fix(flannel): default the interface to each host's default IPv4 interface (#689)

* fix(flannel): default the interface to each host's default IPv4 interface

- Replace the hardcoded flannel_iface: eth0 with a per-host default derived
  from ansible_facts.default_ipv4.interface
- KVM/cloud hosts that are not named eth0 (e.g. enp1s0, ens3) now resolve the
  interface automatically instead of failing the k3s_node_ip lookup
- Update the commented calico_iface / cilium_iface examples to match
- Co-authored-by: Fritz Dunkel <677609+FinalDoom@users.noreply.github.com>
- Fixes #621

* test(flannel): add regression test for per-host interface default

- Add a focused test that renders the sample inventory's flannel_iface
  expression against fake ansible facts
- Assert a non-eth0 host (enp1s0, ens3) resolves its own interface and that
  the expression defaults from ansible_facts.default_ipv4.interface
- Wire it as a local pre-commit hook (default-interface-test)

* test(molecule): assert nodes register a non-loopback InternalIP

- Add a flannel-scenario verify assertion that every node reports an
  InternalIP derived from its configured flannel_iface
- Guards against k3s binding to 127.0.0.1 instead of the cluster interface
- Complements the pre-commit default-interface test with an end-to-end check

.github/scripts/test-default-interface.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""Assert the sample inventory resolves the flannel interface per host.
+
+flannel_iface defaults to the host's default IPv4 interface rather than a
+hardcoded eth0. This test extracts the flannel_iface expression from the
+sample inventory and proves that a host whose primary interface is not named
+eth0 (e.g. enp1s0, ens3) resolves the interface from ansible facts.
+"""
+
+from __future__ import print_function
+
+import os
+import re
+import subprocess
+
+from jinja2 import Environment, StrictUndefined
+
+
+def repo_root():
+    return subprocess.check_output(
+        ["git", "rev-parse", "--show-toplevel"], text=True
+    ).strip()
+
+
+def fail(message):
+    raise SystemExit("default-interface test failed: " + message)
+
+
+class FakeAnsibleFacts(object):
+    """Stand-in for the per-host ``ansible_facts`` dict."""
+
+    def __init__(self, default_iface, iface_ip):
+        self._default = {"interface": default_iface, "address": iface_ip}
+        self._ifaces = {
+            default_iface: {"ipv4": {"address": iface_ip}},
+        }
+
+    @property
+    def default_ipv4(self):
+        return self._default
+
+    def __getitem__(self, key):
+        return self._ifaces[key]
+
+
+def read_all_yml(root):
+    path = os.path.join(root, "inventory", "sample", "group_vars", "all.yml")
+    with open(path, "r") as handle:
+        return handle.read()
+
+
+def extract_value(content, key):
+    # Match a quoted value assigned to the key, e.g. flannel_iface: "...".
+    match = re.search(r"^%s:\s*\"(.+)\"\s*$" % re.escape(key), content, re.M)
+    if not match:
+        fail("could not find %s in the sample inventory" % key)
+    return match.group(1)
+
+
+def resolve(env, expression, facts):
+    template = env.from_string(expression)
+    return template.render(ansible_facts=facts)
+
+
+def main():
+    root = repo_root()
+    content = read_all_yml(root)
+    env = Environment(undefined=StrictUndefined)
+
+    flannel_expr = extract_value(content, "flannel_iface")
+    if "default_ipv4.interface" not in flannel_expr:
+        fail("flannel_iface no longer defaults from ansible facts")
+
+    # A host whose primary interface is enp1s0 (the core #621 scenario).
+    facts = FakeAnsibleFacts("enp1s0", "192.168.30.11")
+    resolved = resolve(env, flannel_expr, facts)
+    if resolved != "enp1s0":
+        fail("flannel_iface resolved to %r, expected enp1s0" % resolved)
+
+    # A different host with a different interface must resolve independently.
+    facts2 = FakeAnsibleFacts("ens3", "192.168.30.12")
+    resolved2 = resolve(env, flannel_expr, facts2)
+    if resolved2 != "ens3":
+        fail("flannel_iface resolved to %r, expected ens3" % resolved2)
+
+    print("default-interface regression test passed")
+
+
+if __name__ == "__main__":
+    main()

.pre-commit-config.yaml

@@ -84,3 +84,11 @@ repos:
         language: system
         pass_filenames: false
         files: ^roles/k3s_server/tasks/metallb\.yml$|^\.github/scripts/test-metallb-remote-read\.sh$
+      - id: default-interface-test
+        name: default interface test
+        entry: python3 .github/scripts/test-default-interface.py
+        language: python
+        additional_dependencies:
+          - Jinja2>=3.1
+        pass_filenames: false
+        files: ^inventory/sample/group_vars/all\.yml$|^\.github/scripts/test-default-interface\.py$

inventory/sample/group_vars/all.yml

@@ -8,16 +8,18 @@ systemd_dir: /etc/systemd/system
 system_timezone: Your/Timezone
 
 # interface which will be used for flannel
-flannel_iface: eth0
+# Defaults to each host's default IPv4 interface (e.g. eth0, enp1s0, ens3)
+# so KVM/cloud hosts without eth0 work out of the box. Override per-host if needed.
+flannel_iface: "{{ ansible_facts.default_ipv4.interface }}"
 
 # uncomment calico_iface to use tigera operator/calico cni instead of flannel https://docs.tigera.io/calico/latest/about
-# calico_iface: "eth0"
+# calico_iface: "{{ ansible_facts.default_ipv4.interface }}"
 calico_ebpf: false # use eBPF dataplane instead of iptables
 calico_tag: v3.32.1 # calico version tag
 
 # uncomment cilium_iface to use cilium cni instead of flannel or calico
 # ensure v4.19.57, v5.1.16, v5.2.0 or more recent kernel
-# cilium_iface: "eth0"
+# cilium_iface: "{{ ansible_facts.default_ipv4.interface }}"
 cilium_mode: native # native when nodes are on the same subnet or use BGP, otherwise set tunnel
 cilium_tag: v1.20.0 # cilium version tag
 cilium_cli_tag: v0.19.7 # cilium cli version tag

molecule/resources/verify_from_outside/tasks/test/verify-components.yml

@@ -38,6 +38,30 @@
           loop_control:
             label: "{{ item.metadata.name }} ready"
 
+        - name: Assert every node registered a node IP from its interface
+          # Each k3s node is launched with --node-ip derived from flannel_iface.
+          # Confirm every node carries a real InternalIP (not a loopback), which
+          # proves k3s bound to the cluster interface rather than defaulting to 127.0.0.1.
+          ansible.builtin.assert:
+            that: >-
+              (node_internal_ips | length) >= 1 and
+              (node_internal_ips | reject('eq', '127.0.0.1') | list | length) == node_internal_ips | length
+            success_msg: "{{ item.metadata.name }} is bound to {{ node_internal_ips | join(', ') }}"
+            fail_msg: >-
+              {{ item.metadata.name }} has no non-loopback InternalIP
+              (got: {{ node_internal_ips | join(', ') }})
+          vars:
+            node_internal_ips: >-
+              {{
+                (item.status.addresses | default([]))
+                | selectattr('type', 'equalto', 'InternalIP')
+                | map(attribute='address')
+                | list
+              }}
+          loop: "{{ verify_nodes.resources }}"
+          loop_control:
+            label: "{{ item.metadata.name }} InternalIP"
+
         - name: Get any Calico namespaces with Flannel enabled
           kubernetes.core.k8s_info:
             kind: Namespace