一,api层
1、nova.api.openstack.compute.api.py
ServersController.create()方法处理创建虚拟机接口。该方法执行self.compute_api.create()
其中compute是nova.compute.api
@wsgi.response(202)
@extensions.expected_errors((400, 403, 409, 413))
@validation.schema(schema_server_create_v20, '2.0', '2.0')
@validation.schema(schema_server_create, '2.1', '2.18')
@validation.schema(schema_server_create_v219, '2.19')
def create(self, req, body):
"""Creates a new server for a given user."""
context = req.environ['nova.context']
server_dict = body['server']
password = self._get_server_admin_password(server_dict)
name = common.normalize_name(server_dict['name'])
if api_version_request.is_supported(req, min_version='2.19'):
if 'description' in server_dict:
# This is allowed to be None
description = server_dict['description']
else:
# No default description
description = None
else:
description = name
# Arguments to be passed to instance create function
create_kwargs = {}
# Query extensions which want to manipulate the keyword
# arguments.
# NOTE(cyeoh): This is the hook that extensions use
# to replace the extension specific code below.
# When the extensions are ported this will also result
# in some convenience function from this class being
# moved to the extension
if list(self.create_extension_manager):
self.create_extension_manager.map(self._create_extension_point,
server_dict, create_kwargs, body)
availability_zone = create_kwargs.pop("availability_zone", None)
target = {
'project_id': context.project_id,
'user_id': context.user_id,
'availability_zone': availability_zone}
authorize(context, target, 'create')
# TODO(Shao He, Feng) move this policy check to os-availabilty-zone
# extension after refactor it.
parse_az = self.compute_api.parse_availability_zone
availability_zone, host, node = parse_az(context, availability_zone)
if host or node:
authorize(context, {}, 'create:forced_host')
block_device_mapping = create_kwargs.get("block_device_mapping")
# TODO(Shao He, Feng) move this policy check to os-block-device-mapping
# extension after refactor it.
if block_device_mapping:
authorize(context, target, 'create:attach_volume')
image_uuid = self._image_from_req_data(server_dict, create_kwargs)
# NOTE(cyeoh): Although an extension can set
# return_reservation_id in order to request that a reservation
# id be returned to the client instead of the newly created
# instance information we do not want to pass this parameter
# to the compute create call which always returns both. We use
# this flag after the instance create call to determine what
# to return to the client
return_reservation_id = create_kwargs.pop('return_reservation_id',
False)
requested_networks = None
if ('os-networks' in self.extension_info.get_extensions()
or utils.is_neutron()):
requested_networks = server_dict.get('networks')
if requested_networks is not None:
requested_networks = self._get_requested_networks(
requested_networks)
if requested_networks and len(requested_networks):
authorize(context, target, 'create:attach_network')
try:
flavor_id = self._flavor_id_from_req_data(body)
except ValueError:
msg = _("Invalid flavorRef provided.")
raise exc.HTTPBadRequest(explanation=msg)
try:
inst_type = flavors.get_flavor_by_flavor_id(
flavor_id, ctxt=context, read_deleted="no")
(instances, resv_id) = self.compute_api.create(context,
inst_type,
image_uuid,
display_name=name,
display_description=description,
availability_zone=availability_zone,
forced_host=host, forced_node=node,
metadata=server_dict.get('metadata', {}),
admin_password=password,
requested_networks=requested_networks,
check_server_group_quota=True,
**create_kwargs)
except (exception.QuotaError,
exception.PortLimitExceeded) as error:
raise exc.HTTPForbidden(
explanation=error.format_message())
except exception.ImageNotFound:
msg = _("Can not find requested image")
raise exc.HTTPBadRequest(explanation=msg)
except exception.FlavorNotFound:
msg = _("Invalid flavorRef provided.")
raise exc.HTTPBadRequest(explanation=msg)
except exception.KeypairNotFound:
msg = _("Invalid key_name provided.")
raise exc.HTTPBadRequest(explanation=msg)
except exception.ConfigDriveInvalidValue:
msg = _("Invalid config_drive provided.")
