feat(ansible): require --external-pool, drop NAT, forward EXTRA_VARS

spx admin init now rejects --external-mode=nat and demands --external-pool
when mode=pool. The ansible init role silently skipped pool flags when the
range was unset, so installs fell over inside the spx validator. Make
targets also swallowed `-e` (make's env-override flag), so operators could
not override pool start/end without editing defaults.yml.

- vars/defaults.yml: rename nat_gateway_ip → external_gateway_ip; add
  spinifex_external_no_external opt-out; document the spx flag contract.
- roles/init/tasks/main.yml: drop NAT branch; assert pool range upfront
  with a fail_msg pointing at EXTRA_VARS / defaults.yml; emit gateway,
  prefix-len, gateway-ip only when explicitly set (let spx auto-detect);
  honour --no-external.
- playbooks/dev-reset.yml: rename captured var; coerce legacy
  external_mode=nat to pool with a warn; tighten gateway regex with \b.
- Makefile: ansible-dev-* targets now forward EXTRA_VARS="key=val ..."
  through --extra-vars so `make` callers can override without editing
  defaults.yml.
- scripts/ansible/README.md: document pool requirement, both invocation
  styles (direct -e vs make EXTRA_VARS), NAT removal.
This commit is contained in:
joshsiv-mulga
2026-05-25 09:33:53 +10:00
parent aed7b2edfb
commit e7bbc64a45
5 changed files with 96 additions and 28 deletions
+13 -5
View File
@@ -281,20 +281,28 @@ distro-clean:
# Ansible dev lifecycle (experimental, parallel to dev-*.sh / reset-dev-env.sh).
# See scripts/ansible/README.md and docs/development/improvements/ansible-dev-lifecycle.md.
#
# Variable overrides: pass EXTRA_VARS="key=val key2=val2" to forward as
# `--extra-vars` to ansible-playbook. Plain `-e` on the make command line is
# make's own flag and does NOT reach ansible.
# make ansible-dev-install EXTRA_VARS="spinifex_external_pool_start=192.168.1.90 spinifex_external_pool_end=192.168.1.99"
EXTRA_VARS ?=
_ANSIBLE_EXTRA = $(if $(strip $(EXTRA_VARS)),--extra-vars "$(EXTRA_VARS)",)
ansible-dev-preflight:
cd scripts/ansible && ansible-playbook playbooks/dev-preflight.yml
cd scripts/ansible && ansible-playbook playbooks/dev-preflight.yml $(_ANSIBLE_EXTRA)
ansible-dev-teardown:
cd scripts/ansible && ansible-playbook playbooks/dev-teardown.yml
cd scripts/ansible && ansible-playbook playbooks/dev-teardown.yml $(_ANSIBLE_EXTRA)
ansible-dev-install:
cd scripts/ansible && ansible-playbook playbooks/dev-install.yml
cd scripts/ansible && ansible-playbook playbooks/dev-install.yml $(_ANSIBLE_EXTRA)
ansible-dev-reset:
cd scripts/ansible && ansible-playbook playbooks/dev-reset.yml
cd scripts/ansible && ansible-playbook playbooks/dev-reset.yml $(_ANSIBLE_EXTRA)
ansible-dev-deploy:
cd scripts/ansible && ansible-playbook playbooks/dev-deploy.yml
cd scripts/ansible && ansible-playbook playbooks/dev-deploy.yml $(_ANSIBLE_EXTRA)
.PHONY: build build-ui build-installer build-lb-agent build-system-image build-microvm-image install-microvm go_build go_run preflight test test-cover test-race test-actions test-harness manifest-check diff-coverage bench run \
deploy reinstall clean \
+30 -3
View File
@@ -83,12 +83,39 @@ Useful overrides:
| `teardown_process_wait_seconds` | `30` | Grace period for processes to exit |
| `spinifex_region` | `ap-southeast-2` | Region passed to `spx admin init` |
| `spinifex_az` | `{{ region }}a` | AZ passed to `spx admin init` |
| `spinifex_external_mode` | `pool` | `pool` \| `nat` external networking |
| `spinifex_external_mode` | `pool` | External networking mode — `pool` or empty (NAT removed) |
| `spinifex_external_no_external` | `false` | `true` → emit `--no-external` and skip external networking |
| `spinifex_external_pool_start` | `""` | **Required** for `pool` mode — first IP of the static WAN pool |
| `spinifex_external_pool_end` | `""` | **Required** for `pool` mode — last IP of the static WAN pool |
| `spinifex_external_gateway` | `""` | WAN gateway (auto-detected when blank) |
| `spinifex_external_prefix_len` | `""` | WAN prefix length (auto-detected when blank) |
| `spinifex_external_gateway_ip` | `""` | OVN router external-IP override (`--gateway-ip`) |
`pool` mode is mandatory unless you set `spinifex_external_no_external=true`.
