docs(inventory): ntp_cluster has two members, edge-1 and edge-2

edge-2 is in [edge_host] and in the ntp_servers map of install-ntp-ha.yml
(BACKUP, prio 60) and answers NTP (stratum 2) on 10.2.30.184. The comment
still called edge-1 the only member.

Refs S28-14

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

ansible/docs/edge-host.md

@@ -164,7 +164,9 @@ role keeps logs off local flash and monitors wear:
 - **Docker logs to journald** (`docker-daemon.json`, `log-driver: journald`)
   instead of unbounded json files under `/var/lib/docker/containers`. Both
   compose services inherit it; `docker logs` still works.
-- **Grafana Alloy ships the journal to Loki** (`edge-alloy.service`). Its
+- **Grafana Alloy ships the journal to Loki** (`edge-alloy.service`, which
+  runs the upstream `grafana/alloy` image with `/run/log/journal` mounted
+  read-only; Arch's `grafana-alloy` package has no `loki.source.journal`). Its
   WAL/positions sit on `/run/alloy` (tmpfs), so the agent writes nothing to
   the eMMC either. Net effect: no log writes hit local flash — the trade-off
   is that logs are RAM-only and lost on reboot unless already shipped.

ansible/inventory/pve_hosts.yml

@@ -22,6 +22,7 @@ proxy-2.renner.uno ansible_host=proxy-2.nb.renner.uno ansible_user=root
 # sub-interface. Nothing here assumes any peripheral is attached.
 [edge_host]
 edge-1.iot.renner.uno ansible_user=root
+edge-2.iot.renner.uno ansible_user=root
 
 # Synology NAS (DSM): nas-1 RS1221+ on site, nas-2 DS1522+ off site.
 [synology_nas]
@@ -48,20 +49,11 @@ edge-1.iot.renner.uno
 zwave_gateway
 heating_can
 
-# NTP servers. edge-1 was added here so the role would survive the PVE hosts
-# being retired for bare-metal Talos, which cannot run chrony or keepalived
-# itself. That retirement has now happened, so edge-1 is the ONLY member.
-#
-# THIS IS NO LONGER HIGHLY AVAILABLE. The group was jupiter (MASTER, prio 100),
-# saturn (90), neptune (80) and edge-1 (BACKUP, 70); the first three are gone.
-# A single VRRP member takes the address regardless of its configured state, so
-# the service address is still served, but by one thin client with
-# no failover behind it. install-ntp-ha.yml still carries the four-host
-# ntp_servers priority map, which now describes hosts that do not exist.
-#
-# Restoring redundancy needs a second chrony host that is not a Talos node.
-# See plays/install-ntp-ha.yml for why keepalived is scoped more narrowly than
-# chrony within this group.
+# NTP servers: every edge host (edge-1 BACKUP prio 70, edge-2 BACKUP prio 60;
+# see the ntp_servers map in plays/install-ntp-ha.yml). Talos nodes cannot run
+# chrony or keepalived. The jupiter/saturn/neptune entries in that map
+# describe retired PVE hosts. See plays/install-ntp-ha.yml for why keepalived
+# is scoped more narrowly than chrony within this group.
 [ntp_cluster:children]
 edge_host
 
@@ -73,6 +65,7 @@ proxy-1.renner.uno
 proxy-2.renner.uno
 netbird.renner.uno
 edge-1.iot.renner.uno
+edge-2.iot.renner.uno
 nas-1.renner.uno
 nas-2.renner.uno
 

ansible/plays/install-edge-host.yml

@@ -34,6 +34,7 @@
   roles:
     - certificates
     - common
+    - pacman-cache
     - edge-flash-wear
     - docker-install
     - edge-log-shipper

ansible/plays/install-ntp-ha.yml

@@ -83,6 +83,9 @@
       edge-1.iot.renner.uno:
         priority: 70
         state: "BACKUP"
+      edge-2.iot.renner.uno:
+        priority: 60
+        state: "BACKUP"
 
   roles:
     - role: chrony-ntp-server

ansible/roles/edge-log-shipper/defaults/main.yml

@@ -7,7 +7,9 @@
 
 edge_alloy_config_file: /etc/alloy/edge.alloy
 edge_alloy_http_port: 12345
-edge_alloy_bin: /usr/bin/grafana-alloy   # Arch `grafana-alloy` pkg names the binary this, not `alloy`
+# Upstream image: Arch's grafana-alloy 1.21 is built without
+# loki.source.journal. Renovate-tracked (customManagers in renovate.json).
+edge_alloy_image: grafana/alloy:v1.21.3@sha256:8ab871206bd2d8f89277f53abffee5f452a293980788d52f85fa183a87a505a4
 edge_loki_push_url: "https://loki.renner.uno/loki/api/v1/push"
 edge_loki_username: edge-1
 edge_alloy_labels:

ansible/roles/edge-log-shipper/tasks/main.yml

@@ -6,15 +6,18 @@
 # directly, so one journal source covers everything. Alloy s storage/WAL sits
 # on /run (tmpfs) so it does not write to flash either.
 
-- name: Install grafana-alloy
+# Alloy runs from the upstream image (see edge-alloy.service); the Arch package
+# lacks journal support.
+- name: Remove the grafana-alloy package
   ansible.builtin.package:
     name: grafana-alloy
-    state: present
+    state: absent
 
 - name: Create alloy system group
   ansible.builtin.group:
     name: alloy
     system: true
+  register: edge_alloy_group
 
 - name: Create alloy system user
   ansible.builtin.user:
@@ -24,6 +27,25 @@
     system: true
     create_home: false
     shell: /usr/bin/nologin
+  register: edge_alloy_user
+
+- name: Look up the systemd-journal group
+  ansible.builtin.getent:
+    database: group
+    key: systemd-journal
+
+- name: Set the container identity
+  ansible.builtin.set_fact:
+    edge_alloy_uid: "{{ edge_alloy_user.uid }}"
+    edge_alloy_gid: "{{ edge_alloy_group.gid }}"
+    edge_alloy_journal_gid: "{{ ansible_facts.getent_group['systemd-journal'][1] }}"
+
+- name: Pull the alloy image
+  ansible.builtin.command:
+    argv: [docker, pull, "{{ edge_alloy_image }}"]
+  register: edge_alloy_pull
+  changed_when: "'Downloaded newer image' in edge_alloy_pull.stdout"
+  notify: Restart alloy
 
 - name: Create alloy config directory
   ansible.builtin.file:

ansible/roles/edge-log-shipper/templates/edge-alloy.service.j2

@@ -1,32 +1,35 @@
 [Unit]
-Description=Grafana Alloy (edge-1 log shipper -> Loki)
+Description=Grafana Alloy (journal -> Loki)
 Documentation=https://grafana.com/docs/alloy/
-After=network-online.target
+After=docker.service network-online.target
+Requires=docker.service
 Wants=network-online.target
 
 [Service]
 Type=simple
-User=alloy
-Group=alloy
-# Read the (volatile) systemd journal.
-SupplementaryGroups=systemd-journal
-# WAL + positions on tmpfs so the agent never writes to the eMMC. %t is the
-# runtime dir root (/run); RuntimeDirectory creates /run/alloy owned by us.
-RuntimeDirectory=alloy
-ExecStart={{ edge_alloy_bin }} run \
+# WAL + positions on tmpfs so the agent never writes to the eMMC.
+ExecStartPre=/usr/bin/install -d -o alloy -g alloy -m 0750 /run/alloy
+ExecStartPre=-/usr/bin/docker rm -f edge-alloy
+# Attached run with --log-driver none: the container's output reaches the
+# journal once, through this unit.
+ExecStart=/usr/bin/docker run --rm --name edge-alloy \
+  --log-driver none \
+  --network host \
+  --user {{ edge_alloy_uid }}:{{ edge_alloy_gid }} \
+  --group-add {{ edge_alloy_journal_gid }} \
+  --read-only --tmpfs /tmp \
+  --cap-drop ALL --security-opt no-new-privileges \
+  -v /run/log/journal:/run/log/journal:ro \
+  -v /etc/machine-id:/etc/machine-id:ro \
+  -v {{ edge_alloy_config_file }}:/etc/alloy/config.alloy:ro \
+  -v /run/alloy:/var/lib/alloy \
+  {{ edge_alloy_image }} run \
   --server.http.listen-addr=127.0.0.1:{{ edge_alloy_http_port }} \
-  --storage.path=%t/alloy \
-  {{ edge_alloy_config_file }}
-ExecReload=/bin/kill -HUP $MAINPID
-Restart=on-failure
+  --storage.path=/var/lib/alloy \
+  /etc/alloy/config.alloy
+ExecStop=/usr/bin/docker stop edge-alloy
+Restart=always
 RestartSec=10s
-LimitNOFILE=65536
-
-# Hardening (bare metal, no LXC namespace limits here).
-NoNewPrivileges=yes
-ProtectSystem=strict
-ProtectHome=yes
-PrivateTmp=yes
 