raise exc.HTTPBadRequest(explanation=msg)
except exception.ExternalNetworkAttachForbidden as error:
raise exc.HTTPForbidden(explanation=error.format_message())
except messaging.RemoteError as err:
msg = "%(err_type)s: %(err_msg)s" % {'err_type': err.exc_type,
'err_msg': err.value}
raise exc.HTTPBadRequest(explanation=msg)
except UnicodeDecodeError as error:
msg = "UnicodeError: %s" % error
raise exc.HTTPBadRequest(explanation=msg)
except (exception.ImageNotActive,
exception.ImageBadRequest,
exception.FixedIpNotFoundForAddress,
exception.FlavorDiskTooSmall,
exception.FlavorMemoryTooSmall,
exception.InvalidMetadata,
exception.InvalidRequest,
exception.InvalidVolume,
exception.MultiplePortsNotApplicable,
exception.InvalidFixedIpAndMaxCountRequest,
exception.InstanceUserDataMalformed,
exception.InstanceUserDataTooLarge,
exception.PortNotFound,
exception.FixedIpAlreadyInUse,
exception.SecurityGroupNotFound,
exception.PortRequiresFixedIP,
exception.NetworkRequiresSubnet,
exception.NetworkNotFound,
exception.NetworkDuplicated,
exception.InvalidBDM,
exception.InvalidBDMSnapshot,
exception.InvalidBDMVolume,
exception.InvalidBDMImage,
exception.InvalidBDMBootSequence,
exception.InvalidBDMLocalsLimit,
exception.InvalidBDMVolumeNotBootable,
exception.InvalidBDMEphemeralSize,
exception.InvalidBDMFormat,
exception.InvalidBDMSwapSize,
exception.AutoDiskConfigDisabledByImage,
exception.ImageNUMATopologyIncomplete,
exception.ImageNUMATopologyForbidden,
exception.ImageNUMATopologyAsymmetric,
exception.ImageNUMATopologyCPUOutOfRange,
exception.ImageNUMATopologyCPUDuplicates,
exception.ImageNUMATopologyCPUsUnassigned,
exception.ImageNUMATopologyMemoryOutOfRange,
exception.InstanceGroupNotFound) as error:
raise exc.HTTPBadRequest(explanation=error.format_message())
except (exception.PortInUse,
exception.InstanceExists,
exception.NetworkAmbiguous,
exception.NoUniqueMatch) as error:
raise exc.HTTPConflict(explanation=error.format_message())
# If the caller wanted a reservation_id, return it
if return_reservation_id:
# NOTE(cyeoh): In v3 reservation_id was wrapped in
# servers_reservation but this is reverted for V2 API
# compatibility. In the long term with the tasks API we
# will probably just drop the concept of reservation_id
return wsgi.ResponseObject({'reservation_id': resv_id})
req.cache_db_instances(instances)
server = self._view_builder.create(req, instances[0])
if CONF.enable_instance_password:
server['server']['adminPass'] = password
robj = wsgi.ResponseObject(server)
return self._add_location(robj)
2、nova.compute.api.py
在此文件处理过程中,除了校验参数外,还有如下步骤
a、通过self._provision_instances()进行校验和在数据库nova创建记录
b、通过self.compute_task_api.build_instances()进入conductor组件,启动创建虚拟机的协程任务(其中compute_task_api位置为nova.conductor.api.py中的ComputeTaskAPI()类)
@hooks.add_hook("create_instance")condo
def create(self, context, instance_type,
image_href, kernel_id=None, ramdisk_id=None,
min_count=None, max_count=None,
display_name=None, display_description=None,
key_name=None, key_data=None, security_group=None,
availability_zone=None, forced_host=None, forced_node=None,
user_data=None, metadata=None, injected_files=None,
admin_password=None, block_device_mapping=None,
access_ip_v4=None, access_ip_v6=None, requested_networks=None,
config_drive=None, auto_disk_config=None, scheduler_hints=None,
legacy_bdm=True, shutdown_terminate=False,
check_server_group_quota=False):
"""Provision instances, sending instance information to the
scheduler. The scheduler will determine where the instance(s)
go and will handle creating the DB entries.
