feat(controller): offer QEMU the kernel datapath, gated per compute

Kernel eligibility becomes "both endpoints on one compute, each able to
anchor": Docker always (adapters are born as veth pairs), QEMU when that
compute's uBridge can create the persistent TAPs its adapters anchor on. The
question is asked per compute, because the link needs both ends anchored --
so a mixed or half-upgraded deployment degrades to the relay instead of
failing an attach.

probe_tap_support() creates and deletes one throwaway persistent TAP through a
scratch uBridge, cached by binary identity like the tc report; /capabilities
exposes `ubridge_tap` (absent = unknown, which keeps links on the relay).

The compute route for a QEMU adapter NIO took UDPNIO only, so a kernel link
was rejected with 422: its body and response now accept
Union[UDPNIO, BridgeNIO] exactly like Docker's.

Stale "Docker-to-Docker" wording in the config, link and MCP descriptions now
talks about anchors, and docs/features/qemu-kernel-datapath.md documents the
datapath -- verified end-to-end on a real instance: 32/32 kernel-datapath
checks and 29/29 on the relay variant.
This commit is contained in:
YueGuobin committed 2026-10-06 00:21:08 +08:00
1 parent 7d2d8c6747
commit 187201a08c
15 files changed
+444 -40

No files matched your search

+31 -1
View File
@@ -22,7 +22,7 @@ payload: spawn a throwaway uBridge, ask once, cache by binary identity.
import pytest
from gns3server.compute.ubridge import tc_probe
from gns3server.compute.ubridge.tc_probe import probe_tc_capabilities
from gns3server.compute.ubridge.tc_probe import probe_tc_capabilities, probe_tap_support
from gns3server.compute.ubridge.ubridge_error import UbridgeError
pytestmark = pytest.mark.asyncio
@@ -31,6 +31,8 @@ pytestmark = pytest.mark.asyncio
class FakeHypervisor:
"""Records spawns; answers `tc capabilities` with a canned reply."""
last = None
reply = ["netem=delay,rate;ebpf=1;cbpf=1;ebpf_modes=nth,quota,window,flow"]
error = None
spawned = 0
@@ -38,6 +40,7 @@ class FakeHypervisor:
def __init__(self, project, path, working_dir, transport, host, node_id):
self.commands = []
FakeHypervisor.last = self
FakeHypervisor.spawned += 1
async def start(self):
@@ -66,6 +69,8 @@ def probe_env(monkeypatch, tmp_path):
FakeHypervisor.error = None
FakeHypervisor.reply = ["netem=delay,rate;ebpf=1;cbpf=1;ebpf_modes=nth,quota,window,flow"]
tc_probe._cache.clear()
tc_probe._tap_cache.clear()
FakeHypervisor.last = None
# a real file on disk: the cache is keyed on its (path, mtime, size)
binary = tmp_path / "ubridge"
binary.write_bytes(b"")
@@ -113,3 +118,28 @@ async def test_probe_empty_reply_means_unknown():
FakeHypervisor.reply = []
assert await probe_tc_capabilities() is None
async def test_probe_tap_support_creates_and_deletes_a_probe_tap():
assert await probe_tap_support() is True
assert FakeHypervisor.spawned == 1
commands = FakeHypervisor.last.commands
assert commands[0].startswith("tap create ")
assert commands[1].startswith("tap delete ")
async def test_probe_tap_support_unknown_on_an_old_build():
FakeHypervisor.error = "202-Unknown command 'create'"
assert await probe_tap_support() is None
# cached like the tc report: no respawn on every /capabilities hit
assert await probe_tap_support() is None
assert FakeHypervisor.spawned == 1
async def test_probe_tap_support_missing_binary(monkeypatch):
monkeypatch.setattr(tc_probe.shutil, "which", lambda name: None)
assert await probe_tap_support() is None
assert FakeHypervisor.spawned == 0