✨ NR ADV K8S Fall 2022

Add more details for startup probes.
Mention GRPC check.
Better spell out recommendations and gotchas.

k8s/dashboard-insecure.yaml

@@ -17,8 +17,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 ---
@@ -30,8 +30,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-certs
   namespace: kubernetes-dashboard
 type: Opaque
@@ -43,8 +43,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-csrf
   namespace: kubernetes-dashboard
 type: Opaque
@@ -56,8 +56,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-key-holder
   namespace: kubernetes-dashboard
 type: Opaque
@@ -71,8 +71,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-settings
   namespace: kubernetes-dashboard
 ---
@@ -84,8 +84,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 rules:
 - apiGroups:
@@ -106,8 +106,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 roleRef:
   apiGroup: rbac.authorization.k8s.io
@@ -126,8 +126,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 rules:
@@ -182,8 +182,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 roleRef:
@@ -204,8 +204,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
     kubernetes.io/cluster-service: "true"
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
@@ -229,8 +229,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 spec:
@@ -253,8 +253,8 @@ spec:
         app.kubernetes.io/instance: kubernetes-dashboard
         app.kubernetes.io/managed-by: Helm
         app.kubernetes.io/name: kubernetes-dashboard
-        app.kubernetes.io/version: 2.5.0
-        helm.sh/chart: kubernetes-dashboard-5.2.0
+        app.kubernetes.io/version: 2.6.1
+        helm.sh/chart: kubernetes-dashboard-5.10.0
     spec:
       containers:
       - args:
@@ -262,7 +262,7 @@ spec:
         - --sidecar-host=http://127.0.0.1:8000
         - --enable-skip-login
         - --enable-insecure-login
-        image: kubernetesui/dashboard:v2.5.0
+        image: kubernetesui/dashboard:v2.6.1
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:
@@ -293,7 +293,7 @@ spec:
           name: kubernetes-dashboard-certs
         - mountPath: /tmp
           name: tmp-volume
-      - image: kubernetesui/metrics-scraper:v1.0.7
+      - image: kubernetesui/metrics-scraper:v1.0.8
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:

k8s/dashboard-recommended.yaml

@@ -17,8 +17,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 ---
@@ -30,8 +30,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-certs
   namespace: kubernetes-dashboard
 type: Opaque
@@ -43,8 +43,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-csrf
   namespace: kubernetes-dashboard
 type: Opaque
@@ -56,8 +56,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-key-holder
   namespace: kubernetes-dashboard
 type: Opaque
@@ -71,8 +71,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-settings
   namespace: kubernetes-dashboard
 ---
@@ -84,8 +84,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 rules:
 - apiGroups:
@@ -106,8 +106,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 roleRef:
   apiGroup: rbac.authorization.k8s.io
@@ -126,8 +126,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 rules:
@@ -182,8 +182,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 roleRef:
@@ -204,8 +204,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
     kubernetes.io/cluster-service: "true"
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
@@ -229,8 +229,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 spec:
@@ -253,15 +253,15 @@ spec:
         app.kubernetes.io/instance: kubernetes-dashboard
         app.kubernetes.io/managed-by: Helm
         app.kubernetes.io/name: kubernetes-dashboard
-        app.kubernetes.io/version: 2.5.0
-        helm.sh/chart: kubernetes-dashboard-5.2.0
+        app.kubernetes.io/version: 2.6.1
+        helm.sh/chart: kubernetes-dashboard-5.10.0
     spec:
       containers:
       - args:
         - --namespace=kubernetes-dashboard
         - --auto-generate-certificates
         - --sidecar-host=http://127.0.0.1:8000
-        image: kubernetesui/dashboard:v2.5.0
+        image: kubernetesui/dashboard:v2.6.1
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:
@@ -292,7 +292,7 @@ spec:
           name: kubernetes-dashboard-certs
         - mountPath: /tmp
           name: tmp-volume
-      - image: kubernetesui/metrics-scraper:v1.0.7
+      - image: kubernetesui/metrics-scraper:v1.0.8
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:

k8s/dashboard-with-token.yaml

@@ -17,8 +17,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 ---
@@ -30,8 +30,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-certs
   namespace: kubernetes-dashboard
 type: Opaque
@@ -43,8 +43,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-csrf
   namespace: kubernetes-dashboard
 type: Opaque
@@ -56,8 +56,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-key-holder
   namespace: kubernetes-dashboard
 type: Opaque
@@ -71,8 +71,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-settings
   namespace: kubernetes-dashboard
 ---
@@ -84,8 +84,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 rules:
 - apiGroups:
@@ -106,8 +106,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard-metrics
 roleRef:
   apiGroup: rbac.authorization.k8s.io
@@ -126,8 +126,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 rules:
@@ -182,8 +182,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 roleRef:
@@ -204,8 +204,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
     kubernetes.io/cluster-service: "true"
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
@@ -229,8 +229,8 @@ metadata:
     app.kubernetes.io/instance: kubernetes-dashboard
     app.kubernetes.io/managed-by: Helm
     app.kubernetes.io/name: kubernetes-dashboard
-    app.kubernetes.io/version: 2.5.0
-    helm.sh/chart: kubernetes-dashboard-5.2.0
+    app.kubernetes.io/version: 2.6.1
+    helm.sh/chart: kubernetes-dashboard-5.10.0
   name: kubernetes-dashboard
   namespace: kubernetes-dashboard
 spec:
@@ -253,15 +253,15 @@ spec:
         app.kubernetes.io/instance: kubernetes-dashboard
         app.kubernetes.io/managed-by: Helm
         app.kubernetes.io/name: kubernetes-dashboard
-        app.kubernetes.io/version: 2.5.0
-        helm.sh/chart: kubernetes-dashboard-5.2.0
+        app.kubernetes.io/version: 2.6.1
+        helm.sh/chart: kubernetes-dashboard-5.10.0
     spec:
       containers:
       - args:
         - --namespace=kubernetes-dashboard
         - --auto-generate-certificates
         - --sidecar-host=http://127.0.0.1:8000
-        image: kubernetesui/dashboard:v2.5.0
+        image: kubernetesui/dashboard:v2.6.1
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:
@@ -292,7 +292,7 @@ spec:
           name: kubernetes-dashboard-certs
         - mountPath: /tmp
           name: tmp-volume
-      - image: kubernetesui/metrics-scraper:v1.0.7
+      - image: kubernetesui/metrics-scraper:v1.0.8
         imagePullPolicy: IfNotPresent
         livenessProbe:
           httpGet:

prepare-local/provisioning.yml

@@ -1,11 +1,10 @@
 ---
 - hosts: nodes
-  sudo: true
+  become: yes
   vars_files:
     - vagrant.yml
 
   tasks:
-
     - name: clean up the home folder
       file:
         path: /home/vagrant/{{ item }}
@@ -24,25 +23,23 @@
 
     - name: installing dependencies
       apt:
-        name: apt-transport-https,ca-certificates,python-pip,tmux
+        name: apt-transport-https,ca-certificates,python3-pip,tmux
         state: present
         update_cache: true
 
     - name: fetching docker repo key
       apt_key:
-        keyserver: hkp://p80.pool.sks-keyservers.net:80
-        id: 58118E89F3A912897C070ADBF76221572C52609D
-
-    - name: adding package repos
-      apt_repository:
-        repo: "{{ item }}"
+        url: https://download.docker.com/linux/ubuntu/gpg
+        state: present
+
+    - name: adding docker repo
+      apt_repository:
+        repo: deb https://download.docker.com/linux/ubuntu focal stable
         state: present
-      with_items:
-        - deb https://apt.dockerproject.org/repo ubuntu-trusty main
 
     - name: installing docker
       apt:
-        name: docker-engine
+        name: docker-ce,docker-ce-cli,containerd.io,docker-compose-plugin
         state: present
         update_cache: true
 