 [Install]
 WantedBy=multi-user.target

ansible/roles/mqtt-bridge/defaults/main.yml

@@ -16,7 +16,7 @@ edge_mqtt_bridge_cafile: /etc/ssl/certs/ca-certificates.crt
 # kubernetes/apps/home-assistant/mqtt-accounts.yaml). The controller pushes
 # its password to edge-mqtt-cred and rotates it when the bridge reports
 # "not connected"; there is no copy in ansible-vault.
-edge_mqtt_bridge_account: edge-1
+edge_mqtt_bridge_account: "{{ inventory_hostname_short }}"
 # HTTPS port of edge-mqtt-cred (esp32 device API, mTLS). Only a client
 # certificate from the MQTT CA with this CN is accepted.
 edge_mqtt_cred_port: 8443

ansible/roles/mqtt-bridge/templates/edge-1-bridge.conf.in.j2

@@ -7,7 +7,7 @@ connection {{ edge_mqtt_bridge_account }}
 address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
 bridge_cafile {{ edge_mqtt_bridge_cafile }}
 bridge_insecure false
-remote_clientid edge1-bridge
+remote_clientid {{ edge_mqtt_bridge_account | replace('-', '') }}-bridge
 cleansession false
 try_private true
 restart_timeout 5 30

ansible/roles/pacman-cache/files/pacman-cache.hook

@@ -0,0 +1,14 @@
+# Managed by ansible (roles/pacman-cache).
+# Downloaded packages are not kept; older versions come from the Arch Linux
+# Archive.
+[Trigger]
+Operation = Install
+Operation = Upgrade
+Operation = Remove
+Type = Package
+Target = *
+
+[Action]
+Description = Removing downloaded packages from the cache...
+When = PostTransaction
+Exec = /usr/bin/find /var/cache/pacman/pkg -mindepth 1 -delete

ansible/roles/pacman-cache/tasks/main.yml

@@ -0,0 +1,21 @@
+---
+# Keep the pacman package cache empty. pacman keeps every downloaded package;
+# on a 7 GB eMMC root the cache grows to gigabytes. Arch hosts only.
+
+- name: Ensure the pacman hook directory exists
+  ansible.builtin.file:
+    path: /etc/pacman.d/hooks
+    state: directory
+    mode: "0755"
+
+- name: Empty the package cache after every transaction
+  ansible.builtin.copy:
+    src: pacman-cache.hook
+    dest: /etc/pacman.d/hooks/pacman-cache.hook
+    mode: "0644"
+
+- name: Empty the package cache
+  ansible.builtin.command:
+    argv: [find, /var/cache/pacman/pkg, -mindepth, "1", -delete, -print]
+  register: pacman_cache_clean
+  changed_when: pacman_cache_clean.stdout | length > 0

ansible/roles/ssh-ca/tasks/main.yml

@@ -143,6 +143,12 @@
     group: root
     mode: "0644"
 
+- name: Install sudo
+  ansible.builtin.package:
+    name: sudo
+    state: present
+  when: not ssh_ca_synouser.stat.exists
+
 - name: Install the Claude sudo rules
   ansible.builtin.template:
     src: sudoers-claude.j2

images/edge-host-iso/airootfs/usr/local/bin/edge-install

@@ -57,7 +57,7 @@ mount --mkdir "$(part 1)" /mnt/boot
 
 # Everything the edge-host ansible role expects to find; the role itself
 # is applied over SSH after first boot (see ansible/docs/edge-host.md).
-pacstrap -K /mnt base linux linux-firmware intel-ucode openssh python git \
+pacstrap -K /mnt base linux linux-firmware intel-ucode openssh sudo python git \
   docker docker-compose
 
 genfstab -U /mnt >> /mnt/etc/fstab

kubernetes/apps/home-assistant/mqtt-accounts.yaml

@@ -61,6 +61,11 @@
   # No sml2mqtt/#: the SML meter reader is retired for good (owner,
   # 2026-09-19; grid data comes from the E380 on the CAN bus).
   acl: ["readwrite open3e/#"]
+# edge-2's local mosquitto bridge, same role and pinning as edge-1.
+- name: edge-2
+  auth: password
+  deliver: {esp32: "https://edge-2.iot.renner.uno:8443"}
+  acl: ["readwrite open3e/#"]
 # Shellies (REN-1017): one password account per device, pushed by the
 # controller through shelly-manager's per-device API. Name shelly-<id> =
 # shelly-manager device id. ACL as the former shared user `shellies`

kubernetes/infrastructure/network-policies/home-assistant-ns.yaml

@@ -516,6 +516,7 @@ spec:
               - matchPattern: "*"
     - toFQDNs:
         - matchName: "edge-1.iot.renner.uno"
+        - matchName: "edge-2.iot.renner.uno"
       toPorts:
         - ports:
             - port: "8443"