Merge branch '3.1' into 3.1

gns3server/controller/node.py

@@ -20,18 +20,33 @@ import copy
 import html
 import logging
 import os
+import re
 import uuid
 
 from ..config import Config
 from ..utils import int_to_macaddress, macaddress_to_int
 from ..utils.application_id import is_iol_runner_environment
 from ..utils.images import images_directories
+from ..utils.vxlan import vxlan_device_name
 from .controller_error import ComputeConflictError, ComputeError, ControllerError, ControllerTimeoutError
 from .node_types import BUILTIN_NODE_TYPES
 from .ports.port_factory import DynamipsPortFactory, PortFactory, StandardPortFactory
 
 log = logging.getLogger(__name__)
 
+# The compute's error when it could not create a VXLAN tunnel device — the
+# wording is a same-repo contract with KernelDatapathMixin._kernel_error
+# (only computes running this codebase carry VXLAN links: the capability
+# gate keeps everything else on the relay), and the captured device name
+# identifies the link (a pure function of link id + node id).
+_VXLAN_CONFLICT_RE = re.compile(r"Could not create VXLAN device (?P<device>\S+)")
+
+# Node-start self-heal rounds over a refused VXLAN VNI: the first re-wires
+# the link on a fresh VNI, the second degrades it to the relay (whose NIOs
+# cannot hit the conflict) — a start must not fail permanently because
+# another link already registered the VNI on the shared dstport socket.
+_VXLAN_START_HEALS = 2
+
 
 # Image properties of a node, mapped by node type. The value is the image
 # "type" used by the image manager (see utils.images). Docker images are not
@@ -43,6 +58,7 @@ IMAGE_PROPERTIES_BY_NODE_TYPE = {
         "hdc_disk_image": "qemu",
         "hdd_disk_image": "qemu",
         "cdrom_image": "qemu",
+        "cdrom2_image": "qemu",
         "initrd": "qemu",
         "kernel_image": "qemu",
         "bios_image": "qemu",
@@ -885,6 +901,7 @@ class Node:
                 "hdc_disk_image",
                 "hdd_disk_image",
                 "cdrom_image",
+                "cdrom2_image",
                 "bios_image",
                 "initrd",
                 "kernel_image",
@@ -955,18 +972,32 @@ class Node:
                     f"Cannot start node '{self._name}': {len(failed_links)} deferred link(s) "
                     "could not be restored. Please try again."
                 )
-        try:
-            # For IOU: we need to send the licence everytime we start a node
-            if self.node_type == "iou":
-                license_check = self._project.controller.iou_license.get("license_check", True)
-                iourc_content = self._project.controller.iou_license.get("iourc_content", None)
-                await self.post(
-                    "/start", timeout=240, data={"license_check": license_check, "iourc_content": iourc_content}
+        for heal in range(_VXLAN_START_HEALS + 1):
+            try:
+                await self._start_on_compute(data)
+                break
+            except asyncio.TimeoutError:
+                raise ControllerTimeoutError(f"Timeout when starting {self._name}")
+            except ComputeError as e:
+                conflicted = self._vxlan_conflicted_link(e)
+                if conflicted is None or heal == _VXLAN_START_HEALS:
+                    raise
+                degrade = heal > 0  # a second conflict takes the relay
+                log.warning(
+                    "Node '%s': start refused over a VXLAN VNI conflict on link %s — %s and retrying",
+                    self._name,
+                    conflicted.id,
+                    "degrading the link to the uBridge relay" if degrade else "re-wiring the link on a fresh VNI",
                 )
-            else:
-                await self.post("/start", data=data, timeout=240)
-        except TimeoutError:
-            raise ControllerTimeoutError(f"Timeout when starting {self._name}")
+                # The refused start leaves the node half-started (the
+                # emulator process runs, the wiring partial) — stop it
+                # first: a start on a running container early-returns
+                # without wiring anything.
+                await self.stop()
+                if await self._project._redispatch_vxlan_links([conflicted], downgrade=degrade) and not degrade:
+                    # The fresh VNI was already refused before the start
+                    # could even retry — degrade the pair to the relay now.
+                    await self._project._redispatch_vxlan_links([conflicted], downgrade=True)
         self._confirm_status("started")
         # A started node may have brought kernel anchors into existence that
         # a link needs to finish wiring (the Ethernet-switch fast path joins
@@ -974,6 +1005,42 @@ class Node:
         for link in self._links:
             await link.node_started(self)
 
+    async def _start_on_compute(self, data=None):
+        """
+        The compute-side start request (IOU carries its licence along).
+        """
+
+        # For IOU: we need to send the licence everytime we start a node
+        if self.node_type == "iou":
+            license_check = self._project.controller.iou_license.get("license_check", True)
+            iourc_content = self._project.controller.iou_license.get("iourc_content", None)
+            await self.post(
+                "/start", timeout=240, data={"license_check": license_check, "iourc_content": iourc_content}
+            )
+        else:
+            await self.post("/start", data=data, timeout=240)
+
+    def _vxlan_conflicted_link(self, error):
+        """
+        The link whose VXLAN device a failed node start could not create,
+        or None for every other failure.
+
+        The compute's error names the device it could not create and the
+        name is a pure function of (link id, node id), so it identifies the
+        link with no extra API surface. An unmatched message — another
+        failure, a future wording change — simply leaves the error to
+        surface unchanged, which is exactly the behaviour without the heal.
+        """
+
+        match = _VXLAN_CONFLICT_RE.search(str(error))
+        if match is None:
+            return None
+        device = match.group("device")
+        for link in self._links:
+            if vxlan_device_name(link.id, self.id) == device and any(nio.get("vxlan") for nio in link._link_data):
+                return link
+        return None
+
     async def stop(self, strict=False):
         """
         Stop a node