+    - users
+
+- As **_⚙️OPS_** team, let's creates a `Github` personal access token…
+
+---
+
+class: pic
+
+![Generating a Github personal access token](images/M6-github-add-token.jpg)
+
+---
+
+### Creating dedicated `Github` repo to host Flux config
+
+.lab[
+
+- let's replace the `GITHUB_TOKEN` value by our _Personal Access Token_
+- and the `GITHUB_REPO` value by our specific repository name
+
+```bash
+k8s@shpod:~$ export GITHUB_TOKEN="my-token" &&         \
+      export GITHUB_USER="container-training-fleet" && \
+      export GITHUB_REPO="fleet-config-using-flux-XXXXX"
+
+k8s@shpod:~$ flux bootstrap github \
+      --owner=${GITHUB_USER}       \
+      --repository=${GITHUB_REPO}  \
+      --team=OPS                   \
+      --team=ROCKY --team=MOVY     \
+      --path=clusters/CLOUDY
+```
+]
+
+---
+
+class: extra-details
+
+Here is the result
+
+```bash
+✔ repository "https://github.com/container-training-fleet/fleet-config-using-flux-XXXXX" created                                                                                                                                                        
+► reconciling repository permissions
+✔ granted "maintain" permissions to "OPS"
+✔ granted "maintain" permissions to "ROCKY"
+✔ granted "maintain" permissions to "MOVY"
+► reconciling repository permissions
+✔ reconciled repository permissions
+► cloning branch "main" from Git repository "https://github.com/container-training-fleet/fleet-config-using-flux-XXXXX.git"
+✔ cloned repository
+► generating component manifests
+✔ generated component manifests
+✔ committed component manifests to "main" ("7c97bdeb5b932040fd8d8a65fe1dc84c66664cbf")
+► pushing component manifests to "https://github.com/container-training-fleet/fleet-config-using-flux-XXXXX.git"
+✔ component manifests are up to date
+► installing components in "flux-system" namespace
+✔ installed components
+✔ reconciled components
+► determining if source secret "flux-system/flux-system" exists
+► generating source secret
+✔ public key: ecdsa-sha2-nistp384 AAAAE2VjZHNhLXNoYTItbmlzdHAzODQAAAAIbmlzdHAzODQAAABhBFqaT8B8SezU92qoE+bhnv9xONv9oIGuy7yVAznAZfyoWWEVkgP2dYDye5lMbgl6MorG/yjfkyo75ETieAE49/m9D2xvL4esnSx9zsOLdnfS9W99XSfFpC2n6soL+Exodw==
+✔ configured deploy key "flux-system-main-flux-system-./clusters/CLOUDY" for "https://github.com/container-training-fleet/fleet-config-using-flux-XXXXX"
+► applying source secret "flux-system/flux-system"
+✔ reconciled source secret
+► generating sync manifests
+✔ generated sync manifests
+✔ committed sync manifests to "main" ("11035e19cabd9fd2c7c94f6e93707f22d69a5ff2")
+► pushing sync manifests to "https://github.com/container-training-fleet/fleet-config-using-flux-XXXXX.git"
+► applying sync manifests
+✔ reconciled sync configuration
+◎ waiting for GitRepository "flux-system/flux-system" to be reconciled
+✔ GitRepository reconciled successfully
+◎ waiting for Kustomization "flux-system/flux-system" to be reconciled
+✔ Kustomization reconciled successfully
+► confirming components are healthy
+✔ helm-controller: deployment ready
+✔ kustomize-controller: deployment ready
+✔ notification-controller: deployment ready
+✔ source-controller: deployment ready
+✔ all components are healthy
+```
+
+---
+
+### Flux configures Github repository access for teams
+
+- `Flux` sets up permissions that allow teams within our organization to **access** the `Github` repository as maintainers
+- Teams need to exist before `Flux` proceeds to this configuration
+
+![Teams in Github](images/M6-github-teams.png)
+
+---
+
+### ⚠️ Disclaimer
+
+- In this lab, adding these teams as maintainers was merely a demonstration of how `Flux` _CLI_ sets up permissions in Github
+
+- But there is no need for dev teams to have access to this `Github` repository
+
+- One advantage of _GitOps_ lies in its ability to easily set up 💪🏼 **Separation of concerns** by using multiple `Flux` sources
+
+---
+
+### 📂 Flux config files
+
+`Flux` has been successfully installed onto our **_☁️CLOUDY_** Kubernetes cluster!