Returns a tuple of (instances, reservation_id)
"""
# Check policies up front to fail before performing more expensive work
self._check_create_policies(context, availability_zone,
requested_networks, block_device_mapping, forced_host,
forced_node)
if requested_networks and max_count > 1:
self._check_multiple_instances_and_specified_ip(requested_networks)
if utils.is_neutron():
self._check_multiple_instances_neutron_ports(
requested_networks)
if availability_zone:
available_zones = availability_zones.\
get_availability_zones(context.elevated(), True)
if forced_host is None and availability_zone not in \
available_zones:
msg = _('The requested availability zone is not available')
raise exception.InvalidRequest(msg)
filter_properties = scheduler_utils.build_filter_properties(
scheduler_hints, forced_host, forced_node, instance_type)
return self._create_instance(
context, instance_type,
image_href, kernel_id, ramdisk_id,
min_count, max_count,
display_name, display_description,
key_name, key_data, security_group,
availability_zone, user_data, metadata,
injected_files, admin_password,
access_ip_v4, access_ip_v6,
requested_networks, config_drive,
block_device_mapping, auto_disk_config,
filter_properties=filter_properties,
legacy_bdm=legacy_bdm,
shutdown_terminate=shutdown_terminate,
check_server_group_quota=check_server_group_quota)
def _create_instance(self, context, instance_type,
image_href, kernel_id, ramdisk_id,
min_count, max_count,
display_name, display_description,
key_name, key_data, security_groups,
availability_zone, user_data, metadata, injected_files,
admin_password, access_ip_v4, access_ip_v6,
requested_networks, config_drive,
block_device_mapping, auto_disk_config, filter_properties,
reservation_id=None, legacy_bdm=True, shutdown_terminate=False,
check_server_group_quota=False):
"""Verify all the input parameters regardless of the provisioning
strategy being performed and schedule the instance(s) for
creation.
"""
# Normalize and setup some parameters
if reservation_id is None:
reservation_id = utils.generate_uid('r')
security_groups = security_groups or ['default']
min_count = min_count or 1
max_count = max_count or min_count
block_device_mapping = block_device_mapping or []
if image_href:
image_id, boot_meta = self._get_image(context, image_href)
else:
image_id = None
boot_meta = self._get_bdm_image_metadata(
context, block_device_mapping, legacy_bdm)
self._check_auto_disk_config(image=boot_meta,
auto_disk_config=auto_disk_config)
base_options, max_net_count = self._validate_and_build_base_options(
context, instance_type, boot_meta, image_href, image_id,
kernel_id, ramdisk_id, display_name, display_description,
key_name, key_data, security_groups, availability_zone,
user_data, metadata, access_ip_v4, access_ip_v6,
requested_networks, config_drive, auto_disk_config,
reservation_id, max_count)
# max_net_count is the maximum number of instances requested by the
# user adjusted for any network quota constraints, including
# consideration of connections to each requested network
if max_net_count < min_count:
raise exception.PortLimitExceeded()
elif max_net_count < max_count:
LOG.info(_LI("max count reduced from %(max_count)d to "
"%(max_net_count)d due to network port quota"),
{'max_count': max_count,
'max_net_count': max_net_count})
max_count = max_net_count
block_device_mapping = self._check_and_transform_bdm(context,
base_options, instance_type, boot_meta, min_count, max_count,
block_device_mapping, legacy_bdm)
# We can't do this check earlier because we need bdms from all sources
# to have been merged in order to get the root bdm.
self._checks_for_create_and_rebuild(context, image_id, boot_meta,
instance_type, metadata, injected_files,
block_device_mapping.root_bdm())
instance_group = self._get_requested_instance_group(context,
filter_properties, check_server_group_quota)
instances = self._provision_instances(context, instance_type,
min_count, max_count, base_options, boot_meta, security_groups,
block_device_mapping, shutdown_terminate,
instance_group, check_server_group_quota, filter_properties)
for instance in instances:
self._record_action_start(context, instance,
instance_actions.CREATE)
self.compute_task_api.build_instances(context,
instances=instances, image=boot_meta,
filter_properties=filter_properties,
admin_password=admin_password,
injected_files=injected_files,
requested_networks=requested_networks,
security_groups=security_groups,
block_device_mapping=block_device_mapping,
legacy_bdm=False)
return (instances, reservation_id)
2,conductor组件
1、nova-conductor对外暴露的虚拟机创建接口为nova.conductor.api.py文件中的ComputeTaskAPI()类build_instances()方法。
def build_instances(self, context, instances, image, filter_properties,
admin_password, injected_files, requested_networks,
security_groups, block_device_mapping, legacy_bdm=True):
self.conductor_compute_rpcapi.build_instances(context,
instances=instances, image=image,
filter_properties=filter_properties,
admin_password=admin_password, injected_files=injected_files,
requested_networks=requested_networks,
security_groups=security_groups,
block_device_mapping=block_device_mapping,
legacy_bdm=legacy_bdm)
该方法通过调用nova.conductor.rpcapi.py中的build_instances()发送rpc信息给conductor的manager,至此创建虚拟机的任务完成从api组件到conductor组件的传递
def build_instances(self, context, instances, image, filter_properties,
admin_password, injected_files, requested_networks,
security_groups, block_device_mapping, legacy_bdm=True):
image_p = jsonutils.to_primitive(image)
version = '1.10'
if not self.client.can_send_version(version):
version = '1.9'
if 'instance_type' in filter_properties:
flavor = filter_properties['instance_type']
flavor_p = objects_base.obj_to_primitive(flavor)
filter_properties = dict(filter_properties,
instance_type=flavor_p)
kw = {'instances': instances, 'image': image_p,
'filter_properties': filter_properties,
'admin_password': admin_password,
'injected_files': injected_files,
'requested_networks': requested_networks,
'security_groups': security_groups}
if not self.client.can_send_version(version):
version = '1.8'
kw['requested_networks'] = kw['requested_networks'].as_tuples()
if not self.client.can_send_version('1.7'):
version = '1.5'
bdm_p = objects_base.obj_to_primitive(block_device_mapping)
kw.update({'block_device_mapping': bdm_p,
'legacy_bdm': legacy_bdm})
cctxt = self.client.prepare(version=version)
cctxt.cast(context, 'build_instances', **kw)
需要注意的是此次采用rpc.cast方法调用,是异步接口
2、nova.conductor.manager.py处理上步传递的rpc.cast(context, ‘build_instances’, **kw),执行方法是build_instances
def build_instances(self, context, instances, image, filter_properties,
admin_password, injected_files, requested_networks,
security_groups, block_device_mapping=None, legacy_bdm=True):
# TODO(ndipanov): Remove block_device_mapping and legacy_bdm in version
# 2.0 of the RPC API.
# TODO(danms): Remove this in version 2.0 of the RPC API
if (requested_networks and
not isinstance(requested_networks,
objects.NetworkRequestList)):
requested_networks = objects.NetworkRequestList(
objects=[objects.NetworkRequest.from_tuple(t)
for t in requested_networks])
# TODO(melwitt): Remove this in version 2.0 of the RPC API
flavor = filter_properties.get('instance_type')
if flavor and not isinstance(flavor, objects.Flavor):
# Code downstream may expect extra_specs to be populated since it
# is receiving an object, so lookup the flavor to ensure this.
flavor = objects.Flavor.get_by_id(context, flavor['id'])
filter_properties = dict(filter_properties, instance_type=flavor)
request_spec = {}
try:
