feat(integration-vm): network + VM boot (overlay, cloud-init seed, virt-install import)

scripts/integration-vm.py

@@ -144,6 +144,87 @@ def ensure_image():
     return img
 
 
+def net_ensure():
+    r = sh(["virsh", "net-info", NET_NAME], check=False, capture=True)
+    if r.returncode != 0:
+        xml = RUN_DIR / "net.xml"
+        RUN_DIR.mkdir(parents=True, exist_ok=True)
+        xml.write_text(NET_XML)
+        sh(["virsh", "net-define", str(xml)])
+        sh(["virsh", "net-autostart", NET_NAME])
+    active = sh(["virsh", "net-info", NET_NAME], capture=True).stdout
+    if "Active:         yes" not in active:
+        sh(["virsh", "net-start", NET_NAME])
+
+
+def _ssh_pubkey():
+    for cand in ("id_ed25519.pub", "id_rsa.pub"):
+        p = pathlib.Path.home() / ".ssh" / cand
+        if p.exists():
+            return p.read_text().strip()
+    raise SystemExit("no SSH public key found in ~/.ssh")
+
+
+def up(host, name=None, mem_mib=DEFAULT_MEM_MIB, vcpus=DEFAULT_VCPUS):
+    free = free_mib(pathlib.Path("/proc/meminfo").read_text())
+    if free < MIN_FREE_MIB:
+        raise SystemExit(f"refusing to start: only {free} MiB free (< {MIN_FREE_MIB})")
+    running = sh(["virsh", "list", "--name"], capture=True).stdout.split()
+    if any(n.startswith(NAME_PREFIX) for n in running):
+        raise SystemExit("an integration VM is already running (one at a time); "
+                         "run `integration-vm prune` first")
+    name = name or vm_name(host)
+    img = ensure_image()
+    net_ensure()
+    RUN_DIR.mkdir(parents=True, exist_ok=True)
+    overlay = RUN_DIR / f"{name}.qcow2"
+    sh(["qemu-img", "create", "-f", "qcow2", "-F", "qcow2", "-b", str(img), str(overlay)])
+    (RUN_DIR / "user-data").write_text(render_user_data(_ssh_pubkey(), "ansible"))
+    (RUN_DIR / "meta-data").write_text(render_meta_data(f"iid-{name}", name))
+    seed = RUN_DIR / f"{name}-seed.img"
+    sh(["cloud-localds", str(seed), str(RUN_DIR / "user-data"), str(RUN_DIR / "meta-data")])
+    DIAG_ROOT.mkdir(parents=True, exist_ok=True)
+    console = DIAG_ROOT / f"{name}-console.log"
+    sh(["virt-install", "--name", name, "--memory", str(mem_mib), "--vcpus", str(vcpus),
+        "--import",
+        "--disk", f"path={overlay},format=qcow2",
+        "--disk", f"path={seed},device=cdrom",
+        "--network", f"network={NET_NAME}",
+        "--osinfo", "debian13",
+        "--graphics", "none",
+        "--serial", f"file,path={console}",
+        "--noautoconsole"])
+    ip = wait_for_ip(name)
+    wait_for_ssh(ip, "ansible")
+    (RUN_DIR / "current").write_text(f"{name}\n{ip}\n{host}\n")
+    print(f"VM {name} up at {ip}")
+    return name, ip
+
+
+def wait_for_ip(name, timeout=120):
+    end = time.time() + timeout
+    while time.time() < end:
+        out = sh(["virsh", "domifaddr", name, "--source", "lease"],
+                 check=False, capture=True).stdout
+        ip = parse_lease_ip(out)
+        if ip:
+            return ip
+        time.sleep(4)
+    raise SystemExit(f"timed out waiting for {name} to get a DHCP lease")
+
+
+def wait_for_ssh(ip, user, timeout=180):
+    end = time.time() + timeout
+    while time.time() < end:
+        r = sh(["ssh", "-o", "StrictHostKeyChecking=no",
+                "-o", "UserKnownHostsFile=/dev/null", "-o", "ConnectTimeout=5",
+                f"{user}@{ip}", "true"], check=False, capture=True)
+        if r.returncode == 0:
+            return
+        time.sleep(5)
+    raise SystemExit(f"timed out waiting for SSH to {ip}")
+
+
 def main(argv=None):
     p = argparse.ArgumentParser(prog="integration-vm", description=__doc__)
     sub = p.add_subparsers(dest="cmd", required=True)