🗼 Highfive Mai 2024

.gitignore

@@ -9,7 +9,6 @@ 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

prepare-labs/dns-netlify.sh

@@ -1,9 +1,7 @@
 #!/bin/sh
 
-set -eu
-
 # https://open-api.netlify.com/#tag/dnsZone
-[ "${1-}" ] || {
+[ "$1" ] || {
   echo ""
   echo "Add a record in Netlify DNS."
   echo "This script is hardcoded to add a record to container.training".
@@ -20,7 +18,7 @@ set -eu
 }
 
 NETLIFY_CONFIG_FILE=~/.config/netlify/config.json
-if ! [ "${DOMAIN-}" ]; then
+if ! [ "$DOMAIN" ]; then
   DOMAIN=container.training
 fi
 

prepare-labs/konk.sh

@@ -1,15 +1,5 @@
 #!/bin/sh
-#
-# Baseline resource usage per vcluster in our usecase:
-# 500 MB RAM
-# 10% CPU
-# (See https://docs.google.com/document/d/1n0lwp6rQKQUIuo_A5LQ1dgCzrmjkDjmDtNj1Jn92UrI)
-# PRO2-XS = 4 core, 16 gb
-
-set -e
-
 PROVIDER=scaleway
-STUDENTS=30
 
 case "$PROVIDER" in
 linode)
@@ -22,26 +12,20 @@ scaleway)
   ;;
 esac
 
+./labctl create --mode mk8s --settings settings/konk.env --provider $PROVIDER --tag konk
+
 # set kubeconfig file
 export KUBECONFIG=~/kubeconfig
-
-if [ "$PROVIDER" = "kind" ]; then
-  kind create cluster --name konk
-  ADDRTYPE=InternalIP
-else
-  ./labctl create --mode mk8s --settings settings/konk.env --provider $PROVIDER --tag konk
-  cp tags/konk/stage2/kubeconfig.101 $KUBECONFIG
-  ADDRTYPE=ExternalIP
-fi
+cp tags/konk/stage2/kubeconfig.101 $KUBECONFIG
 
 # set external_ip labels
-kubectl get nodes -o=jsonpath='{range .items[*]}{.metadata.name} {.status.addresses[?(@.type=="'$ADDRTYPE'")].address}{"\n"}{end}' |
+kubectl get nodes -o=jsonpath='{range .items[*]}{.metadata.name} {.status.addresses[?(@.type=="ExternalIP")].address}{"\n"}{end}' |
 while read node address; do
   kubectl label node $node external_ip=$address
 done
 
 # vcluster all the things
-./labctl create --settings settings/mk8s.env --provider vcluster --mode mk8s --students $STUDENTS
+./labctl create --settings settings/mk8s.env --provider vcluster --mode mk8s --students 30
 
 # install prometheus stack because that's cool
 helm upgrade --install --repo https://prometheus-community.github.io/helm-charts \

prepare-labs/lib/cli.sh

@@ -57,7 +57,7 @@ need_tag() {
     if [ ! -d "tags/$TAG" ]; then
         die "Tag $TAG not found (directory tags/$TAG does not exist)."
     fi
-    for FILE in mode provider settings.env status; do
+    for FILE in settings.env ips.txt; do
         if [ ! -f "tags/$TAG/$FILE" ]; then
           warning "File tags/$TAG/$FILE not found."
         fi

prepare-labs/lib/commands.sh

@@ -19,22 +19,20 @@ _cmd_cards() {
     TAG=$1
     need_tag
 
-    OPTIONS_FILE=$2
-    [ -f "$OPTIONS_FILE" ] || die "Please specify a YAML options file as 2nd argument."
-    OPTIONS_FILE_PATH="$(readlink -f "$OPTIONS_FILE")"
+    die FIXME
 
-    # This will process logins.jsonl to generate two files: cards.pdf and cards.html
+    # This will process ips.txt to generate two files: ips.pdf and ips.html
     (
         cd tags/$TAG
-        ../../../lib/make-login-cards.py "$OPTIONS_FILE_PATH"
+        ../../../lib/ips-txt-to-html.py settings.yaml
     )
 
-    ln -sf ../tags/$TAG/cards.html www/$TAG.html
-    ln -sf ../tags/$TAG/cards.pdf www/$TAG.pdf
+    ln -sf ../tags/$TAG/ips.html www/$TAG.html
+    ln -sf ../tags/$TAG/ips.pdf www/$TAG.pdf
 
     info "Cards created. You can view them with:"
-    info "xdg-open tags/$TAG/cards.html tags/$TAG/cards.pdf (on Linux)"
-    info "open tags/$TAG/cards.html (on macOS)"
+    info "xdg-open tags/$TAG/ips.html tags/$TAG/ips.pdf (on Linux)"
+    info "open tags/$TAG/ips.html (on macOS)"
     info "Or you can start a web server with:"
     info "$0 www"
 }
@@ -49,41 +47,6 @@ _cmd_clean() {
 	done	
 }
 
-_cmd codeserver "Install code-server on the clusters"
-_cmd_codeserver() {
-    TAG=$1
-    need_tag
-
-    ARCH=${ARCHITECTURE-amd64}
-    CODESERVER_VERSION=4.96.2
-    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 0:1789
-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=$1
@@ -294,12 +257,21 @@ _cmd_create() {
         terraform init
         echo tag = \"$TAG\" >> terraform.tfvars
         echo how_many_clusters = $STUDENTS >> terraform.tfvars
-        if [ "$CLUSTERSIZE" ]; then
-            echo nodes_per_cluster = $CLUSTERSIZE >> terraform.tfvars
+        echo nodes_per_cluster = $CLUSTERSIZE >> terraform.tfvars
+        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.
@@ -352,8 +324,8 @@ _cmd_clusterize() {
     grep KUBECOLOR_ /etc/ssh/sshd_config || echo 'AcceptEnv KUBECOLOR_*' | sudo tee -a /etc/ssh/sshd_config
     sudo systemctl restart ssh.service"
 
-    pssh -I < tags/$TAG/clusters.tsv "
-    grep -w \$PSSH_HOST | tr '\t' '\n' > /tmp/cluster"
+    pssh -I < tags/$TAG/clusters.txt "
+    grep -w \$PSSH_HOST | tr ' ' '\n' > /tmp/cluster"
     pssh "
     echo \$PSSH_HOST > /tmp/ipv4
     head -n 1 /tmp/cluster | sudo tee /etc/ipv4_of_first_node
@@ -374,10 +346,6 @@ _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/$TAG/logins.jsonl
-
     echo cluster_ok > tags/$TAG/status
 }
 
@@ -549,7 +517,6 @@ _cmd_kubeadm() {
         CLUSTER_CONFIGURATION_KUBERNETESVERSION='kubernetesVersion: "v'$KUBEVERSION'"'
         IGNORE_SYSTEMVERIFICATION="- SystemVerification"
         IGNORE_SWAP="- Swap"
-        IGNORE_IPTABLES="- FileContent--proc-sys-net-bridge-bridge-nf-call-iptables"
     fi
 
     # Install a valid configuration for containerd
@@ -573,7 +540,6 @@ nodeRegistration:
   - NumCPU
   $IGNORE_SYSTEMVERIFICATION
   $IGNORE_SWAP
-  $IGNORE_IPTABLES
 ---
 kind: JoinConfiguration
 apiVersion: kubeadm.k8s.io/v1beta3
@@ -587,7 +553,6 @@ nodeRegistration:
   - NumCPU
   $IGNORE_SYSTEMVERIFICATION
   $IGNORE_SWAP
-  $IGNORE_IPTABLES
 ---
 kind: KubeletConfiguration
 apiVersion: kubelet.config.k8s.io/v1beta1
@@ -616,9 +581,7 @@ EOF
     # Install weave as the pod network
     pssh "
     if i_am_first_node; then
-        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-
+        kubectl apply -f https://github.com/weaveworks/weave/releases/download/v2.8.1/weave-daemonset-k8s-1.11.yaml
     fi"
 
     # FIXME this is a gross hack to add the deployment key to our SSH agent,
@@ -781,16 +744,6 @@ EOF
         aws-iam-authenticator version
     fi"
 
-    # Install jless (jless.io)
-    pssh "
-    if [ ! -x /usr/local/bin/jless ]; then
-        ##VERSION##
-        sudo apt-get install -y libxcb-render0 libxcb-shape0 libxcb-xfixes0
-        wget https://github.com/PaulJuliusMartinez/jless/releases/download/v0.9.0/jless-v0.9.0-x86_64-unknown-linux-gnu.zip
-        unzip jless-v0.9.0-x86_64-unknown-linux-gnu
-        sudo mv jless /usr/local/bin
-    fi"
-
     # Install the krew package manager
     pssh "
     if [ ! -d /home/$USER_LOGIN/.krew ]; then
@@ -803,7 +756,7 @@ EOF
     fi"
 
     # Install kubecolor
-    KUBECOLOR_VERSION=0.4.0
+    KUBECOLOR_VERSION=0.3.2
     URL=https://github.com/kubecolor/kubecolor/releases/download/v${KUBECOLOR_VERSION}/kubecolor_${KUBECOLOR_VERSION}_linux_${ARCH}.tar.gz
     pssh "
     if [ ! -x /usr/local/bin/kubecolor ]; then
@@ -968,15 +921,6 @@ _cmd_inventory() {
     FIXME
 }
 
-_cmd logins "Show login information for a group of instances"
-_cmd_logins() {
-    TAG=$1
-    need_tag $TAG
-
-    cat tags/$TAG/logins.jsonl \
-    | 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"
 _cmd_maketag() {
     if [ -z $USER ]; then
@@ -1027,9 +971,6 @@ _cmd_stage2() {
     cd tags/$TAG/stage2
     terraform init -upgrade
     terraform apply -auto-approve
-    terraform output -raw logins_jsonl > ../logins.jsonl
-    terraform output -raw ips_txt > ../ips.txt
-    echo "stage2_ok" > status
 }
 
 _cmd standardize "Deal with non-standard Ubuntu cloud images"
@@ -1114,7 +1055,6 @@ _cmd_tailhist () {
     # halfway through and we're actually trying to download it again.
     pssh "
     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
     sudo mv websocketd /usr/local/bin/websocketd
@@ -1139,35 +1079,14 @@ 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 argon2 emacs-nox git httping htop jid joe jq mosh tree unzip
+    sudo apt-get -qy install apache2-utils emacs-nox git httping htop jid joe jq mosh python-setuptools tree unzip
     # This is for VMs with broken PRNG (symptom: running docker-compose randomly hangs)
     sudo apt-get -qy install haveged
     "
@@ -1230,8 +1149,8 @@ _cmd_tags() {
         cd tags
         echo "[#] [Status] [Tag] [Mode] [Provider]"
         for tag in *; do
-            if [ -f $tag/logins.jsonl ]; then
-                count="$(wc -l < $tag/logins.jsonl)"
+            if [ -f $tag/ips.txt ]; then
+                count="$(wc -l < $tag/ips.txt)"
             else
                 count="?"
             fi
@@ -1307,13 +1226,7 @@ _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 '
-                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
-                '
+            echo $USER_LOGIN:$password | ssh $SSHOPTS -i tags/$TAG/id_rsa ubuntu@$node sudo chpasswd
         done
     done
     info "Done."
@@ -1345,11 +1258,6 @@ _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"
 }
 
@@ -1405,7 +1313,7 @@ EOF"
 _cmd www "Run a web server to access card HTML and PDF"
 _cmd_www() {
     cd www
-    IPADDR=$(curl -fsSL canihazip.com/s || echo localhost)
+    IPADDR=$(curl -sL canihazip.com/s)
     info "The following files are available:"
     for F in *; do
         echo "http://$IPADDR:8000/$F"

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

@@ -1,22 +1,32 @@
 #!/usr/bin/env python3
-import json
 import os
 import sys
 import yaml
 import jinja2
 
+
 # Read settings from user-provided settings file
 context = yaml.safe_load(open(sys.argv[1]))
 
-context["logins"] = []
-for line in open("logins.jsonl"):
-    if line.strip():
-        context["logins"].append(json.loads(line))
+ips = list(open("ips.txt"))
+clustersize = context["clustersize"]
 
 print("---------------------------------------------")
-print("   Number of cards: {}".format(len(context["logins"])))
+print("   Number of IPs: {}".format(len(ips)))
+print(" VMs per cluster: {}".format(clustersize))
 print("---------------------------------------------")
 
+assert len(ips)%clustersize == 0
+
+clusters = []
+
+while ips:
+    cluster = ips[:clustersize]
+    ips = ips[clustersize:]
+    clusters.append(cluster)
+
+context["clusters"] = clusters
+
 template_file_name = context["cards_template"]
 template_file_path = os.path.join(
     os.path.dirname(__file__),
@@ -25,23 +35,23 @@ template_file_path = os.path.join(
     template_file_name
     )
 template = jinja2.Template(open(template_file_path).read())
-with open("cards.html", "w") as f:
-    f.write(template.render(**context))
-print("Generated cards.html")
+with open("ips.html", "w") as f:
+	f.write(template.render(**context))
+print("Generated ips.html")
 
 
 try:
     import pdfkit
     paper_size = context["paper_size"]
     margin = {"A4": "0.5cm", "Letter": "0.2in"}[paper_size]
-    with open("cards.html") as f:
-        pdfkit.from_file(f, "cards.pdf", options={
+    with open("ips.html") as f:
+        pdfkit.from_file(f, "ips.pdf", options={
             "page-size": paper_size,
             "margin-top": margin,
             "margin-bottom": margin,
             "margin-left": margin,
             "margin-right": margin,
             })
-    print("Generated cards.pdf")
+    print("Generated ips.pdf")
 except ImportError:
-    print("WARNING: could not import pdfkit; did not generate cards.pdf")
+    print("WARNING: could not import pdfkit; did not generate ips.pdf")

prepare-labs/settings/admin-kubenet.env

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

prepare-labs/settings/admin-kuberouter.env

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

prepare-labs/settings/admin-monokube.env

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

prepare-labs/settings/admin-oldversion.env

@@ -7,10 +7,9 @@ USER_PASSWORD=training
 
 # For a list of old versions, check:
 # https://kubernetes.io/releases/patch-releases/#non-active-branch-history
-KUBEVERSION=1.28.9
+KUBEVERSION=1.24.14
 
 STEPS="
-  terraform
   wait
   standardize
   clusterize

prepare-labs/settings/admin-polykube.env

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

prepare-labs/settings/admin-test.env

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

prepare-labs/settings/docker.env

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

prepare-labs/settings/konk.env

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

prepare-labs/settings/kubernetes.env

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

prepare-labs/settings/largekube.env

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

prepare-labs/settings/mk8s.env

@@ -1,4 +1,6 @@
+CLUSTERSIZE=2
+
 USER_LOGIN=k8s
 USER_PASSWORD=
 
-STEPS="terraform stage2"
+STEPS="stage2"

prepare-labs/settings/portal.env

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

prepare-labs/templates/cards.html

@@ -7,7 +7,7 @@
 {%- set url = url
     | default("http://FIXME.container.training/") -%}
 {%- set pagesize = pagesize
-    | default(10) -%}
+    | default(9) -%}
 {%- set lang = lang
     | default("en") -%}
 {%- set event = event
@@ -15,36 +15,79 @@
 {%- set backside = backside
     | default(False) -%}
 {%- set image = image
-    | default(False) -%}
+    | default("kube") -%}
 {%- set clusternumber = clusternumber
     | default(None) -%}
-{%- set thing = thing
-    | default("lab environment") -%}
-
-{%- if lang == "en" -%}
-    {%- set intro -%}
-    Here is the connection information to your very own
-    {{ thing }} for this {{ event }}.
-    You can connect to it with any SSH client.
-    {%- endset -%}
+{%- if qrcode == True -%}
+    {%- set qrcode = "https://container.training/q" -%}
+{%- elif qrcode -%}
+    {%- set qrcode = qrcode -%}
 {%- endif -%}
-{%- if lang == "fr" -%}
-    {%- set intro -%}
-    Voici les informations permettant de se connecter à votre
-    {{ thing }} pour cette formation.
-    Vous pouvez vous y connecter
-    avec n'importe quel client SSH.
-    {%- endset -%}
+
+{# You can also set img_bottom_src instead. #}
+{%- set img_logo_src = {
+	"docker": "https://s3-us-west-2.amazonaws.com/www.breadware.com/integrations/docker.png",
+	"swarm": "https://cdn.wp.nginx.com/wp-content/uploads/2016/07/docker-swarm-hero2.png",
+	"kube": "https://avatars1.githubusercontent.com/u/13629408",
+	"enix": "https://enix.io/static/img/logos/logo-domain-cropped.png",
+    }[image] -%}
+{%- if lang == "en" and clustersize == 1 -%}
+	{%- set intro -%}
+	Here is the connection information to your very own
+	machine for this {{ event }}.
+	You can connect to this VM with any SSH client.
+	{%- endset -%}
+    {%- set listhead -%}
+    Your machine is:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "en" and clustersize != 1 -%}
+	{%- set intro -%}
+	Here is the connection information to your very own
+	cluster for this {{ event }}.
+	You can connect to each VM with any SSH client.
+	{%- endset -%}
+    {%- set listhead -%}
+    Your machines are:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "fr" and clustersize == 1 -%}
+	{%- set intro -%}
+	Voici les informations permettant de se connecter à votre
+	machine pour cette formation.
+	Vous pouvez vous connecter à cette machine virtuelle
+	avec n'importe quel client SSH.
+	{%- endset -%}
+    {%- set listhead -%}
+    Adresse IP:
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "en" and clusterprefix != "node" -%}
+	{%- set intro -%}
+    Here is the connection information for the
+    <strong>{{ clusterprefix }}</strong> environment.
+	{%- endset -%}
+{%- endif -%}
+{%- if lang == "fr" and clustersize != 1 -%}
+	{%- set intro -%}
+	Voici les informations permettant de se connecter à votre
+	cluster pour cette formation.
+	Vous pouvez vous connecter à chaque machine virtuelle
+	avec n'importe quel client SSH.
+	{%- endset -%}
+    {%- set listhead -%}
+	Adresses IP:
+	{%- endset -%}
 {%- endif -%}
 {%- if lang == "en"  -%}
-    {%- set slides_are_at -%}
-    You can find the slides at:
-    {%- endset -%}
+	{%- set slides_are_at -%}
+	You can find the slides at:
+	{%- endset -%}
 {%- endif -%}
 {%- if lang == "fr" -%}
-    {%- set slides_are_at -%}
-      Le support de formation est à l'adresse suivante :
-    {%- endset -%}
+	{%- set slides_are_at -%}
+  	Le support de formation est à l'adresse suivante :
+	{%- endset -%}
 {%- endif -%}
 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
 <html>
@@ -59,21 +102,25 @@
 }
 body {
     /* this is A4 minus 0.5cm margins */
-    width: 20cm;
-    height: 28.7cm;
+	width: 20cm;
+	height: 28.7cm;
 }
 {% elif paper_size == "Letter" %}
 @page {
-    size: Letter; /* 8.5in x 11in */
+	size: Letter;
+	margin: 0.2in;
 }
 body {
-    width: 6.75in; /* two cards wide */
-    margin-left: 0.875in; /* (8.5in - 6.75in)/2 */
-    margin-top: 0.1875in; /* (11in - 5 cards)/2 */
+	/* this is Letter minus 0.2in margins */
+	width: 8.6in;
+	heigth: 10.6in;
 }
 {% endif %}
 
+
 body, table {
+    margin: 0;
+    padding: 0;
     line-height: 1em;
     font-size: 15px;
     font-family: 'Slabo 27px';
@@ -87,45 +134,47 @@ table {
     padding-left: 0.4em;
 }
 
-td:first-child {
-    width: 10.5em;
-}
-
-div.card {
+div {
     float: left;
-    border: 0.01in dotted black;
+    border: 1px dotted black;
+    {% if backside %}
+    height: 33%;
+    {% endif %}
+    /* columns * (width+left+right) < 100% */
     /*
-      columns * (width+left+right) < 100% 
-      height: 33%;
-      width: 24.8%;
-      width: 33%;
+    width: 24.8%;
     */
-    width: 3.355in; /* 3.375in minus two 0.01in borders */
-    height: 2.105in; /* 2.125in minus two 0.01in borders */
+    /**/
+    width: 33%;
+    /**/    
 }
 
 p {
     margin: 0.8em;
 }
 
-div.front {
-    {% if image %}
-    background-image: url("{{ image }}");
-    background-repeat: no-repeat;
-    background-size: 1in;
-    background-position-x: 2.8in;
-    background-position-y: center;
-    {% endif %}
+div.back {
+	border: 1px dotted grey;
 }
 
 span.scale {
-    white-space: nowrap;
+	white-space: nowrap;
+}
+
+img.logo {
+    height: 4.5em;
+    float: right;
+ }
+
+img.bottom {
+    height: 2.5em;
+    display: block;
+    margin: 0.5em auto;
 }
 
 .qrcode img {
-    height: 5.8em;
-    padding: 1em 1em 0.5em 1em;
-    float: left;
+    width: 40%;
+    margin: 1em;
 }
 
 .logpass {
@@ -140,97 +189,101 @@ span.scale {
     height: 0;
 }
 </style>
-<script type="text/javascript" src="qrcode.min.js"></script>
+<script type="text/javascript" src="https://cdn.rawgit.com/davidshimjs/qrcodejs/gh-pages/qrcode.min.js"></script>
 <script type="text/javascript">
 function qrcodes() {
-    [].forEach.call(
-        document.getElementsByClassName("qrcode"),
-        (e, index) => {
-            new QRCode(e, {
-                text: "{{ qrcode }}",
-                correctLevel: QRCode.CorrectLevel.L
-            });
-        }
-    );
+	[].forEach.call(
+		document.getElementsByClassName("qrcode"),
+		(e, index) => {
+			new QRCode(e, {
+				text: "{{ qrcode }}",
+				correctLevel: QRCode.CorrectLevel.L
+			});
+		}
+	);
 }
 
 function scale() {
-    [].forEach.call(
-        document.getElementsByClassName("scale"),
-        (e, index) => {
-            var text_width = e.getBoundingClientRect().width;
-            var box_width = e.parentElement.getBoundingClientRect().width;
-            var percent = 100 * box_width / text_width + "%";
-            e.style.fontSize = percent;
-        }
-    );
+	[].forEach.call(
+		document.getElementsByClassName("scale"),
+		(e, index) => {
+			var text_width = e.getBoundingClientRect().width;
+			var box_width = e.parentElement.getBoundingClientRect().width;
+			var percent = 100 * box_width / text_width + "%";
+			e.style.fontSize = percent;
+		}
+	);
 }
 </script>
 </head>
 <body onload="qrcodes(); scale();">
-{% for login in logins %}
-    <div class="card front">
+{% for cluster in clusters %}
+    <div>
         <p>{{ intro }}</p>
         <p>
+            {% if img_logo_src %}
+            <img class="logo" src="{{ img_logo_src }}" />
+            {% endif %}
             <table>
-              <tr>
-                <td>login:</td>
-                <td>password:</td>
-              </tr>
-              <tr>
-                <td class="logpass">{{ login.login }}</td>
-                <td class="logpass">{{ login.password }}</td>
-              </tr>
-              <tr>
-                <td>IP address:</td>
-                {% if login.port %}
-                <td>port:</td>
-                {% endif %}
-              </tr>
-              <tr>
-                <td class="logpass">{{ login.ipaddrs.split("\t")[0] }}</td>
-                {% if login.port %}
-                <td class="logpass">{{ login.port }}</td>
-                {% endif %}
-              </tr>
+            	{% if clusternumber != None %}
+	            <tr><td>cluster:</td></tr>
+	            <tr><td class="logpass">{{ clusternumber + loop.index }}</td></tr>
+            	{% endif %}
+                <tr><td>login:</td></tr>
+                <tr><td class="logpass">{{ user_login }}</td></tr>
+                <tr><td>password:</td></tr>
+                <tr><td class="logpass">{{ user_password }}</td></tr>
             </table>
+
         </p>
+        <p>
+            {{ listhead }}
+            <table>
+                {% for node in cluster %}
+                <tr>
+                	<td>{{ clusterprefix }}{{ loop.index }}:</td>
+                	<td>{{ node }}</td>
+                </tr>
+                {% endfor %}
+            </table>
+        </p>
+
         <p>
             {% if url %}
-            {{ slides_are_at }}
+        	{{ slides_are_at }}
             <p>
                 <span class="scale">{{ url }}</span>
             </p>
             {% endif %}
+            {% if img_bottom_src %}
+            <img class="bottom" src="{{ img_bottom_src }}" />
+            {% endif %}
         </p>
     </div>
     {% if loop.index%pagesize==0 or loop.last %}
         <span class="pagebreak"></span>
         {% if backside %}
-            {% for x in range(pagesize) %}
-                <div class="card back">
-                {{ backside }}
-                {#
-                <p>Thanks for attending
-                "Getting Started With Kubernetes and Container Orchestration"
-                during CONFERENCE in Month YYYY!</p>
-                <p>If you liked that workshop,
-                I can train your team, in person or
-                online, with custom courses of
-                any length and any level.
-                </p>
-                {% if qrcode %}
-                <p>If you're interested, please scan that QR code to contact me:</p>
-                <span class="qrcode"></span>
+			{% for x in range(pagesize) %}
+		        <div class="back">
+				<p>Thanks for attending
+				"Getting Started With Kubernetes and Container Orchestration"
+				during CONFERENCE in Month YYYY!</p>
+				<p>If you liked that workshop,
+				I can train your team, in person or
+				online, with custom courses of
+				any length and any level.
+				</p>
+	            {% if qrcode %}
+	            <p>If you're interested, please scan that QR code to contact me:</p>
+				<span class="qrcode"></span>
                 {% else %}
-                <p>If you're interested, you can contact me at:</p>
-                {% endif %}
-                <p>jerome.petazzoni@gmail.com</p>
-                #}
-                </div>
-            {% endfor %}
-        <span class="pagebreak"></span>
-        {% endif %}
+				<p>If you're interested, you can contact me at:</p>
+				{% endif %}
+				<p>jerome.petazzoni@gmail.com</p>
+		        </div>
+			{% endfor %}
+		<span class="pagebreak"></span>
+		{% endif %}
     {% endif %}
 {% endfor %}
 </body>

prepare-labs/templates/cards.yaml

@@ -1,19 +0,0 @@
-cards_template: cards.html
-paper_size: Letter
-url: https://2024-11-qconsf.container.training
-event: workshop
-backside: |
-  <div class="qrcode"></div>
-  <p>
-    Thanks for attending the Asynchronous Architecture Patterns workshop at QCON!
-  </p>
-  <p>
-    <b>This QR code will give you my contact info</b> as well as a link to a feedback form.
-  </p>
-  <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-kubernetes.png

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

@@ -8,8 +8,8 @@ resource "random_string" "_" {
 resource "time_static" "_" {}
 
 locals {
-  min_nodes_per_pool = var.min_nodes_per_cluster
-  max_nodes_per_pool = var.max_nodes_per_cluster
+  min_nodes_per_pool = var.nodes_per_cluster
+  max_nodes_per_pool = var.nodes_per_cluster * 2
   timestamp          = formatdate("YYYY-MM-DD-hh-mm", time_static._.rfc3339)
   tag                = random_string._.result
   # Common tags to be assigned to all resources

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

@@ -14,20 +14,6 @@ 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_${index}
   metadata {
@@ -35,57 +21,120 @@ resource "kubernetes_namespace" "shpod_${index}" {
   }
 }
 
-data "kubernetes_service" "shpod_${index}" {
-  depends_on = [ helm_release.shpod_${index} ]
+resource "kubernetes_deployment" "shpod_${index}" {
   provider = kubernetes.cluster_${index}
   metadata {
     name = "shpod"
-    namespace = "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 "helm_release" "shpod_${index}" {
-  provider = helm.cluster_${index}
-  repository = "https://shpod.in"
-  chart = "shpod"
-  name = "shpod"
-  namespace = "shpod"
-  create_namespace = false
-  set {
-    name = "service.type"
-    value = "NodePort"
+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 ]
   }
-  set {
-    name = "resources.requests.cpu"
-    value = "100m"
+  metadata {
+    name = "shpod"
+    namespace = kubernetes_namespace.shpod_${index}.metadata.0.name
   }
-  set {
-    name = "resources.requests.memory"
-    value = "500M"
+  spec {
+    selector = {
+      app = "shpod"
+    }
+    port {
+      name = "ssh"
+      port = 22
+      target_port = 22
+    }
+    type = "NodePort"
   }
-  set {
-    name = "resources.limits.cpu"
-    value = "1"
+}
+
+resource "kubernetes_service_account" "shpod_${index}" {
+  provider = kubernetes.cluster_${index}
+  metadata {
+    name = "shpod"
+    namespace = kubernetes_namespace.shpod_${index}.metadata.0.name
   }
-  set {
-    name = "resources.limits.memory"
-    value = "1000M"
+}
+
+resource "kubernetes_cluster_role_binding" "shpod_${index}" {
+  provider = kubernetes.cluster_${index}
+  metadata {
+    name = "shpod"
   }
-  set {
-    name = "persistentVolume.enabled"
-    value = "true"
+  role_ref {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "ClusterRole"
+    name      = "cluster-admin"
   }
-  set {
-    name = "ssh.password"
-    value = random_string.shpod_${index}.result
+  subject {
+    kind      = "ServiceAccount"
+    name      = "shpod"
+    namespace = "shpod"
   }
-  set {
-    name = "rbac.cluster.clusterRoles"
-    value = "{cluster-admin}"
+  subject {
+    api_group = "rbac.authorization.k8s.io"
+    kind      = "Group"
+    name      = "shpod-cluster-admins"
   }
-  set {
-    name = "codeServer.enabled"
-    value = "true"
+}
+
+resource "random_string" "shpod_${index}" {
+  length  = 6
+  special = false
+  upper   = false
+}
+
+provider "helm" {
+  alias = "cluster_${index}"
+  kubernetes {
+    config_path = "./kubeconfig.${index}"
   }
 }
 
@@ -168,28 +217,16 @@ resource "kubernetes_certificate_signing_request_v1" "cluster_admin_${index}" {
 
 %{ endfor ~}
 
-output "ips_txt" {
+output "ip_addresses_of_nodes" {
   value = join("\n", [
   %{ for index, cluster in clusters ~}
-    join("\n", concat(
+    join("\t", concat(
+      [
+        random_string.shpod_${index}.result,
+        "ssh -l k8s -p $${kubernetes_service.shpod_${index}.spec[0].port[0].node_port}"
+      ],
       split(" ", file("./externalips.${index}"))
     )),
   %{ endfor ~}
-  ""
-  ])
-}
-
-output "logins_jsonl" {
-  value = join("\n", [
-  %{ for index, cluster in clusters ~}
-    jsonencode({
-      login = "k8s",
-      password = random_string.shpod_${index}.result,
-      port = data.kubernetes_service.shpod_${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

@@ -7,16 +7,11 @@ variable "how_many_clusters" {
   default = 2
 }
 
-variable "min_nodes_per_cluster" {
+variable "nodes_per_cluster" {
   type    = number
   default = 2
 }
 
-variable "max_nodes_per_cluster" {
-  type    = number
-  default = 4
-}
-
 variable "node_size" {
   type    = string
   default = "M"

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

@@ -4,7 +4,6 @@ resource "helm_release" "_" {
   create_namespace = true
   repository       = "https://charts.loft.sh"
   chart            = "vcluster"
-  version          = "0.19.7"
   set {
     name  = "service.type"
     value = "NodePort"

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

@@ -14,9 +14,9 @@ $ hcloud server-type list | grep shared
 variable "node_sizes" {
   type = map(any)
   default = {
-    S = "cpx11"
-    M = "cpx21"
-    L = "cpx31"
+    S = "cx11"
+    M = "cx21"
+    L = "cx31"
   }
 }
 

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

@@ -1,25 +0,0 @@
-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_template_node_name" {
-  type    = string
-  default = null
-}
-
-variable "proxmox_template_vm_id" {
-  type    = number
-  default = null
-}
-

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

@@ -1,11 +0,0 @@
-# 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/virtual-machines/common.tf

@@ -56,7 +56,6 @@ 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]
     }
   }
 }
@@ -72,10 +71,10 @@ resource "local_file" "ip_addresses" {
 resource "local_file" "clusters" {
   content = join("", formatlist("%s\n", [
     for cid in range(1, 1 + var.how_many_clusters) :
-    join("\t",
+    join(" ",
       [for nid in range(1, 1 + var.nodes_per_cluster) :
         local.ip_addresses[format("c%03dn%03d", cid, nid)]
   ])]))
-  filename        = "clusters.tsv"
+  filename        = "clusters.txt"
   file_permission = "0600"
 }

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

@@ -13,7 +13,7 @@ data "openstack_images_image_v2" "_" {
   most_recent = true
   properties = {
     os      = "ubuntu"
-    version = "24.04"
+    version = "22.04"
   }
 }
 

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

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

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

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

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

@@ -1,77 +0,0 @@
-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
-  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 = "ceph"
-  #  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
-  }
-  agent {
-    enabled = true
-  }
-  initialization {
-    datastore_id = "ceph"
-    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

@@ -1,15 +0,0 @@
-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

@@ -1,14 +0,0 @@
-# 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"
-
-proxmox_template_node_name = "CHANGEME"
-proxmox_template_vm_id = CHANGEME
-
-

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

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

slides/1.yml

@@ -5,7 +5,7 @@ chat: "[Mattermost](https://training.enix.io/mattermost)"
 
 gitrepo: github.com/jpetazzo/container.training
 
-slides: https://2025-01-enix.container.training/
+slides: https://2024-05-enix.container.training/
 
 #slidenumberprefix: "#SomeHashTag — "
 

slides/2.yml

@@ -5,7 +5,7 @@ chat: "[Mattermost](https://training.enix.io/mattermost)"
 
 gitrepo: github.com/jpetazzo/container.training
 
-slides: https://2025-01-enix.container.training/
+slides: https://2024-05-enix.container.training/
 
 #slidenumberprefix: "#SomeHashTag — "
 

slides/3.yml

@@ -6,7 +6,7 @@ chat: "[Mattermost](https://training.enix.io/mattermost)"
 
 gitrepo: github.com/jpetazzo/container.training
 
-slides: https://2025-01-enix.container.training/
+slides: https://2024-05-enix.container.training/
 
 #slidenumberprefix: "#SomeHashTag — "
 
@@ -39,7 +39,6 @@ content:
   - k8s/helm-secrets.md
   - exercises/helm-umbrella-chart-details.md
 -
-  - k8s/helmfile.md
   - k8s/ytt.md
   - k8s/gitworkflows.md
   - k8s/flux.md

slides/4.yml

@@ -5,7 +5,7 @@ chat: "[Mattermost](https://training.enix.io/mattermost)"
 
 gitrepo: github.com/jpetazzo/container.training
 
-slides: https://2025-01-enix.container.training/
+slides: https://2024-05-enix.container.training/
 
 #slidenumberprefix: "#SomeHashTag — "
 
@@ -26,9 +26,7 @@ content:
 - shared/toc.md
 - exercises/netpol-brief.md
 - exercises/sealed-secrets-brief.md
-- exercices/rbac-brief.md
 - exercises/kyverno-ingress-domain-name-brief.md
-- exercises/reqlim-brief.md
 - #1
   - k8s/demo-apps.md
   - k8s/netpol.md
@@ -39,7 +37,6 @@ content:
   - k8s/ingress-tls.md
   - exercises/netpol-details.md
   - exercises/sealed-secrets-details.md
-  - exercises/rbac-details.md
 - #2
   - k8s/extending-api.md
   - k8s/crd.md
@@ -56,7 +53,6 @@ content:
   - k8s/apiserver-deepdive.md
   - k8s/aggregation-layer.md
   - k8s/hpa-v2.md
-  - exercises/reqlim-details.md
 - #4
   - k8s/statefulsets.md
   - k8s/consul.md

slides/5.yml

@@ -5,7 +5,7 @@ chat: "[Mattermost](https://training.enix.io/mattermost)"
 
 gitrepo: github.com/jpetazzo/container.training
 
-slides: https://2025-01-enix.container.training/
+slides: https://2024-05-enix.container.training/
 
 #slidenumberprefix: "#SomeHashTag — "
 

slides/_redirects

@@ -16,7 +16,7 @@
 
 # Shortlinks for next training in English and French
 #/next https://www.eventbrite.com/e/livestream-intensive-kubernetes-bootcamp-tickets-103262336428
-/next https://qconsf.com/training/nov2024/asynchronous-architecture-patterns-scale-ml-and-other-high-latency-workloads
+/next https://skillsmatter.com/courses/700-advanced-kubernetes-concepts-workshop-jerome-petazzoni
 /hi5 https://enix.io/fr/services/formation/online/
 /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

slides/autopilot/package.json

@@ -2,8 +2,8 @@
   "name": "container-training-pub-sub-server",
   "version": "0.0.1",
   "dependencies": {
-    "express": "^4.21.1",
-    "socket.io": "^4.8.0",
+    "express": "^4.16.2",
+    "socket.io": "^4.7.5",
     "socket.io-client": "^4.7.5"
   }
 }

slides/containers/Buildkit.md

@@ -40,7 +40,7 @@
 
 - In multi-stage builds, all stages can be built in parallel
 
-  (example: https://github.com/jpetazzo/shpod; [before][shpod-before-parallel] and [after][shpod-after-parallel])
+  (example: https://github.com/jpetazzo/shpod; [before] and [after])
 
 - Stages are built only when they are necessary
 
@@ -50,8 +50,8 @@
 
 - Files are cached in the builder
 
-[shpod-before-parallel]: https://github.com/jpetazzo/shpod/blob/c6efedad6d6c3dc3120dbc0ae0a6915f85862474/Dockerfile
-[shpod-after-parallel]: https://github.com/jpetazzo/shpod/blob/d20887bbd56b5fcae2d5d9b0ce06cae8887caabf/Dockerfile
+[before]: https://github.com/jpetazzo/shpod/blob/c6efedad6d6c3dc3120dbc0ae0a6915f85862474/Dockerfile
+[after]: https://github.com/jpetazzo/shpod/blob/d20887bbd56b5fcae2d5d9b0ce06cae8887caabf/Dockerfile
 
 ---
 
@@ -121,10 +121,10 @@ docker buildx build … \
 
 - Must not use binary downloads with hard-coded architectures!
 