# check retry policy. Rather ugly use of instances[0]...
# but if we've exceeded max retries... then we really only
# have a single instance.
scheduler_utils.populate_retry(
filter_properties, instances[0].uuid)
request_spec = scheduler_utils.build_request_spec(
context, image, instances)
hosts = self._schedule_instances(
context, request_spec, filter_properties)
except Exception as exc:
updates = {'vm_state': vm_states.ERROR, 'task_state': None}
for instance in instances:
self._set_vm_state_and_notify(
context, instance.uuid, 'build_instances', updates,
exc, request_spec)
self._cleanup_allocated_networks(
context, instance, requested_networks)
return
for (instance, host) in six.moves.zip(instances, hosts):
try:
instance.refresh()
except (exception.InstanceNotFound,
exception.InstanceInfoCacheNotFound):
LOG.debug('Instance deleted during build', instance=instance)
continue
local_filter_props = copy.deepcopy(filter_properties)
scheduler_utils.populate_filter_properties(local_filter_props,
host)
# The block_device_mapping passed from the api doesn't contain
# instance specific information
bdms = objects.BlockDeviceMappingList.get_by_instance_uuid(
context, instance.uuid)
self.compute_rpcapi.build_and_run_instance(context,
instance=instance, host=host['host'], image=image,
request_spec=request_spec,
filter_properties=local_filter_props,
admin_password=admin_password,
injected_files=injected_files,
requested_networks=requested_networks,
security_groups=security_groups,
block_device_mapping=bdms, node=host['nodename'],
limits=host['limits'])
该方法实现的重要功能有如下几点
- 执行hosts = self._schedule_instances(context, request_spec, filter_properties)进行调度,为虚拟机创建选择最合适的服务节点执行,关于调度的细节相见第五节分析
- 在获取到host后,执行self.compute_rpcapi.build_and_run_instance(),调用对应计算节点的compute服务rpc接口创建虚拟机,关于调用compute_rpcapi见第三节compute源码分析
三,compute计算节点
1、nova.compute.rpcapi.py接收到conductor调用的方法build_and_run_instance
def build_and_run_instance(self, ctxt, instance, host, image, request_spec,
filter_properties, admin_password=None, injected_files=None,
requested_networks=None, security_groups=None,
block_device_mapping=None, node=None, limits=None):
version = '4.0'
cctxt = self.client.prepare(server=host, version=version)
cctxt.cast(ctxt, 'build_and_run_instance', instance=instance,
image=image, request_spec=request_spec,
filter_properties=filter_properties,
admin_password=admin_password,
injected_files=injected_files,
requested_networks=requested_networks,
security_groups=security_groups,
block_device_mapping=block_device_mapping, node=node,
limits=limits)
该接口方法中,通过host初始化创建调用计算节点的client,调用cast方法远程执行nova.compute.manager.py中的build_and_run_instance。
至此,创建虚拟机的任务从conductor传递到compute计算节点
2、nova.compute.manager.py执行虚拟机创建
@wrap_exception()
@reverts_task_state
@wrap_instance_fault
def build_and_run_instance(self, context, instance, image, request_spec,
filter_properties, admin_password=None,
injected_files=None, requested_networks=None,
security_groups=None, block_device_mapping=None,
node=None, limits=None):
@utils.synchronized(instance.uuid)
def _locked_do_build_and_run_instance(*args, **kwargs):
# NOTE(danms): We grab the semaphore with the instance uuid
# locked because we could wait in line to build this instance
# for a while and we want to make sure that nothing else tries
# to do anything with this instance while we wait.
with self._build_semaphore:
self._do_build_and_run_instance(*args, **kwargs)
# NOTE(danms): We spawn here to return the RPC worker thread back to
# the pool. Since what follows could take a really long time, we don't
# want to tie up RPC workers.
utils.spawn_n(_locked_do_build_and_run_instance,
context, instance, image, request_spec,
filter_properties, admin_password, injected_files,
requested_networks, security_groups,
block_device_mapping, node, limits)
执行的工作如下
通过utils.spawn_n()启动协程创建虚拟机(没有返回信息),协程执行的方法是_locked_do_build_and_run_instance封装的_do_build_and_run_instance()
@hooks.add_hook('build_instance')
@wrap_exception()
@reverts_task_state
@wrap_instance_event
@wrap_instance_fault
def _do_build_and_run_instance(self, context, instance, image,
request_spec, filter_properties, admin_password, injected_files,
requested_networks, security_groups, block_device_mapping,
node=None, limits=None):
try:
LOG.debug('Starting instance...', context=context,
instance=instance)
instance.vm_state = vm_states.BUILDING
instance.task_state = None
instance.save(expected_task_state=
(task_states.SCHEDULING, None))
except exception.InstanceNotFound:
msg = 'Instance disappeared before build.'