+
+Its configuration is managed through a _Gitops_ workflow sourced directly from our `Github` repository
+
+Let's review our `Flux` configuration files we've created and pushed into the `Github` repository…  
+… as well as the corresponding components running in our Kubernetes cluster
+
+![Flux config files](images/M6-flux-config-files.png)
+
+---
+
+class: pic
+<!-- FIXME: wrong schema -->
+![Flux architecture](images/M6-flux-controllers.png)
+
+---
+
+class: extra-details
+
+### Flux resources 1/2
+
+.lab[
+
+```bash
+k8s@shpod:~$ kubectl get all --namespace flux-system
+NAME                                           READY   STATUS    RESTARTS   AGE
+pod/helm-controller-b6767d66-h6qhk             1/1     Running   0          5m
+pod/kustomize-controller-57c7ff5596-94rnd      1/1     Running   0          5m
+pod/notification-controller-58ffd586f7-zxfvk   1/1     Running   0          5m
+pod/source-controller-6ff87cb475-g6gn6         1/1     Running   0          5m
+
+NAME                              TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)   AGE
+service/notification-controller   ClusterIP   10.104.139.156   <none>        80/TCP    5m1s
+service/source-controller         ClusterIP   10.106.120.137   <none>        80/TCP    5m
+service/webhook-receiver          ClusterIP   10.96.28.236     <none>        80/TCP    5m
+(…)
+```
+
+]
+
+---
+
+class: extra-details
+
+### Flux resources 2/2
+
+.lab[
+
+```bash
+k8s@shpod:~$ kubectl get all --namespace flux-system
+(…)
+NAME                                      READY   UP-TO-DATE   AVAILABLE   AGE
+deployment.apps/helm-controller           1/1     1            1           5m
+deployment.apps/kustomize-controller      1/1     1            1           5m
+deployment.apps/notification-controller   1/1     1            1           5m
+deployment.apps/source-controller         1/1     1            1           5m
+
+NAME                                                 DESIRED   CURRENT   READY   AGE
+replicaset.apps/helm-controller-b6767d66             1         1         1       5m
+replicaset.apps/kustomize-controller-57c7ff5596      1         1         1       5m
+replicaset.apps/notification-controller-58ffd586f7   1         1         1       5m
+replicaset.apps/source-controller-6ff87cb475         1         1         1       5m
+```
+
+]
+
+---
+
+### Flux components
+
+- the `source controller` monitors `Git` repositories to apply Kubernetes resources on the cluster
+
+- the `Helm controller` checks for new `Helm` _charts_ releases in `Helm` repositories and installs updates as needed
+
+- _CRDs_ store `Flux` configuration within the Kubernetes control plane
+
+---
+
+class: extra-details
+
+### Flux resources that have been created
+
+.lab[
+
+```bash
+k8s@shpod:~$ flux get all --all-namespaces
+NAMESPACE       NAME                            REVISION                SUSPENDED
+      READY   MESSAGE
+flux-system     gitrepository/flux-system       main@sha1:d48291a8      False
+      True    stored artifact for revision 'main@sha1:d48291a8'
+
+NAMESPACE       NAME                            REVISION                SUSPENDED
+      READY   MESSAGE
+flux-system     kustomization/flux-system       main@sha1:d48291a8      False
+      True    Applied revision: main@sha1:d48291a8
+```
+
+]
+
+---
+
+### Flux CLI
+
+`Flux` Command-Line Interface fulfills 3 primary functions:
+
+1. It installs and configures first mandatory `Flux` resources in a _Gitops_ `git` repository
+  - ensuring proper access and permissions
+
+2. It locally generates `YAML` files for desired `Flux` resources so that we just need to `git push` them
+  - _tenants_
+  - sources
+  - …
+
+3. It requests the API server to manage `Flux`-related resources
+     - _operators_
+     - _CRDs_
+     - logs
+
+---
+
+class: extra-details
+
+### Flux -- for more info
+
+Please, refer to the [`Flux` chapter in the High Five M3 module](./3.yml.html#toc-helm-chart-format)
+
+---
+
+### Flux relies on Kustomize
+
+The `Flux` component named `kustomize controller` look for `Kustomize` resources in `Flux` code-based sources
+
+1. `Kustomize` look for `YAML` manifests listed in the `kustomization.yaml` file
+
+2. and aggregates, hydrates and patches them following the `kustomization` configuration
+
+---
+
+class: extra-details
+
+### 2 different kustomization resources
+
+⚠️ `Flux` uses 2 distinct resources with `kind: kustomization`
+
+```yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: kustomization
+```
+
+describes how Kustomize (the _CLI_ tool) appends and transforms `YAML` manifests into a single bunch of `YAML` described resources
+
+```yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1 group
+kind: Kustomization
+```
+
+describes where `Flux kustomize-controller` looks for a `kustomization.yaml` file in a given `Flux` code-based source
+
+---
+
+class: extra-details
+
+### Kustomize -- for more info
+
+Please, refer to the [`Kustomize` chapter in the High Five M3 module](./3.yml.html#toc-kustomize)
+
+---
+
+class: extra-details
+
+### Group / Version / Kind -- for more info
+
+For more info about how Kubernetes resource natures are identified by their `Group / Version / Kind` triplet…  
+… please, refer to the [`Kubernetes API` chapter in the High Five M5 module](./5.yml.html#toc-the-kubernetes-api)
+
+---
+
+### 🗺️ Where are we in our scenario?