-  (streamlining a Dockerfile for multi-arch: [before][shpod-before-multiarch], [after][shpod-after-multiarch])
+  (streamlining a Dockerfile for multi-arch: [before], [after])
 
-[shpod-before-multiarch]: https://github.com/jpetazzo/shpod/blob/d20887bbd56b5fcae2d5d9b0ce06cae8887caabf/Dockerfile
-[shpod-after-multiarch]: https://github.com/jpetazzo/shpod/blob/c50789e662417b34fea6f5e1d893721d66d265b7/Dockerfile
+[before]: https://github.com/jpetazzo/shpod/blob/d20887bbd56b5fcae2d5d9b0ce06cae8887caabf/Dockerfile
+[after]: https://github.com/jpetazzo/shpod/blob/c50789e662417b34fea6f5e1d893721d66d265b7/Dockerfile
 
 ---
 

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 (the "Compose file")
+2. Describe our stack of containers in a YAML file called `docker-compose.yml`
 
-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.
@@ -141,17 +141,7 @@ After ten seconds (or if we press `^C` again) it will forcibly kill them.
 
 ---
 
-## 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
+## The `docker-compose.yml` file
 
 Here is the file used in the demo:
 
@@ -182,9 +172,9 @@ services:
 
 A Compose file has multiple sections:
 
-* `services` is mandatory. Each service corresponds to a container.
+* `version` is mandatory. (Typically use "3".)
 
-* `version` is optional (it used to be mandatory). It can be ignored.
+* `services` is mandatory. Each service corresponds to a container.
 
 * `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.)
@@ -193,24 +183,24 @@ 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 a `services` block, it's a legacy v1 file.)
+  (If you see a Compose file without `version` and `services`, 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 Compose file
+## Containers in `docker-compose.yml`
 
 Each service in the YAML file must contain either `build`, or `image`.
 
@@ -288,7 +278,7 @@ 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)
 
@@ -298,10 +288,10 @@ 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               
@@ -320,13 +310,13 @@ 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...
@@ -337,19 +327,19 @@ 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.
 
 ---
 
@@ -379,15 +369,15 @@ 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`!)
  
 ---
 
@@ -406,9 +396,9 @@ 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`
 
 ---
 
@@ -427,7 +417,7 @@ 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`
 
 ---
 
@@ -461,7 +451,7 @@ 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!
 
@@ -481,9 +471,7 @@ class: extra-details
 
   - `docker compose` command to deploy Compose stacks to some clouds
 
-  - in Go instead of Python
-
-  - progressively getting feature parity with `docker compose`
+  - progressively getting feature parity with `docker-compose`
 
   - also provides numerous improvements (e.g. leverages BuildKit by default)
 

slides/containers/Copying_Files_During_Build.md

@@ -120,11 +120,11 @@ class: extra-details
 
   (and won't end up in the resulting image)
 
-- See the [documentation][dockerignore] for the little details
+- See the [documentation] for the little details
 
   (exceptions can be made with `!`, multiple directory levels with `**`...)
 
-[dockerignore]: https://docs.docker.com/engine/reference/builder/#dockerignore-file
+[documentation]: https://docs.docker.com/engine/reference/builder/#dockerignore-file
 
 ???
 

slides/docker-compose.yaml

@@ -1,3 +1,5 @@
+version: "2"
+
 services:
   www:
     image: nginx

slides/exercises/ingress-brief.md

@@ -1,4 +1,4 @@
-## Exercise — Ingress Controller
+## Exercise — Ingress
 
 - Add an ingress controller to a Kubernetes cluster
 

slides/exercises/ingress-details.md

@@ -1,4 +1,4 @@
-# Exercise — Ingress Controller
+# Exercise — Ingress
 
 - We want to expose a couple of web apps through an ingress controller
 
@@ -128,4 +128,4 @@ This is similar to the previous scenario, but with two significant changes:
 
 1. We only want to run the ingress controller on nodes that have the role `ingress`.
 
-2. We want to either use `hostPort`, or a list of `externalIPs` (not `hostNetwork`).
+2. We don't want to use `hostNetwork`, but a list of `externalIPs` instead.

slides/exercises/reqlim-brief.md

@@ -1,7 +0,0 @@
-## Exercise — Requests and Limits
-
-- Check current resource allocation and utilization
-
-- Make sure that all workloads have requests (and perhaps limits)
-
-- Make sure that all *future* workloads too!

slides/exercises/reqlim-details.md

@@ -1,55 +0,0 @@
-# Exercise — Requests and Limits
-
-By default, if we don't specify *resource requests*,
-our workloads will run in `BestEffort` quality of service.
-
-`BestEffort` is very bad for production workloads,
-because the scheduler has no idea of the actual resource
-requirements of our apps, and won't be able to make
-smart decisions about workload placement.
-
-As a result, when the cluster gets overloaded, 
-containers will be killed, pods will be evicted,
-and service disruptions will happen.
-
-Let's solve this!
-
----
-
-## Check current state
-
-- Check *allocations*
-
-  (i.e. which pods have requests and limits for CPU and memory)
-
-- Then check *utilization*
-
-  (i.e. actual resource usage)
-
-- Possible tools: `kubectl`, plugins like `view-allocations`, Prometheus...
-
----
-
-## Follow best practices
-
-- We want to make sure that *all* workloads have requests
-
-  (and perhaps limits, too!)
-
-- Depending on the workload:
-
-  - edit its YAML manifest
-
-  - adjust its Helm values
-
-  - add LimitRange in its Namespace
-
-- Then check again to confirm that the job has been done properly!
-
----
-
-## Be future-proof!
-
-- We want to make sure that *future* workloads will have requests, too
-
-- How can that be implemented?

slides/find-duplicate-markdown-links.sh

@@ -1,5 +0,0 @@
-#!/bin/sh
-for LINK in $(cat */*.md | sed -n 's/^\[\(.*\)\]:.*/\1/p' | sort | uniq -d); do
-  grep '^\['"$LINK"'\]:' */*.md
-done
-

slides/highfive.html

@@ -12,113 +12,113 @@
     <table>
 
       <tr>
-        <td>Mardi 21 janvier 2025</td>
+        <td>Mardi 14 mai 2024</td>
         <td>
           <a href="1.yml.html">Docker Intensif</a>
         </td>
       </tr>
       <tr>
-        <td>Mercredi 22 janvier 2025</td>
+        <td>Mercredi 15 mai 2024</td>
         <td>
           <a href="1.yml.html">Docker Intensif</a>
         </td>
       </tr>
       <tr>
-        <td>Jeudi 23 janvier 2025</td>
+        <td>Jeudi 16 mai 2024</td>
         <td>
           <a href="1.yml.html">Docker Intensif</a>
         </td>
       </tr>
       <tr>
-        <td>Vendredi 24 janvier 2025</td>
+        <td>Vendredi 17 mai 2024</td>
         <td>
           <a href="1.yml.html">Docker Intensif</a>
         </td>
       </tr>
 
       <tr>
-        <td>Mardi 28 janvier 2025</td>
+        <td>Mardi 21 mai 2024</td>
         <td>
           <a href="2.yml.html">Fondamentaux Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Mercredi 29 janvier 2025</td>
+        <td>Mercredi 22 mai 2024</td>
         <td>
           <a href="2.yml.html">Fondamentaux Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Jeudi 30 janvier 2025</td>
+        <td>Jeudi 23 mai 2024</td>
         <td>
           <a href="2.yml.html">Fondamentaux Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Vendredi 31 janvier 2025</td>
+        <td>Vendredi 24 mai 2024</td>
         <td>
           <a href="2.yml.html">Fondamentaux Kubernetes</a>
         </td>
       </tr>
 
       <tr>
-        <td>Lundi 3 février 2025</td>
+        <td>Mardi 28 mai 2024</td>
+        <td>
+          <a href="4.yml.html">Kubernetes Avancé</a>
+        </td>
+      </tr>
+      <tr>
+        <td>Mercredi 29 mai 2024</td>
+        <td>
+          <a href="4.yml.html">Kubernetes Avancé</a>
+        </td>
+      </tr>
+      <tr>
+        <td>Jeudi 30 mai 2024</td>
+        <td>
+          <a href="4.yml.html">Kubernetes Avancé</a>
+        </td>
+      </tr>
+      <tr>
+        <td>Vendredi 31 mai 2024</td>
+        <td>
+          <a href="4.yml.html">Kubernetes Avancé</a>
+        </td>
+      </tr>
+
+      <tr>
+        <td>Mardi 4 juin 2024</td>
         <td>
           <a href="3.yml.html">Packaging d'applications pour Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Mardi 4 février 2025</td>
+        <td>Mercredi 5 juin 2024</td>
         <td>
           <a href="3.yml.html">Packaging d'applications pour Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Mercredi 5 février 2025</td>
+        <td>Jeudi 6 juin 2024</td>
         <td>
           <a href="3.yml.html">Packaging d'applications pour Kubernetes</a>
         </td>
       </tr>
 
       <tr>
-        <td>Jeudi 7 février 2025</td>
-        <td>
-          <a href="4.yml.html">Kubernetes Avancé</a>
-        </td>
-      </tr>
-      <tr>
-        <td>Vendredi 7 février 2025</td>
-        <td>
-          <a href="4.yml.html">Kubernetes Avancé</a>
-        </td>
-      </tr>
-      <tr>
-        <td>Lundi 10 février 2025</td>
-        <td>
-          <a href="4.yml.html">Kubernetes Avancé</a>
-        </td>
-      </tr>
-      <tr>
-        <td>Mardi 11 février 2025</td>
-        <td>
-          <a href="4.yml.html">Kubernetes Avancé</a>
-        </td>
-      </tr>
-
-      <tr>
-        <td>Mercredi 12 février 2025</td>
+        <td>Lundi 10 juin 2024</td>
         <td>
           <a href="5.yml.html">Opérer Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Jeudi 13 février 2025</td>
+        <td>Mardi 11 juin 2024</td>
         <td>
           <a href="5.yml.html">Opérer Kubernetes</a>
         </td>
       </tr>
       <tr>
-        <td>Vendredi 14 février 2025</td>
+        <td>Mercredi 12 juin 2024</td>
         <td>
           <a href="5.yml.html">Opérer Kubernetes</a>
         </td>

slides/k8s/architecture.md

@@ -141,6 +141,12 @@ class: pic
 
 class: pic
 
+![](images/control-planes/non-dedicated-stacked-nodes.svg)
+
+---
+
+class: pic
+
 ![](images/control-planes/advanced-control-plane.svg)
 
 ---
@@ -151,12 +157,6 @@ class: pic
 
 ---
 
-class: pic
-
-![](images/control-planes/non-dedicated-stacked-nodes.svg)
-
----
-
 # The Kubernetes API
 
 [

slides/k8s/argocd.md

@@ -42,19 +42,22 @@ ArgoCD manages **applications** by **syncing** their **live state** with their *
 
 - It's OK to use local clusters (kind, minikube...)
 
-- We need to install the ArgoCD CLI ([argocd-packages], [argocd-binaries])
+- We need to install the ArgoCD CLI ([packages], [binaries])
 
 - **Highly recommended:** set up CLI completion!
 
 - Of course we'll need a Git service, too
 
+[packages]: https://argo-cd.readthedocs.io/en/stable/cli_installation/
+[binaries]: https://github.com/argoproj/argo-cd/releases/latest
+
 ---
 
 ## Setting up ArgoCD
 
 - The easiest way is to use upstream YAML manifests
 
-- There is also a [Helm chart][argocd-helmchart] if we need more customization
+- There is also a [Helm chart][argohelmchart] if we need more customization
 
 .lab[
 
@@ -67,6 +70,8 @@ ArgoCD manages **applications** by **syncing** their **live state** with their *
 
 ]
 
+[argohelmchart]: https://artifacthub.io/packages/helm/argo/argocd-apps
+
 ---
 
 ## Logging in with the ArgoCD CLI
@@ -132,6 +137,8 @@ ArgoCD manages **applications** by **syncing** their **live state** with their *
 
 - Let's have a look at ArgoCD architecture!
 
+[issue14167]: https://github.com/argoproj/argo-cd/issues/14167
+
 ---
 
 class: pic
@@ -190,6 +197,8 @@ It is responsible for invoking any user-defined hooks for lifecycle events (*Pre
 
 - If you create a new, empty repository, add some manifests to it
 
+[kubercoins]: https://github.com/jpetazzo/kubercoins
+
 ---
 
 ## Add an Application
@@ -259,6 +268,8 @@ It is responsible for invoking any user-defined hooks for lifecycle events (*Pre
 
 🤔 We're getting errors!
 
+[pollinginterval]: https://argo-cd.readthedocs.io/en/stable/faq/#how-often-does-argo-cd-check-for-changes-to-my-git-or-helm-repository
+
 ---
 
 ## Sync failed
@@ -446,6 +457,8 @@ Then click on the "CREATE" button (top left).
 
 - Today we'll just turn on automated sync for the staging namespace
 
+[rollouts]: https://argoproj.github.io/rollouts/
+
 ---
 
 ## Enabling auto-sync
@@ -502,7 +515,7 @@ git push origin staging
 
 - Let's how to deploy Helm charts with ArgoCD!
 
-- In the [kubercoins] repository, there is a branch called [helm-branch]
+- In the [kubercoins] repository, there is a branch called [helm]
 
 - It provides a generic Helm chart, in the [generic-service] directory
 
@@ -510,6 +523,12 @@ git push origin staging
 
 - Let's create one application for each of the 5 components of our app!
 
+[cmp]: https://argo-cd.readthedocs.io/en/stable/operator-manual/config-management-plugins/
+[kubercoins]: https://github.com/jpetazzo/kubercoins
+[helm]: https://github.com/jpetazzo/kubercoins/tree/helm
+[generic-service]: https://github.com/jpetazzo/kubercoins/tree/helm/generic-service
+[values]: https://github.com/jpetazzo/kubercoins/tree/helm/values
+
 ---
 
 ## Creating a Helm Application
@@ -560,31 +579,9 @@ git push origin staging
 
   (blue/green, canary...)
 
----
-
-## Acknowledgements
-
-Many thanks to
-Anton (Ant) Weiss ([antweiss.com](https://antweiss.com), [@antweiss](https://twitter.com/antweiss))
-and
-Guilhem Lettron
-for contributing an initial version and suggestions to this ArgoCD chapter.
-
-All remaining typos, mistakes, or approximations are mine (Jérôme Petazzoni). 
-
-[argocd-binaries]: https://github.com/argoproj/argo-cd/releases/latest
-[argocd-helmchart]: https://artifacthub.io/packages/helm/argo/argocd-apps
-[argocd-packages]: https://argo-cd.readthedocs.io/en/stable/cli_installation/
-[cmp]: https://argo-cd.readthedocs.io/en/stable/operator-manual/config-management-plugins/
-[Dex]: https://github.com/dexidp/dex
-[generic-service]: https://github.com/jpetazzo/kubercoins/tree/helm/generic-service
-[helm-branch]: https://github.com/jpetazzo/kubercoins/tree/helm
-[issue14167]: https://github.com/argoproj/argo-cd/issues/14167
-[kubercoins]: https://github.com/jpetazzo/kubercoins
-[pollinginterval]: https://argo-cd.readthedocs.io/en/stable/faq/#how-often-does-argo-cd-check-for-changes-to-my-git-or-helm-repository
-[rollouts]: https://argoproj.github.io/rollouts/
 [sso]: https://argo-cd.readthedocs.io/en/stable/operator-manual/user-management/#sso
-[values]: https://github.com/jpetazzo/kubercoins/tree/helm/values
+[Dex]: https://github.com/dexidp/dex
+[rollouts]: https://argoproj.github.io/argo-rollouts/
 
 ???
 