LOG.debug(msg, instance=instance)
return build_results.FAILED
except exception.UnexpectedTaskStateError as e:
LOG.debug(e.format_message(), instance=instance)
return build_results.FAILED
# b64 decode the files to inject:
decoded_files = self._decode_files(injected_files)
if limits is None:
limits = {}
if node is None:
node = self.driver.get_available_nodes(refresh=True)[0]
LOG.debug('No node specified, defaulting to %s', node,
instance=instance)
try:
with timeutils.StopWatch() as timer:
self._build_and_run_instance(context, instance, image,
decoded_files, admin_password, requested_networks,
security_groups, block_device_mapping, node, limits,
filter_properties)
LOG.info(_LI('Took %0.2f seconds to build instance.'),
timer.elapsed(), instance=instance)
return build_results.ACTIVE
except exception.RescheduledException as e:
retry = filter_properties.get('retry')
if not retry:
# no retry information, do not reschedule.
LOG.debug("Retry info not present, will not reschedule",
instance=instance)
self._cleanup_allocated_networks(context, instance,
requested_networks)
compute_utils.add_instance_fault_from_exc(context,
instance, e, sys.exc_info(),
fault_message=e.kwargs['reason'])
self._nil_out_instance_obj_host_and_node(instance)
self._set_instance_obj_error_state(context, instance,
clean_task_state=True)
return build_results.FAILED
LOG.debug(e.format_message(), instance=instance)
# This will be used for logging the exception
retry['exc'] = traceback.format_exception(*sys.exc_info())
# This will be used for setting the instance fault message
retry['exc_reason'] = e.kwargs['reason']
# NOTE(comstud): Deallocate networks if the driver wants
# us to do so.
# NOTE(vladikr): SR-IOV ports should be deallocated to
# allow new sriov pci devices to be allocated on a new host.
# Otherwise, if devices with pci addresses are already allocated
# on the destination host, the instance will fail to spawn.
# info_cache.network_info should be present at this stage.
if (self.driver.deallocate_networks_on_reschedule(instance) or
self.deallocate_sriov_ports_on_reschedule(instance)):
self._cleanup_allocated_networks(context, instance,
requested_networks)
else:
# NOTE(alex_xu): Network already allocated and we don't
# want to deallocate them before rescheduling. But we need
# to cleanup those network resources setup on this host before
# rescheduling.
self.network_api.cleanup_instance_network_on_host(
context, instance, self.host)
self._nil_out_instance_obj_host_and_node(instance)
instance.task_state = task_states.SCHEDULING
instance.save()
self.compute_task_api.build_instances(context, [instance],
image, filter_properties, admin_password,
injected_files, requested_networks, security_groups,
block_device_mapping)
return build_results.RESCHEDULED
except (exception.InstanceNotFound,
exception.UnexpectedDeletingTaskStateError):
msg = 'Instance disappeared during build.'
LOG.debug(msg, instance=instance)
self._cleanup_allocated_networks(context, instance,
requested_networks)
return build_results.FAILED
except exception.BuildAbortException as e:
LOG.exception(e.format_message(), instance=instance)
self._cleanup_allocated_networks(context, instance,
requested_networks)
self._cleanup_volumes(context, instance.uuid,
block_device_mapping, raise_exc=False)
compute_utils.add_instance_fault_from_exc(context, instance,
e, sys.exc_info())
self._nil_out_instance_obj_host_and_node(instance)
self._set_instance_obj_error_state(context, instance,
clean_task_state=True)
return build_results.FAILED
except Exception as e:
# Should not reach here.
msg = _LE('Unexpected build failure, not rescheduling build.')