@@ -56,7 +53,7 @@
       lineinfile:
         dest: /etc/default/docker
         line: DOCKER_OPTS="--host=unix:///var/run/docker.sock --host=tcp://0.0.0.0:55555"
-        regexp: '^#?DOCKER_OPTS=.*$'
+        regexp: "^#?DOCKER_OPTS=.*$"
         state: present
       register: docker_opts
 
@@ -66,22 +63,14 @@
         state: restarted
       when: docker_opts is defined and docker_opts.changed
 
-    - name: performing pip autoupgrade
-      pip:
-        name: pip
-        state: latest
-
-    - name: installing virtualenv
-      pip:
-        name: virtualenv
-        state: latest
-
-    - name: Install Docker Compose via PIP
-      pip: name=docker-compose
+    - name: install docker-compose from official github repo
+      get_url:
+        url: https://github.com/docker/compose/releases/download/1.29.2/docker-compose-Linux-x86_64
+        dest: /usr/local/bin/docker-compose
+        mode: "u+x,g+x"
 
     - name:
-      file:
-        path="/usr/local/bin/docker-compose"
+      file: path="/usr/local/bin/docker-compose"
         state=file
         mode=0755
         owner=vagrant
@@ -128,5 +117,3 @@
           line: "127.0.0.1 localhost {{ inventory_hostname }}"
         - regexp: '^127\.0\.1\.1'
           line: "127.0.1.1 {{ inventory_hostname }}"
-
-

prepare-local/vagrant.yml

@@ -1,13 +1,12 @@
 ---
 vagrant:
-  default_box: ubuntu/trusty64
+  default_box: ubuntu/focal64
   default_box_check_update: true
   ssh_insert_key: false
   min_memory: 256
   min_cores: 1
 
 instances:
-
   - hostname: node1
     private_ip: 10.10.10.10
     memory: 1512
@@ -37,6 +36,3 @@ instances:
     private_ip: 10.10.10.50
     memory: 512
     cores: 1
-
-
-

prepare-vms/lib/commands.sh

@@ -182,9 +182,23 @@ _cmd_clusterize() {
     pssh "
     if [ -f /etc/iptables/rules.v4 ]; then
         sudo sed -i 's/-A INPUT -j REJECT --reject-with icmp-host-prohibited//' /etc/iptables/rules.v4
+        sudo netfilter-persistent flush
         sudo netfilter-persistent start
     fi"
 
+    # oracle-cloud-agent upgrades pacakges in the background.
+    # This breaks our deployment scripts, because when we invoke apt-get, it complains
+    # that the lock already exists (symptom: random "Exited with error code 100").
+    # Workaround: if we detect oracle-cloud-agent, remove it.
+    # But this agent seems to also take care of installing/upgrading
+    # the unified-monitoring-agent package, so when we stop the snap,
+    # it can leave dpkg in a broken state. We "fix" it with the 2nd command.
+    pssh "
+    if [ -d /snap/oracle-cloud-agent ]; then
+        sudo snap remove oracle-cloud-agent
+        sudo dpkg --remove --force-remove-reinstreq unified-monitoring-agent
+    fi"
+
     # Copy settings and install Python YAML parser
     pssh -I tee /tmp/settings.yaml <tags/$TAG/settings.yaml
     pssh "
@@ -262,13 +276,14 @@ EOF
     "
 
     ##VERSION## https://github.com/docker/compose/releases
-    if [ "$ARCHITECTURE" ]; then
-        COMPOSE_VERSION=v2.2.3
-        COMPOSE_PLATFORM='linux-$(uname -m)'
-    else
-        COMPOSE_VERSION=1.29.2
-        COMPOSE_PLATFORM='Linux-$(uname -m)'
-    fi
+    COMPOSE_VERSION=v2.11.1
+    COMPOSE_PLATFORM='linux-$(uname -m)'
+    
+    # Just in case you need Compose 1.X, you can use the following lines.
+    # (But it will probably only work for x86_64 machines.)
+    #COMPOSE_VERSION=1.29.2
+    #COMPOSE_PLATFORM='Linux-$(uname -m)'
+
     pssh "
     set -e
     ### Install docker-compose.
@@ -478,12 +493,13 @@ _cmd_kubetools() {
     # Install kube-ps1
     pssh "
     set -e
-    if ! [ -f /etc/profile.d/kube-ps1.sh ]; then
+    if ! [ -d /opt/kube-ps1 ]; then
       cd /tmp
       git clone https://github.com/jonmosco/kube-ps1
-      sudo cp kube-ps1/kube-ps1.sh /etc/profile.d/kube-ps1.sh
+      sudo mv kube-ps1 /opt/kube-ps1
       sudo -u $USER_LOGIN sed -i s/docker-prompt/kube_ps1/ /home/$USER_LOGIN/.bashrc &&
       sudo -u $USER_LOGIN tee -a /home/$USER_LOGIN/.bashrc <<EOF
+. /opt/kube-ps1/kube-ps1.sh
 KUBE_PS1_PREFIX=""
 KUBE_PS1_SUFFIX=""
 KUBE_PS1_SYMBOL_ENABLE="false"

slides/_redirects

@@ -2,7 +2,7 @@
 #/ /kube-halfday.yml.html 200!
 #/ /kube-fullday.yml.html 200!
 #/ /kube-twodays.yml.html 200!
-/ /kube.yml.html 200!
+/ /kube-adv.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

slides/containers/Ambassadors.md

@@ -19,7 +19,7 @@ They abstract the connection details for this services, and can help with:
 
 * fail over (how do I know to which instance of a replicated service I should connect?)
 
-* load balancing (how to I spread my requests across multiple instances of a service?)
+* load balancing (how do I spread my requests across multiple instances of a service?)
 
 * authentication (what if my service requires credentials, certificates, or otherwise?)
 

slides/exercises/healthchecks-brief.md

@@ -4,6 +4,6 @@
 
   (we will use the `rng` service in the dockercoins app)
 
-- See what happens when the load increses
+- See what happens when the load increases
 
   (spoiler alert: it involves timeouts!)

slides/interlude-form.md

@@ -0,0 +1,17 @@
+# Interlude
+
+- As mentioned earlier:
+
+  *the content of this course will be adapted to suit your needs!*
+
+- Please take a look at the form that we just shared in Slack
+
+  (you don't need to fill it *right now*)
+
+- If there are parts that you are curious about, ask us now!
+
+- We'll ask you to fill the form after today's session
+
+  (before the end of the day, basically, so we can process the results by tomorrow)
+
+- Thank you!

slides/k8s/architecture.md

@@ -203,12 +203,12 @@ What does that mean?
 
 ## Let's experiment a bit!
 
-- For this section, connect to the first node of the `test` cluster
+- The examples in this section require a Kubernetes cluster
+
+  (any local development cluster will suffice)
 
 .lab[
 
-- SSH to the first node of the test cluster
-
 - Check that the cluster is operational:
   ```bash
   kubectl get nodes

slides/k8s/healthchecks.md

@@ -1,46 +1,62 @@
 # Healthchecks
 
-- Containers can have *healthchecks*
+- Containers can have *healthchecks* (also called "probes")
 
-- There are three kinds of healthchecks, corresponding to very different use-cases:
+- There are three kinds of healthchecks, corresponding to different use-cases:
 
-  - liveness  = detect when a container is "dead" and needs to be restarted
-
-  - readiness = detect when a container is ready to serve traffic
-
-  - startup = detect if a container has finished to boot
+  `startupProbe`, `readinessProbe`, `livenessProbe`
 
 - These healthchecks are optional (we can use none, all, or some of them)
 
-- Different probes are available (HTTP request, TCP connection, program execution)
+- Different probes are available:
 
-- Let's see the difference and how to use them!
+  HTTP GET, TCP connection, arbitrary program execution, GRPC
+
+- All these probes have a binary result (success/failure)
+
+- Probes that aren't defined will default to a "success" result
 
 ---
 
-## Liveness probe
+## Use-cases in brief
+
+*My container takes a long time to boot before being able to serve traffic.*
+
+→ use a `startupProbe` (but often a `readinessProbe` can also do the job)
+
+*Sometimes, my container is unavailable or overloaded, and needs to e.g. be taken temporarily out of load balancer rotation.*
+
+→ use a `readinessProbe`
+
+*Sometimes, my container enters a broken state which can only be fixed by a restart.*
+
+→ use a `livenessProbe`
+
+---
+
+## Liveness probes
 
 *This container is dead, we don't know how to fix it, other than restarting it.*
 
-- Indicates if the container is dead or alive
+- Check if the container is dead or alive
 
-- A dead container cannot come back to life
+- If Kubernetes determines that the container is dead:
 
-- If the liveness probe fails, the container is killed (destroyed)
+  - it terminates the container gracefully
 
-  (to make really sure that it's really dead; no zombies or undeads!)
+  - it restarts the container (unless the Pod's `restartPolicy` is `Never`)
 
-- What happens next depends on the pod's `restartPolicy`:
+- With the default parameters, it takes:
 
-  - `Never`: the container is not restarted
+  - up to 30 seconds to determine that the container is dead
 
-  - `OnFailure` or `Always`: the container is restarted
+  - up to 30 seconds to terminate it
 
 ---
 
 ## When to use a liveness probe
 
-- To indicate failures that can't be recovered
+- To detect failures that can't be recovered
 
   - deadlocks (causing all requests to time out)
 
@@ -48,47 +64,45 @@
 
 - Anything where our incident response would be "just restart/reboot it"
 
+---
+
+## Liveness probes gotchas
+
 .warning[**Do not** use liveness probes for problems that can't be fixed by a restart]
 
 - Otherwise we just restart our pods for no reason, creating useless load
 
----
+.warning[**Do not** depend on other services within a liveness probe]
 
-## Readiness probe (1)
+- Otherwise we can experience cascading failures
 
-*Make sure that a container is ready before continuing a rolling update.*
+  (example: web server liveness probe that makes a requests to a database)
 
-- Indicates if the container is ready to handle traffic
+.warning[**Make sure** that liveness probes respond quickly]
 
-- When doing a rolling update, the Deployment controller waits for Pods to be ready
+- The default probe timeout is 1 second (this can be tuned!)
 
-  (a Pod is ready when all the containers in the Pod are ready)
-
-- Improves reliability and safety of rolling updates:
-
-  - don't roll out a broken version (that doesn't pass readiness checks)
-
-  - don't lose processing capacity during a rolling update
+- If the probe takes longer than that, it will eventually cause a restart
 
 ---
 
-## Readiness probe (2)
+## Readiness probes
 
-*Temporarily remove a container (overloaded or otherwise) from a Service load balancer.*
+*Sometimes, my container "needs a break".*
 
-- A container can mark itself "not ready" temporarily
+- Check if the container is ready or not
 
-  (e.g. if it's overloaded or needs to reload/restart/garbage collect...)
+- If the container is not ready, its Pod is not ready
 
-- If a container becomes "unready" it might be ready again soon
+- If the Pod belongs to a Service, it is removed from its Endpoints
 
-- If the readiness probe fails:
+  (it stops receiving new connections but existing ones are not affected)
 
-  - the container is *not* killed
+- If there is a rolling update in progress, it might pause
 
-  - if the pod is a member of a service, it is temporarily removed
+  (Kubernetes will try to respect the MaxUnavailable parameter)
 
-  - it is re-added as soon as the readiness probe passes again
+- As soon as the readiness probe suceeds again, everything goes back to normal
 
 ---
 
@@ -102,67 +116,31 @@
 
 - To indicate temporary failure or unavailability
 
+  - runtime is busy doing garbage collection or (re)loading data
+
   - application can only service *N* parallel connections
 
-  - runtime is busy doing garbage collection or initial data load
-
-- To redirect new connections to other Pods
-
-  (e.g. fail the readiness probe when the Pod's load is too high)
+  - new connections will be directed to other Pods
 
 ---
 
-## Dependencies
+## Startup probes
 
-- If a web server depends on a database to function, and the database is down:
+*My container takes a long time to boot before being able to serve traffic.*
 
-  - the web server's liveness probe should succeed
+- After creating a container, Kubernetes runs its startup probe
 
-  - the web server's readiness probe should fail
+- The container will be considered "unhealthy" until the probe succeeds
 
-- Same thing for any hard dependency (without which the container can't work)
+- As long as the container is "unhealthy", its Pod...:
 
-.warning[**Do not** fail liveness probes for problems that are external to the container]
+  - is not added to Services' endpoints
 
----
+  - is not considered as "available" for rolling update purposes
 
-## Timing and thresholds
+- Readiness and liveness probes are enabled *after* startup probe reports success
 
-- Probes are executed at intervals of `periodSeconds` (default: 10)
-
-- The timeout for a probe is set with `timeoutSeconds` (default: 1)
-
-.warning[If a probe takes longer than that, it is considered as a FAIL]
-
-- A probe is considered successful after `successThreshold` successes (default: 1)
-
-- A probe is considered failing after `failureThreshold` failures (default: 3)
-
-- A probe can have an `initialDelaySeconds` parameter (default: 0)
-
-- Kubernetes will wait that amount of time before running the probe for the first time
-
-  (this is important to avoid killing services that take a long time to start)
-
----
-
-## Startup probe
-
-*The container takes too long to start, and is killed by the liveness probe!*
-
-- By default, probes (including liveness) start immediately
-
-- With the default probe interval and failure threshold:
-
-  *a container must respond in less than 30 seconds, or it will be killed!*
-
-- There are two ways to avoid that:
-
-  - set `initialDelaySeconds` (a fixed, rigid delay)
-
-  - use a `startupProbe`
-
-- Kubernetes will run only the startup probe, and when it succeeds, run the other probes
+  (if there is no startup probe, readiness and liveness probes are enabled right away)
 
 ---
 
@@ -178,121 +156,296 @@
 
 ---
 
+## Startup probes gotchas
+
+- When defining a `startupProbe`, we almost always want to adjust its parameters
+
+  (specifically, its `failureThreshold` - this is explained in next slide)
+
+- Otherwise, if the container fails to start within 30 seconds...
+
+  *Kubernetes terminates the container and restarts it!*
+
+- Sometimes, it's easier/simpler to use a `readinessProbe` instead
+
+  (except when also using a `livenessProbe`)
+
+---
+
+## Timing and thresholds
+
+- Probes are executed at intervals of `periodSeconds` (default: 10)
+
+- The timeout for a probe is set with `timeoutSeconds` (default: 1)
+
+.warning[If a probe takes longer than that, it is considered as a FAIL]
+
+.warning[For liveness probes **and startup probes** this terminates and restarts the container]
+
+- A probe is considered successful after `successThreshold` successes (default: 1)
+
+- A probe is considered failing after `failureThreshold` failures (default: 3)
+
+- All these parameters can be set independently for each probe
+
+---
+
+class: extra-details
+
+## `initialDelaySeconds`
+
+- A probe can have an `initialDelaySeconds` parameter (default: 0)
+
+- Kubernetes will wait that amount of time before running the probe for the first time
+
+- It is generally better to use a `startupProbe` instead
+
+  (but this parameter did exist before startup probes were implemented)
+
+---
+
+class: extra-details
+
+## `readinessProbe` vs `startupProbe`
+
+- A lot of blog posts / documentations / tutorials recommend readiness probes...
+
+- ...even in scenarios where a startup probe would seem more appropriate!
+
+- This is because startup probes are relatively recent
+
+  (they reached GA status in Kubernetes 1.20)
+
+- When there is no `livenessProbe`, using a `readinessProbe` is simpler:
+
+  - a `startupProbe` generally requires to change the `failureThreshold`
+
+  - a `startupProbe` generally also requires a `readinessProbe`
+
+  - a single `readinessProbe` can fulfill both roles
+
+---
+
 ## Different types of probes
 
-- HTTP request
+- Kubernetes supports the following mechanisms:
 
-  - specify URL of the request (and optional headers)
+  - `exec` (arbitrary program execution)
 
-  - any status code between 200 and 399 indicates success
+  - `httpGet` (HTTP GET request)
 
-- TCP connection
+  - `tcpSocket` (check if a TCP port is accepting connections)
 
-  - the probe succeeds if the TCP port is open
+  - `grpc` (standard [GRPC Health Checking Protocol][grpc])
 
-- arbitrary exec
+- All probes give binary results ("it works" or "it doesn't")
 
-  - a command is executed in the container
+- Let's see the specific details for each of them!
 
-  - exit status of zero indicates success
+[grpc]: https://grpc.github.io/grpc/core/md_doc_health-checking.html
 
 ---
 
-## Benefits of using probes
+## `exec`
 
-- Rolling updates proceed when containers are *actually ready*
+- Runs an arbitrary program *inside* the container
 
-  (as opposed to merely started)
+  (like with `kubectl exec` or `docker exec`)
 
-- Containers in a broken state get killed and restarted
+- The program must be available in the container image
 
-  (instead of serving errors or timeouts)
+- Kubernetes uses the exit status of the program
 
-- Unavailable backends get removed from load balancer rotation
-
-  (thus improving response times across the board)
-
-- If a probe is not defined, it's as if there was an "always successful" probe
+  (standard UNIX convention: 0 = success, anything else = failure)
 
 ---
 
-## Example: HTTP probe
+## `exec` example
 
-Here is a pod template for the `rng` web service of the DockerCoins app:
+When the worker is ready, it should create `/tmp/ready`.
+<br/>
+The following probe will give it 5 minutes to do so.
 
 ```yaml
 apiVersion: v1
 kind: Pod
 metadata:
-  name: healthy-app
+  name: queueworker
 spec:
   containers:
-  - name: myapp
-    image: myregistry.io/myapp:v1.0
+  - name: worker
+    image: myregistry.../worker:v1.0
+    startupProbe:
+      exec:
+        command:
+        - test
+        - -f
+        - /tmp/ready
+      failureThreshold: 30
+```
+
+---
+
+## Using shell constructs
+
+- If we want to use pipes, conditionals, etc. we should invoke a shell
+
+- Example:
+  ```yaml
+    exec:
+      command:
+      - sh
+      - -c
+      - "curl http://localhost:5000/status | jq .ready | grep true"
+  ```
+
+---
+
+## `httpGet`
+
+- Make an HTTP GET request to the container
+
+- The request will be made by Kubelet
+
+  (doesn't require extra binaries in the container image)
+
+- `port` must be specified
+
+- `path` and extra `httpHeaders` can be specified optionally
+
+- Kubernetes uses HTTP status code of the response:
+
+  - 200-399 = success
+
+  - anything else = failure
+
+---
+
+## `httpGet` example
+
+The following liveness probe restarts the container if it stops responding on `/healthz`:
+
+```yaml
+apiVersion: v1
+kind: Pod
+metadata:
+  name: frontend
+spec:
+  containers:
+  - name: frontend
+    image: myregistry.../frontend:v1.0
     livenessProbe:
       httpGet:
-        path: /health
         port: 80
-      periodSeconds: 5
+        path: /healthz
 ```
 
-If the backend serves an error, or takes longer than 1s, 3 times in a row, it gets killed.
+---
+
+## `tcpSocket`
+
+- Kubernetes checks if the indicated TCP port accepts connections
+
+- There is no additional check
+
+.warning[It's quite possible for a process to be broken, but still accept TCP connections!]
 
 ---
 
-## Example: exec probe
+## `grpc`
 
-Here is a pod template for a Redis server:
+<!-- ##VERSION## -->
 
-```yaml
-apiVersion: v1
-kind: Pod
-metadata:
-  name: redis-with-liveness
-spec:
-  containers:
-  - name: redis
-    image: redis
-    livenessProbe:
-      exec:
-        command: ["redis-cli", "ping"]
-```
+- Available in beta since Kubernetes 1.24
 
-If the Redis process becomes unresponsive, it will be killed.
+- Leverages standard [GRPC Health Checking Protocol][grpc]
+
+[grpc]: https://grpc.github.io/grpc/core/md_doc_health-checking.html
 
 ---
 
-## Questions to ask before adding healthchecks
+## Best practices for healthchecks
 
-- Do we want liveness, readiness, both?
+- Readiness probes are almost always beneficial
 
-  (sometimes, we can use the same check, but with different failure thresholds)
+  - don't hesitate to add them early!
 
-- Do we have existing HTTP endpoints that we can use?
+  - we can even make them *mandatory*
 
-- Do we need to add new endpoints, or perhaps use something else?
+- Be more careful with liveness and startup probes
 
-- Are our healthchecks likely to use resources and/or slow down the app?
+  - they aren't always necessary
 
-- Do they depend on additional services?
-
-  (this can be particularly tricky, see next slide)
+  - they can even cause harm
 
 ---
 
-## Healthchecks and dependencies
+## Readiness probes
 
-- Liveness checks should not be influenced by the state of external services
+- Almost always beneficial
 
-- All checks should reply quickly (by default, less than 1 second)
+- Exceptions:
 
-- Otherwise, they are considered to fail
+  - web service that doesn't have a dedicated "health" or "ping" route
 
-- This might require to check the health of dependencies asynchronously
+  - ...and all requests are "expensive" (e.g. lots of external calls)
 
-  (e.g. if a database or API might be healthy but still take more than
-  1 second to reply, we should check the status asynchronously and report
-  a cached status)
+---
+
+## Liveness probes
+
+- If we're not careful, we end up restarting containers for no reason
+
+  (which can cause additional load on the cluster, cascading failures, data loss, etc.)
+
+- Suggestion:
+
+  - don't add liveness probes immediately
+
+  - wait until you have a bit of production experience with that code
+
+  - then add narrow-scoped healthchecks to detect specific failure modes
+
+- Readiness and liveness probes should be different
+
+  (different check *or* different timeouts *or* different thresholds)
+
+---
+
+## Startup probes
+
+- Only beneficial for containers that need a long time to start
+
+  (more than 30 seconds)
+
+- If there is no liveness probe, it's simpler to just use a readiness probe
+
+  (since we probably want to have a readiness probe anyway)
+
+- In other words, startup probes are useful in one situation:
+
+  *we have a liveness probe, AND the container needs a lot of time to start*
+
+- Don't forget to change the `failureThreshold`
+
+  (otherwise the container will fail to start and be killed)
+
+---
+
+## Recap of the gotchas
+
+- The default timeout is 1 second
+
+  - if a probe takes longer than 1 second to reply, Kubernetes considers that it fails
+
+  - this can be changed by setting the `timeoutSeconds` parameter
+    <br/>(or refactoring the probe)
+
+- Liveness probes should not be influenced by the state of external services
+
+- Liveness probes and readiness probes should have different paramters
+
+- For startup probes, remember to increase the `failureThreshold`
 
 ---
 
@@ -300,21 +453,21 @@ If the Redis process becomes unresponsive, it will be killed.
 
 (In that context, worker = process that doesn't accept connections)
 
-- Readiness is useful mostly for rolling updates
+- A relatively easy solution is to use files
 
-  (because workers aren't backends for a service)
+- For a startup or readiness probe:
 
-- Liveness may help us restart a broken worker, but how can we check it?
+  - worker creates `/tmp/ready` when it's ready
+  - probe checks the existence of `/tmp/ready`
 
-- Embedding an HTTP server is a (potentially expensive) option
+- For a liveness probe:
 
-- Using a "lease" file can be relatively easy:
+  - worker touches `/tmp/alive` regularly
+    <br/>(e.g. just before starting to work on a job)
+  - probe checks that the timestamp on `/tmp/alive` is recent
+  - if the timestamp is old, it means that the worker is stuck
 
-  - touch a file during each iteration of the main loop
-
-  - check the timestamp of that file from an exec probe
-
-- Writing logs (and checking them from the probe) also works
+- Sometimes it can also make sense to embed a web server in the worker
 
 ???
 

slides/k8s/ingress-canary.md

@@ -0,0 +1,148 @@
+## Ingress and canary releases
+
+- Let's see how to implement *canary releases*
+
+- The example here will use Traefik v1
+
+  (which is obsolete)
+
+- It won't work on your Kubernetes cluster!
+
+  (unless you're running an oooooold version of Kubernetes)
+
+  (and an equally oooooooold version of Traefik)
+
+- We've left it here just as an example!
+
+---
+
+## Canary releases
+
+- A *canary release* (or canary launch or canary deployment) is a release that will process only a small fraction of the workload
+
+- After deploying the canary, we compare its metrics to the normal release
+
+- If the metrics look good, the canary will progressively receive more traffic
+
+  (until it gets 100% and becomes the new normal release)
+
+- If the metrics aren't good, the canary is automatically removed
+
+- When we deploy a bad release, only a tiny fraction of traffic is affected
+
+---
+
+## Various ways to implement canary
+