slides/k8s/bento-cnpg.md

@@ -1,173 +0,0 @@
-# Bento & PostgreSQL
-
-- Bento can also use SQL databases for input/output
-
-- We're going to demonstrate that by writing to a PostgreSQL database
-
-- That database will be deployed with the Cloud Native PostGres operator
-
-  (https://cloudnative-pg.io/)
-
----
-
-## CNPG in a nutshell
-
-- Free, open source
-
-- Originally created by [EDB] (EnterpriseDB, well-known PgSQL experts)
-
-- Non-exhaustive list of features:
-
-  - provisioning of Postgres servers, replicas, bouncers
-
-  - automatic failover
-
-  - backups (full backups and WAL shipping)
-
-  - provisioning from scratch, from backups, PITR
-
-  - manual and automated switchover (e.g. for node maintenance)
-
-  - and many more!
-
-[EDB]: https://www.enterprisedb.com/workload/kubernetes
-
----
-
-## What we're going to do
-
-1. Install CNPG.
-
-2. Provision a Postgres cluster.
-
-3. Configure Bento to write to that cluster.
-
-4. Set up a Grafana dashboard to see the data.
-
----
-
-## 1️⃣ Installing CNPG
-
-Many options available, see the [documentation][cnpg-install]:
-
-- raw YAML manifests
-
-- kubectl CNPG plugin (`kubectl cnpg install generate`)
-
-- Helm chart
-
-- OLM
-
-[cnpg-install]: https://cloudnative-pg.io/documentation/1.24/installation_upgrade/
-
----
-
-## 2️⃣ Provisioning a Postgres cluster
-
-Minimal manifest:
-
-```yaml
-apiVersion: postgresql.cnpg.io/v1
-kind: Cluster
-metadata:
-  name: db
-spec:
-  storage:
-    size: 1Gi
-```
-
----
-
-class: extra-details
-
-## For production...
-
-We might also add:
-
-- `spec.monitoring.enablePodMonitor: true`
-
-- `spec.instances: 2`
-
-- `resources.{requests,limits}.{cpu,memory}`
-
-- `walStorage.size`
-
-- `backup`
-
-- `postgresql.parameters`
-
-See [this manifest][cluster-maximal] for a detailed example.
-
-[cluster-maximal]: https://github.com/jpetazzo/pozok/blob/main/cluster-maximal.yaml
-
----
-
-## 3️⃣ Configuring Bento to write to SQL
-
-- We'll use the [`sql_insert`][sql-insert] output
-
-- If our cluster is named `mydb`, there will be a Secret `mydb-app`
-
-- This Secret will contain a `uri` field
-
-- That field can be used as the `dns` in the Bento configuration
-
-- We will also need to create the table that we want to use
-
-  (see next slide for instructions)
-
-[sql-insert]: https://warpstreamlabs.github.io/bento/docs/components/outputs/sql_insert
-
----
-
-## Creating a table
-
-- If we just want to store the city name and its population:
-  ```sql
-      CREATE TABLE IF NOT EXISTS cities (
-        city varchar(100) NOT NULL,
-        population integer
-      );
-  ```
-
-- This statement can be executed:
-
-  - manually, by getting a `psql` shell with `kubectl cnpg psql mydb app`
-
-  - automatically, with Bento's `init_statatement`
-
----
-
-## 4️⃣ Viewing the table in Grafana
-
-- In Grafana, in the home menu on the lift, click "connections"
-
-- Add a PostgreSQL data source
-
-- Enter the host:port, database, user, password
-
-- Then add a visualization using that data source
-
-  (it should be relatively self-explanatory!)
-
----
-
-class: extra-details
-
-## Automating it all
-
-- Expose PostgreSQL credentials through environment variables
-
-  (in the Bento container)
-
-- Use the `${...}` syntax in Bento to use these environment variables
-
-- Export the Grafana dashboard to a JSON file
-
-- Store the JSON file in a ConfigMap, with label `grafana_dashboard=1`
-
-- Create that ConfigMap in the namespace where Grafana is running
-
-- Similarly, data sources (like the Redis and the PostgreSQL one) can be defined in YAML
-
-- And that YAML can be put in a ConfigMap with label `grafana_datasource=1`

slides/k8s/bento-hpa.md

@@ -1,450 +0,0 @@
-# Autoscaling with KEDA
-
-- Cluster autoscaling = automatically add nodes *when needed*
-
-- *When needed* = when Pods are `Pending`
-
-- How do these pods get created?
-
-- When the Ollama Deployment is scaled up
-
-  - ... manually (e.g. `kubectl scale`)
-
-  - ... automatically (that's what we want to investigate now!)
-
----
-
-## Ways to implement autoscaling
-
-- Custom code
-
-  (e.g. crontab checking some value every few minutes and scaling accordingly)
-
-- Kubernetes Horizontal Pod Autoscaler v1
-
-  (aka `kubectl autoscale`)
-
-- Kubernetes Horizontal Pod Autoscaler v2 with custom metrics
-
-  (e.g. with Prometheus Adapter)
-
-- Kubernetes Horizontal Pod Autoscaler v2 with external metrics
-
-  (e.g. with KEDA)
-
----
-
-## Custom code
-
-- No, we're not going to do that!
-
-- But this would be an interesting exercise in RBAC
-
-  (setting minimal amount of permissions for the pod running our custom code)
-
----
-
-## HPAv1
-
-Pros: very straightforward
-
-Cons: can only scale on CPU utilization
-
-How it works:
-
-- periodically measures average CPU *utilization* across pods
-
-- if utilization is above/below a target (default: 80%), scale up/down
-
----
-
-## HPAv1 in practice
-
-- Create the autoscaling policy:
-  ```bash
-  kubectl autoscale deployment ollama --max=1000
-  ```
-  (The `--max` is required; it's a safety limit.)
-
-- Check it:
-  ```bash
-  kubectl describe hpa
-  ```
-
-- Send traffic, wait a bit: pods should be created automatically
-
----
-
-## HPAv2 custom vs external
-
-- Custom metrics = arbitrary metrics attached to Kubernetes objects
-
-- External metrics = arbitrary metrics not related to Kubernetes objects
-
---
-
-🤔
-
----
-
-## HPAv2 custom metrics
-
-- Examples:
-
-  - on Pods: CPU, RAM, network traffic...
-
-  - on Ingress: requests per second, HTTP status codes, request duration...
-
-  - on some worker Deployment: number of tasks processed, task duration...
-
-- Requires an *adapter* to:
-
-  - expose the metrics through the Kubernetes *aggregation layer*
-
-  - map the actual metrics source to Kubernetes objects
-
-Example: the [Prometheus adapter][prometheus-adapter]
-
-[prometheus-adapter]: https://github.com/kubernetes-sigs/prometheus-adapter
-
----
-
-## HPAv2 custom metrics in practice
-
-- We're not going to cover this here
-
-  (too complex / not enough time!)
-
-- If you want more details, check [my other course material][hpav2slides]
-
-[hpav2slides]: https://2024-10-enix.container.training/4.yml.html#toc-scaling-with-custom-metrics
-
----
-
-## HPAv2 external metrics
-
-- Examples:
-
-  - arbitrary Prometheus query
-
-  - arbitrary SQL query
-
-  - number of messages in a queue
-
-  - and [many, many more][keda-scalers]
-
-- Also requires an extra components to expose the metrics
-
-Example: [KEDA (https://keda.sh/)](https://keda.sh)
-
-[keda-scalers]: https://keda.sh/docs/latest/scalers/
-
----
-
-## HPAv2 external metrics in practice
-
-- We're going to install KEDA
-
-- And set it up to autoscale depending on the number of messages in Redis
-
----
-
-## Installing KEDA
-
-Multiple options (details in the [documentation][keda-deploy]):
-
-- YAML
-
-- Operator Hub
-
-- Helm chart 💡
-
-```bash
-helm upgrade --install --repo https://kedacore.github.io/charts \
- --namespace keda-system --create-namespace keda keda
-```
-
-[keda-deploy]: https://keda.sh/docs/latest/deploy/
-
----
-
-## Scaling according to Redis
-
-- We need to create a KEDA Scaler
-
-- This is done with a "ScaledObject" manifest
-
-- [Here is the documentation][keda-redis-lists] for the Redis Lists Scaler
-
-- Let's write that manifest!
-
-[keda-redis-lists]: https://keda.sh/docs/latest/scalers/redis-lists/
-
----
-
-## `keda-redis-scaler.yaml`
-
-```yaml
-apiVersion: keda.sh/v1alpha1
-kind: ScaledObject
-metadata:
-  name: ollama
-spec:
-  scaleTargetRef:
-    name: ollama
-  triggers:
-  - type: redis
-    metadata:
-      address: redis.`default`.svc:6379
-      listName: cities
-      listLength: "10"
-```
-
----
-
-## Notes
-
-- We need to update the `address` field with our namespace
-
-  (unless we are running in the `default` namespace)
-
-- Alternative: use `addressFromEnv` and set an env var in the Ollama pods
-
-- `listLength` gives the target ratio of `messages / replicas`
-
-- In our example, KEDA will scale the Deployment to `messages / 100`
-
-  (rounded up!)
-
----
-
-## Trying it out
-
-- Apply the ScaledObject manifest
-
-- Start a Bento pipeline loading e.g. 100-1000 cities in Redis
-
-  (100 on smaller clusters / slower CPUs, 1000 on bigger / faster ones)
-
-- Check pod and nod resource usage
-
-- What do we see?
-
---
-
-🤩 The Deployment scaled up automatically!
-
---
-
-🤔 But Pod resource usage remains very low (A few busy pods, many idle)
-
---
-
-💡 Bento doesn't submit enough requests in parallel!
-
----
-
-## Improving throughput
-
-We're going to review multiple techniques:
-
-1. Increase parallelism inside the Bento pipeline.
-
-2. Run multiple Bento consumers.
-
-3. Couple consumers and processors more tightly.
-
----
-
-## 1️⃣ Increase pipeline parallelism
-
-- Set `parallel` to `true` in the `http` processor
-
-- Wrap the input around a `batched` input
-
-  (otherwise, we don't have enough messages in flight)
-
-- Increase `http` timeout significantly (e.g. to 5 minutes)
-
----
-
-## Results
-
-🎉 More messages flow through the pipeline
-
-🎉 Many requests happen in parallel
-
-🤔 Average Pod and Node CPU utilization is higher, but not maxed out
-
-🤔 HTTP queue size (measured with HAProxy metrics) is relatively high
-
-🤔 Latency is higher too
-
-Why?
-
----
-
-## Too many requests in parallel
-
-- Ealier, we didn't have enough...
-
-- ...Now, we have too much!
-
-- However, for a very big request queue, it still wouldn't be enough
-
-💡 We currently have a fixed parallelism. We need to make it dynamic!
-
----
-
-## 2️⃣ Run multiple Bento consumers
-
-- Restore the original Bento configuration
-
-  (flip `parallel` back to `false`; remove the `batched` input)
-
-- Run Bento in a Deployment
-
-  (e.g. with the [Bento Helm chart][bento-helm-chart])
-
-- Autoscale that Deployment like we autoscaled the Ollama Deployment
-
-[bento-helm-chart]: https://github.com/warpstreamlabs/bento-helm-chart
-
----
-
-## Results
-
-🤔🤔🤔 Pretty much the same as before!
-
-(High throughput, high utilization but not maxed out, high latency...)
-
---
-
-🤔🤔🤔 Why?
-
----
-
-## Unbalanced load balancing
-
-- All our requests go through the `ollama` Service
-
-- We're still using the default Kubernetes service proxy!
-
-- It doesn't spread the requests properly across all the backends
-
----
-
-## 3️⃣ Couple consumers and processors
-
-What if:
-
---
-
-instead of sending requests to a load balancer,
-
---
-
-each queue consumer had its own Ollama instance?
-
----
-
-## Current architecture
-
-<pre class="mermaid">
-flowchart LR
-  subgraph P1["Pod"]
-    H1["HAProxy"] --> O1["Ollama"]
-  end
-  subgraph P2["Pod"]
-    H2["HAProxy"] --> O2["Ollama"]
-  end
-  subgraph P3["Pod"]
-    H3["HAProxy"] --> O3["Ollama"]
-  end
-  Q["Queue<br/>(Redis)"] <--> C["Consumer<br/>(Bento)"] --> LB["Load Balancer<br/>(kube-proxy)"]
-  LB --> H1 & H2 & H3
-</pre>
-
----
-
-## Proposed architecture
-
-<pre class="mermaid">
-flowchart LR
-  subgraph P1["Consumer Pod"]
-    C1["Bento"] --> H1["HAProxy"] --> O1["Ollama"]
-  end
-  subgraph P2["Consumer Pod"]
-    C2["Bento"] --> H2["HAProxy"] --> O2["Ollama"]
-  end
-  subgraph P3["Consumer Pod"]
-    C3["Bento"] --> H3["HAProxy"] --> O3["Ollama"]
-  end
-  Queue["Queue"] <--> C1 & C2 & C3
-</pre>
-
----
-
-## 🏗️ Let's build something!
-
-- Let's implement that architecture!
-
-- See next slides for hints / getting started
-
----
-
-## Hints
-
-We need to:
-
-- Update the Bento consumer configuration to talk to localhost
-
-- Store that configuration in a ConfigMap
-
-- Add a Bento container to the Ollama Deployment
-
-- Profit!
-
----
-
-## Results
-
-🎉 Node and Pod utilization is maximized
-
-🎉 HTTP queue size is bounded
-
-🎉 Deployment autoscales up and down
-
----
-
-## ⚠️ Scaling down
-
-- Eventually, there are less messages in the queue
-
-- The HPA scales down the Ollama Deployment
-
-- This terminates some Ollama Pods
-
-🤔 What happens if these Pods were processing requests?
-
---
-
-- The requests might be lost!
-
----
-
-## Avoiding lost messages
-
-Option 1:
-
-- cleanly shutdown the consumer
-
-- make sure that Ollama can complete in-flight requests
-
-  (by extending its grace period)
-
-- find a way to terminate Ollama when no more requests are in flight
-
-Option 2:
-  
-- use *message acknowledgement*

slides/k8s/bento-intro.md

@@ -1,623 +0,0 @@
-# Getting started with Bento
-
-How can we move to a message queue architecture...
-
-*...without rewriting a bunch of code?*
-
-🤔
-
----
-
-## Bento
-
-https://bento.dev/
-
-"Fancy stream processing made operationally mundane"
-
-"Written in Go, deployed as a static binary, declarative configuration. Open source and cloud native as utter heck."
-
-With ✨ amazing ✨ documentation 😍
-
----
-
-class: extra-details
-
-## Tiny bit of history
-
-- Original project: Benthos
-
-- May 30, 2024: [Redpanda acquires Benthos][redpanda-acquires-benthos]
-
-  - Benthos is now Redpanda Connect
-
-  - some parts have been relicensed as commercial products
-
-- May 31, 2024: [Warpstream forks Benthos][warpstream-forks-benthos]
-
-  - that fork is named "Bento"
-
-  - it's fully open source
-
-- We're going to use Bento here, but Redpanda Connect should work fine too!
-
----
-
-## Bento concepts
-
-- Message stream processor
-
-- Each pipeline is configured by a YAML configuration that defines:
-
-  - input (where do we get the messages?)
-
-  - pipeline (optional: how do we transform the messages?)
-
-  - output (where do we put the messages afterwards?)
-
-- Once Bento is started, it runs the pipelines forever
-
-  (except for pipelines that have a logical end, e.g. reading from a file)
-
-- Embedded language (Bloblang) to manipulate/transform messages
-
----
-
-## Messages
-
-- Typically JSON objects
-
-  (but raw strings are also possible)
-
-- Nesting, arrays, etc. are OK
-
----
-
-## Getting started with Bento
-
-We're going to:
-
-1. Import a bunch of cities from a CSV file into a Redis queue.
-
-2. Read back these cities using a web server.
-
-3. Use an "enrichment workflow" to query our LLM for each city.
-
----
-
-## 1️⃣ Importing cities
-
-Let's break down the work:
-
-- download the data set
-
-- create the Bento configuration
-
-- deploy Redis
-
-- start Bento
-
----
-
-## Downloading the data set
-
-- Example database:
-
-  https://www.kaggle.com/datasets/juanmah/world-cities
-
-- Let's download and uncompress the data set:
-  ```bash
-  curl -fsSL https://www.kaggle.com/api/v1/datasets/download/juanmah/world-cities |
-    funzip > cities.csv
-  ```
-
-  (Ignore the "length error", it's harmless!)
-
-- Check the structure of the data set:
-  ```bash
-  head cities.csv
-  ```
-
----
-
-## Creating the Bento configuration
-
-- We need to find which `input` and `output` to use
-
-- Check the list with `bento list` or the [documentation][bento-inputs]
-
-- Then run `bento create INPUTNAME/PIPELINENAME/OUTPUTNAME`
-
-- Generate a configuration file:
-  ```bash
-  bento create csv//redis_list > csv2redis.yaml
-  ```
-
-- Edit that configuration file; look for the `(required)` parameters
-
-  (Everything else can go away!)
-
----
-
-## Resulting configuration
-
-If we trim all the default values, here is the result:
-
-```yaml
-input:
-  csv:
-    paths: ["cities.csv"]
-output:
-  redis_list:
-    url: redis://redis:6379 # No default (required)
-    key: cities
-```
-
-We'll call that value `csv2redis.yaml`.
-
----
-
-## Deploying Redis
-
-- Create a Deployment:
-  ```bash
-  kubectl create deployment redis --image redis
-  ```
-
-- Expose it:
-  ```bash
-  kubectl expose deployment redis --port 6379
-  ```
-
----
-
-## Starting Bento
-
-Option 1: run it manually in a pod, to see what's going on.
-
-```bash
-bento --config csv2redis.yaml
-```
-
-Option 2: run it with e.g. the Bento Helm chart.
-
-*We're not going to do that yet, since this particular pipeline has a logical end.*
-
-*(The Helm chart is best suited to pipelines that run forever.)*
-
----
-
-## Expected output
-
-.small[
-```
-INFO Running main config from specified file       @service=bento bento_version="" path=csv2redis.yaml
-INFO Launching a Bento instance, use CTRL+C to close  @service=bento
-INFO Listening for HTTP requests at: http://0.0.0.0:4195  @service=bento
-INFO Input type csv is now active                  @service=bento label="" path=root.input
-INFO Output type redis_list is now active          @service=bento label="" path=root.output
-INFO Pipeline has terminated. Shutting down the service  @service=bento
-```
-]
-
-The pipeline should complete in just a few seconds.
-
----
-
-## Checking what's in Redis
-
-- Connect to our Redis instance:
-  ```bash
-  redis-cli -h redis
-  ```
-
-- List keys:
-  ```redis
-  KEYS *
-  ```
-
-- Check that the `cities` list has approx. 47000 elements:
-  ```redis
-  LLEN cities
-  ```
-
-- Get the first element of the list:
-  ```redis
-  LINDEX cities 0
-  ```
-
----
-
-## Fun with Bloblang
-
-- Let's add a filter to keep only cities with a population above 10,000,000
-
-- Add the following block to the Bento configuration:
-
-```yaml
-pipeline:
-  processors:
-    - switch:
-        - check: this.population == ""
-          processors:
-            - mapping: root = deleted()
-        - check: this.population.int64() < 10000000
-          processors:
-            - mapping: root = deleted()
-```
-
-(See the [docs][bento-switch] for details about the `switch` processor.)
-
----
-
-## Testing our processor
-
-- First, delete the existing `cities` list:
-  ```bash
-  redis-cli -h redis DEL cities
-  ```
-
-- Then, run the Bento pipeline again:
-  ```bash
-  bento --config csv2redis.yaml
-  ```
-  (It should complain about a few cities where the population has a decimal point.)
-
-- Check how many cities were loaded:
-  ```bash
-  redis-cli -h redis LLEN cities
-  ```
-  (There should be 47.)
-
----
-
-## 2️⃣ Consume the queue over HTTP
-
-- We want to "get the next city" in the queue with a simple `curl`
-
-- Our input will be `redis_list`
-
-- Our output will be `http_server`
-
----
-
-## Generate the Bento configuration
-
-Option 1: `bento create redis_list//http_server`
-
-Option 2: [read the docs][output-http-server]
-
----
-
-## 🙋 Choose your own adventure
-
-Do you want to try to write that configuration?
-
-Or shall we see it right away?
-
---
-
-⚠️ Spoilers on next slide!
-
----
-
-## `redis2http.yaml`
-
-```yaml
-input:
-  redis_list:
-    url: redis://redis:`6379`
-    key: cities
-output:
-  http_server:
-    path: /nextcity
-```
-
-This will set up an HTTP route to fetch *one* city.
-
-It's also possible to batch, stream...
-
-⚠️ As of November 2024, `bento create` uses port 6397 instead of 6379 for Redis!
-
----
-
-## Trying it out
-
-- Run Bento with this configuration:
-  ```bash
-  bento --config redis2http.yaml &
-  ```
-
-- Retrieve one city:
-  ```bash
-  curl http://localhost:4195/nextcity
-  ```
-
-- Check what happens after we retrive *all* the cities!
-
----
-
-## 3️⃣ Query our LLM for each city
-
-- We want to ask our LLM who's the mayor of each of these cities
-
-- We'll use a prompt that will usually ensure a short answer
-
-  (so that it's faster; we don't want to wait 30 seconds per city!)
-
-- We'll test the prompt with the Ollama CLI
-
-- Then we'll craft a proper HTTP API query
-
-- Finally, we'll configure an [enrichment workflow][enrichment] in Bento
-
----
-
-## Test our prompt
-
-Assuming that our earlier Ollama Deployment is still running:
-
-```bash
-kubectl exec deployment/ollama -- \
-ollama run qwen2:1.5b "
-Who is the mayor of San Francisco?
-Just give the name by itself on a single line.
-If you don't know, don't say anything.
-"
-```
-
----
-
-## Turn the prompt into an HTTP API query
-
-Note: to install `http` in an Alpine container, run `apk add httpie`.
-
-```bash
-http http://ollama.default:11434/api/generate \
-model=qwen2:1.5b stream:=false prompt="
-Who is the mayor of Paris?
-Just give the name by itself on a single line.
-If you don't know, don't say anything.
-"
-```
-
-We get a JSON payload, and we want to use the `response` field.
-
----
-
-## Configure an enrichment workflow
-
-The [Bento documentation][enrichment] is really good!
-
-We need to set up:
-
-- a `branch` processor
-
-- a `request_map` to transform the city into an Ollama request
-
-- an `http` processor to submit the request to Ollama
-
-- a `result_map` to transform the Ollama response
-
----
-
-## Without the `branch` processor
-
-<pre class="mermaid">
-flowchart LR
-
-  CITY["
-    city: Paris
-    country: France
-    population: 1106000
-    iso2: FR
-    ...
-    "]
-
-  REQ["
-    model: qwen2:1.5b
-    stream: false
-    prompt: Who is the mayor of Paris?
-    "]
-
-  REP["
-    response: Anne Hidalgo
-    eval_count: ...
-    prompt_eval_count: ...
-    (other ollama fields)
-    "]
-
-  CITY@{ shape: card}
-  REQ@{ shape: card}
-  REP@{ shape: card}
-
-  style CITY text-align: left
-  style REQ text-align: left
-  style REP text-align: left
-
-  mapping@{ shape: diam }
-  http["http processor"]@{ shape: diam }
-
-  CITY --> mapping --> REQ --> http --> REP
-</pre>
-
-- We transform the `city` into an Ollama request
-
-- The `http` processor submits the request to Ollama
-
-- The final output is the Ollama response
-
----
-
-## With the `branch` processor
-
-<pre class="mermaid">
-flowchart LR
-
-  CITY["
-    city: Paris
-    country: France
-    population: 1106000
-    iso2: FR
-    ...
-    "]
-
-  REQ["
-    model: qwen2:1.5b
-    stream: false
-    prompt: Who is the mayor of Paris?
-    "]
-
-  REP["
-    response: Anne Hidalgo
-    eval_count: ...
-    prompt_eval_count: ...
-    (other ollama fields)
-    "]
-
-  OUT["
-    city: Paris
-    country: France
-    population: 1106000
-    iso2: FR
-    ...
-    mayor: Anne Hidalgo
-    "]
-
-  CITY@{ shape: card}
-  REQ@{ shape: card}
-  REP@{ shape: card}
-  OUT@{ shape: card}
-
-  style CITY text-align: left
-  style REQ text-align: left
-  style REP text-align: left
-  style OUT text-align: left
-
-  branch@{ shape: diam }
-  request_map@{ shape: diam }
-  result_map@{ shape: diam }
-  http["http processor"]@{ shape: diam }
-
-  CITY --> branch
-  branch --> result_map
-  branch --> request_map
-  request_map --> REQ
-  REQ --> http
-  http --> REP
-  REP --> result_map
-  result_map --> OUT
-</pre>
-
-- The `branch` processor allows doing the processing "on the side"
-
-- `request_map` and `result_map` transform the message before/after processing
-
-- Then, the result is combined with the original message (the `city`)
-
----
-
-```yaml
-input:
-  csv:
-    paths: ["cities.csv"]
-pipeline:
-  processors:
-    - branch:
-        request_map: |
-          root.model = "qwen2:1.5b"
-          root.stream = false
-          root.prompt = (
-            "Who is the mayor of %s? ".format(this.city) +
-            "Just give the name by itself on a single line. " +
-            "If you don't know, don't say anything."
-            )
-        processors:
-          - http:
-              url: http://ollama:11434/api/generate
-              verb: POST
-        result_map: |
-          root.mayor = this.response
-```
-
----
-
-## Trying it out
-
-- Save the YAML on the previous page into a configuration file
-
-- Run Bento with that configuration file
-
-- What happens?
-
---
-
-🤔 We're seeing errors due to timeouts
-
-```
-ERRO HTTP request to 'http://ollama...' failed: http://ollama...:
-Post "http://ollama...": context deadline exceeded
-(Client.Timeout exceeded while awaiting headers)
-```
-
----
-
-## 🙋 Choose your own adventure
-
-How should we address errors?
-
-- Option 1: increase the timeout in the [http][bento-http] processor
-
-- Option 2: use a [retry][bento-retry] processor in the pipeline
-
-- Option 3: use a [reject_errored][bento-reject] output
-
----
-
-## 🏗️ Let's build something!
-
-- We want to process 1000 cities with our LLM
-
-  (guessing who the mayor is, or something similar)
-
-- Store the output wherever we want
-
-  (Redis, CSV file, JSONL files...)
-
-- Deal correctly with errors
-
-  (we'll check that there are, indeed, 1000 cities in the output)
-
-- Scale out to process faster
-
-  (scale ollama to e.g. 10 replicas, enable parallelism in Bento)
-
----
-
-class: title
-
-🍱 Lunch time! 🍱
-
----
-
-## What happened?
-
-- If your Ollama pods have *resource requests*:
-
-  → your cluster may have auto-scaled
-
-- If your Ollama pods don't have *resource requests*:
-
-  → you probably have a bunch of container restarts, due to out-of-memory errors
-
-🤔 What's that about?
-
-[bento-http]: https://warpstreamlabs.github.io/bento/docs/components/processors/http/
-[bento-inputs]: https://warpstreamlabs.github.io/bento/docs/components/inputs/about/
-[bento-reject]: https://warpstreamlabs.github.io/bento/docs/components/outputs/reject_errored
-[bento-retry]: https://warpstreamlabs.github.io/bento/docs/components/processors/retry
-[bento-switch]: https://warpstreamlabs.github.io/bento/docs/components/processors/switch/
-[enrichment]: https://warpstreamlabs.github.io/bento/cookbooks/enrichments/
-[output-http-server]: https://warpstreamlabs.github.io/bento/docs/components/outputs/http_server
-[redpanda-acquires-benthos]: https://www.redpanda.com/press/redpanda-acquires-benthos
-[warpstream-forks-benthos]: https://www.warpstream.com/blog/announcing-bento-the-open-source-fork-of-the-project-formerly-known-as-benthos
-