LOG.exception(msg, instance=instance)
self._cleanup_allocated_networks(context, instance,
requested_networks)
self._cleanup_volumes(context, instance.uuid,
block_device_mapping, raise_exc=False)
compute_utils.add_instance_fault_from_exc(context, instance,
e, sys.exc_info())
self._nil_out_instance_obj_host_and_node(instance)
self._set_instance_obj_error_state(context, instance,
clean_task_state=True)
return build_results.FAILED
在_do_build_and_run_instance方法中执行调用_build_and_run_instance方法
def _build_and_run_instance(self, context, instance, image, injected_files,
admin_password, requested_networks, security_groups,
block_device_mapping, node, limits, filter_properties):
image_name = image.get('name')
self._notify_about_instance_usage(context, instance, 'create.start',
extra_usage_info={'image_name': image_name})
try:
rt = self._get_resource_tracker(node)
with rt.instance_claim(context, instance, limits):
# NOTE(russellb) It's important that this validation be done
# *after* the resource tracker instance claim, as that is where
# the host is set on the instance.
self._validate_instance_group_policy(context, instance,
filter_properties)
image_meta = objects.ImageMeta.from_dict(image)
with self._build_resources(context, instance,
requested_networks, security_groups, image_meta,
block_device_mapping) as resources:
instance.vm_state = vm_states.BUILDING
instance.task_state = task_states.SPAWNING
# NOTE(JoshNang) This also saves the changes to the
# instance from _allocate_network_async, as they aren't
# saved in that function to prevent races.
instance.save(expected_task_state=
task_states.BLOCK_DEVICE_MAPPING)
block_device_info = resources['block_device_info']
network_info = resources['network_info']
LOG.debug('Start spawning the instance on the hypervisor.',
instance=instance)
with timeutils.StopWatch() as timer:
self.driver.spawn(context, instance, image_meta,
injected_files, admin_password,
network_info=network_info,
block_device_info=block_device_info)
LOG.info(_LI('Took %0.2f seconds to spawn the instance on '
'the hypervisor.'), timer.elapsed(),
instance=instance)
except (exception.InstanceNotFound,
exception.UnexpectedDeletingTaskStateError) as e:
with excutils.save_and_reraise_exception():
self._notify_about_instance_usage(context, instance,
'create.end', fault=e)
except exception.ComputeResourcesUnavailable as e:
LOG.debug(e.format_message(), instance=instance)
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
raise exception.RescheduledException(
instance_uuid=instance.uuid, reason=e.format_message())
except exception.BuildAbortException as e:
with excutils.save_and_reraise_exception():
LOG.debug(e.format_message(), instance=instance)
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
except (exception.FixedIpLimitExceeded,
exception.NoMoreNetworks, exception.NoMoreFixedIps) as e:
LOG.warning(_LW('No more network or fixed IP to be allocated'),
instance=instance)
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
msg = _('Failed to allocate the network(s) with error %s, '
'not rescheduling.') % e.format_message()
raise exception.BuildAbortException(instance_uuid=instance.uuid,
reason=msg)
except (exception.VirtualInterfaceCreateException,
exception.VirtualInterfaceMacAddressException) as e:
LOG.exception(_LE('Failed to allocate network(s)'),
instance=instance)
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
msg = _('Failed to allocate the network(s), not rescheduling.')
raise exception.BuildAbortException(instance_uuid=instance.uuid,
reason=msg)
except (exception.FlavorDiskTooSmall,
exception.FlavorMemoryTooSmall,
exception.ImageNotActive,
exception.ImageUnacceptable,
exception.InvalidDiskInfo) as e:
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
raise exception.BuildAbortException(instance_uuid=instance.uuid,
reason=e.format_message())
except Exception as e:
self._notify_about_instance_usage(context, instance,
'create.error', fault=e)
raise exception.RescheduledException(
instance_uuid=instance.uuid, reason=six.text_type(e))
# NOTE(alaski): This is only useful during reschedules, remove it now.
instance.system_metadata.pop('network_allocated', None)