`spx admin init` rejects the run without a `--external-pool` range, so the
init role asserts `spinifex_external_pool_start/_end` upfront. Either persist
them in `vars/defaults.yml`, or pass them at invocation:
Direct `ansible-playbook` (use `-e` here — this is ansible's flag):
```
ansible-playbook playbooks/dev-install.yml \
-e spinifex_external_pool_start=192.168.1.150 \
-e spinifex_external_pool_end=192.168.1.250
```
Via `make` (use `EXTRA_VARS=` — make eats its own `-e`):
```
make ansible-dev-install \
EXTRA_VARS="spinifex_external_pool_start=192.168.1.150 spinifex_external_pool_end=192.168.1.250"
```
`dev-reset.yml` automatically captures `region`, `az`, `external_mode`,
pool range, gateway, prefix-len, nat gateway_ip from the existing
pool range, gateway, prefix-len and `gateway_ip` from the existing
`/etc/spinifex/spinifex.toml` before teardown and replays them into
`init`. Use `-e` to override.
`init`. Legacy `external_mode = "nat"` is coerced to `"pool"` with a warn.
Use `-e` to override.
## Leak catalog
+18 -3
View File
@@ -23,6 +23,7 @@
when: reset_config_stat.stat.exists
# List-concat-and-take-first pattern: missing regex match falls back to current default.
# `gateway\s*=` deliberately does not match `gateway_ip` / `gateway_lrp_*`.
- name: capture — extract scalars
ansible.builtin.set_fact:
spinifex_region: "{{ (reset_config_txt | regex_findall('region\\s*=\\s*\"([^\"]+)\"') + [spinifex_region])[0] }}"
@@ -30,11 +31,25 @@
spinifex_external_mode: "{{ (reset_config_txt | regex_findall('external_mode\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_mode])[0] }}"
spinifex_external_pool_start: "{{ (reset_config_txt | regex_findall('range_start\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_pool_start])[0] }}"
spinifex_external_pool_end: "{{ (reset_config_txt | regex_findall('range_end\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_pool_end])[0] }}"
spinifex_external_gateway: "{{ (reset_config_txt | regex_findall('gateway\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_gateway])[0] }}"
spinifex_external_gateway: "{{ (reset_config_txt | regex_findall('\\bgateway\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_gateway])[0] }}"
spinifex_external_prefix_len: "{{ (reset_config_txt | regex_findall('prefix_len\\s*=\\s*([0-9]+)') + [spinifex_external_prefix_len | string])[0] }}"
spinifex_nat_gateway_ip: "{{ (reset_config_txt | regex_findall('gateway_ip\\s*=\\s*\"([^\"]+)\"') + [spinifex_nat_gateway_ip])[0] }}"
spinifex_external_gateway_ip: "{{ (reset_config_txt | regex_findall('gateway_ip\\s*=\\s*\"([^\"]+)\"') + [spinifex_external_gateway_ip])[0] }}"
when: reset_config_stat.stat.exists
# Legacy: external_mode = "nat" was removed from spx. Coerce to "pool"
# so old configs still reset cleanly; warn so the operator notices.
- name: capture — coerce legacy external_mode=nat to pool
ansible.builtin.set_fact:
spinifex_external_mode: "pool"
when: spinifex_external_mode == 'nat'
- name: capture — warn on legacy nat coercion
ansible.builtin.debug:
msg: "⚠️ Captured external_mode=nat from legacy config; coerced to 'pool' (NAT mode removed from spx admin init)."
when:
- reset_config_stat.stat.exists
- (reset_config_txt | regex_findall('external_mode\\s*=\\s*\"nat\"')) | length > 0
- name: capture — summary
ansible.builtin.debug:
msg: |
@@ -44,7 +59,7 @@
external_mode={{ spinifex_external_mode }}
pool={{ spinifex_external_pool_start }}-{{ spinifex_external_pool_end }}
gateway={{ spinifex_external_gateway }}, prefix={{ spinifex_external_prefix_len }}
nat_gateway={{ spinifex_nat_gateway_ip }}
gateway_ip={{ spinifex_external_gateway_ip }}
{% else %}
No existing config; using defaults from vars/defaults.yml (or -e overrides).
