feat(firecracker): move pool off CGNAT, add overlap guard + flake module

The default TAP-pool base was 100.64.0.0/10 (RFC-6598 CGNAT) — chosen to
dodge RFC-1918, but that's exactly the range Tailscale assigns node
addresses from, so on a Tailscale host it's the worst pick. Move the
default to 10.243.0.0/16, an obscure RFC-1918 block that steers clear of
docker/libvirt/k8s/LAN and Tailscale.

No default is collision-proof, so add netpool.overlapping_routes(): it
parses `ip -json route show table all` and flags any route intersecting
the pool range (excluding our own bbfc* TAPs and the default route). The
launch preflight warns on overlap; `backend status` reports it.

Distribute the NixOS host setup as a flake module instead of a
copy-pasted blob: nix/firecracker-netpool.nix computes the taps / nft
table from typed options (poolSize, ipBase, ifacePrefix, owner) with a
/31-alignment assertion, and flake.nix exposes it as
nixosModules.firecracker-netpool. Defaults mirror the backend constants;
writeEnvFile emits the matching BOT_BOTTLE_FC_* so the host pool and the
launcher can't drift.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
This commit is contained in:
2026-07-11 15:18:21 -04:00
parent c07ebca867
commit ce3fad9320
7 changed files with 324 additions and 17 deletions
+52 -1
View File
@@ -38,7 +38,15 @@ class TestNetpoolSlots(unittest.TestCase):
(s1.iface, s1.host_ip, s1.guest_ip))
def test_guest_cidr_is_31(self):
self.assertEqual("100.64.0.1/31", netpool.slot(0).guest_cidr)
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "100.64.0.0"}):
self.assertEqual("100.64.0.1/31", netpool.slot(0).guest_cidr)
def test_default_base_avoids_cgnat_and_common_private_ranges(self):
# The default base must NOT sit in 100.64.0.0/10 (RFC-6598 CGNAT,
# which Tailscale hands node addresses from); it's an obscure
# RFC-1918 block instead.
with patch.dict(os.environ, {}, clear=True):
self.assertEqual("10.243.0.0", netpool.ip_base())
def test_pool_size_env_override(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_POOL_SIZE": "4"}):
@@ -65,6 +73,49 @@ class TestNetpoolRenderers(unittest.TestCase):
self.assertIn("firecracker-netpool.sh up", out)
class TestNetpoolOverlap(unittest.TestCase):
"""`overlapping_routes()` flags a pool base that collides with an
existing host route (Tailscale CGNAT peer, docker/libvirt bridge,
LAN) and ignores our own bbfc TAPs + the default route."""
def _routes(self, entries: list[dict]) -> object:
import json
import subprocess
def fake_run(argv, **kwargs):
return subprocess.CompletedProcess(
argv, 0, stdout=json.dumps(entries), stderr="",
)
return patch.object(netpool.subprocess, "run", side_effect=fake_run)
def test_flags_route_overlapping_pool(self):
# base 100.64.0.0 + a Tailscale peer /32 inside the pool window.
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "100.64.0.0",
"BOT_BOTTLE_FC_POOL_SIZE": "8"}), \
self._routes([
{"dst": "default", "dev": "enp4s0"},
{"dst": "100.64.0.5", "dev": "tailscale0"},
]):
conflicts = netpool.overlapping_routes()
self.assertEqual(1, len(conflicts))
self.assertEqual("tailscale0", conflicts[0].dev)
def test_ignores_own_taps_and_default(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "10.243.0.0",
"BOT_BOTTLE_FC_POOL_SIZE": "8"}), \
self._routes([
{"dst": "default", "dev": "enp4s0"},
{"dst": "10.243.0.0/31", "dev": "bbfc0"},
{"dst": "192.168.1.0/24", "dev": "enp4s0"},
]):
self.assertEqual([], netpool.overlapping_routes())
def test_empty_when_ip_missing(self):
with self._routes([]) as run:
run.side_effect = FileNotFoundError()
self.assertEqual([], netpool.overlapping_routes())
class TestNetpoolAllocation(unittest.TestCase):
def test_allocate_is_mutually_exclusive(self):
with patch.dict(os.environ, {"BOT_BOTTLE_FC_POOL_SIZE": "1"}):