slides/k8s/bento-rmq.md

@@ -1,250 +0,0 @@
-# Bento & RabbitMQ
-
-- In some of the previous runs, messages were dropped
-
-  (we start with 1000 messages in `cities` and have e.g. 955 in `mayors`)
-
-- This is caused by various errors during processing
-
-  (e.g. too many timeouts; Bento being shutdown halfway through...)
-
-- ...And by the fact that we are using a Redis queue
-
-  (which doesn't offer delivery guarantees or acknowledgements)
-
-- Can we get something better?
-
----
-
-## The problem
-
-- Some inputs (like `redis_list`) don't support *acknowledgements*
-
-- When a message is pulled from the queue, it is deleted immediately
-
-- If the message is lost for any reason, it is lost permanently
-
----
-
-## The solution
-
-- Some inputs (like `amqp_0_9`) support acknowledgements
-
-- When a message is pulled from the queue:
-
-  - it is not visible anymore to other consumers
-
-  - it needs to be explicitly acknowledged
-
-- The acknowledgement is done by Bento when the message reaches the output
-
-- The acknowledgement deletes the message
-
-- No acknowledgement after a while? Consumer crashes/disconnects?
-
-  Message gets requeued automatically!
-
----
-
-## `amqp_0_9`
-
-- Protocol used by RabbitMQ
-
-- Very simplified behavior:
-
-  - messages are published to an [*exchange*][amqp-exchanges]
-
-  - messages have a *routing key*
-
-  - the exchange routes the message to one (or zero or more) queues
-    </br>(possibly using the routing key or message headers to decide which queue(s))
-
-  - [*consumers*][amqp-consumers] subscribe to queues to receive messages
-
-[amqp-exchanges]: https://www.rabbitmq.com/tutorials/amqp-concepts#exchanges
-[amqp-consumers]: https://www.rabbitmq.com/tutorials/amqp-concepts#consumers
-
----
-
-## Using the default exchange
-
-- There is a default exchange (called `""` - empty string)
-
-- The routing key indicates the name of the queue to deliver to
-
-- The queue needs to exist (we need to create it beforehand)
-
----
-
-class: extra-details
-
-## Defining custom exchanges
-
-- Create an exchange
-
-  - exchange types: direct, fanout, topic, headers
-
-  - durability: persisted to disk to survive server restart or not?
-
-- Create a binding
-
-  - which exchange?
-
-  - which routing key? (for direct exchanges)
-
-  - which queue?
-
----
-
-## RabbitMQ on Kubernetes
-
-- RabbitMQ can be deployed on Kubernetes:
-
-  - directly (creating e.g. a StatefulSet)
-
-  - with the RabbitMQ operator
-
-- We're going to do the latter!
-
-- The operator includes the "topology operator"
-
-  (to configure queues, exchanges, and bindings through custom resources)
-
----
-
-## Installing the RabbitMQ operator
-
-- Let's install it with this Helm chart:
-
-  ```bash
-  helm upgrade --install --repo https://charts.bitnami.com/bitnami \
-      --namespace rabbitmq-system --create-namespace \
-      rabbitmq-cluster-operator rabbitmq-cluster-operator
-  ```
-
----
-
-## Deploying a simple RabbitMQ cluster
-
-- Let's use the YAML manifests in that directory:
-
-  https://github.com/jpetazzo/beyond-load-balancers/tree/main/rabbitmq
-
-- This creates:
-
-  - a `RabbitmqCluster` called `mq`
-
-  - a `Secret` called `mq-default-user` containing access credentials
-
-  - a durable `Queue` named `q1` 
-
-(We can ignore the `Exchange` and the `Binding`, we won't use them.)
-
----
-
-## 🏗️ Let's build something!
-
-Let's replace the `cities` Redis list with our RabbitMQ queue.
-
-(See next slide for steps and hints!)
-
----
-
-## Steps
-
-1. Edit the Bento configuration for our "CSV importer".
-
-   (replace the `redis_list` output with `amqp_0_9`)
-
-2. Run that pipeline and confirm that messages show up in RabbitMQ.
-
-3. Edit the Bento configuration for the Ollama consumer.
-
-   (replace the `redis_list` input with `amqp_0_9`)
-
-4. Trigger a scale up of the Ollama consumer.
-
-5. Update the KEDA Scaler to use RabbitMQ instead of Redis.
-
----
-
-## 1️⃣ Sending messages to RabbitMQ
-
-- Edit our Bento configuration (the one feeding the CSV file to Redis)
-
-- We want the following `output` section:
-  ```yaml
-    output:
-      amqp_0_9:
-        exchange: ""
-        key: q1
-        mandatory: true
-        urls:
-         - "${AMQP_URL}"
-  ```
-
-- Then export the AMQP_URL environment variable using `connection_string` from Secret `mq-default-user`
-
-💡 Yes, we can directly use environment variables in Bento configuration!
-
----
-
-## 2️⃣ Testing our AMQP output
-
-- Run the Bento pipeline
-
-- To check that our messages made it:
-  ```bash
-  kubectl exec mq-server-0 -- rabbitmqctl list_queues
-  ```
-
-- We can also use Prometheus metrics, e.g. `rabbitmq_queue_messages`
-
----
-
-## 3️⃣ Receiving messages from RabbitMQ
-
-- Edit our other Bento configuration (the one in the Ollama consumer Pod)
-
-- We want the following `input` section:
-  ```yaml
-    input:
-      amqp_0_9:
-        urls:
-          - `amqp://...:5672/`
-        queue: q1
-  ```
-
----
-
-## 4️⃣ Triggering Ollama scale up
-
-- If the autoscaler is configured to scale to zero, disable it
-
-  (easiest solution: delete the ScaledObject)
-
-- Then manually scale the Deployment to e.g. 4 Pods
-
-- Check that messages are processed and show up in the output
- 
-  (it should still be a Redis list at this point)
-
----
-
-## 5️⃣ Autoscaling on RabbitMQ
-
-- We need to update our ScaledObject
-
-- Check the [RabbitMQ Queue Scaler][keda-rabbitmq]
-
-- Multiple ways to pass the AMQP URL:
-
-  - hardcode it (easier solution for testing!)
-
-  - use `...fromEnv` and set environment variables in target pod
-
-  - create and use a TriggerAuthentication
-
-💡 Since we have the AMQP URL in a Secret, TriggerAuthentication works great!
-
-[keda-rabbitmq]: https://keda.sh/docs/latest/scalers/rabbitmq-queue/

slides/k8s/cainjector.md

@@ -55,7 +55,6 @@
 
   `cert-manager.io/allow-direct-injection: "true"`
 
-- See [cert-manager documentation] for details
-
-[cert-manager documentation]: https://cert-manager.io/docs/concepts/ca-injector/
+- See [cert-manager documentation][docs] for details
 
+[docs]: https://cert-manager.io/docs/concepts/ca-injector/

slides/k8s/cluster-autoscaler.md

@@ -272,9 +272,9 @@ This can be overridden by setting the annotation:
 
 - Can express `minAvailable` or `maxUnavailable`
 
-- See [documentation][doc-pdb] for details and examples
+- See [documentation] for details and examples
 
-[doc-pdb]: https://kubernetes.io/docs/tasks/run-application/configure-pdb/
+[documentation]: https://kubernetes.io/docs/tasks/run-application/configure-pdb/
 
 ---
 

slides/k8s/cluster-upgrade.md

@@ -81,7 +81,7 @@
 
 ## What version are we running anyway?
 
-- When I say, "I'm running Kubernetes 1.28", is that the version of:
+- When I say, "I'm running Kubernetes 1.22", is that the version of:
 
   - kubectl
 
@@ -129,15 +129,15 @@
 
 ## Kubernetes uses semantic versioning
 
-- Kubernetes versions look like MAJOR.MINOR.PATCH; e.g. in 1.28.9:
+- Kubernetes versions look like MAJOR.MINOR.PATCH; e.g. in 1.22.17:
 
   - MAJOR = 1
-  - MINOR = 28
-  - PATCH = 9
+  - MINOR = 22
+  - PATCH = 17
 
 - It's always possible to mix and match different PATCH releases
 
-  (e.g. 1.28.9 and 1.28.13 are compatible)
+  (e.g. 1.22.17 and 1.22.5 are compatible)
 
 - It is recommended to run the latest PATCH release
 
@@ -153,9 +153,9 @@
 
 - All components support a difference of one¹ MINOR version
 
-- This allows live upgrades (since we can mix e.g. 1.28 and 1.29)
+- This allows live upgrades (since we can mix e.g. 1.22 and 1.23)
 
-- It also means that going from 1.28 to 1.30 requires going through 1.29
+- It also means that going from 1.22 to 1.24 requires going through 1.23
 
 .footnote[¹Except kubelet, which can be up to two MINOR behind API server,
 and kubectl, which can be one MINOR ahead or behind API server.]
@@ -254,7 +254,7 @@ and kubectl, which can be one MINOR ahead or behind API server.]
   sudo vim /etc/kubernetes/manifests/kube-apiserver.yaml
   ```
 
-- Look for the `image:` line, and update it to e.g. `v1.30.1`
+- Look for the `image:` line, and update it to e.g. `v1.24.1`
 
 ]
 
@@ -320,29 +320,53 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 - First things first: we need to upgrade kubeadm
 
-- The Kubernetes package repositories are now split by minor versions
+.lab[
 
-  (i.e. there is one repository for 1.28, another for 1.29, etc.)
+- Upgrade kubeadm:
+  ```
+  sudo apt install kubeadm=1.27.0-00
+  ```
 
-- This avoids accidentally upgrading from one minor version to another
+- Check what kubeadm tells us:
+  ```
+  sudo kubeadm upgrade plan
+  ```
 
-  (e.g. with unattended upgrades or if packages haven't been held/pinned)
+]
 
-- We'll need to add the new package repository and unpin packages!
+Problem: kubeadm doesn't know know how to handle
+upgrades from version 1.22.
+
+This is because we installed version 1.27.
+
+We need to install kubeadm version 1.23.X.
 
 ---
 
-## Installing the new packages
+## Downgrading kubeadm
 
-- Edit `/etc/apt/sources.list.d/kubernetes.list`
+- We need to go back to kubeadm version 1.23.X.
 
-  (or copy it to e.g. `kubernetes-1.29.list` and edit that)
+.lab[
 
-- `apt-get update`
+- View available versions for package `kubeadm`:
+  ```bash
+  apt show kubeadm -a | grep ^Version | grep 1.23
+  ```
 
-- Now edit (or remove) `/etc/apt/preferences.d/kubernetes`
+- Downgrade kubeadm:
+  ```
+  sudo apt install kubeadm=1.23.0-00
+  ```
 
-- `apt-get install kubeadm` should now upgrade `kubeadm` correctly! 🎉
+- Check what kubeadm tells us:
+  ```
+  sudo kubeadm upgrade plan
+  ```
+
+]
+
+kubeadm should now agree to upgrade to 1.23.X.
 
 ---
 
@@ -361,7 +385,7 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 - Look for the `image:` line, and restore it to the original value
 
-  (e.g. `v1.28.9`)
+  (e.g. `v1.22.17`)
 
 - Wait for the control plane to come back up
 
@@ -375,14 +399,9 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 .lab[
 
-- Check the upgrade plan:
-  ```bash
-  sudo kubeadm upgrade plan
-  ```
-
 - Perform the upgrade:
   ```bash
-  sudo kubeadm upgrade apply v1.29.0
+  sudo kubeadm upgrade apply v1.23.0
   ```
 
 ]
@@ -399,9 +418,15 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 - Log into node `oldversion2`
 
-- Update package lists and APT pins like we did before
+- View available versions for package `kubelet`:
+  ```bash
+  apt show kubelet -a | grep ^Version
+  ```
 
-- Then upgrade kubelet
+- Upgrade kubelet:
+  ```bash
+  sudo apt install kubelet=1.23.0-00
+  ```
 
 ]
 
@@ -454,16 +479,13 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 .lab[
 
-- Execute the whole upgrade procedure on each node:
+- Download the configuration on each node, and upgrade kubelet:
   ```bash
     for N in 1 2 3; do
       ssh oldversion$N "
-        sudo sed -i s/1.28/1.29/ /etc/apt/sources.list.d/kubernetes.list &&
-        sudo rm /etc/apt/preferences.d/kubernetes &&
-        sudo apt update &&
-        sudo apt install kubeadm -y &&
+        sudo apt install kubeadm=1.23.0-00 &&
         sudo kubeadm upgrade node &&
-        sudo apt install kubelet -y"
+        sudo apt install kubelet=1.23.0-00"
     done
   ```
 ]
@@ -472,7 +494,7 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 ## Checking what we've done
 
-- All our nodes should now be updated to version 1.29
+- All our nodes should now be updated to version 1.23.0
 
 .lab[
 
@@ -565,35 +587,17 @@ Note 2: kubeadm itself is still version 1.22.1..
 
 ---
 
-## Database operators to the rescue
-
-- Moving stateful pods (e.g.: database server) can cause downtime
-
-- Database replication can help:
-
-  - if a node contains database servers, we make sure these servers aren't primaries
-
-  - if they are primaries, we execute a *switch over*
-
-- Some database operators (e.g. [CNPG]) will do that switch over automatically
-
-  (when they detect that a node has been *cordoned*)
-
-[CNPG]: https://cloudnative-pg.io/
-
----
-
 class: extra-details
 
 ## Skipping versions
 
-- This example worked because we went from 1.28 to 1.29
+- This example worked because we went from 1.22 to 1.23
 
-- If you are upgrading from e.g. 1.26, you will have to go through 1.27 first
+- If you are upgrading from e.g. 1.21, you will have to go through 1.22 first
 
-- This means upgrading kubeadm to 1.27.X, then using it to upgrade the cluster
+- This means upgrading kubeadm to 1.22.X, then using it to upgrade the cluster
 
-- Then upgrading kubeadm to 1.28.X, etc.
+- Then upgrading kubeadm to 1.23.X, etc.
 
 - **Make sure to read the release notes before upgrading!**
 

slides/k8s/consul.md

@@ -225,4 +225,4 @@ consul agent -data-dir=/consul/data -client=0.0.0.0 -server -ui \
 :EN:- Scheduling pods together or separately
 :EN:- Example: deploying a Consul cluster
 :FR:- Lancer des pods ensemble ou séparément
-:FR:- Exemple : lancer un cluster Consul
+:FR:- Example : lancer un cluster Consul

slides/k8s/flux.md

@@ -20,45 +20,6 @@ This is (approximately) what we're going to do:
 
 ---
 
-## Resource graph
-
-<pre class="mermaid">
-flowchart TD
-H/D["charts/dockercoins<br/>(Helm chart)"]
-H/C["charts/color<br/>(Helm chart)"]
-
-A/D["apps/dockercoins/flux.yaml<br/>(HelmRelease)"]
-A/B["apps/blue/flux.yaml<br/>(HelmRelease)"]
-A/G["apps/green/flux.yaml<br/>(HelmRelease)"]
-A/CM["apps/cert-manager/flux.yaml<br/>(HelmRelease)"]
-A/P["apps/kube-prometheus-stack/flux.yaml<br/>(HelmRelease + Kustomization)"]
-A/T["traefik/flux.yaml<br/>(HelmRelease)"]
-
-C/D["clusters/dev/kustomization.yaml<br/>(Kustomization)"]
-C/P["clusters/prod/kustomization.yaml<br/>(Kustomization)"]
-
-C/D --> A/B
-C/D --> A/D
-C/D --> A/G
-
-C/P --> A/D
-C/P --> A/G
-C/P --> A/T
-C/P --> A/CM
-C/P --> A/P
-
-A/D --> H/D
-A/B --> H/C
-A/G --> H/C
-A/P --> CHARTS & PV["apps/kube-prometheus-stack/manifests/configmap.yaml<br/>(Helm values)"]
-A/CM --> CHARTS
-A/T --> CHARTS
-
-CHARTS["Charts on external repos"]
-</pre>
-
----
-
 ## Getting ready
 
 - Let's make sure we have two clusters
@@ -114,7 +75,7 @@ CHARTS["Charts on external repos"]
       --repository=$GITHUB_REPO \
       --branch=main \
       --path=./clusters/$FLUX_CLUSTER \
-      --personal --private=false
+      --personal --public
   ```
 
 ]
@@ -298,8 +259,8 @@ class: extra-details
 
 - Put application manifests in their directory:
   ```bash
-  mkdir -p apps/dockercoins/manifests
-  cp ~/container.training/k8s/dockercoins.yaml apps/dockercoins/manifests
+  mkdir -p apps/dockercoins
+  cp ~/container.training/k8s/dockercoins.yaml apps/dockercoins/
   ```
 
 - Create kustomization manifest:
@@ -466,10 +427,6 @@ class: extra-details
 
   `flux create helmrelease ... --values-from=ConfigMap/myapp`
 
-- The ConfigMap or Secret must be in the same Namespace as the HelmRelease
-
-  (not the target namespace of that HelmRelease!)
-
 ---
 
 ## Gotchas

slides/k8s/handson-mlops.md

@@ -1,132 +0,0 @@
-class: title
-
-*Tell me and I forget.*
-<br/>
-*Teach me and I remember.*
-<br/>
-*Involve me and I learn.*
-
-Misattributed to Benjamin Franklin
-
-[(Probably inspired by Chinese Confucian philosopher Xunzi)](https://www.barrypopik.com/index.php/new_york_city/entry/tell_me_and_i_forget_teach_me_and_i_may_remember_involve_me_and_i_will_lear/)
-
----
-
-## Hands-on sections
-
-- There will be *a lot* of examples and demos
-
-- If you are attending a live workshop:
-
-  - follow along with the demos, ask questions at any time
-
-  - if you can, try to run some of the examples and demos in your environment
-
-  - if things are going too fast, ask the trainer to slow down :)
-
-- If you are watching a recording or only reading the slides:
-
-  - it is **strongly** recommended to run **all** the examples and demos
-
-  - take advantage of the fact that you can pause at any time
-
----
-
-class: in-person
-
-## Where are we going to run our containers?
-
----
-
-class: in-person, pic
-
-![You get a cluster](images/you-get-a-cluster.jpg)
-
----
-
-## If you're attending a live training or workshop
-
-- Each person gets a private lab environment
-
-- Your lab environments will be available for the duration of the workshop
-
-  (check with your instructor to know exactly when they'll be shut down)
-
-- Note that for budget reasons¹, your environment will be fairly modest
-
-  - scenario 1: 4 nodes with 2 cores and 4 GB RAM ; no cluster autoscaling
-
-  - scenario 2: 1 node with 4 cores and 8 GB RAM ; cluster autoscaling
-
-.footnote[¹That cloud thing is mighty expensive, yo]
-
----
-
-## Running your own lab environment
-
-- If you are following a self-paced course...
-
-- Or watching a replay of a recorded course...
-
-- ...You will need to set up a local environment for the labs
-
-  *or*
-
-- If you want to use a specific cloud provider...
-
-- Or want to see these concepts "at scale"...
-
-- ...You can set up your own clusters with whatever capacity suits you
-
----
-
-## Deploying your own Kubernetes cluster
-
-- You need cloud provider credentials for this
-
-- Option 1: use the cloud provider CLI, web UI, ...
-
-- Option 2: use [one of these Terraform configurations][one-kubernetes]
-
-  (set `cluster_name`, `node_size`, `max_nodes_per_pool`, `location`, and GO!)
-
-[one-kubernetes]: https://github.com/jpetazzo/container.training/tree/main/prepare-labs/terraform/one-kubernetes
-
----
-
-## Deploying your own Kubernetes cluster.red[**s**]
-
-- If you want to deliver your own training or workshop:
-
-  - deployment scripts are available in the [prepare-labs] directory
-
-  - you can use them to automatically deploy many lab environments
-
-  - they support many different infrastructure providers
-
-  - they can deploy dozens (even hundreds) of clusters at a time
-
-[prepare-labs]: https://github.com/jpetazzo/container.training/tree/main/prepare-labs
-
----
-
-class: in-person
-
-## Why don't we run containers locally?
-
-- Installing this stuff can be hard on some machines
-
-  (32 bits CPU or OS... Laptops without administrator access... etc.)
-
-- *"The whole team downloaded all these container images from the WiFi!
-  <br/>... and it went great!"* (Literally no-one ever)
-
-- All you need is a computer (or even a phone or tablet!), with:
-
-  - an Internet connection
-
-  - a web browser
-
-  - an SSH client
-
-- Some of the demos require multiple nodes to demonstrate scaling

slides/k8s/healthchecks.md

@@ -158,6 +158,8 @@
 
 - Let's see the specific details for each of them!
 
+[grpc]: https://grpc.github.io/grpc/core/md_doc_health-checking.html
+
 ---
 
 ## `httpGet`
@@ -294,6 +296,8 @@ class: extra-details
 
 - Leverages standard [GRPC Health Checking Protocol][grpc]
 
+[grpc]: https://grpc.github.io/grpc/core/md_doc_health-checking.html
+
 ---
 
 ## Timing and thresholds
@@ -509,10 +513,7 @@ class: extra-details
 
 - Sometimes it can also make sense to embed a web server in the worker
 
-[grpc]: https://grpc.github.io/grpc/core/md_doc_health-checking.html
-
 ???
 
 :EN:- Using healthchecks to improve availability
 :FR:- Utiliser des *healthchecks* pour améliorer la disponibilité
-

slides/k8s/helmfile.md

@@ -1,166 +0,0 @@
-# Managing our stack with `helmfile`
-
-- We've installed a few things with Helm
-
-- And others with raw YAML manifests
-
-- Perhaps you've used Kustomize sometimes
-
-- How can we automate all this? Make it reproducible?
-
----
-
-## Requirements
-
-- We want something that is *idempotent*
-
-  = running it 1, 2, 3 times, should only install the stack once
-
-- We want something that handles udpates
-
-  = modifying / reconfiguring without restarting from scratch
-
-- We want something that is configurable
-
-  = with e.g. configuration files, environment variables...
-
-- We want something that can handle *partial removals*
-
-  = ability to remove one element without affecting the rest
-
-- Inspiration: Terraform, Docker Compose...
-
----
-
-## Shell scripts?
-
-✅ Idempotent, thanks to `kubectl apply -f`, `helm upgrade --install`
-
-✅ Handles updates (edit script, re-run)
-
-✅ Configurable
-
-❌ Partial removals
-
-If we remove an element from our script, it won't be uninstalled automatically.
-
----
-
-## Umbrella chart?
-
-Helm chart with dependencies on other charts.
-
-✅ Idempotent
-
-✅ Handles updates
-
-✅ Configurable (with Helm values: YAML files and `--set`)
-
-✅ Partial removals
-
-❌ Complex (requires to learn advanced Helm features)
-
-❌ Requires everything to be a Helm chart (adds (lots of) boilerplate)
-
----
-
-## Helmfile
-
-https://github.com/helmfile/helmfile
-
-✅ Idempotent
-
-✅ Handles updates
-
-✅ Configurable (with values files, environment variables, and more)
-
-✅ Partial removals
-
-✅ Fairly easy to get started
-
-🐙 Sometimes feels like summoning unspeakable powers / staring down the abyss
-
----
-
-## What `helmfile` can install
-
-- Helm charts from remote Helm repositories
-
-- Helm charts from remote git repositories
-
-- Helm charts from local directories
-
-- Kustomizations
-
-- Directories with raw YAML manifests
-
----
-
-## How `helmfile` works
-
-- Everything is defined in a main `helmfile.yaml`
-
-- That file defines:
-
-  - `repositories` (remote Helm repositories)
-
-  - `releases` (things to install: Charts, YAML...)
-
-  - `environments` (optional: to specialize prod vs staging vs ...)
-
-- Helm-style values file can be loaded in `enviroments`
-
-- These values can then be used in the rest of the Helmfile
-
-- Examples: [install essentials on a cluster][helmfile-ex-1], [run a Bento stack][helmfile-ex-2]
-
-[helmfile-ex-1]: https://github.com/jpetazzo/beyond-load-balancers/blob/main/helmfile.yaml
-[helmfile-ex-2]: https://github.com/jpetazzo/beyond-load-balancers/blob/main/bento/helmfile.yaml
-
----
-
-## `helmfile` commands
-
-- `helmfile init` (optional; downloads plugins if needed)
-
-- `helmfile apply` (updates all releases that have changed)
-
-- `helmfile sync` (updates all releases even if they haven't changed)
-
-- `helmfile destroy` (guess!)
-
----
-
-## Helmfile tips
-
-As seen in [this example](https://github.com/jpetazzo/beyond-load-balancers/blob/main/bento/helmfile.yaml#L21):
-
-- variables can be used to simplify the file
-
-- configuration values and secrets can be loaded from external sources
-
-  (Kubernetes Secrets, Vault... See [vals] for details)
-
-- current namespace isn't exposed by default
-
-- there's often more than one way to do it!
-
-  (this particular section could be improved by using Bento `${...}`)
-
-[vals]: https://github.com/helmfile/vals
-
-???
-
-## 🏗️ Let's build something!
-
-- Write a helmfile (or two) to set up today's entire stack on a brand new cluster!
-
-- Suggestion:
-
-  - one helmfile for singleton, cluster components
-    <br/>
-    (All our operators: Prometheus, Grafana, KEDA, CNPG, RabbitMQ Operator)
-
-  - one helmfile for the application stack
-    <br/>
-    (Bento, PostgreSQL cluster, RabbitMQ)

slides/k8s/ingress-tls.md

@@ -96,7 +96,7 @@ class: extra-details
 
 ---
 
-## Choose your own adventure!
+## Choose your adventure!
 
 - We present 3 methods to obtain a certificate
 

slides/k8s/metrics-server.md

@@ -195,4 +195,4 @@ class: extra-details
 :EN:- Installing metrics-server
 
 :EN:- Le *resource metrics pipeline*
-:FR:- Installation de metrics-server
+:FR:- Installtion de metrics-server

slides/k8s/mlops-headsup.md

@@ -1,53 +0,0 @@
-## What we will / won't cover
-
-- Kubernetes provides low-level building blocks (pods, deployments, services...)
-
-- There are many high-level frameworks out there for serverless, AI...:
-
-  [Knative](https://knative.dev/docs/),
-  [KubeAI](https://www.kubeai.org/),
-  [Kueue](https://kueue.sigs.k8s.io/)...
-
-- We're going to sit somewhere in the middle:
-
-  reimplement some of the features of these high-level frameworks, in a flexible way
-
-- This workshop will (hopefully!) give you a better eye to evaluate these frameworks, too
-
-- We won't showcase GPUs today for budget reasons
-
-  (giving everyone a few GPU nodes would be prohibitive, sorry!)
-
----
-
-## A word about our demo app
-
-- We'll use Ollama with a relatively small LLM
-
-  (qwen2:1.5b)
-
-- We'll use it to generate very short completions
-
-  (a few seconds of CPU)
-
-- All the challenges that we will address are also visible on longer requests
-
-  (in fact, they are even more visible on longer requests!)
-
-- We're sticking to short requests to save time and cover a lot of ground today
-
-  (but feel free to use more expensive prompts if you'd like!)
-
----
-
-## Tiny bit of backstory...
-
-The original prompt that we used when building the first version of this content was:
-
-```
-If you go to {city}, I suggest that you
-```
-
-This would typically take 10-30 seconds - and with much bigger Kubernetes nodes.
-
-Today, we suggest that we use a prompt that generates shorter answers!