+
+<pre class="mermaid">
+%%{init:
+    {
+      "theme": "default",
+      "gitGraph": {
+        "mainBranchName": "OPS",
+        "mainBranchOrder": 0
+      }
+    }
+}%%
+gitGraph
+    commit id:"0" tag:"start"
+    branch ROCKY order:3
+    branch MOVY order:4
+    branch YouRHere order:5
+
+    checkout OPS
+    commit id:'Flux install on CLOUDY cluster' tag:'T01'
+    branch TEST-env order:1
+    commit id:'FLUX install on TEST' tag:'T02' type: HIGHLIGHT
+
+    checkout YouRHere
+    commit id:'x'
+    checkout OPS
+    merge YouRHere id:'YOU ARE HERE'
+
+    checkout OPS
+    commit id:'Flux config. for TEST tenant' tag:'T03'
+    commit id:'namespace isolation by RBAC'
+    checkout TEST-env
+    merge OPS id:'ROCKY tenant creation' tag:'T04'
+
+    checkout OPS
+    commit id:'ROCKY deploy. config.' tag:'R01'
+
+    checkout TEST-env
+    merge OPS id:'TEST ready to deploy ROCKY' type: HIGHLIGHT tag:'R02'
+
+    checkout ROCKY
+    commit id:'ROCKY' tag:'v1.0.0'
+
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.0'
+</pre>

slides/flux/ingress.md

@@ -0,0 +1,284 @@
+# T05- Configuring ingress for **_🎸ROCKY_** app
+
+🍾 **_🎸ROCKY_** team has just deployed its `v1.0.0`
+
+We would like to reach it from our workstations  
+The regular way to do it in Kubernetes is to configure an `Ingress` resource.
+
+- `Ingress` is an abstract resource that manages how services are exposed outside of the Kubernetes cluster (Layer 7).  
+- It relies on `ingress-controller`(s) that are technical solutions to handle all the rules related to ingress.
+
+- Available features vary, depending on the `ingress-controller`: load-balancing, networking, firewalling, API management, throttling, TLS encryption, etc.
+- `ingress-controller` may provision Cloud _IaaS_ network resources such as load-balancer, persistent IPs, etc.
+
+---
+
+class: extra-details
+
+## Ingress -- for more info
+
+Please, refer to the [`Ingress` chapter in the High Five M2 module](./2.yml.html#toc-exposing-http-services-with-ingress-resources)
+
+---
+
+## Installing `ingress-nginx` as our `ingress-controller`
+
+We'll use `ingress-nginx` (relying on `NGinX`), quite a popular choice.
+
+- It is able to provision IaaS load-balancer in ScaleWay Cloud services
+- As a reverse-proxy, it is able to balance HTTP connections on an on-premises cluster
+
+The **_⚙️OPS_** Team add this new install to its `Flux` config. repo
+
+---
+
+### Creating a `Github` source in Flux for `ingress-nginx`
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$             \
+    mkdir -p ./clusters/CLOUDY/ingress-nginx &&        \
+    flux create source git ingress-nginx               \
+    --namespace=ingress-nginx                          \
+    --url=https://github.com/kubernetes/ingress-nginx/ \
+    --branch=release-1.12                              \
+    --export > ./clusters/CLOUDY/ingress-nginx/sync.yaml
+```
+
+]
+
+---
+
+### Creating `kustomization` in Flux for `ingress-nginx`
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ flux create kustomization ingress-nginx \
+    --namespace=ingress-nginx                                                      \
+    --source=GitRepository/ingress-nginx                                           \
+    --path="./deploy/static/provider/scw/"                                         \
+    --export >> ./clusters/CLOUDY/ingress-nginx/sync.yaml
+
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cp -p ~/container.training/k8s/M6-ingress-nginx-kustomization.yaml    \
+                    ./clusters/CLOUDY/ingress-nginx/kustomization.yaml && \
+    cp -p ~/container.training/k8s/M6-ingress-nginx-components.yaml       \
+          ~/container.training/k8s/M6-ingress-nginx-*-patch.yaml          \
+                    ./clusters/CLOUDY/ingress-nginx/
+```
+
+]
+
+---
+
+### Applying the new config
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    git add ./clusters/CLOUDY/ingress-nginx && \
+    git commit -m':wrench: :rocket: add Ingress-controller' && \
+    git push
+```
+
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+class: pic
+
+![Ingress-nginx provisionned a IaaS load-balancer in Scaleway Cloud services](images/M6-ingress-nginx-scaleway-lb.png)
+
+---
+
+class: extra-details
+
+### Using external Git source
+
+💡 Note that you can directly use pubilc `Github` repository (not maintained by your company).  
