kubernetes/talos/patches/k8s-2.yaml

@@ -1,31 +1,99 @@
+# k8s-2 runs Talos directly on saturn's MS-01 hardware. Structurally identical
+# to k8s-1.yaml — see that file for the reasoning behind each choice; only the
+# serials, MACs and addresses differ. k8s-3 is still a Proxmox VM and keeps the
+# VM-era layout until neptune is converted.
 machine:
   network:
     hostname: k8s-2
-    # Shared control-plane VIP — see k8s-1.yaml for the busPath rationale.
-    interfaces:
-      - deviceSelector:
-          busPath: "0000:06:12.0"
-        dhcp: true
-        vip:
-          ip: 10.2.40.60
-      # v30iot: link only, no host addressing — see k8s-1.yaml.
-      - deviceSelector:
-          busPath: "0000:06:13.0"
-        dhcp: false
-      # See k8s-1.yaml for context on the dedicated Ceph cluster network.
-      - deviceSelector:
-          driver: i40e
-        addresses:
-          - 10.99.0.2/29
-        mtu: 9000
   sysctls:
-    # v30iot NIC carries no host addressing — see k8s-1.yaml.
+    # ens19 (VLAN 30, v30iot) is LINK ONLY — no host addressing. It is the
+    # macvlan parent for the v30iot pod attachments; host addresses on that L2
+    # make node replies bypass the UDM and break every UDM-DNATed flow.
     net.ipv6.conf.ens19.disable_ipv6: "1"
   install:
-    disk: /dev/vda
+    # Three NVMe drives are visible on bare metal. Select the installer target
+    # by serial so it cannot land on the OSD drive or on EPHEMERAL, whatever
+    # order the kernel enumerates them in — Talos and Proxmox do not agree on
+    # that order.
+    diskSelector:
+      serial: 50026B7382DA5F6E
   certSANs:
     - k8s-2.srv.renner.uno
   nodeLabels:
     topology.kubernetes.io/zone: saturn
 cluster:
   allowSchedulingOnControlPlanes: true
+---
+# EPHEMERAL (/var) goes on the retired Crucial P3, not the system disk. That
+# drive is at 81% of its rated endurance and is finished as an OSD, but
+# everything EPHEMERAL holds is reconstructible, so it is consumable in this
+# role. It also gives /var ~931 GB instead of the 64 GB the VM-era zvol had.
+#
+# ONLY TAKES EFFECT ON FIRST PROVISION. Talos applies volume configuration
+# solely when the volume does not yet exist; applied later it is silently
+# ignored and relocating needs a disk wipe and a boot from install media.
+#
+# Matched by serial deliberately: a broad selector such as
+# `disk.transport == 'nvme' && !system_disk` would match the PM983 as well.
+apiVersion: v1alpha1
+kind: VolumeConfig
+name: EPHEMERAL
+provisioning:
+  diskSelector:
+    match: disk.serial == '2332E86B74BC'
+  minSize: 50GiB
+  grow: true
+---
+# X710 port 0 carries the switch trunk and takes no addressing itself — the
+# port's untagged VLAN is not one this node belongs on. Management and v30iot
+# both ride it as tagged VLANs.
+#
+# Addressed by predictable kernel name, not by LinkAliasConfig. Aliases are
+# valid VLAN parents, but a selector matching zero links is skipped silently
+# and Talos disables default DHCP machine-wide as soon as any new-style network
+# document exists — so a silent miss leaves the node with no address on any
+# interface. See RUNBOOK-baremetal-conversion.md.
+apiVersion: v1alpha1
+kind: LinkConfig
+name: enp2s0f0np0
+up: true
+---
+# Management, VLAN 40. Node IP, etcd, the API and Ceph's public network.
+apiVersion: v1alpha1
+kind: VLANConfig
+name: mgmt0
+vlanID: 40
+parent: enp2s0f0np0
+up: true
+---
+apiVersion: v1alpha1
+kind: DHCPv4Config
+name: mgmt0
+---
+# Shared control-plane VIP, etcd-elected. Exposed via UniFi DNS as
+# k8s.renner.uno.
+apiVersion: v1alpha1
+kind: Layer2VIPConfig
+name: 10.2.40.60
+link: mgmt0
+---
+# Named ens19 on purpose: the four v30iot macvlan NADs hard-code
+# `master: ens19`, and k8s-3 still presents the VLAN as a virtio NIC of that
+# name. VLANConfig.name is free-form, so one set of NADs serves both.
+apiVersion: v1alpha1
+kind: VLANConfig
+name: ens19
+vlanID: 30
+parent: enp2s0f0np0
+up: true
+---
+# Dedicated Ceph cluster network on X710 port 1, VLAN 49 / 10.99.0.0/29,
+# untagged on the wire. OSD<->OSD replication only. Not routed off its own
+# segment and deliberately has no default route.
+apiVersion: v1alpha1
+kind: LinkConfig
+name: enp2s0f1np1
+up: true
+mtu: 9000
+addresses:
+  - address: 10.99.0.2/29