feat: cross-compute VXLAN kernel datapath

Cross-compute links can ride kernel VXLAN tunnels instead of the uBridge
UDP relay: each endpoint creates one VXLAN device (uBridge's rtnetlink
vxlan module) enslaved into the same per-link Linux bridge the same-host
datapath uses, so filters, markers, capture and suspend keep running on
the anchor unchanged. Opt-in (Server.enable_vxlan_cross_compute, default
off) because the tunnel caps the usable MTU at the underlay minus the
outer headers; the relay stays the default and the fallback.

The controller derives what the pair must agree on: one VNI per link
(upper VNI space, per-link random salt) and deterministic device names
(gvl{link}{node}) that make crashed-run leftovers claimable
(show -> delete -> create). Same-host compute pairs, switch endpoints
and serial/unix-socket containers stay on the relay.

A VNI the kernel refuses self-heals on every path it can surface:
interactive create retries a fresh salt then degrades to the relay;
project open re-dispatches refused batch entries the same way; node
start recognises the refused device, stops the half-started node,
re-wires both ends on a fresh VNI (or degrades the link) and retries
the start. The device MTU is derived from the lower device (dev=) and
the per-link bridge inherits it - no configuration. The capability
probe (ubridge_vxlan in /capabilities) runs one scratch create/delete
on a scratch port that never equals the configured dstport.

The e2e scenario runs two computes on one machine (a network namespace
joined by a veth pair as the fabric) and needs root.
This commit is contained in:
YueGuobin committed 2026-10-17 14:11:00 +08:00
1 parent 5514b2e929
commit 21b866aeed
24 files changed
+2107 -59

No files matched your search

+27 -7
View File
@@ -35,6 +35,7 @@ from fastapi.encoders import jsonable_encoder
from fastapi.responses import FileResponse
from gns3server import schemas
from gns3server.compute.error import NodeError
from gns3server.compute.project import Project
from gns3server.compute.project_manager import ProjectManager
from gns3server.utils.path import is_safe_path
@@ -271,16 +272,35 @@ async def create_batch_nios(
# count (standard == 1, Dynamips == 2) and await the async variant.
sig = inspect.signature(node.manager.create_nio)
dynamips_style = len(sig.parameters) >= 2
failed = []
for entry in entries:
nio_settings = jsonable_encoder(entry.nio, exclude_unset=True)
if dynamips_style:
nio = await node.manager.create_nio(node, nio_settings)
else:
nio = node.manager.create_nio(nio_settings)
await _add_nio_binding(node, entry.adapter_number, entry.port_number, nio)
try:
if dynamips_style:
nio = await node.manager.create_nio(node, nio_settings)
else:
nio = node.manager.create_nio(nio_settings)
await _add_nio_binding(node, entry.adapter_number, entry.port_number, nio)
except NodeError:
# A VXLAN entry that cannot be wired (its VNI already
# registered on the host's shared socket, no route to the
# peer) must not fail the whole project open: report it so
# the controller can degrade that link to the uBridge relay.
# Every other NIO type keeps the fail-the-batch semantics.
if not nio_settings.get("vxlan"):
raise
failed.append(
{
"node_id": entry.node_id,
"adapter_number": entry.adapter_number,
"port_number": entry.port_number,
}
)
return failed
await asyncio.gather(*[_create_one_node(nid, ents) for nid, ents in per_node.items()])
return {"added": len(batch.nios)}
results = await asyncio.gather(*[_create_one_node(nid, ents) for nid, ents in per_node.items()])
failed = [item for node_failed in results for item in node_failed]
return {"added": len(batch.nios) - len(failed), "failed": failed}
@router.put(