+
+- If you have to alter the configuration, `Kustomize` patching capabilities might help.
+
+- Depending on the _gitflow_ this repository uses, updates will be deployed automatically to your cluster (here we're using a `release` branch).
+
+- This repo exposes a `kustomization.yaml`. Well done!
+
+---
+
+## Adding the `ingress` resource to ROCKY app
+
+.lab[
+
+- Add the new manifest to our kustomization bunch
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    cp -pr ~/container.training/k8s/M6-rocky-ingress.yaml ./tenants/base/rocky && \
+    echo '- M6-rocky-ingress.yaml' >> ./tenants/base/rocky/kustomization.yaml
+```
+
+- Commit and its done
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$ \
+    git add . && \
+    git commit -m':wrench: :rocket: add Ingress' && \
+    git push
+```
+
+]
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### Here is the result
+
+After Flux reconciled the whole bunch of sources and kustomizations, you should see
+
+- `Ingress-NGinX` controller components in `ingress-nginx` namespace
+- A new `Ingress` in `rocky-test` namespace
+
+.lab[
+
+```bash
+k8s@shpod:~$ kubectl get all -n ingress-nginx && \
+             kubectl get ingress -n rocky-test
+
+k8s@shpod:~$ \
+    PublicIP=$(kubectl get ingress rocky -n rocky-test \
+                -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
+
+k8s@shpod:~$ \
+    curl --header 'rocky.test.mybestdomain.com' http://$PublicIP/
+```
+
+]
+
+---
+
+class: pic
+
+![Rocky application screenshot](images/M6-rocky-app-screenshot.png)
+
+---
+
+## Upgrading **_🎸ROCKY_** app
+
+**_🎸ROCKY_** team is now fully able to upgrade and deploy its app autonomously.
+
+Just give it a try!
+- In the `deployment.yaml` file
+- in the app repo ([https://github.com/Musk8teers/container.training-spring-music/])
+- you can change the `spec.template.spec.containers.image` to `1.0.1` and then to `1.0.2`
+
+Dont' forget which branch is watched by `Flux` Git source named `rocky`
+
+Don't forget to commit!
+
+---
+
+## Few considerations
+
+- The **_⚙️OPS_** team has to decide how to manage name resolution for public IPs
+  - Scaleway propose to expose a wildcard domain for its Kubernetes clusters
+
+- Here, we chose that `Ingress-controller` (that makes sense) but `Ingress` as well were managed by the **_⚙️OPS_** team.
+  - It might have been done in many different ways!
+
+---
+
+### 🗺️ Where are we in our scenario?
