Fix prod compose port collision and make ansible deploy re-runnable
docker-compose.prod.yml: compose merges `ports` by appending, so the prod override left the base file's 8888:8000 and 3000:3000 in place next to the 127.0.0.1-scoped ones. Each container tried to bind its port twice and the second bind failed with "address already in use", so c2-core and frontend could never start. It also meant the localhost-only binding never applied — both ports were published on every interface. Marked both `!override`, the same way mosquitto already used `!reset`. infra/ansible: - add the missing "Reload Caddy" handler; the Deploy Caddyfile task notified a handler that did not exist, which aborts the play - guard mkswap/swapon on whether /swapfile is already active, so a second run does not fail on "mounted" / "Device or resource busy" - git task now updates instead of clone-once, otherwise a re-run redeploys whatever code was on the VM at first clone - vault.yml.example: correct the registry token comment to read-only scope Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -12,9 +12,14 @@ services:
|
|||||||
restart: always
|
restart: always
|
||||||
ports: !reset [] # Remove the dev 1883:1883 mapping — internal only
|
ports: !reset [] # Remove the dev 1883:1883 mapping — internal only
|
||||||
|
|
||||||
|
# !override, not a plain list: compose MERGES `ports` by appending, so a plain
|
||||||
|
# list leaves the base file's "8888:8000" in place alongside this one. The
|
||||||
|
# container then tries to bind 8888 twice — 0.0.0.0 and 127.0.0.1 — and the
|
||||||
|
# second bind fails with "address already in use". It also silently defeated
|
||||||
|
# the whole point of this override, publishing the port on every interface.
|
||||||
c2-core:
|
c2-core:
|
||||||
restart: always
|
restart: always
|
||||||
ports:
|
ports: !override
|
||||||
- "127.0.0.1:8888:8000" # Caddy proxies, not exposed publicly
|
- "127.0.0.1:8888:8000" # Caddy proxies, not exposed publicly
|
||||||
|
|
||||||
discord-bot:
|
discord-bot:
|
||||||
@@ -22,5 +27,5 @@ services:
|
|||||||
|
|
||||||
frontend:
|
frontend:
|
||||||
restart: always
|
restart: always
|
||||||
ports:
|
ports: !override
|
||||||
- "127.0.0.1:3000:3000" # Caddy proxies, not exposed publicly
|
- "127.0.0.1:3000:3000" # Caddy proxies, not exposed publicly
|
||||||
|
|||||||
@@ -0,0 +1,13 @@
|
|||||||
|
---
|
||||||
|
# The "Deploy Caddyfile" task notifies this. Without this file the play aborts
|
||||||
|
# with "The requested handler 'Reload Caddy' was not found" — notify does not
|
||||||
|
# tolerate a missing handler.
|
||||||
|
#
|
||||||
|
# reloaded, not restarted: caddy reload swaps config with zero downtime and
|
||||||
|
# keeps existing TLS certs/connections; a restart drops every in-flight request.
|
||||||
|
|
||||||
|
- name: Reload Caddy
|
||||||
|
ansible.builtin.systemd_service:
|
||||||
|
name: caddy
|
||||||
|
state: reloaded
|
||||||
|
enabled: true
|
||||||
@@ -2,12 +2,19 @@
|
|||||||
# First-time setup: clone repo, write secrets, pull pre-built images and start stack.
|
# First-time setup: clone repo, write secrets, pull pre-built images and start stack.
|
||||||
# Images are built and pushed by Gitea CI — this role never builds on the VM.
|
# Images are built and pushed by Gitea CI — this role never builds on the VM.
|
||||||
|
|
||||||
- name: Clone repo (skipped if already present)
|
# update: true (was false) — with update disabled, every re-run of this playbook
|
||||||
|
# redeployed the code that happened to be on the VM at first clone, so any fix
|
||||||
|
# pushed to main was invisible here and the only way to ship one was CI or a
|
||||||
|
# manual pull. force: true discards local edits made on the VM; the templated
|
||||||
|
# .env files and Caddyfile live outside git tracking, so nothing generated by
|
||||||
|
# this role is at risk.
|
||||||
|
- name: Clone or update repo
|
||||||
git:
|
git:
|
||||||
repo: "{{ repo_url }}"
|
repo: "{{ repo_url }}"
|
||||||
dest: "{{ app_dir }}"
|
dest: "{{ app_dir }}"
|
||||||
version: main
|
version: main
|
||||||
update: false
|
update: true
|
||||||
|
force: true
|
||||||
become: false
|
become: false
|
||||||
|
|
||||||
- name: Set ownership of app directory
|
- name: Set ownership of app directory
|
||||||
|
|||||||
+19
-2
@@ -36,16 +36,33 @@
|
|||||||
path: /swapfile
|
path: /swapfile
|
||||||
mode: "0600"
|
mode: "0600"
|
||||||
|
|
||||||
|
# mkswap refuses to touch a file that is already active as swap, so a
|
||||||
|
# re-run would fail here without this guard. The swap file survives
|
||||||
|
# reboots via the fstab entry below, so on any second run it IS active.
|
||||||
|
- name: Check whether the swap file is already active
|
||||||
|
command: swapon --show=NAME --noheadings
|
||||||
|
register: _active_swaps
|
||||||
|
changed_when: false
|
||||||
|
failed_when: false
|
||||||
|
|
||||||
- name: Format swap file
|
- name: Format swap file
|
||||||
command: mkswap /swapfile
|
command: mkswap /swapfile
|
||||||
|
when: "'/swapfile' not in _active_swaps.stdout"
|
||||||
register: _mkswap
|
register: _mkswap
|
||||||
changed_when: _mkswap.rc == 0
|
changed_when: _mkswap.rc == 0
|
||||||
|
|
||||||
|
# Guarded by the same check as mkswap above. The stderr test alone was not
|
||||||
|
# enough: an already-active swap file reports "Device or resource busy",
|
||||||
|
# not "already", so the original failed_when never matched it.
|
||||||
- name: Enable swap
|
- name: Enable swap
|
||||||
command: swapon /swapfile
|
command: swapon /swapfile
|
||||||
|
when: "'/swapfile' not in _active_swaps.stdout"
|
||||||
register: _swapon
|
register: _swapon
|
||||||
failed_when: _swapon.rc != 0 and 'already' not in _swapon.stderr
|
failed_when: >
|
||||||
changed_when: _swapon.rc == 0
|
_swapon.rc is defined and _swapon.rc != 0
|
||||||
|
and 'already' not in _swapon.stderr
|
||||||
|
and 'busy' not in _swapon.stderr
|
||||||
|
changed_when: _swapon.rc is defined and _swapon.rc == 0
|
||||||
|
|
||||||
- name: Persist swap in fstab
|
- name: Persist swap in fstab
|
||||||
lineinfile:
|
lineinfile:
|
||||||
|
|||||||
@@ -22,7 +22,14 @@ vault_firestore_database: "c2-server"
|
|||||||
# ── Gitea Container Registry ──────────────────────────────────────────────────
|
# ── Gitea Container Registry ──────────────────────────────────────────────────
|
||||||
vault_registry_host: "git.vpn.cusano.net"
|
vault_registry_host: "git.vpn.cusano.net"
|
||||||
vault_registry_user: "logan"
|
vault_registry_user: "logan"
|
||||||
vault_registry_token: "" # Gitea access token with package:write scope
|
vault_registry_token: "" # Gitea access token, READ-ONLY package scope.
|
||||||
|
# The VM only pulls (roles/deploy/tasks/main.yml:62-72);
|
||||||
|
# nothing here pushes. Pushing is CI's job and uses a
|
||||||
|
# separate write-scoped token (BUILD_TOKEN in Gitea
|
||||||
|
# repo secrets). Keep them separate: this token sits on
|
||||||
|
# an internet-facing VM, and a write-scoped one there
|
||||||
|
# would let an attacker publish a poisoned image that
|
||||||
|
# every future deploy and edge node would install.
|
||||||
vault_registry: "git.vpn.cusano.net/logan" # full image prefix
|
vault_registry: "git.vpn.cusano.net/logan" # full image prefix
|
||||||
|
|
||||||
# ── Discord Bot ───────────────────────────────────────────────────────────────
|
# ── Discord Bot ───────────────────────────────────────────────────────────────
|
||||||
|
|||||||
Reference in New Issue
Block a user