kubernetes/RUNBOOK-baremetal-conversion.md

@@ -198,7 +198,7 @@ talosctl gen secrets --from-controlplane-config cp.yaml -o secrets.yaml
 talosctl gen config homelab https://k8s.renner.uno:6443 \
   --with-secrets secrets.yaml --output-types controlplane \
   --config-patch @talos/patches/cluster.yaml \
-  --config-patch @talos/patches/registry-mirror.yaml \
+  --config-patch @talos/patches/containerd-layer-retention.yaml \
   --config-patch @talos/patches/k8s-N.yaml -o install.yaml
 ```
 

kubernetes/RUNBOOK-cold-rebuild.md

@@ -136,11 +136,18 @@ in `talos/patches/k8s-N.yaml`.
 
 ## Step 2 — talos: form the cluster + get kubeconfig
 
-**Do not use `kubernetes/bootstrap.sh talos`.** That phase is dead: it fails on
-a `cilium-cni.yaml` that no longer exists, and before that it failed because it
-passed the file whole (#581). Nobody has fixed it because nothing needs it —
-the procedure below is what is actually used. Its other phases — `flux`,
-`wait-apps` — are still used, in Steps 3, 5 and 6.
+`kubernetes/bootstrap.sh talos` does this, including the CNI install that used
+to be a hand-typed step. It was unusable for months because it passed
+`cilium-cni.yaml` whole and the file's `$patch: delete` document failed against
+a fresh config (#581); that file no longer exists, so the failure is gone with
+it.
+
+Verified as far as it can be without wiping a cluster: `talosctl gen config`
+with exactly the patches the script passes produces a config carrying
+`cni: none` and `proxy: disabled` that passes `talosctl validate --mode metal`.
+The apply-and-bootstrap half has not been exercised since the rewrite. Read the
+manual procedure below before running the script, so you know what it is doing
+and can take over at any step if it stops.
 
 The procedure below is what actually works, and is the same one
 `RUNBOOK-baremetal-conversion.md` uses.
@@ -160,7 +167,7 @@ for N in 1 2 3; do
   talosctl gen config homelab https://k8s.renner.uno:6443 \
     --with-secrets secrets.yaml --output-types controlplane \
     --config-patch @talos/patches/cluster.yaml \
-    --config-patch @talos/patches/registry-mirror.yaml \
+    --config-patch @talos/patches/containerd-layer-retention.yaml \
     --config-patch @talos/patches/k8s-$N.yaml -o install-k8s-$N.yaml
 done
 ```
@@ -224,6 +231,9 @@ place it is configured, and this installs from those same values so the cluster
 comes up on what git describes rather than on a second, drifting copy. See
 PROPOSAL-cilium-single-owner.md for why it works this way.
 
+`bootstrap.sh talos` already did this. What follows is the same thing by hand,
+for when the script stopped partway or you are not using it.
+
 Every input is read out of `helmrelease.yaml`. Nothing here is a version or a
 URL you have to keep in step with anything — copy the block as it stands:
 