+
+<pre class="mermaid">
+%%{init:
+    {
+      "theme": "default",
+      "gitGraph": {
+        "mainBranchName": "OPS",
+        "mainBranchOrder": 0
+      }
+    }
+}%%
+gitGraph
+    commit id:"0" tag:"start"
+    branch ROCKY order:3
+    branch MOVY order:4
+    branch YouRHere order:5
+
+    checkout OPS
+    commit id:'Flux install on CLOUDY cluster' tag:'T01'
+    branch TEST-env order:1
+    commit id:'FLUX install on TEST' tag:'T02' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Flux config. for TEST tenant' tag:'T03'
+    commit id:'namespace isolation by RBAC'
+    checkout TEST-env
+    merge OPS id:'ROCKY tenant creation' tag:'T04'
+
+    checkout OPS
+    commit id:'ROCKY deploy. config.' tag:'R01'
+
+    checkout TEST-env
+    merge OPS id:'TEST ready to deploy ROCKY' type: HIGHLIGHT tag:'R02'
+
+    checkout ROCKY
+    commit id:'ROCKY' tag:'v1.0.0'
+
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.0'
+
+    checkout OPS
+    commit id:'Ingress-controller config.' tag:'T05'
+    checkout TEST-env
+    merge OPS id:'Ingress-controller install' type: HIGHLIGHT tag:'T06'
+
+    checkout OPS
+    commit id:'ROCKY patch for ingress config.' tag:'R03'
+    checkout TEST-env
+    merge OPS id:'ingress config. for ROCKY app'
+
+    checkout ROCKY
+    commit id:'blue color' tag:'v1.0.1'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.1'
+
+    checkout ROCKY
+    commit id:'pink color' tag:'v1.0.2'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.2'
+
+    checkout YouRHere
+    commit id:'x'
+    checkout OPS
+    merge YouRHere id:'YOU ARE HERE'
+
+    checkout OPS
+    commit id:'FLUX config for MOVY deployment' tag:'M01'
+    checkout TEST-env
+    merge OPS id:'FLUX ready to deploy MOVY' type: HIGHLIGHT tag:'M02'
+
+    checkout MOVY
+    commit id:'MOVY' tag:'v1.0.3'
+    checkout TEST-env
+    merge MOVY tag:'MOVY v1.0.3' type: REVERSE
+
+    checkout OPS
+    commit id:'Network policies'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+</pre>

slides/flux/kyverno.md

@@ -0,0 +1,241 @@
+## introducing Kyverno
+
+Kyverno is a tool to extend Kubernetes permission management to express complex policies…
+</br>… and override manifests delivered by client teams.
+
+---
+
+class: extra-details
+
+### Kyverno -- for more info
+
+Please, refer to the [`Setting up Kubernetes` chapter in the High Five M4 module](./4.yml.html#toc-policy-management-with-kyverno) for more infos about `Kyverno`.
+
+---
+
+## Creating an `Helm` source in Flux for OpenEBS Helm chart
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$  \
+        mkdir -p clusters/CLOUDY/kyverno && \
+        cp -pr ~/container.training/k8s/
+
+k8s@shpod ~$ flux create source helm kyverno \
+    --namespace=kyverno                         \
+    --url=https://kyverno.github.io/kyverno/ \
+    --interval=3m                            \
+    --export > ./clusters/CLOUDY/kyverno/sync2.yaml
+```
+
+]
+
+---
+
+## Creating the `HelmRelease` in Flux
+
+.lab[
+
+```bash
+k8s@shpod ~$ flux create helmrelease kyverno    \
+    --namespace=kyverno                         \
+    --source=HelmRepository/kyverno.flux-system \
+    --target-namespace=kyverno                  \
+    --create-target-namespace=true              \
+    --chart-version=">=3.4.2"                   \
+    --chart=kyverno                             \
+    --export >> ./clusters/CLOUDY/kyverno/sync.yaml
+```
+
+]
+
+---
+
+## Add Kyverno policy
+
+This polivy is just an example.
+It enforces the use of a `Service Account` in `Flux` configurations
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$           \
+    mkdir -p clusters/CLOUDY/kyverno-policies &&     \
+    cp -pr ~/container.training/k8s/M6-kyverno-enforce-service-account.yaml \
+            ./clusters/CLOUDY/kyverno-policies/
+
+---
+
+### Creating `kustomization` in Flux for Kyverno policies
+
+.lab[
+
+```bash
+k8s@shpod:~/fleet-config-using-flux-XXXXX$           \
+    flux create kustomization kyverno-policies       \
+        --namespace=kyverno                          \
+        --source=GitRepository/flux-system           \
+        --path="./clusters/CLOUDY/kyverno-policies/" \
+        --prune true --interval 5m                   \
+        --depends-on kyverno                         \
+        --export >> ./clusters/CLOUDY/kyverno-policies/sync.yaml
+```
+
+]
+
+
+## Apply Kyverno policy
+```bash
+flux create kustomization 
+
+--path 
+--source GitRepository/
+--export > ./clusters/CLOUDY/kyverno-policies/sync.yaml
+```
+
+---
+
+## Add Kyverno dependency for **_⚗️TEST_** cluster
+
+- Now that we've got `Kyverno` policies,
+- ops team will enforce any upgrade from any kustomization in our dev team tenants
+- to wait for the `kyverno` policies to be reconciled (in a `Flux` perspective)
+
+- upgrade file `./clusters/CLOUDY/tenants.yaml`,
+- by adding this property:  `spec.dependsOn.{name: kyverno-policies}`
+
+---
+
+class: pic
+
+![Running Mario](images/M6-running-Mario.gif)
+
+---
+
+### Debugging
+
+`Kyverno-policies` `Kustomization` failed because `spec.dependsOn` property can only target a resource from the same `Kind`.