slides/k8s/ollama-intro.md

@@ -1,343 +0,0 @@
-# Ollama in a nutshell
-
-https://ollama.dev
-
-"Get up and running with large language models"
-
-"Docker, but for LLMs"
-
-- Server to host (run) LLMs
-
-- Controlled with CLI or API
-
-- Download a model with `ollama pull`
-
-- Run inference with `ollama run`
-
----
-
-## Quick demo
-
-⚠️ **Important note 1:** the commands in this section aren't meant
-to be executed on your Kubernetes clusters. They are meant to
-be executed on a local machine, and they assume that Ollama is
-installed and running. If you don't have Ollama on your local
-machine, it's OK to skip these demos!
-
-⚠️ **Important note 2:** the models used by Ollama are fairly big
-(1.5 GB for the one used here; up to 10s or 100s of GB for bigger
-models). We do not recommend downloading them on conference WiFi.
-
-Assuming Ollama is installed and running:
-
-```
-ollama run qwen2:1.5b "What's the solution to global warming?"
-```
-
-We're going to use this model because it's relatively small.
-
-Many others are available (see https://ollama.dev/search).
-
----
-
-## Other useful commands
-
-- Start an interactive chat session:
-  ```bash
-  ollama run qwen2:1.5b
-  ```
-
-- Pull an model (or check for updates):
-  ```bash
-  ollama pull qwen2:1.5b
-  ```
-
-- See information on a model:
-  ```bash
-  ollama show qwen2:1.5b
-  ```
-
----
-
-## Models on disk, in memory
-
-- See models available on disk:
-  ```bash
-  ollama list
-  ```
-
-- See models loaded in memory:
-  ```bash
-  ollama ps
-  ```
-
-- Unload a model:
-  ```bash
-  ollama stop qwen2:1.5b
-  ```
-
-Models are automatically unloaded after 5 minutes (by default).
-
-Ollama loads models in RAM, and in VRAM if it detects a supported GPU.
-
----
-
-# Ollama on Kubernetes
-
-Let's run Ollama on our Kubernetes cluster!
-
-- Option 1: `kubectl run`
-
-- Option 2: create a Deployment and a Service
-
-- Option 3: use a Helm chart
-
----
-
-## 1️⃣ `kubectl run`
-
-Note: the `ollama/ollama` image is quite big (~2 GB transfer, ~4 GB on disk).
-
-```bash
-kubectl run ollama --image ollama/ollama
-```
-
-Wait for the pod to be up and running:
-```bash
-kubectl wait pod ollama --for=condition=Ready
-```
-
-(If that command times out, try again and/or specify a higher timeout.)
-
-```bash
-kubectl exec ollama -- ollama run qwen2:1.5b "What's Bach's best piece?"
-```
-
-Shutdown the pod:
-```bash
-kubectl delete pod ollama
-```
-
----
-
-## 2️⃣ Deployment + Service
-
-Create the Deployment:
-```bash
-kubectl create deployment ollama --image ollama/ollama
-```
-
-Create the Service:
-```bash
-kubectl create service clusterip ollama --tcp 11343
-```
-
-Wait for the Service Endpoints to be available:
-```bash
-kubectl wait endpoints ollama --for=jsonpath={..ip}
-```
-
----
-
-## By the way... Why port 11434?
-
-| 1 | 1 | 4 | 3 | 4 |
-|---|---|---|---|---|
-| L | L | A | M | A |
-
----
-
-## Connecting to the Service
-
-Let's use the `/api/generate` endpoint:
-
-```bash
-kubectl run httpclient --rm -it --image alpine/httpie -- --ignore-stdin \
-  http://ollama:11434/api/generate \
-  model=qwen2:1.5b prompt="Write a limerick about Kubernetes"
-```
-
-(See [Ollama API docs](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-completion) for details.)
-
---
-
-🤔 We get an error: the model needs to be downloaded first.
-
-💡 When we used the `ollama run` CLI command earlier, it did it automatically for us.
-
----
-
-## Pulling the model
-
-Method 1:
-```bash
-kubectl exec deployment/ollama -- ollama pull qwen2:1.5b
-```
-
-Method 2:
-```bash
-kubectl run httpclient --rm -it --image alpine/httpie -- --ignore-stdin \
-  http://ollama:11434/api/pull \
-  name=qwen2:1.5b
-```
-
----
-
-## Houston, we (are going to) have a problem...
-
-- This works when there is only one pod
-
-- What happens if we scale up the Deployment?
-
-- We need to pull the model on every pod
-
-- How should we do that?
-
----
-
-## Potential solutions
-
-- Bake the model into the image
-
-  🙅 Personal opinion: this is a bad idea (image size, maintenance...)
-
-- Directly send a "pull" command to each pod, individually
-
-  🙁 Hackish, not great
-
-- Use a Kubernetes lifecycle hook
-
-  💡 That works!
-
-- Use a sidecar container to pull the model
-
-  🤔 Doable, but more work than the lifecycle hook
-
----
-
-## 🙋 Choose your own adventure
-
-Should we add that lifecycle hook?
-
----
-
-## 3️⃣ Helm chart
-
-- Let's check the [ArtifactHUB] for an Ollama Helm chart
-
-- The most popular (as of November 2024) is [this one, by OTWLD][ollama-chart]
-
-- ~~It has pockets~~
-
-- It can pre-pull models! 🎉
-
-[ArtifactHub]: https://artifacthub.io
-[ollama-chart]: https://artifacthub.io/packages/helm/ollama-helm/ollama
-
----
-
-## Installing the Helm chart
-
-Traditional method:
-```bash
-helm repo add ollama https://otwld.github.io/ollama-helm/
-helm install ollama ollama/ollama --set ollama.models={qwen2:1.5b}
-```
-
-Idempotent¹, single-command method:
-```bash
-helm upgrade --install --repo https://otwld.github.io/ollama-helm/ \
-  ollama ollama --set ollama.models={qwen2:1.5b}
-```
-
-.footnote[¹Idempotent: which can be executed multiple times without adverse effect.]
-
----
-
-## Testing the Helm installation
-
-Just like before:
-```bash
-kubectl run httpclient --rm -it --image alpine/httpie -- --ignore-stdin \
-  http://ollama:11434/api/generate \
-  model=qwen2:1.5b prompt="Write a limerick about YAML" stream:=false
-```
-
-And while we're here, check resource usage:
-```bash
-kubectl exec deployment/ollama -ti -- top
-```
-
-There should be two processes:
-
-- `ollama` itself, relatively small (~100 MB)
-
-- the LLM subprocess, relatively big (~1.4 GB for qwen2:1.5b)
-
----
-
-class: extra-details
-
-## HTTPie
-
-https://httpie.io/
-
-- CLI client to send requests to web services
-
-- Similar to curl, but made specifically to talk to API backends
-
-```bash
-httpie <URL> [key=value] [key=value] [key:=value]
-```
-
-- The `key=value` pairs get turned into a JSON object
-
-- `key:=value` indicates a parameter to be sent "as-is"
-
-  (ideal for e.g. boolean or numbers)
-
----
-
-## Sending some load
-
-We're going to use `hey`:
-
-```bash
-kubectl run hey --rm -it --image nixery.dev/hey -- \
-  hey -c 10 -n 10 -t 60 -m POST \
-  -d '{"model": "qwen2:1.5b", "prompt": "vi or emacs?"}' \
-  http://ollama:11434/api/generate
-```
-
-Some explanations:
-
-- `nixery.dev` = automatically generates images with [Nixery]
-- `-c` = concurrent requests
-- `-n` = total number of requests
-- `-t` = timeout in seconds
-
-This is probably going to take (literally) a minute.
-
-[Nixery]: https://nixery.dev/
-
----
-
-## Performance analysis
-
-- Let's start an interactive container with `hey`
-
-  (e.g., use the `alpine` image, then `apk add hey`)
-
-- Try 10 requests, with a concurrency of 1/2/4
-
-- Meanwhile, check the logs of the `ollama` pod
-
-- Some results (your results may vary depending on CPU, random seed...):
-
-  - 1 = 0.08 reqs/s, average latency: 12s
-  - 2 = 0.10 reqs/s, average latency: 18s
-  - 4 = 0.12 reqs/s, average latency: 28s
-
-- Higher concurrency = slightly higher throughput, much higher latency
-
-🤔 We need metrics!

slides/k8s/ollama-metrics.md

@@ -1,273 +0,0 @@
-# Adding metrics
-
-We want multiple kinds of metrics:
-
-- instantaneous pod and node resource usage
-
-- historical resource usage (=graphs)
-
-- request duration
-
----
-
-## 1️⃣ Instantaneous resource usage
-
-- We're going to use metrics-server
-
-- Check if it's already installed:
-  ```bash
-  kubectl top nodes
-  ```
-
-- If we see a list of nodes, with CPU and RAM usage:
-
-  *great, metrics-server is installed!*
-
-- If we see `error: Metrics API not available`:
-
-  *metrics-server isn't installed, so we'll install it!*
-
----
-
-## Installing metrics-server
-
-- In a lot of places, this is done with a little bit of custom YAML
-
-  (derived from the [official installation instructions](https://github.com/kubernetes-sigs/metrics-server#installation))
-
-- We can also use a Helm chart:
-  ```bash
-    helm upgrade --install metrics-server metrics-server \
-      --create-namespace --namespace metrics-server \
-      --repo https://kubernetes-sigs.github.io/metrics-server/ \
-      --set args={--kubelet-insecure-tls=true}
-  ```
-
-- The `args` flag specified above should be sufficient on most clusters
-
-- After a minute, `kubectl top nodes` should show resource usage
-
----
-
-## 2️⃣ Historical resource usage
-
-- We're going to use Prometheus (specifically: kube-prometheus-stack)
-
-- This is a Helm chart bundling:
-
-  - Prometheus
-
-  - multiple exporters (node, kube-state-metrics...)
-
-  - Grafana
-
-  - a handful of Grafana dashboards
-
-- Open Source
-
-- Commercial alternatives: Datadog, New Relic...
-
----
-
-## Installing kube-prometheus-stack
-
-We're going to expose both Prometheus and Grafana with a NodePort:
-
-```bash
-helm upgrade --install --repo https://prometheus-community.github.io/helm-charts \
-  promstack kube-prometheus-stack \
-  --namespace prom-system --create-namespace \
-  --set prometheus.service.type=NodePort \
-  --set grafana.service.type=NodePort \
-  --set prometheus.prometheusSpec.podMonitorSelectorNilUsesHelmValues=false \
-  --set prometheus.prometheusSpec.serviceMonitorSelectorNilUsesHelmValues=false \
-  #
-```
-
-This chart installation can take a while (up to a couple of minutes).
-
----
-
-class: extra-details
-
-## `...NilUsersHelmValues=false` ???
-
-- kube-prometheus-stack uses the "Prometheus Operator"
-
-- To configure "scrape targets", we create PodMonitor or ServiceMonitor resources
-
-- By default, the Prometheus Operator will only look at \*Monitors with the right labels
-
-- Our extra options mean "use all the Monitors that you find!"
-
----
-
-## Connecting to Grafana
-
-Check the NodePort allocated to Grafana:
-
-```bash
-kubectl get service promstack-grafana --namespace prom-system
-```
-
-Get the public address of one of our nodes:
-
-```bash
-kubectl get nodes -o wide
-```
-
-In a browser, connect to the public address of any node, on the node port.
-
-The default login and password are `admin` / `prom-operator`.
-
-Check the dashboard "Kubernetes / Compute Resources / Namespace (Pods)".
-
-Select a namespace and see the CPU and RAM usage for the pods in that namespace.
-
----
-
-## 3️⃣ Request duration
-
-- Unfortunately, as of November 2024, ollama doesn't expose metrics
-
-  (there is ongoing discussion about it: [issue 3144][3144], [PR 6537][6537])
-
-- There are some [garbage AI-generated blog posts claiming otherwise][garbage]
-
-  (but it's AI-generated, so it bears no connection to truth whatsoever)
-
-- So, what can we do?
-
-[3144]: https://github.com/ollama/ollama/issues/3144#issuecomment-2153184254
-[6537]: https://github.com/ollama/ollama/pull/6537
-[garbage]: https://www.arsturn.com/blog/setting-up-ollama-prometheus-metrics
-
----
-
-## HAProxy to the rescue
-
-- HAProxy is a proxy that can handle TCP, HTTP, and more
-
-- It can expose detailed Prometheus metrics about HTTP requests
-
-- The plan: add a sidecar HAProxy to each Ollama container
-
-- For that, we need to give up on the Ollama Helm chart
-
-  (and go back to basic manifests)
-
----
-
-## 🙋 Choose your own adventure
-
-Do we want to...
-
-- write all the corresponding manifests?
-
-- look at pre-written manifests and explain how they work?
-
-- apply the manifests and carry on?
-
----
-
-## 🏗️ Let's build something!
-
-- If you have created Deployments / Services: clean them up first!
-
-- Deploy Ollama with a sidecar HAProxy (sample configuration on next slide)
-
-- Run a short benchmark campaign
-
-  (e.g. scale to 4 pods, try 4/8/16 parallel requests, 2 minutes each)
-
-- Check live resource usage with `kubectl top nodes` / `kubectl top pods`
-
-- Check historical usage with the Grafana dashboards
-
-  (for HAProxy metrics, you can use [Grafana dashboard 12693, HAProxy 2 Full][grafana-12693])
-
-- If you don't want to write the manifests, you can use [these][ollama-yaml]
-
-[grafana-12693]: https://grafana.com/grafana/dashboards/12693-haproxy-2-full/
-[ollama-yaml]: https://github.com/jpetazzo/beyond-load-balancers/tree/main/ollama
-
----
-
-```
-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
-```
-
----
-
-class: extra-details
-
-## ⚠️ Connection queues
-
-- HAProxy will happily queue *many* connections
-
-- If a client sends a request, then disconnects:
-
-  - the request stays in the queue
-
-  - the request gets processed by the backend
-
-  - eventually, when the backend starts sending the reply, the connection is closed
-
-- This can result in a backlog of queries that take a long time to resorb
-
-- To avoid that: `option abortonclose` (see [HAProxy docs for details][abortonclose])
-
-- Note that the issue is less severe when replies are streamed
-
-[abortonclose]: https://www.haproxy.com/documentation/haproxy-configuration-manual/latest/#4-option%20abortonclose
-
----
-
-class: extra-details
-
-## Ad-hoc HAProxy dashboard
-
-- To consolidate all frontend and backend queues on a single graph:
-
-  - query: `haproxy_frontend_current_sessions`
-
-  - legend: `{{namespace}}/{{pod}}/{{proxy}}`
-
-  - options, "Color scheme", select "Classic palette (by series name)"
-
----
-
-## What do we see?
-
-- Imperfect load balancing
-
-- Some backends receive more requests than others
-
-- Sometimes, some backends are idle while others are busy
-
-- However, CPU utilization on the node is maxed out
-
-- This is because our node is oversubscribed
-
-- This is because we haven't specified resource requests/limits (yet)
-
-  (we'll do that later!)

slides/k8s/ollama-reqlim.md

@@ -1,155 +0,0 @@
-## Setting resource requests and limits
-
-- Thanks to *requests*:
-
-  - our pods will have resources *reserved* for them
-
-  - we won't pack too many pods on a single node
-
-  - cluster autoscaling will trigger when needed (if possible!)
-
-- Thanks to *limits*:
-
-  - our pods won't use more than a given amount of resources
-
-  - they won't use up all the available resources on the node
-
-  - behavior will be more consistent between loaded and unloaded state
-
----
-
-## Memory
-
-- Personal advice: set request and limit to the same value
-
-- Check current or historical usage and add a bit of padding
-
-  (the more data historical data we have, the less padding we need)
-
-- Consider 10% padding for "dataless" pods, more for pods with data
-
-  (so that the pod has "reserves" for page cache usage)
-
-⚠️ Pods hitting their memory limit will be **killed!**
-
----
-
-## CPU
-
-- It's not necessary to set requests and limits to the same value
-
-  (this would cause a lot of waste for idle workloads)
-
-- Let's see a few possible strategies!
-
----
-
-## CPU for mostly idle pods
-
-E.g.: web services, workers handling very few requests...
-
-- Set the limit to at least one whole core
-    
-  (to avoid throttling, especially on bursty workloads)
-
-- Requests can be very low (e.g. 0.1 core)
-
-⚠️ If requests are too low and the node is very loaded,
-the pod will slow down significantly!
-
-(Because CPU cycles are allocated proportionally to CPU requests.)
-
----
-
-## Inelastic CPU-hungry pods
-
-- Pods with a fixed number of threads:
-
-  *set requests and limits to that number of threads*
-
-- Pods where a specific level of performance needs to be guaranteed:
-
-  *set requests and limits to the number of cores providing that performance*
-
-⚠️ If you set limits to higher levels, performance will be unpredictible!
-
-(You'll get good performance when the node has extra cycles.)
-
----
-
-## Elastic CPU-hungry pods
-
-- Pods that could potentially use all the cores
-
-  (e.g. machine learning training and inference, depending on the models)
-
-- Decide how many pods per node you want to pack
-
-- Set CPU requests as a fraction of the number of cores of the nodes
-
-  (minus some padding)
-
-- Example:
-
-  - nodes with 32 cores
-  - we want 4 pods per node
-  - CPU request: 7.5 cores
-
-- Set limits to a higher level (up to node size)
-
----
-
-## In practice
-
-- Check memory usage of our Ollama pods:
-  ```bash
-  kubectl top pods
-  ```
-  (Or even better, look at historical usage in Prometheus or Grafana!)
-
-- Check how many cores we have on our nodes:
-  ```bash
-  kubectl get nodes -o json | jq .items[].status.capacity.cpu
-  kubectl get nodes -o custom-columns=NAME:metadata.name,CPU:status.capacity.cpu
-  ```
-
-- Let's decide that we want two Ollama pods per node
-
-- What requests/limits should we set?
-
----
-
-## Setting resources for Ollama
-
-- Assumptions:
-
-  - we want two pods per node
-  - each pod uses ~1500MiB RAM
-  - nodes have 4 cores
-
-- We'll set memory requests and limits to 2G
-
-- We'll set CPU requests to 1.5 (4 cores / 2 pods, minus padding)
-
-- We'll set CPU limits to twice the requests
-
-```bash
-kubectl set resources deployment ollama \
-  --requests=cpu=1.5,memory=2G \
-  --limits=cpu=3,memory=2G
-```
-
-⚠️ If you have an HAProxy side car, this will set its resources too!
-
----
-
-## Results
-
-- After setting these resource requests, we should see cluster autoscaling
-
-- If not: scale up the Ollama Deployment to at least 3 replicas
-
-- Check cluster autoscaler status with:
-  ```bash
-  kubectl describe configmap --namespace kube-system cluster-autoscaler-status
-  ```

slides/k8s/operators.md

@@ -40,7 +40,7 @@ using Kubernetes manifests and tooling.*
 
 - etc.
 
-[ArgoCD]: https://argoproj.github.io/cd/
+[ArgoCD]: https://github.com/argoproj/argo-cd
 [AWS]: https://aws-controllers-k8s.github.io/community/docs/community/services/
 [cert-manager]: https://cert-manager.io/
 [External Secrets Operator]: https://external-secrets.io/

slides/k8s/queue-architecture.md

@@ -1,210 +0,0 @@
-# Message Queue Architecture
-
-There are (at least) three ways to distribute load:
-
-- load balancers
-
-- batch jobs
-
-- message queues
-
-Let's do a quick review of their pros/cons!
-
----
-
-## 1️⃣ Load balancers
-
-<pre class="mermaid">
-  flowchart TD
-    Client["Client"] ---> LB["Load balancer"]
-    LB ---> B1["Backend"] & B2["Backend"] & B3["Backend"]
-</pre>
-
----
-
-## Load balancers
-
-- Latency: ~milliseconds (network latency)
-
-- Overhead: very low (one extra network hop, one log message?)
-
-- Great for short requests (a few milliseconds to a minute)
-
-- Supported out of the box by the Kubernetes Service Proxy
-
-  (by default, this is `kube-proxy`)
-
-- Suboptimal resource utilization due to imperfect balancing
-
-  (especially when there are multiple load balancers) 
-
----
-
-## 2️⃣ Batch jobs
-
-<pre class="mermaid">
-  flowchart TD
-  subgraph K["Kubernetes Control Plane"]
-    J1["Job"]@{ shape: card}
-    J2["Job"]@{ shape: card}
-    J3["..."]@{ shape: text}
-    J4["Job"]@{ shape: card}
-  end
-  C["Client"] ---> K
-  K <---> N1["Node"] & N2["Node"] & N3["Node"]
-</pre>
-
----
-
-## Batch jobs
-
-- Latency: a few seconds (many Kubernetes controllers involved)
-
-- Overhead: significant due to all the moving pieces involved
-
-  (job controller, scheduler, kubelet; many writes to etcd and logs)
-
-- Great for long requests (a few minutes to a few days)
-
-- Supported out of the box by Kubernetes
-
-  (`kubectl create job hello --image alpine -- sleep 60`)
-
-- Asynchronous processing requires some refactoring
-
-  (we don't get the response immediately)
-
----
-
-## 3️⃣ Message queues
-
-<pre class="mermaid">
-  flowchart TD
-  subgraph Q["Message queue"]
-    M1["Message"]@{ shape: card}
-    M2["Message"]@{ shape: card}
-    M3["..."]@{ shape: text}
-    M4["Message"]@{ shape: card}
-  end
-  C["Client"] ---> Q
-  Q <---> W1["Worker"] & W2["Worker"] & W3["Worker"]
-</pre>
-
----
-
-## Message queues
-
-- Latency: a few milliseconds to a few seconds
-
-- Overhead: intermediate
-
-  (very low with e.g. Redis, higher with e.g. Kafka)
-
-- Great for all except very short requests
-
-- Requires additional setup
-
-- Asynchronous processing requires some refactoring
-
----
-
-## Dealing with errors
-
-- Load balancers
-
-  - errors reported immediately (client must retry)
-  - some load balancers can retry automatically
-
-- Batch jobs
-
-  - Kubernetes retries automatically
-  - after `backoffLimit` retries, Job is marked as failed
-
-- Message queues
-
-  - some queues have a concept of "acknowledgement"
-  - some queues have a concept of "dead letter queue"
-  - some extra work is required
-
----
-
-## Some queue brokers
-
-- Redis (with e.g. RPUSH, BLPOP)
-
-  *light, fast, easy to setup... no durability guarantee, no acknowledgement, no dead letter queue*
-
-- Kafka
-
-  *heavy, complex to setup... strong deliverability guarantee, full featured*
-
-- RabbitMQ
-
-  *somewhat in-between Redis and Kafka*
-
-- SQL databases
-
-  *often requires polling, which adds extra latency; not as scalable as a "true" broker*
-
----
-
-## More queue brokers
-
-Many cloud providers offer hosted message queues (e.g.: Amazon SQS).
-
-These are usually great options, with some drawbacks:
-
-- vendor lock-in
-
-- setting up extra environments (testing, staging...) can be more complex
-
-(Setting up a singleton environment is usually very easy, thanks to web UI, CLI, etc.; setting up extra environments and assigning the right permissions with e.g. IAC is usually significantly more complex.)
-
----
-
-## Implementing a message queue
-
-1. Pick a broker
-
-2. Deploy the broker
-
-3. Set up the queue
-
-4. Refactor our code
-
----
-
-## Code refactoring (client)
-
-Before:
-```python
-response = http.POST("http://api", payload=Request(...))
-```
-
-After:
-```python
-client = queue.connect(...)
-client.publish(message=Request(...))
-```
-
-Note: we don't get the response right way (if at all)!
-
----
-
-## Code refactoring (server)
-
-Before:
-```python
-server = http.server(request_handler=handler)
-server.listen("80")
-server.run()
-```
-
-After:
-```python
-client = queue.connect(...)
-while true:
-  message = client.consume()
-  response = handler(message)
-  # Write the response somewhere
-```

slides/k8s/resource-limits.md

@@ -194,7 +194,7 @@ class: extra-details
 
   - use [static CPU manager policy](https://kubernetes.io/docs/tasks/administer-cluster/cpu-management-policies/#static-policy)
 
-For more details, check [this blog post](https://erickhun.com/posts/kubernetes-faster-services-no-cpu-limits/) or these: ([part 1](https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/), [part 2](https://engineering.indeedblog.com/blog/2019/12/cpu-throttling-regression-fix/)).
+For more details, check [this blog post](https://erickhun.com/posts/kubernetes-faster-services-no-cpu-limits/) or these ones ([part 1](https://engineering.indeedblog.com/blog/2019/12/unthrottled-fixing-cpu-limits-in-the-cloud/), [part 2](https://engineering.indeedblog.com/blog/2019/12/cpu-throttling-regression-fix/)).
 