+- Example 1: canary for a microservice
+
+  - 1% of all requests (sampled randomly) are sent to the canary
+  - the remaining 99% are sent to the normal release
+
+- Example 2: canary for a web app
+
+  - 1% of users are sent to the canary web site
+  - the remaining 99% are sent to the normal release
+
+- Example 3: canary for shipping physical goods
+
+  - 1% of orders are shipped with the canary process
+  - the remaining 99% are shipped with the normal process
+
+- We're going to implement example 1 (per-request routing)
+
+---
+
+## Canary releases with Traefik v1
+
+- We need to deploy the canary and expose it with a separate service
+
+- Then, in the Ingress resource, we need:
+
+  - multiple `paths` entries (one for each service, canary and normal)
+
+  - an extra annotation indicating the weight of each service
+
+- If we want, we can send requests to more than 2 services
+
+---
+
+## The Ingress resource
+
+.small[
+```yaml
+apiVersion: networking.k8s.io/v1beta1
+kind: Ingress
+metadata:
+  name: rgb
+  annotations:
+    traefik.ingress.kubernetes.io/service-weights: |
+      red: 50%
+      green: 25%
+      blue: 25%
+spec:
+  rules:
+  - host: rgb.`A.B.C.D`.nip.io
+    http:
+      paths:
+      - path: /
+        backend:
+          serviceName: red
+          servicePort: 80
+      - path: /
+        backend:
+          serviceName: green
+          servicePort: 80
+      - path: /
+        backend:
+          serviceName: blue
+          servicePort: 80
+```
+]
+
+---
+
+class: extra-details
+
+## Other ingress controllers
+
+*Just to illustrate how different things are ...*
+
+- With the NGINX ingress controller:
+
+  - define two ingress ressources
+    <br/>
+    (specifying rules with the same host+path)
+
+  - add `nginx.ingress.kubernetes.io/canary` annotations on each
+
+
+- With Linkerd2:
+
+  - define two services
+
+  - define an extra service for the weighted aggregate of the two
+
+  - define a TrafficSplit (this is a CRD introduced by the SMI spec)
+
+---
+
+class: extra-details
+
+## We need more than that
+
+What we saw is just one of the multiple building blocks that we need to achieve a canary release.
+
+We also need:
+
+- metrics (latency, performance ...) for our releases
+
+- automation to alter canary weights
+
+  (increase canary weight if metrics look good; decrease otherwise)
+
+- a mechanism to manage the lifecycle of the canary releases
+
+  (create them, promote them, delete them ...)
+
+For inspiration, check [flagger by Weave](https://github.com/weaveworks/flagger).

slides/k8s/ingress.md

@@ -1,34 +1,36 @@
 # Exposing HTTP services with Ingress resources
 
-- HTTP services are typically exposed on port 80
+- Service = layer 4 (TCP, UDP, SCTP)
 
-  (and 443 for HTTPS)
+  - works with every TCP/UDP/SCTP protocol
 
-- `NodePort` services are great, but they are *not* on port 80
+  - doesn't "see" or interpret HTTP
 
-  (by default, they use port range 30000-32767)
+- Ingress = layer 7 (HTTP)
 
-- How can we get *many* HTTP services on port 80? 🤔
+  - only for HTTP
+
+  - can route requests depending on URI or host header
+
+  - can handle TLS
 
 ---
 
-## Various ways to expose something on port 80
+## Why should we use Ingress resources?
 
-- Service with `type: LoadBalancer`
+A few use-cases:
 
-  *costs a little bit of money; not always available*
+- URI routing (e.g. for single page apps)
 
-- Service with one (or multiple) `ExternalIP`
+  `/api` → service `api:5000`
 
-  *requires public nodes; limited by number of nodes*
+  everything else → service `static:80`
 
-- Service with `hostPort` or `hostNetwork`
+- Cost optimization
 
-  *same limitations as `ExternalIP`; even harder to manage*
+  (because individual `LoadBalancer` services typically cost money)
 
-- Ingress resources
-
-  *addresses all these limitations, yay!*
+- Automatic handling of TLS certificates
 
 ---
 
@@ -181,20 +183,70 @@ class: extra-details
 
 ---
 
-## Deploying pods listening on port 80
+## Accepting connections on port 80 (and 443)
 
-- We want our ingress load balancer to be available on port 80
+- Web site users don't want to specify port numbers
 
-- The best way to do that would be with a `LoadBalancer` service
+  (e.g. "connect to https://blahblah.whatever:31550")
 
-  ... but it requires support from the underlying infrastructure
+- Our ingress controller needs to actually be exposed on port 80
 
-- Instead, we are going to use the `hostNetwork` mode on the Traefik pods
+  (and 443 if we want to handle HTTPS)
 
-- Let's see what this `hostNetwork` mode is about ...
+- Let's see how we can achieve that!
 
 ---
 
+## Various ways to expose something on port 80
+
+- Service with `type: LoadBalancer`
+
+  *costs a little bit of money; not always available*
+
+- Service with one (or multiple) `ExternalIP`
+
+  *requires public nodes; limited by number of nodes*
+
+- Service with `hostPort` or `hostNetwork`
+
+  *same limitations as `ExternalIP`; even harder to manage*
+
+---
+
+## Deploying pods listening on port 80
+
+- We are going to run Traefik in Pods with `hostNetwork: true`
+
+  (so that our load balancer can use the "real" port 80 of our nodes)
+
+- Traefik Pods will be created by a DaemonSet
+
+  (so that we get one instance of Traefik on every node of the cluster)
+
+- This means that we will be able to connect to any node of the cluster on port 80
+
+.warning[This is not typical of a production setup!]
+
+---
+
+## Doing it in production
+
+- When running "on cloud", the easiest option is a `LoadBalancer` service
+
+- When running "on prem", it depends:
+
+  - [MetalLB] is a good option if a pool of public IP addresses is available
+
+  - otherwise, using `externalIPs` on a few nodes (2-3 for redundancy)
+
+- Many variations/optimizations are possible depending on our exact scenario!
+
+[MetalLB]: https://metallb.org/
+
+---
+
+class: extra-details
+
 ## Without `hostNetwork`
 
 - Normally, each pod gets its own *network namespace*
@@ -211,6 +263,8 @@ class: extra-details
 
 ---
 
+class: extra-details
+
 ## With `hostNetwork: true`
 
 - No network namespace gets created
@@ -229,26 +283,6 @@ class: extra-details
 
 ---
 
-class: extra-details
-
-## Other techniques to expose port 80
-
-- We could use pods specifying `hostPort: 80` 
-
-  ... but with most CNI plugins, this [doesn't work or requires additional setup](https://github.com/kubernetes/kubernetes/issues/23920)
-
-- We could use a `NodePort` service
-
-  ... but that requires [changing the `--service-node-port-range` flag in the API server](https://kubernetes.io/docs/reference/command-line-tools-reference/kube-apiserver/)
-
-- We could create a service with an external IP
-
-  ... this would work, but would require a few extra steps
-
-  (figuring out the IP address and adding it to the service)
-
----
-
 ## Running Traefik
 
 - The [Traefik documentation][traefikdoc] recommends to use a Helm chart
@@ -270,6 +304,8 @@ class: extra-details
 
 ---
 
+class: extra-details
+
 ## Taints and tolerations
 
 - A *taint* is an attribute added to a node
@@ -496,10 +532,6 @@ This is normal: we haven't provided any ingress rule yet.
 
 ## Creating ingress resources
 
-- Before Kubernetes 1.19, we must use YAML manifests
-
-  (see example on next slide)
-
 - Since Kubernetes 1.19, we can use `kubectl create ingress`
 
   ```bash
@@ -534,7 +566,21 @@ This is normal: we haven't provided any ingress rule yet.
 
