Merge "libvirt: Add a workaround to skip compareCPU() on destination"

Author: Zuul

nova/conf/workarounds.py

@@ -401,6 +401,14 @@
 Related options:
 
 * :oslo.config:option:`quota.driver`
+"""),
+    cfg.BoolOpt('skip_cpu_compare_on_dest',
+               default=False,
+               help="""
+With the libvirt driver, during live migration, skip comparing guest CPU
+with the destination host. When using QEMU >= 2.9 and libvirt >=
+4.4.0, libvirt will do the correct thing with respect to checking CPU
+compatibility on the destination host during live migration.
 """),
 ]
 

nova/tests/unit/virt/libvirt/test_driver.py

@@ -10915,6 +10915,25 @@ def test_check_can_live_migrate_guest_cpu_none_model(
                           'serial_listen_addr': None},
                          result.obj_to_primitive()['nova_object.data'])
 
+    @mock.patch(
+        'nova.network.neutron.API.has_port_binding_extension',
+        new=mock.Mock(return_value=False))
+    @mock.patch.object(libvirt_driver.LibvirtDriver,
+                       '_create_shared_storage_test_file',
+                       return_value='fake')
+    @mock.patch.object(libvirt_driver.LibvirtDriver, '_compare_cpu')
+    def test_check_can_live_migrate_guest_cpu_none_model_skip_compare(
+            self, mock_cpu, mock_test_file):
+        self.flags(group='workarounds', skip_cpu_compare_on_dest=True)
+        instance_ref = objects.Instance(**self.test_instance)
+        instance_ref.vcpu_model = test_vcpu_model.fake_vcpumodel
+        instance_ref.vcpu_model.model = None
+        drvr = libvirt_driver.LibvirtDriver(fake.FakeVirtAPI(), False)
+        compute_info = {'cpu_info': 'asdf', 'disk_available_least': 1}
+        drvr.check_can_live_migrate_destination(
+            self.context, instance_ref, compute_info, compute_info)
+        mock_cpu.assert_not_called()
+
     @mock.patch(
         'nova.network.neutron.API.has_port_binding_extension',
         new=mock.Mock(return_value=False))

nova/virt/libvirt/driver.py

@@ -9330,15 +9330,16 @@ def check_can_live_migrate_destination(self, context, instance,
         disk_available_mb = (
             (disk_available_gb * units.Ki) - CONF.reserved_host_disk_mb)
 
-        # Compare CPU
-        try:
-            if not instance.vcpu_model or not instance.vcpu_model.model:
-                source_cpu_info = src_compute_info['cpu_info']
-                self._compare_cpu(None, source_cpu_info, instance)
-            else:
-                self._compare_cpu(instance.vcpu_model, None, instance)
-        except exception.InvalidCPUInfo as e:
-            raise exception.MigrationPreCheckError(reason=e)
+        if not CONF.workarounds.skip_cpu_compare_on_dest:
+            # Compare CPU
+            try:
+                if not instance.vcpu_model or not instance.vcpu_model.model:
+                    source_cpu_info = src_compute_info['cpu_info']
+                    self._compare_cpu(None, source_cpu_info, instance)
+                else:
+                    self._compare_cpu(instance.vcpu_model, None, instance)
+            except exception.InvalidCPUInfo as e:
+                raise exception.MigrationPreCheckError(reason=e)
 
         # Create file on storage, to be checked on source host
         filename = self._create_shared_storage_test_file(instance)

releasenotes/notes/skip-compare-cpu-on-dest-6ae419ddd61fd0f8.yaml

@@ -0,0 +1,24 @@
+---
+issues:
+  - |
+    Nova's use of libvirt's compareCPU() API served its purpose over the
+    years, but its design limitations break live migration in subtle
+    ways. For example, the compareCPU() API compares against the host
+    physical CPUID. Some of the features from this CPUID aren not
+    exposed by KVM, and then there are some features that KVM emulates
+    that are not in the host CPUID. The latter can cause bogus live
+    migration failures.
+
+    With QEMU >=2.9 and libvirt >= 4.4.0, libvirt will do the right
+    thing in terms of CPU compatibility checks on the destination host
+    during live migration. Nova satisfies these minimum version
+    requirements by a good margin. So, this workaround provides a way to
+    skip the CPU comparison check on the destination host before
+    migrating a guest, and let libvirt handle it correctly.
+
+    This workaround will be deprecated and removed once Nova replaces
+    the older libvirt APIs with their newer counterparts. The work is
+    being tracked via this `blueprint
+    cpu-selection-with-hypervisor-consideration`_.
+
+    .. _blueprint cpu-selection-with-hypervisor-consideration: https://blueprints.launchpad.net/nova/+spec/cpu-selection-with-hypervisor-consideration