 ---
 

slides/k8s/service-types.md

@@ -352,87 +352,6 @@ class: pic
 class: pic
 ![](images/kubernetes-services/64-ING-nolocal.png)
 
----
-
-class: extra-details
-
-## Traffic engineering
-
-- By default, connections to a ClusterIP or a NodePort are load balanced
-  across all the backends of their Service
-
-- This can incur extra network hops (which add latency)
-
-- To remove that extra hop, multiple mechanisms are available:
-
-  - `spec.externalTrafficPolicy`
-
-  - `spec.internalTrafficPolicy`
-
-  - [Topology aware routing](https://kubernetes.io/docs/concepts/services-networking/topology-aware-routing/) annotation (beta)
-
-  - `spec.trafficDistribution` (alpha in 1.30, beta in 1.31)
-
----
-
-## `internal / externalTrafficPolicy`
-
-- Applies respectively to `ClusterIP` and `NodePort` connections
-
-- Can be set to `Cluster` or `Local`
-
-- `Cluster`: load balance connections across all backends (default)
-
-- `Local`: load balance connections to local backends (on the same node)
-
-- With `Local`, if there is no local backend, the connection will fail!
-
-  (the parameter expresses a "hard rule", not a preference)
-
-- Example: `externalTrafficPolicy: Local` for Ingress controllers
-
-  (as shown on earlier diagrams)
-
----
-
-class: extra-details
-
-## Topology aware routing
-
-- In beta since Kubernetes 1.23
-
-- Enabled with annotation `service.kubernetes.io/topology-mode=Auto` 
-
-- Relies on node label `topology.kubernetes.io/zone`
-
-- Kubernetes service proxy will try to keep connections within a zone
-
-  (connections made by a pod in zone `a` will be sent to pods in zone `a`)
-
-- ...Except if there are no pods in the zone (then fallback to all zones)
-
-- This can mess up autoscaling!
-
----
-
-class: extra-details
-
-## `spec.trafficDistribution`
-
-- [KEP4444, Traffic Distribution for Services][kep4444]
-
-- In alpha since Kubernetes 1.30, beta since Kubernetes 1.31
-
-- Should eventually supersede topology aware routing
-
-- Can be set to `PreferClose` (more values might be supported later)
-
-- The meaning of `PreferClose` is implementation dependent
-
-  (with kube-proxy, it should work like topology aware routing: stay in a zone)
-
-[kep4444]: https://github.com/kubernetes/enhancements/issues/4444
-
 ???
 
 :EN:- Service types: ClusterIP, NodePort, LoadBalancer

slides/k8s/setup-devel.md

@@ -144,30 +144,6 @@
 
 ---
 
-## [Orbstack](https://orbstack.dev/)
-
-- Mac only
-
-- Runs Docker containers, Kubernetes, and Linux virtual machines
-
-- Emphasis on speed and energy usage (battery life)
-
-- Great support for `ClusterIP` and `LoadBalancer` services
-
-- Free for personal use; paid product otherwise
-
----
-
-## [Podman Desktop](https://podman-desktop.io/)
-
-- Available on Linux, Mac, and Windows
-
-- Free and open-source
-
-- Doesn't support Kubernetes directly, but [supports KinD](https://podman-desktop.io/docs/kind)
-
----
-
 ## [Rancher Desktop](https://rancherdesktop.io/)
 
 - Available on Linux, Mac, and Windows
@@ -182,6 +158,8 @@
 
 - Emphasis on ease of use (like Docker Desktop)
 
+- Relatively young product (first release in May 2021)
+
 - Based on k3s and other proven components
 
 ---

slides/k8s/user-cert.md

@@ -77,7 +77,7 @@ This is the flag that we're looking for:
 
 - We only need to transfer the CSR (Certificate Signing Request) to the CA
 
-  (we never need to expose the private key)
+  (we never need to expoes the private key)
 
 .lab[
 

slides/k8s/ytt.md

@@ -245,9 +245,9 @@
 
   - command-line flags
 
-- Precedence of the different methods is defined in the [docs][data-values-merge-order]
+- Precedence of the different methods is defined in the [docs]
 
-[data-values-merge-order]: https://carvel.dev/ytt/docs/v0.41.0/ytt-data-values/#data-values-merge-order
+[docs]: https://carvel.dev/ytt/docs/v0.41.0/ytt-data-values/#data-values-merge-order
 
 ---
 
@@ -462,13 +462,13 @@ spec:
 
 - By default, `#@overlay/match` must find *exactly* one match
 
-  (that can be changed by specifying `expects=...`, `missing_ok=True`... see [docs][docs-ytt-overlaymatch])
+  (that can be changed by specifying `expects=...`, `missing_ok=True`... see [docs])
 
 - By default, the specified fields (here, `spec.replicas`) must exist
 
   (that can also be changed by annotating the optional fields)
 
-[docs-ytt-overlaymatch]: https://carvel.dev/ytt/docs/v0.41.0/lang-ref-ytt-overlay/#overlaymatch
+[docs]: https://carvel.dev/ytt/docs/v0.41.0/lang-ref-ytt-overlay/#overlaymatch
 
 ---
 
@@ -573,7 +573,7 @@ metadata:
 
 ## Overlays vs data values
 
-- The documentation has a [detailed discussion][data-values-vs-overlays] about this question
+- The documentation has a [detailed discussion][docs] about this question
 
 - In short:
 
@@ -587,7 +587,7 @@ metadata:
 
   (keeping in mind that overlays are harder to write/understand/maintain)
 
-[data-values-vs-overlays]: https://carvel.dev/ytt/docs/v0.41.0/data-values-vs-overlays/
+[docs]: https://carvel.dev/ytt/docs/v0.41.0/data-values-vs-overlays/
 
 ---
 

slides/logistics-template.md

@@ -4,7 +4,7 @@
 
 - Sur scène : Jérôme ([@jpetazzo@hachyderm.io])
 
-- En backstage : Alexandre, Antoine, Aurélien (x2), Benjamin, David, Kostas, Nicolas, Paul, Sébastien, Thibault...
+- En backstage : Alexandre, Antoine, Aurélien (x2), Benjamin (x2), David, Kostas, Nicolas, Paul, Sébastien, Thibault...
 
 - Horaires : tous les jours de 9h à 13h
 
@@ -57,22 +57,24 @@
 
 ## Allô Docker¹ ?
 
+<!--
+
 - Chaque après-midi : une heure de questions/réponses ouvertes !
 
   (sauf le dernier jour)
 
-- Une heure de questions/réponses ouvertes !
+-->
+
+- Une heure de questions/réposnes ouvertes !
+
+- Mercredi: 15h00-16h00
 
 - Jeudi: 16h00-17h00
 
-- Vendredi: 15h00-16h00
-
-- Lundi: 15h30-16h30
-
 - Sur [Jitsi][jitsi] (lien "visioconf" sur le portail de formation)
 
 .footnote[¹Clin d'œil à l'excellent ["Quoi de neuf Docker?"][qdnd] de l'excellent [Nicolas Deloof][ndeloof] 🙂]
 
 [qdnd]: https://www.youtube.com/channel/UCOAhkxpryr_BKybt9wIw-NQ
 [ndeloof]: https://github.com/ndeloof
-[jitsi]: https://training.enix.io/jitsi-magic/jitsi.container.training/Janvier2025
+[jitsi]: https://training.enix.io/jitsi-magic/jitsi.container.training/AlloDockerMai2024

slides/mlops.yml

@@ -1,44 +0,0 @@
-title: |
-  Asynchronous Architecture Patterns To Scale ML and Other High Latency Workloads on Kubernetes
-
-#chat: "[Slack](https://dockercommunity.slack.com/messages/C7GKACWDV)"
-#chat: "[Gitter](https://gitter.im/jpetazzo/workshop-yyyymmdd-city)"
-chat: "In person!"
-
-gitrepo: github.com/jpetazzo/container.training
-
-slides: https://FIXME.container.training/
-
-#slidenumberprefix: "#SomeHashTag — "
-
-exclude:
-- self-paced
-
-content:
-- shared/title.md
-- logistics.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
-- k8s/prereqs-advanced.md
-- k8s/handson-mlops.md
-- shared/connecting.md
-- k8s/mlops-headsup.md
-- shared/toc.md
--
-  - k8s/ollama-intro.md
-  - k8s/ollama-metrics.md
-  - k8s/queue-architecture.md
-  - k8s/bento-intro.md
--
-  - k8s/resource-limits.md
-  - k8s/cluster-autoscaler.md
-  - k8s/ollama-reqlim.md
-  - k8s/bento-hpa.md
-  - k8s/bento-rmq.md
-  - k8s/bento-cnpg.md
-  - k8s/helmfile.md
-  - shared/thankyou.md
-  - shared/contact.md

slides/shared/about-slides.md

@@ -46,7 +46,7 @@
 
   (let's say we'll keep them online at least 1 year, how about that?)
 
-- You can download the slides using this URL:
+- You can download the slides using that URL:
 
   @@ZIP@@
 

slides/shared/connecting.md

@@ -1,16 +1,15 @@
 class: in-person
 
-## Testing the connection to our lab environment
+## Connecting to our lab environment
 
 .lab[
 
-- Connect to your lab environment with your SSH client:
+- Log into the first VM (`node1`) with your SSH client:
   ```bash
   ssh `user`@`A.B.C.D`
-  ssh -p `32323` `user`@`A.B.C.D`
   ```
 
-  (Make sure to replace the highlighted values with the ones provided to you!)
+  (Replace `user` and `A.B.C.D` with the user and IP address provided to you)
 
 <!--
 ```bash
@@ -28,7 +27,7 @@ done
 
 You should see a prompt looking like this:
 ```
-[A.B.C.D] (...) user@machine ~
+[A.B.C.D] (...) user@node1 ~
 $
 ```
 If anything goes wrong — ask for help!
@@ -41,11 +40,9 @@ class: in-person
 
 - The shell history of the instructor is available online in real time
 
-- The instructor will provide you a "magic URL"
+- Note the IP address of the instructor's virtual machine (A.B.C.D)
 
-  (typically, the instructor's lab address on port 1088 or 30088)
-
-- Open that URL in your browser and you should see the history
+- Open http://A.B.C.D:1088 in your browser and you should see the history
 
 - The history is updated in real time
 
@@ -60,7 +57,7 @@ class: in-person
 ## Doing or re-doing the workshop on your own?
 
 - Use something like
-  [Play-With-Docker](https://labs.play-with-docker.com/) or
+  [Play-With-Docker](http://play-with-docker.com/) or
   [Play-With-Kubernetes](https://training.play-with-kubernetes.com/)
 
   Zero setup effort; but environment are short-lived and
@@ -103,13 +100,13 @@ class: self-paced
 
 .lab[
 
-- Go to https://labs.play-with-docker.com/
+- Go to http://www.play-with-docker.com/
 
 - Log in
 
 - Create your first node
 
-<!-- ```open https://labs.play-with-docker.com/``` -->
+<!-- ```open http://www.play-with-docker.com/``` -->
 
 ]
 
@@ -119,17 +116,21 @@ You will need a Docker ID to use Play-With-Docker.
 
 ---
 
-## We don't need to connect to ALL the nodes
+## We will (mostly) interact with node1 only
 
-- If your cluster has multiple nodes (e.g. `node1`, `node2`, ...):
+*These remarks apply only when using multiple nodes, of course.*
 
-  unless instructed, **all commands must be run from the first node**
+- Unless instructed, **all commands must be run from the first VM, `node1`**
 
-- We don't need to check out/copy code or manifests on other nodes
+- We will only check out/copy the code on `node1`
 
 - During normal operations, we do not need access to the other nodes
 
-  (but we could log into these nodes to troubleshoot or examine stuff)
+- If we had to troubleshoot issues, we would use a combination of:
+
+  - SSH (to access system logs, daemon status...)
+
+  - Docker API (to check running containers and container engine status)
 
 ---
 

slides/shared/contact.md

@@ -1,45 +0,0 @@
-name: contact
-
-## Contact information
-
-.column-half[
-Instructor:
-
-📛 Jérôme Petazzoni
-<br/>
-📩 jerome.petazzoni@gmail.com
-<br/>
-🔗 https://linkedin.com/in/jpetazzo
-<br/>
-🦣 https://hachyderm.io/@jpetazzo
-
-I can teach custom courses:
-
-- Docker, Kubernetes, MLOps
-- from intro level to "black belt"
-- on site or remotely
-
-Reach out if you're interested!
-]
-
-.column-half[
-Assistant:
-
-📛 AJ Bowen
-<br/>
-📩 aj@soulshake.net
-<br/>
-🔗 https://linkedin.com/in/ajbowen
-<br/>
-📃 https://github.com/soulshake
-
-
-I can consult on the following topics:
-
-- Kubernetes
-- CI/CD
-- Terraform & Infra-as-code
-- Docker
-- AWS
-]
-

slides/shared/pwd.md

@@ -1,6 +1,6 @@
 ## Using Play-With-Docker
 
-- Open a new browser tab to [labs.play-with-docker.com](https://labs.play-with-docker.com/)
+- Open a new browser tab to [www.play-with-docker.com](http://www.play-with-docker.com/)
 
 - Confirm that you're not a robot
 

slides/shared/qrcode.md

@@ -1,26 +0,0 @@
-<!-- QRcode generated with "qrencode -t UTF-8" -->
-
-.center[
-<pre style="padding-top: 0em; font-size: 18px; line-height: 20px;">
-█▀▀▀▀▀█ ▀▀▀█▄▀ ▀▄ ▀▄ ▀▄ ▄█▀ ▄ █▀▀▀▀▀█
-█ ███ █  ▀▄█ ▀▀▄█  ▄▀▀   ██▄▄ █ ███ █
-█ ▀▀▀ █  ▄▀█▀ █▀▀▀█ ▄█▀▄███ ▄ █ ▀▀▀ █
-▀▀▀▀▀▀▀ █▄▀ █▄█ ▀ █ █ ▀▄█▄▀ █ ▀▀▀▀▀▀▀
-▀▀ █▀▄▀  ▀▄ ▀▀█▄▄█▄▄ ▄▄▄   █▀ ▀▄▄  ▄▀
-▄█▄▀▄▀▀██▀  ▀▀██▄█  ▀▀▄█  ██▀ █▄█▀█▀▀
-▄ ▄▀▀ ▀ ▀█▀ ▄█▄▀▄▀ ▀ █ █ █▄▄▀▀▀▀▄█▄█▀
-█ ▀▀█▄▀▀█▀█ ▄▀ ▀▀ █▀▄ ▀▄  ██▄▀ ▄█ ▄▀█
-█▄▀▀▀ ▀▀ ███▀█▀▄ ▄▄█  ██   █▀▄▀▄ █▀▀▀
- ▄ █▀▄▀ ▄▀ ▄▀▄ ██ ▀▀█ ▄█ █▀▀▄█▀  ▄  █
-█▀▀▄▄ ▀ ▀ ▀▀█ ▀▀▀   ▀▀ █▀██▄▀▀▀███▄█▀
-█▀█▀▄█▀██ ██ ▀ █▄█▀ ▀ ██▀ ██▄  █▄█▄▄█
-█▀█▀▄▄▀▀▀▄▀▄▀ ▄█   ▄▀█ ▄▀▄ █▄ ▀▀▄█▄▄▀
-█▀█▄█ ▀  ▀▀▄█▀ █▄▀ █  ▄ ▄▀▄█ █▄▄█▄▄▀█
-▀ ▀▀  ▀▀█▄ ▀ ▀    ▄▄███▄  ▄ █▀▀▀█▀██
-█▀▀▀▀▀█  ▀██ █ █▀▀ ▀█▀██▄█▀▄█ ▀ █▄ ▄▀
-█ ███ █ █▄██▀ ▀▄▀▀▄█▀ ▄▄▀██▀▀▀█▀▀ ▄ ▀
-█ ▀▀▀ █ ▄█▀▀▀▀▄▀▄▄█ ▄▀█▀▄    ▀ ▀█ █▄█
-▀▀▀▀▀▀▀ ▀▀ ▀▀   ▀  ▀ ▀ ▀ ▀  ▀    ▀  ▀
-</pre>
-]
-

slides/workshop.css

@@ -221,10 +221,3 @@ td {
   padding: 0.1em 0.5em;
   background: #eee;
 }
-
-/* Use this to layout a slide in two columns */
-.column-half {
-  float: left;
-  width: 50%;
-}
-

slides/workshop.html

@@ -32,19 +32,7 @@
         excludedClasses: [@@EXCLUDE@@]
       });
     </script>
-    <script type="module">
-      import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs';
-        mermaid.initialize({ startOnLoad: false });
-        slideshow.on('afterShowSlide', function (slide) {
-          mermaid.run({
-            nodes: document.querySelectorAll('div.remark-visible .mermaid'),
-          });
-        });
-        // Reminder, if you want to tinker with mermaid,
-        // you need to export it, for instance like this:
-        // window.mermaid = mermaid;
-    </script>
-
+    
     <!-- 
     These two scripts will be available only when loading the
     content using the pub/sub server. Otherwise, they'll just