 ---
 
-## Ingress resources in YAML
+## Before Kubernetes 1.19
+
+- Before Kubernetes 1.19:
+
+  - `kubectl create ingress` wasn't available
+
+  - `apiVersion: networking.k8s.io/v1` wasn't supported
+
+- It was necessary to use YAML, and `apiVersion: networking.k8s.io/v1beta1`
+
+  (see example on next slide)
+
+---
+
+## YAML for old ingress resources
 
 Here is a minimal host-based ingress resource:
 
@@ -555,23 +601,15 @@ spec:
 
 ```
 
-(It is in `k8s/ingress.yaml`.)
-
 ---
 
-class: extra-details
-
-## Ingress API version
-
-- The YAML on the previous slide uses `apiVersion: networking.k8s.io/v1beta1`
+## YAML for new ingress resources
 
 - Starting with Kubernetes 1.19, `networking.k8s.io/v1` is available
 
-- However, with Kubernetes 1.19 (and later), we can use `kubectl create ingress`
+- And we can use `kubectl create ingress` 🎉
 
-- We chose to keep an "old" (deprecated!) YAML example for folks still using older versions of Kubernetes
-
-- If we want to see "modern" YAML, we can use `-o yaml --dry-run=client`:
+- We can see "modern" YAML with `-o yaml --dry-run=client`:
 
   ```bash
   kubectl create ingress red -o yaml --dry-run=client \
@@ -641,157 +679,6 @@ class: extra-details
 
 - It is still in alpha stage
 
----
-
-## Vendor-specific example
-
-- Let's see how to implement *canary releases*
-
-- The example here will use Traefik v1
-
-  (which is obsolete)
-
-- It won't work on your Kubernetes cluster!
-
-  (unless you're running an oooooold version of Kubernetes)
-
-  (and an equally oooooooold version of Traefik)
-
-- We've left it here just as an example!
-
----
-
-## Canary releases
-
-- A *canary release* (or canary launch or canary deployment) is a release that will process only a small fraction of the workload
-
-- After deploying the canary, we compare its metrics to the normal release
-
-- If the metrics look good, the canary will progressively receive more traffic
-
-  (until it gets 100% and becomes the new normal release)
-
-- If the metrics aren't good, the canary is automatically removed
-
-- When we deploy a bad release, only a tiny fraction of traffic is affected
-
----
-
-## Various ways to implement canary
-
-- Example 1: canary for a microservice
-
-  - 1% of all requests (sampled randomly) are sent to the canary
-  - the remaining 99% are sent to the normal release
-
-- Example 2: canary for a web app
-
-  - 1% of users are sent to the canary web site
-  - the remaining 99% are sent to the normal release
-
-- Example 3: canary for shipping physical goods
-
-  - 1% of orders are shipped with the canary process
-  - the remaining 99% are shipped with the normal process
-
-- We're going to implement example 1 (per-request routing)
-
----
-
-## Canary releases with Traefik v1
-
-- We need to deploy the canary and expose it with a separate service
-
-- Then, in the Ingress resource, we need:
-
-  - multiple `paths` entries (one for each service, canary and normal)
-
-  - an extra annotation indicating the weight of each service
-
-- If we want, we can send requests to more than 2 services
-
----
-
-## The Ingress resource
-
-.small[
-```yaml
-apiVersion: networking.k8s.io/v1beta1
-kind: Ingress
-metadata:
-  name: rgb
-  annotations:
-    traefik.ingress.kubernetes.io/service-weights: |
-      red: 50%
-      green: 25%
-      blue: 25%
-spec:
-  rules:
-  - host: rgb.`A.B.C.D`.nip.io
-    http:
-      paths:
-      - path: /
-        backend:
-          serviceName: red
-          servicePort: 80
-      - path: /
-        backend:
-          serviceName: green
-          servicePort: 80
-      - path: /
-        backend:
-          serviceName: blue
-          servicePort: 80
-```
-]
-
----
-
-class: extra-details
-
-## Other ingress controllers
-
-*Just to illustrate how different things are ...*
-
-- With the NGINX ingress controller:
-
-  - define two ingress ressources
-    <br/>
-    (specifying rules with the same host+path)
-
-  - add `nginx.ingress.kubernetes.io/canary` annotations on each
-
-
-- With Linkerd2:
-
-  - define two services
-
-  - define an extra service for the weighted aggregate of the two
-
-  - define a TrafficSplit (this is a CRD introduced by the SMI spec)
-
----
-
-class: extra-details
-
-## We need more than that
-
-What we saw is just one of the multiple building blocks that we need to achieve a canary release.
-
-We also need:
-
-- metrics (latency, performance ...) for our releases
-
-- automation to alter canary weights
-
-  (increase canary weight if metrics look good; decrease otherwise)
-
-- a mechanism to manage the lifecycle of the canary releases
-
-  (create them, promote them, delete them ...)
-
-For inspiration, check [flagger by Weave](https://github.com/weaveworks/flagger).
-
 ???
 
 :EN:- The Ingress resource

slides/k8s/prereqs-admin.md

@@ -40,7 +40,9 @@
 
 - Each person gets their own private set of VMs
 
-- Each person should have a printed card with connection information
+- The connection information is on a shared spreadsheet
+
+  (URL to be shared through portal and chat)
 
 - We will connect to these VMs with SSH
 

slides/k8s/resource-limits.md

@@ -14,32 +14,20 @@
 
 - CPU is a *compressible resource*
 
-  (it can be preempted immediately without adverse effect)
+  - it can be preempted immediately without adverse effect
+
+  - if we have N CPU and need 2N, we run at 50% speed
 
 - Memory is an *incompressible resource*
 
-  (it needs to be swapped out to be reclaimed; and this is costly)
+  - it needs to be swapped out to be reclaimed; and this is costly
+
+  - if we have N GB RAM and need 2N, we might run at... 0.1% speed!
 
