本文主要包含openstack,热迁移,openstack,虚拟机迁移等服务器相关知识,尛鱼 希望可以进行参考
话说虚机迁移分为冷迁移以及热迁移，所谓热迁移用度娘的话说即是：热迁移（Live Migration，又叫动态迁移、实时迁移），即虚机保存/恢复(Save/Restore)：将整个虚拟机的运行状态完整保存下来，同时可以快速的恢复到原有硬件平台甚至是不同硬件平台上。恢复以后，虚机仍旧平滑运行，用户不会察觉到任何差异。OpenStack的虚机迁移是基于Libvirt实现的，下面来看看Openstack虚机热迁移的具体代码实现。
首先，由API入口进入到nova/api/openstack/compute/contrib/admin_actions.py
@wsgi.action('os-migrateLive')
def _migrate_live(self, req, id, body):
"""Permit admins to (live) migrate a server to a new host."""
context = req.environ["nova.context"]
authorize(context, 'migrateLive')
try:
block_migration = body["os-migrateLive"]["block_migration"]
disk_over_commit = body["os-migrateLive"]["disk_over_commit"]
host = body["os-migrateLive"]["host"]
except (TypeError, KeyError):
msg = _("host, block_migration and disk_over_commit must "
"be specified for live migration.")
raise exc.HTTPBadRequest(explanation=msg)
try:
block_migration = strutils.bool_from_string(block_migration,
strict=True)
disk_over_commit = strutils.bool_from_string(disk_over_commit,
strict=True)
except ValueError as err:
raise exc.HTTPBadRequest(explanation=str(err))
try:
instance = self.compute_api.get(context, id, want_objects=True)
self.compute_api.live_migrate(context, instance, block_migration,
disk_over_commit, host)
except (exception.ComputeServiceUnavailable,
exception.InvalidHypervisorType,
exception.UnableToMigrateToSelf,
exception.DestinationHypervisorTooOld,
exception.NoValidHost,
exception.InvalidLocalStorage,
exception.InvalidSharedStorage,
exception.MigrationPreCheckError) as ex:
raise exc.HTTPBadRequest(explanation=ex.format_message())
except exception.InstanceNotFound as e:
raise exc.HTTPNotFound(explanation=e.format_message())
except exception.InstanceInvalidState as state_error:
common.raise_http_conflict_for_instance_invalid_state(state_error,
'os-migrateLive')
except Exception:
if host is None:
msg = _("Live migration of instance %s to another host "
"failed") % id
else:
msg = _("Live migration of instance %(id)s to host %(host)s "
"failed") % {'id': id, 'host': host}
LOG.exception(msg)
# Return messages from scheduler
raise exc.HTTPBadRequest(explanation=msg)
return webob.Response(status_int=202)
这里第一行可以看到是与API文档的第二行照应的：
{
"os-migrateLive": {
"host": "0443e9a1254044d8b99f35eace132080",
"block_migration": false,
"disk_over_commit": false
}
}
好了，源码中其实执行迁移工作的就是第26、27行的一条语句：
self.compute_api.live_migrate(context, instance, block_migration,
disk_over_commit, host)
由这句进入到nova/compute/api.py中，源码如下：
@check_instance_cell
@check_instance_state(vm_state=[vm_states.ACTIVE])
def live_migrate(self, context, instance, block_migration,
disk_over_commit, host_name):
"""Migrate a server lively to a new host."""
LOG.debug(_("Going to try to live migrate instance to %s"),
host_name or "another host", instance=instance)
instance.task_state = task_states.MIGRATING
instance.save(expected_task_state=[None])
self.compute_task_api.live_migrate_instance(context, instance,
host_name, block_migration=block_migration,
disk_over_commit=disk_over_commit)
第2行是一个装饰器，用于在进入API方法之前，检测虚拟机和/或任务的状态， 如果实例处于错误的状态，将会引发异常；接下来实时迁移虚机到新的主机，并将虚机状态置于“migrating”,然后由12行进入nova/conductor/api.py
def live_migrate_instance(self, context, instance, host_name,
block_migration, disk_over_commit):
scheduler_hint = {'host': host_name}
self._manager.migrate_server(
context, instance, scheduler_hint, True, False, None,
block_migration, disk_over_commit, None)
将主机名存入字典scheduler_hint中，然后调用nova/conductor/manager.py方法migrate_server,
def migrate_server(self, context, instance, scheduler_hint, live, rebuild,
flavor, block_migration, disk_over_commit, reservations=None):
if instance and not isinstance(instance, instance_obj.Instance):
# NOTE(danms): Until v2 of the RPC API, we need to tolerate
# old-world instance objects here
attrs = ['metadata', 'system_metadata', 'info_cache',
'security_groups']
instance = instance_obj.Instance._from_db_object(
context, instance_obj.Instance(), instance,
expected_attrs=attrs)
if live and not rebuild and not flavor:
self._live_migrate(context, instance, scheduler_hint,
block_migration, disk_over_commit)
elif not live and not rebuild and flavor:
instance_uuid = instance['uuid']
with compute_utils.EventReporter(context, self.db,
'cold_migrate', instance_uuid):
self._cold_migrate(context, instance, flavor,
scheduler_hint['filter_properties'],
reservations)
else:
raise NotImplementedError()
由于在nova/conductor/api.py中传过来的参数是
self._manager.migrate_server(
context, instance, scheduler_hint, True, False, None,
block_migration, disk_over_commit, None)
因此live是True，rebuild是Flase,flavor是None，执行第12、13行代码：
if live and not rebuild and not flavor:
self._live_migrate(context, instance, scheduler_hint,
block_migration, disk_over_commit)
_live_migrate代码如下：
def _live_migrate(self, context, instance, scheduler_hint,
block_migration, disk_over_commit):
destination = scheduler_hint.get("host")
try:
live_migrate.execute(context, instance, destination,
block_migration, disk_over_commit)
except (exception.NoValidHost,
exception.ComputeServiceUnavailable,
exception.InvalidHypervisorType,
exception.InvalidCPUInfo,
exception.UnableToMigrateToSelf,
exception.DestinationHypervisorTooOld,
exception.InvalidLocalStorage,
exception.InvalidSharedStorage,
exception.HypervisorUnavailable,
exception.MigrationPreCheckError) as ex:
with excutils.save_and_reraise_exception():
#TODO(johngarbutt) - eventually need instance actions here
request_spec = {'instance_properties': {
'uuid': instance['uuid'], },
}
scheduler_utils.set_vm_state_and_notify(context,
'compute_task', 'migrate_server',
dict(vm_state=instance['vm_state'],
task_state=None,
expected_task_state=task_states.MIGRATING,),
ex, request_spec, self.db)
except Exception as ex:
LOG.error(_('Migration of instance %(instance_id)s to host'
' %(dest)s unexpectedly failed.'),
{'instance_id': instance['uuid'], 'dest': destination},
exc_info=True)
raise exception.MigrationError(reason=ex)
首先，第三行中将主机名赋给destination,然后执行迁移，后面的都是异常的捕捉，执行迁移的代码分为两部分，先看第一部分，在nova/conductor/tasks/live_migrate.py的184行左右：