+
+- Let's suppress the `spec.dependsOn` property.
+
+Now `Kustomizations` for **_🎸ROCKY_** and **_🎬MOVY_** tenants failed because of our policies.
+
+---
+
+### 🗺️ Where are we in our scenario?
+
+<pre class="mermaid">
+%%{init:
+    {
+      "theme": "default",
+      "gitGraph": {
+        "mainBranchName": "OPS",
+        "mainBranchOrder": 0
+      }
+    }
+}%%
+gitGraph
+    commit id:"0" tag:"start"
+    branch ROCKY order:4
+    branch MOVY order:5
+    branch YouRHere order:6
+
+    checkout OPS
+    commit id:'Flux install on CLOUDY cluster' tag:'T01'
+    branch TEST-env order:1
+    commit id:'FLUX install on TEST' tag:'T02' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Flux config. for TEST tenant' tag:'T03'
+    commit id:'namespace isolation by RBAC'
+    checkout TEST-env
+    merge OPS id:'ROCKY tenant creation' tag:'T04'
+
+    checkout OPS
+    commit id:'ROCKY deploy. config.' tag:'R01'
+
+    checkout TEST-env
+    merge OPS id:'TEST ready to deploy ROCKY' type: HIGHLIGHT tag:'R02'
+
+    checkout ROCKY
+    commit id:'ROCKY' tag:'v1.0.0'
+
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.0'
+
+    checkout OPS
+    commit id:'Ingress-controller config.' tag:'T05'
+    checkout TEST-env
+    merge OPS id:'Ingress-controller install' type: HIGHLIGHT tag:'T06'
+
+    checkout OPS
+    commit id:'ROCKY patch for ingress config.' tag:'R03'
+    checkout TEST-env
+    merge OPS id:'ingress config. for ROCKY app'
+
+    checkout ROCKY
+    commit id:'blue color' tag:'v1.0.1'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.1'
+
+    checkout ROCKY
+    commit id:'pink color' tag:'v1.0.2'
+    checkout TEST-env
+    merge ROCKY tag:'ROCKY v1.0.2'
+
+    checkout OPS
+    commit id:'FLUX config for MOVY deployment' tag:'M01'
+    checkout TEST-env
+    merge OPS id:'FLUX ready to deploy MOVY' type: HIGHLIGHT tag:'M02'
+
+    checkout MOVY
+    commit id:'MOVY' tag:'v1.0.3'
+    checkout TEST-env
+    merge MOVY tag:'MOVY v1.0.3' type: REVERSE
+
+    checkout OPS
+    commit id:'Network policies'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT tag:'T07'
+
+    checkout OPS
+    commit id:'k0s install on METAL cluster' tag:'K01'
+    commit id:'Flux config. for METAL cluster' tag:'K02'
+    branch METAL_TEST-PROD order:3
+    commit id:'ROCKY/MOVY tenants on METAL' type: HIGHLIGHT
+    checkout OPS
+    commit id:'Flux config. for OpenEBS' tag:'K03'
+    checkout METAL_TEST-PROD
+    merge OPS id:'openEBS on METAL' type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Prometheus install'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+
+    checkout OPS
+    commit id:'Kyverno install'
+    commit id:'Kyverno rules'
+    checkout TEST-env
+    merge OPS type: HIGHLIGHT
+
+    checkout YouRHere
+    commit id:'x'
+    checkout OPS
+    merge YouRHere id:'YOU ARE HERE'
+
+    checkout OPS
+    commit id:'Flux config. for PROD tenant' tag:'P01'
+    branch PROD-env order:2
+    commit id:'ROCKY tenant on PROD'
+    checkout OPS
+    commit id:'ROCKY patch for PROD' tag:'R04'
+    checkout PROD-env
+    merge OPS id:'PROD ready to deploy ROCKY' type: HIGHLIGHT
+    checkout PROD-env
+    merge ROCKY tag:'ROCKY v1.0.2'
+
+    checkout MOVY
+    commit id:'MOVY HELM chart' tag:'M03'
+    checkout TEST-env
+    merge MOVY tag:'MOVY v1.0'
+</pre>