 - As a result, exceeding limits will have different consequences for CPU and memory
 
 ---
 
-## Exceeding CPU limits
-
-- CPU can be reclaimed instantaneously
-
-  (in fact, it is preempted hundreds of times per second, at each context switch)
-
-- If a container uses too much CPU, it can be throttled
-
-  (it will be scheduled less often)
-
-- The processes in that container will run slower
-
-  (or rather: they will not run faster)
-
----
-
 class: extra-details
 
 ## CPU limits implementation details
@@ -146,39 +134,59 @@ For more details, check [this blog post](https://erickhun.com/posts/kubernetes-f
 
 ---
 
-## Exceeding memory limits
+## Running low on memory
 
-- Memory needs to be swapped out before being reclaimed
+- When the system runs low on memory, it starts to reclaim used memory
 
-- "Swapping" means writing memory pages to disk, which is very slow
+  (we talk about "memory pressure")
 
-- On a classic system, a process that swaps can get 1000x slower
+- Option 1: free up some buffers and caches
 
-  (because disk I/O is 1000x slower than memory I/O)
+  (fastest option; might affect performance if cache memory runs very low)
 
-- Exceeding the memory limit (even by a small amount) can reduce performance *a lot*
+- Option 2: swap, i.e. write to disk some memory of one process to give it to another
 
-- Kubernetes *does not support swap* (more on that later!)
+  (can have a huge negative impact on performance because disks are slow)
 
-- Exceeding the memory limit will cause the container to be killed
+- Option 3: terminate a process and reclaim all its memory
+
+  (OOM or Out Of Memory Killer on Linux)
 
 ---
 
-## Limits vs requests
+## Memory limits on Kubernetes
 
-- Limits are "hard limits" (they can't be exceeded)
+- Kubernetes *does not support swap*
+
+  (but it may support it in the future, thanks to [KEP 2400])
+
+- If a container exceeds its memory *limit*, it gets killed immediately
+
+- If a node is overcommitted and under memory pressure, it will terminate some pods
+
+  (see next slide for some details about what "overcommit" means here!)
+
+[KEP 2400]: https://github.com/kubernetes/enhancements/blob/master/keps/sig-node/2400-node-swap/README.md#implementation-history
+
+---
+
+## Overcommitting resources
+
+- *Limits* are "hard limits" (a container *cannot* exceed its limits)
 
   - a container exceeding its memory limit is killed
 
   - a container exceeding its CPU limit is throttled
 
-- Requests are used for scheduling purposes
+- On a given node, the sum of pod *limits* can be higher than the node size
 
-  - a container using *less* than what it requested will never be killed or throttled
+- *Requests* are used for scheduling purposes
 
-  - the scheduler uses the requested sizes to determine placement
+  - a container can use more than its requested CPU or RAM amounts
 
-  - the resources requested by all pods on a node will never exceed the node size
+  - a container using *less* than what it requested should never be killed or throttled
+
+- On a given node, the sum of pod *requests* cannot be higher than the node size
 
 ---
 
@@ -222,9 +230,31 @@ Each pod is assigned a QoS class (visible in `status.qosClass`).
 
 ---
 
-## Where is my swap?
+class: extra-details
 
-- The semantics of memory and swap limits on Linux cgroups are complex
+## CPU and RAM reservation
+
+- Kubernetes passes resources requests and limits to the container engine
+
+- The container engine applies these requests and limits with specific mechanisms
+
+- Example: on Linux, this is typically done with control groups aka cgroups
+
+- Most systems use cgroups v1, but cgroups v2 are slowly being rolled out
+
+  (e.g. available in Ubuntu 22.04 LTS)
+
+- Cgroups v2 have new, interesting features for memory control:
+
+  - ability to set "minimum" memory amounts (to effectively reserve memory)
+
+  - better control on the amount of swap used by a container
+
+---
+
+class: extra-details
+
+## What's the deal with swap?
 
 - With cgroups v1, it's not possible to disable swap for a cgroup
 
@@ -238,6 +268,8 @@ Each pod is assigned a QoS class (visible in `status.qosClass`).
 
 - The simplest solution was to disable swap entirely
 
+- Kubelet will refuse to start if it detects that swap is enabled!
+
 ---
 
 ## Alternative point of view
@@ -268,7 +300,7 @@ Each pod is assigned a QoS class (visible in `status.qosClass`).
 
 - You will need to add the flag `--fail-swap-on=false` to kubelet
 
-  (otherwise, it won't start!)
+  (remember: it won't otherwise start if it detects that swap is enabled)
 
 ---
 
@@ -666,6 +698,18 @@ class: extra-details
 
 ---
 
+## Underutilization
+
+- Remember: when assigning a pod to a node, the scheduler looks at *requests*
+
+  (not at current utilization on the node)
+
+- If pods request resources but don't use them, this can lead to underutilization
+
+  (because the scheduler will consider that the node is full and can't fit new pods)
+
+---
+
 ## Viewing a namespace limits and quotas
 
 - `kubectl describe namespace` will display resource limits and quotas

slides/k8s/setup-devel.md

@@ -20,13 +20,17 @@
 
 ## Docker Desktop
 
-- Available on Mac and Windows
+- Available on Linux, Mac, and Windows
+
+- Free for personal use and small businesses
+
+  (less than 250 employees and less than $10 millions in annual revenue)
 
 - Gives you one cluster with one node
 
-- Very easy to use if you are already using Docker Desktop:
+- Streamlined installation and user experience
 
-  go to Docker Desktop preferences and enable Kubernetes
+- Great integration with various network stacks and e.g. corporate VPNs
 
 - Ideal for Docker users who need good integration between both platforms
 
@@ -40,13 +44,11 @@
 
 - Runs Kubernetes nodes in Docker containers
 
-- Can deploy multiple clusters, with multiple nodes, and multiple master nodes
+- Can deploy multiple clusters, with multiple nodes
 
-- As of June 2020, two versions co-exist: stable (1.7) and beta (3.0)
+- Runs the control plane on Kubernetes nodes
 
-- They have different syntax and options, this can be confusing
-
-  (but don't let that stop you!)
+- Control plane can also run on multiple nodes
 
 ---
 
@@ -84,7 +86,7 @@
 
 - More advanced scenarios require writing a short [config file](https://kind.sigs.k8s.io/docs/user/quick-start#configuring-your-kind-cluster)
 
-  (to define multiple nodes, multiple master nodes, set Kubernetes versions ...)
+  (to define multiple nodes, multiple control plane nodes, set Kubernetes versions ...)
  
 - Can deploy multiple clusters
 
@@ -124,7 +126,9 @@
 
 ## [Rancher Desktop](https://rancherdesktop.io/)
 
-- Available on Mac and Windows
+- Available on Linux, Mac, and Windows
+
+- Free and open-source
 
 - Runs a single cluster with a single node
 
@@ -134,7 +138,7 @@
 
 - Emphasis on ease of use (like Docker Desktop)
 
-- Very young product (first release in May 2021)
+- Relatively young product (first release in May 2021)
 
 - Based on k3s and other proven components
 

slides/kube-adv.yml

@@ -0,0 +1,109 @@
+title: |
+  Advanced
+  Kubernetes
+
+chat: "[Slack](https://newrelic.slack.com/archives/C0438EFM97F)"
+
+gitrepo: github.com/jpetazzo/container.training
+
+slides: https://2022-09-nr2.container.training/
+
+#slidenumberprefix: "#SomeHashTag — "
+
+exclude:
+- self-paced
+
+content:
+- shared/title.md
+- logistics.md
+- k8s/intro.md
+- shared/about-slides.md
+#- shared/chat-room-im.md
+#- shared/chat-room-slack.md
+#- shared/chat-room-zoom-meeting.md
+#- shared/chat-room-zoom-webinar.md
+- shared/toc.md
+- #1
+  - k8s/prereqs-admin.md
+  - k8s/architecture.md
+  - k8s/deploymentslideshow.md
+  - k8s/dmuc.md
+  - interlude-form.md
+  - k8s/multinode.md
+  - k8s/cni.md
+  - k8s/interco.md
+  - k8s/cni-internals.md
+  - k8s/apilb.md
+- #2
+  - k8s/demo-apps.md
+  - k8s/netpol.md
+  - k8s/authn-authz.md
+  - k8s/user-cert.md
+  - k8s/csr-api.md
+  - k8s/openid-connect.md
+  - k8s/pod-security-intro.md
+  - k8s/pod-security-policies.md
+  - k8s/pod-security-admission.md
+  - exercises/netpol-details.md
+  - exercises/rbac-details.md
+- #3
+  - k8s/helm-intro.md
+  - k8s/ingress.md
+  - k8s/cert-manager.md
+  - k8s/ingress-tls.md
+  - k8s/ingress-advanced.md
+  - k8s/kustomize.md
+  - k8s/helm-chart-format.md
+  - k8s/helm-create-basic-chart.md
+  - k8s/helm-create-better-chart.md
+  - k8s/helm-dependencies.md
+  - k8s/helm-values-schema-validation.md
+  - k8s/helm-secrets.md
+  - exercises/helm-generic-chart-details.md
+  - exercises/helm-umbrella-chart-details.md
+- #4
+  - k8s/extending-api.md
+  - k8s/admission.md
+  - k8s/cainjector.md
+  - k8s/kyverno.md
+  - k8s/crd.md
+  - k8s/operators.md
+  - k8s/sealed-secrets.md
+  - k8s/operators-design.md
+  - k8s/operators-example.md
+  - k8s/owners-and-dependents.md
+  - k8s/events.md
+  - k8s/finalizers.md
+  - exercises/sealed-secrets-details.md
+- #5
+  - k8s/resource-limits.md
+  - k8s/cluster-sizing.md
+  - k8s/cluster-autoscaler.md
+  - k8s/horizontal-pod-autoscaler.md
+  - k8s/aggregation-layer.md
+  - k8s/metrics-server.md
+  - k8s/hpa-v2.md
+  - k8s/batch-jobs.md
+  - k8s/statefulsets.md
+  - k8s/consul.md
+  - k8s/pv-pvc-sc.md
+  - k8s/volume-claim-templates.md
+  - k8s/stateful-failover.md
+  - shared/thankyou.md
+-
+  - |
+    # (Extra content I)
+  - k8s/setup-devel.md
+  - k8s/accessinternal.md
+  - k8s/kubectlproxy.md  
+  - k8s/k9s.md
+  - k8s/tilt.md
+  - k8s/ytt.md
+-
+  - |
+    # (Extra content II)
+  - k8s/internal-apis.md
+  - k8s/staticpods.md
+  - k8s/cluster-upgrade.md
+  - k8s/control-plane-auth.md
+  - k8s/kubebuilder.md

slides/kube.yml

@@ -1,93 +0,0 @@
-title: |
-  Intermediate Kubernetes
-
-chat: "[FIXME](#FIXME)"
-
-gitrepo: github.com/jpetazzo/container.training
-
-slides: https://2022-08-nasa.container.training/
-
-#slidenumberprefix: "#SomeHashTag — "
-
-exclude:
-- self-paced
-
-content:
-- shared/title.md
-- logistics.md
-- k8s/intro.md
-- shared/about-slides.md
-- shared/chat-room-im.md
-#- shared/chat-room-zoom-meeting.md
-#- shared/chat-room-zoom-webinar.md
-- shared/prereqs.md
-#- shared/webssh.md
-- shared/connecting.md
-- shared/toc.md
-- # 1
-  #- k8s/versions-k8s.md
-  - shared/sampleapp.md
-  #- shared/composescale.md
-  #- shared/hastyconclusions.md
-  - shared/composedown.md
-  - k8s/concepts-k8s.md
-  - k8s/kubectlget.md
-  - k8s/kubectl-run.md
-  - k8s/kubenet.md
-  - k8s/kubectlexpose.md
-  - k8s/shippingimages.md
-  #- k8s/buildshiprun-selfhosted.md
-  - k8s/buildshiprun-dockerhub.md
-  - exercises/k8sfundamentals-details.md
-  - k8s/ourapponkube.md
-  #- k8s/exercise-wordsmith.md
-- # 2
-  - k8s/labels-annotations.md
-  - k8s/kubectl-logs.md
-  - k8s/logs-cli.md
-  - k8s/namespaces.md
-  - k8s/yamldeploy.md
-  - shared/declarative.md
-  - k8s/declarative.md
-  - k8s/deploymentslideshow.md
-  - k8s/authoring-yaml.md
-  - k8s/setup-overview.md
-  - k8s/setup-devel.md
-  #- k8s/setup-managed.md
-  #- k8s/setup-selfhosted.md
-  - k8s/localkubeconfig.md
-  - k8s/accessinternal.md
-  - k8s/kubectlproxy.md
-  - exercises/localcluster-details.md
-- # 3
-  #- k8s/kubectlscale.md
-  - k8s/scalingdockercoins.md
-  - shared/hastyconclusions.md
-  - k8s/daemonset.md
-  - k8s/rollout.md
-  - k8s/healthchecks.md
-  - k8s/ingress.md
-  #- k8s/healthchecks-more.md
-  - exercises/healthchecks-details.md
-- # 4
-  - k8s/netpol.md
-  - k8s/authn-authz.md
-  - k8s/resource-limits.md
-  - k8s/metrics-server.md
-  - k8s/cluster-sizing.md
-  - k8s/horizontal-pod-autoscaler.md
-  - exercises/netpol-details.md
-  - exercises/rbac-details.md
-- # 5
-  #- k8s/ingress-tls.md
-  - k8s/volumes.md
-  #- k8s/exercise-configmap.md
-  #- k8s/build-with-docker.md
-  #- k8s/build-with-kaniko.md
-  - k8s/configuration.md
-  - k8s/secrets.md
-  - k8s/batch-jobs.md
-  - k8s/dashboard.md
-  - k8s/k9s.md
-  - k8s/tilt.md
-  - shared/thankyou.md

slides/logistics-template.md

@@ -1,19 +1,21 @@
-## Introductions
+## Intros
 
 - Hello! We are:
 
-   - Jérôme Petazzoni ([@jpetazzo])
+  - Jérôme Petazzoni ([@jpetazzo])
 
-   - Dana Engebretson ([@bigdana])
-   
-   - Amy Bowen ([@s0ulshake])
+  - Dana Engebretson ([@bigdana])
 
-- The training will run for 4 hours, with a 10 minutes break every hour
+- The training will from 8am to noon, Monday to Friday
+
+- There will be breaks every hour
 
 - Feel free to interrupt for questions at any time
 
 - *Especially when you see full screen container pictures!*
 
+  (I will watch them in awkward silence while I wait for your questions)
+
 - Live feedback, questions, help: @@CHAT@@
 
 <!-- -->
@@ -27,16 +29,12 @@
 
 ---
 
-## Exercises
+## Dynamic content
 
-- At the end of each day, there is a series of exercises
+- The content of this course will be adapted to suit your needs!
 
-- To make the most out of the training, please try the exercises!
+- We'll share a link to a form so you can tell us what we should work on
 
-  (it will help to practice and memorize the content of the day)
+- Expect the content of the deck to change between Monday and Tuesday
 
-- We recommend to take at least one hour to work on the exercises
-
-  (if you understood the content of the day, it will be much faster)
-
-- Each day will start with a quick review of the exercises of the previous day
+  (we will reorder/reorganize the content accordingly)

slides/shared/prereqs.md

@@ -1,4 +1,4 @@
-## Pre-requirements
+# Pre-requirements
 
 - Be comfortable with the UNIX command line