kubernetes/bootstrap.sh

@@ -21,6 +21,13 @@ set -euo pipefail
 
 TALOS_DIR="$(cd "$(dirname "$0")/talos" && pwd)"
 REPO_ROOT="$(cd "$(dirname "$0")/.." && pwd)"
+# Cilium's single source of truth. Talos ships `cni: none` (talos/patches/
+# cluster.yaml) and nothing else, so the CNI has to be installed here, between
+# `talosctl bootstrap` and Flux — Flux's own controllers are pods and cannot
+# reconcile the network they need in order to start. Everything the install
+# needs is read out of this file at run time so there is no second copy of a
+# version or a value to keep in step. See PROPOSAL-cilium-single-owner.md.
+CILIUM_HR="$REPO_ROOT/kubernetes/infrastructure/cilium/helmrelease.yaml"
 ACCESS_STAGING="$REPO_ROOT/kubernetes/access-staging"
 NODES=(k8s-1 k8s-2 k8s-3)
 # No dedicated workers since the k8s-edge VM was retired (2026-07-02) —
@@ -82,9 +89,11 @@ if phase_runs talos; then
     echo -e "${YELLOW}=== Phase: Talos bootstrap ===${NC}"
     command -v talosctl >/dev/null || fail "talosctl not found"
     command -v kubectl >/dev/null  || fail "kubectl not found"
+    command -v helm >/dev/null   || fail "helm not found (needed to install the CNI)"
+    command -v yq >/dev/null     || fail "yq not found (needed to read the Cilium HelmRelease)"
     [[ -f "$TALOS_DIR/patches/cluster.yaml"         ]] || fail "cluster.yaml patch not found"
-    [[ -f "$TALOS_DIR/patches/cilium-cni.yaml"      ]] || fail "cilium-cni.yaml patch not found"
-    [[ -f "$TALOS_DIR/patches/registry-mirror.yaml" ]] || fail "registry-mirror.yaml patch not found"
+    [[ -f "$TALOS_DIR/patches/containerd-layer-retention.yaml" ]] || fail "containerd-layer-retention.yaml patch not found"
+    [[ -f "$CILIUM_HR"                              ]] || fail "cilium helmrelease not found at $CILIUM_HR"
 
     step 0 "Generating Talos configs..."
     TALOS_GEN_DIR=$(mktemp -d)
@@ -123,8 +132,7 @@ if phase_runs talos; then
             if err=$(talosctl apply-config --insecure -n "$node_ip" \
                 --file "$base_config" \
                 --config-patch "@$TALOS_DIR/patches/cluster.yaml" \
-                --config-patch "@$TALOS_DIR/patches/cilium-cni.yaml" \
-                --config-patch "@$TALOS_DIR/patches/registry-mirror.yaml" \
+                --config-patch "@$TALOS_DIR/patches/containerd-layer-retention.yaml" \
                 --config-patch "@$TALOS_DIR/patches/${node}.yaml" 2>&1); then
                 echo "    applied via $node_ip ${GREEN}(OK)${NC}"
                 return 0
@@ -174,6 +182,35 @@ if phase_runs talos; then
     done
     ok
 
+    step 0 "Installing Cilium (CNI)..."
+    # Must run before the node-Ready wait below: with `cni: none` the kubelet
+    # reports NotReady until a CNI is present, so that loop would time out.
+    #
+    # Chart repo, version constraint and values all come out of the HelmRelease
+    # so this cannot drift from what Flux will reconcile minutes later. helm
+    # accepts the semver range verbatim and resolves it the same way Flux does.
+    #
+    # serviceMonitor is the one override, and it is a bootstrap constraint
+    # rather than a value: its CRD arrives with the monitoring stack much
+    # later, and the object would fail to apply. Nothing else is overridden,
+    # which is what lets helm-controller adopt this release instead of
+    # replacing it.
+    CILIUM_VALUES=$(mktemp)
+    yq 'select(.kind == "HelmRelease") | .spec.values' "$CILIUM_HR" > "$CILIUM_VALUES"
+    grep -q 'policyMapMax' "$CILIUM_VALUES" \
+        || fail "extracted Cilium values look wrong (no policyMapMax) — check $CILIUM_HR"
+
+    helm repo add cilium "$(yq -r 'select(.kind == "HelmRepository") | .spec.url' "$CILIUM_HR")" >/dev/null
+    helm repo update cilium >/dev/null
+    helm upgrade --install cilium cilium/cilium \
+        --version "$(yq -r 'select(.kind == "HelmRelease") | .spec.chart.spec.version' "$CILIUM_HR")" \
+        --namespace kube-system \
+        -f "$CILIUM_VALUES" \
+        --set prometheus.serviceMonitor.enabled=false \
+        --wait --timeout 10m
+    rm -f "$CILIUM_VALUES"
+    ok
+
     step 0 "Waiting for K8s nodes..."
     expected=${#ALL_NODES[@]}
     for i in $(seq 1 60); do