{% endif %}
+26 -16
View File
@@ -8,28 +8,38 @@
--node {{ spinifex_node_name }}
--nodes {{ spinifex_node_count }}
- name: init — no-external opt-out
ansible.builtin.set_fact:
init_external_flags: "--no-external"
when: spinifex_external_no_external | bool
- name: init — assert pool range supplied when mode=pool
ansible.builtin.assert:
that:
- spinifex_external_pool_start | length > 0
- spinifex_external_pool_end | length > 0
fail_msg: |
spx admin init requires --external-pool when --external-mode=pool.
Set spinifex_external_pool_start / spinifex_external_pool_end in
scripts/ansible/vars/defaults.yml, or pass:
-e spinifex_external_pool_start=192.168.1.150
-e spinifex_external_pool_end=192.168.1.250
Pass -e spinifex_external_no_external=true to skip external networking.
when:
- not (spinifex_external_no_external | bool)
- spinifex_external_mode == 'pool'
- name: init — pool-mode external flags
ansible.builtin.set_fact:
init_external_flags: >-
--external-mode=pool
--external-pool={{ spinifex_external_pool_start }}-{{ spinifex_external_pool_end }}
--external-gateway={{ spinifex_external_gateway }}
--external-prefix-len={{ spinifex_external_prefix_len }}
{% if spinifex_external_gateway | length > 0 %}--external-gateway={{ spinifex_external_gateway }}{% endif %}
{% if spinifex_external_prefix_len | string | length > 0 %}--external-prefix-len={{ spinifex_external_prefix_len }}{% endif %}
{% if spinifex_external_gateway_ip | length > 0 %}--gateway-ip={{ spinifex_external_gateway_ip }}{% endif %}
when:
- not (spinifex_external_no_external | bool)
- spinifex_external_mode == 'pool'
- spinifex_external_pool_start | length > 0
- spinifex_external_pool_end | length > 0
- name: init — NAT-mode external flags
ansible.builtin.set_fact:
init_external_flags: >-
--external-mode=nat
--gateway-ip={{ spinifex_nat_gateway_ip }}
--external-gateway={{ spinifex_external_gateway }}
--external-prefix-len={{ spinifex_external_prefix_len }}
when:
- spinifex_external_mode == 'nat'
- spinifex_nat_gateway_ip | length > 0
- name: init — assemble full flag string
ansible.builtin.set_fact:
@@ -79,6 +89,6 @@
msg: |
Init complete:
region={{ spinifex_region }}, az={{ spinifex_az }}, node={{ spinifex_node_name }}
external_mode={{ spinifex_external_mode }}
external_mode={{ 'disabled' if (spinifex_external_no_external | bool) else spinifex_external_mode }}
spinifex.target: started
CA: {{ spinifex_ca_trust_path }}
+9 -1
View File
@@ -23,12 +23,20 @@ spinifex_node_name: node1
spinifex_node_count: 1
# External network.
# spx admin init contract (as of network-layer-redesign):
# external_mode : "pool" or "" (NAT path removed)
# external_pool : MANDATORY when mode=pool — set start/end below or pass -e.
# external_gw : auto-detected from default route when blank.
# external_prefix: auto-detected from WAN when blank.
# external_gw_ip : OVN router external-IP override (was nat_gateway_ip).
# no_external : true → emit --no-external (skip external networking).
spinifex_external_mode: pool
spinifex_external_no_external: false
spinifex_external_pool_start: ""
spinifex_external_pool_end: ""
spinifex_external_gateway: ""
spinifex_external_prefix_len: ""
spinifex_nat_gateway_ip: ""
spinifex_external_gateway_ip: ""
# Preflight checks.
spinifex_ports: