net: detect unstable network names and trigger a settle if needed

The cloud-init-local.service expects that any network device name changes
have already been completed by the kernel or udev daemon.

In some situations we've found that the renaming of interfaces from kernel
names (eth0, eth1, etc) to their persistent names (eno1, ens3, enp0s1,
etc) may happen after cloud-init-local has started where it reads values
from sysfs about what network devices are present, and which device to use
as a fallback nic.

Subsequently, cloud-init-local would write out network configuration for a
kernel device name which would no longer be present by the time that
networking services start to bring up the devices. The result is that the
instance does not get networking configured. Prior to use of
systemd-networkd, the Ubuntu 'networking.service' unit included a call to
udevadm settle which is why this race is not seen on a Xenial system.

This change adds the ability to detect if an interface has a stable name,
if if we find one without stable names and stable names have not been
disabled (net.ifnames=0 in /proc/cmdline), then cloud-init will invoke
udevadm settle.

LP: #1766287

1 files changed, 69 insertions, 4 deletions

diff --git a/tests/unittests/test_net.py b/tests/unittests/test_net.py
index 84839fd7..fac82678 100644
--- a/tests/unittests/test_net.py
+++ b/tests/unittests/test_net.py
@@ -1442,6 +1442,7 @@ DEFAULT_DEV_ATTRS = {
         "address": "07-1C-C6-75-A4-BE",
         "device/driver": None,
         "device/device": None,
+        "name_assign_type": "4",
     }
 }
 
@@ -1489,11 +1490,14 @@ class TestGenerateFallbackConfig(CiTestCase):
             'eth0': {
                 'bridge': False, 'carrier': False, 'dormant': False,
                 'operstate': 'down', 'address': '00:11:22:33:44:55',
-                'device/driver': 'hv_netsvc', 'device/device': '0x3'},
+                'device/driver': 'hv_netsvc', 'device/device': '0x3',
+                'name_assign_type': '4'},
             'eth1': {
                 'bridge': False, 'carrier': False, 'dormant': False,
                 'operstate': 'down', 'address': '00:11:22:33:44:55',
-                'device/driver': 'mlx4_core', 'device/device': '0x7'},
+                'device/driver': 'mlx4_core', 'device/device': '0x7',
+                'name_assign_type': '4'},
+
         }
 
         tmp_dir = self.tmp_dir()
@@ -1549,11 +1553,13 @@ iface eth0 inet dhcp
             'eth1': {
                 'bridge': False, 'carrier': False, 'dormant': False,
                 'operstate': 'down', 'address': '00:11:22:33:44:55',
-                'device/driver': 'hv_netsvc', 'device/device': '0x3'},
+                'device/driver': 'hv_netsvc', 'device/device': '0x3',
+                'name_assign_type': '4'},
             'eth0': {
                 'bridge': False, 'carrier': False, 'dormant': False,
                 'operstate': 'down', 'address': '00:11:22:33:44:55',
-                'device/driver': 'mlx4_core', 'device/device': '0x7'},
+                'device/driver': 'mlx4_core', 'device/device': '0x7',
+                'name_assign_type': '4'},
         }
 
         tmp_dir = self.tmp_dir()
@@ -1602,6 +1608,65 @@ iface eth1 inet dhcp
         ]
         self.assertEqual(", ".join(expected_rule) + '\n', contents.lstrip())
 
+    @mock.patch("cloudinit.util.udevadm_settle")
+    @mock.patch("cloudinit.net.sys_dev_path")
+    @mock.patch("cloudinit.net.read_sys_net")
+    @mock.patch("cloudinit.net.get_devicelist")
+    def test_unstable_names(self, mock_get_devicelist, mock_read_sys_net,
+                            mock_sys_dev_path, mock_settle):
+        """verify that udevadm settle is called when we find unstable names"""
+        devices = {
+            'eth0': {
+                'bridge': False, 'carrier': False, 'dormant': False,
+                'operstate': 'down', 'address': '00:11:22:33:44:55',
+                'device/driver': 'hv_netsvc', 'device/device': '0x3',
+                'name_assign_type': False},
+            'ens4': {
+                'bridge': False, 'carrier': False, 'dormant': False,
+                'operstate': 'down', 'address': '00:11:22:33:44:55',
+                'device/driver': 'mlx4_core', 'device/device': '0x7',
+                'name_assign_type': '4'},
+
+        }
+
+        tmp_dir = self.tmp_dir()
+        _setup_test(tmp_dir, mock_get_devicelist,
+                    mock_read_sys_net, mock_sys_dev_path,
+                    dev_attrs=devices)
+        net.generate_fallback_config(config_driver=True)
+        self.assertEqual(1, mock_settle.call_count)
+
+    @mock.patch("cloudinit.util.get_cmdline")
+    @mock.patch("cloudinit.util.udevadm_settle")
+    @mock.patch("cloudinit.net.sys_dev_path")
+    @mock.patch("cloudinit.net.read_sys_net")
+    @mock.patch("cloudinit.net.get_devicelist")
+    def test_unstable_names_disabled(self, mock_get_devicelist,
+                                     mock_read_sys_net, mock_sys_dev_path,
+                                     mock_settle, m_get_cmdline):
+        """verify udevadm settle not called when cmdline has net.ifnames=0"""
+        devices = {
+            'eth0': {
+                'bridge': False, 'carrier': False, 'dormant': False,
+                'operstate': 'down', 'address': '00:11:22:33:44:55',
+                'device/driver': 'hv_netsvc', 'device/device': '0x3',
+                'name_assign_type': False},
+            'ens4': {
+                'bridge': False, 'carrier': False, 'dormant': False,
+                'operstate': 'down', 'address': '00:11:22:33:44:55',
+                'device/driver': 'mlx4_core', 'device/device': '0x7',
+                'name_assign_type': '4'},
+
+        }
+
+        m_get_cmdline.return_value = 'net.ifnames=0'
+        tmp_dir = self.tmp_dir()
+        _setup_test(tmp_dir, mock_get_devicelist,
+                    mock_read_sys_net, mock_sys_dev_path,
+                    dev_attrs=devices)
+        net.generate_fallback_config(config_driver=True)
+        self.assertEqual(0, mock_settle.call_count)
+
 
 class TestSysConfigRendering(CiTestCase):