# If CONF.default_access_ip_network_name is set, grab the
# corresponding network and set the access ip values accordingly.
network_name = CONF.default_access_ip_network_name
if (network_name and not instance.access_ip_v4 and
not instance.access_ip_v6):
# Note that when there are multiple ips to choose from, an
# arbitrary one will be chosen.
for vif in network_info:
if vif['network']['label'] == network_name:
for ip in vif.fixed_ips():
if not instance.access_ip_v4 and ip['version'] == 4:
instance.access_ip_v4 = ip['address']
if not instance.access_ip_v6 and ip['version'] == 6:
instance.access_ip_v6 = ip['address']
break
self._update_instance_after_spawn(context, instance)
try:
instance.save(expected_task_state=task_states.SPAWNING)
except (exception.InstanceNotFound,
exception.UnexpectedDeletingTaskStateError) as e:
with excutils.save_and_reraise_exception():
self._notify_about_instance_usage(context, instance,
'create.end', fault=e)
self._update_scheduler_instance_info(context, instance)
self._notify_about_instance_usage(context, instance, 'create.end',
extra_usage_info={'message': _('Success')},
network_info=network_info)
在该方法中会执行self.driver.spawn(context, instance, image_meta, injected_files, admin_password, network_info=network_info, block_device_info=block_device_info)调用底层的driver创建虚拟机
默认为kvm的libvirt.driver接口spawn
四,libvirt底层创建
1、nova.virt.libvirt.driver.py执行虚拟机spawn操作
# NOTE(ilyaalekseyev): Implementation like in multinics
# for xenapi(tr3buchet)
def spawn(self, context, instance, image_meta, injected_files,
admin_password, network_info=None, block_device_info=None):
disk_info = blockinfo.get_disk_info(CONF.libvirt.virt_type,
instance,
image_meta,
block_device_info)
self._create_image(context, instance,
disk_info['mapping'],
network_info=network_info,
block_device_info=block_device_info,
files=injected_files,
admin_pass=admin_password)
xml = self._get_guest_xml(context, instance, network_info,
disk_info, image_meta,
block_device_info=block_device_info,
write_to_disk=True)
self._create_domain_and_network(context, xml, instance, network_info,
disk_info,
block_device_info=block_device_info)
LOG.debug("Instance is running", instance=instance)
def _wait_for_boot():
"""Called at an interval until the VM is running."""
state = self.get_info(instance).state
if state == power_state.RUNNING:
LOG.info(_LI("Instance spawned successfully."),
instance=instance)
raise loopingcall.LoopingCallDone()
timer = loopingcall.FixedIntervalLoopingCall(_wait_for_boot)
timer.start(interval=0.5).wait()
执行工作如下
- self._create_image检查并加载镜像到本地
- self._get_guest_xml根据虚拟机请求生成xml配置信息
- self._create_domain_and_network根据xml等信息创建domain并配置网络
2、nova.virt.libvirt.driver.py执行_create_domain_and_network
def _create_domain_and_network(self, context, xml, instance, network_info,
disk_info, block_device_info=None,
power_on=True, reboot=False,
vifs_already_plugged=False):
"""Do required network setup and create domain."""
block_device_mapping = driver.block_device_info_get_mapping(
block_device_info)
for vol in block_device_mapping:
connection_info = vol['connection_info']
if (not reboot and 'data' in connection_info and
'volume_id' in connection_info['data']):
volume_id = connection_info['data']['volume_id']
encryption = encryptors.get_encryption_metadata(
context, self._volume_api, volume_id, connection_info)
if encryption:
encryptor = self._get_volume_encryptor(connection_info,
encryption)
encryptor.attach_volume(context, **encryption)
timeout = CONF.vif_plugging_timeout
if (self._conn_supports_start_paused and
utils.is_neutron() and not
vifs_already_plugged and power_on and timeout):
events = self._get_neutron_events(network_info)
else:
events = []
pause = bool(events)
guest = None
try:
with self.virtapi.wait_for_instance_event(
instance, events, deadline=timeout,
error_callback=self._neutron_failed_callback):
self.plug_vifs(instance, network_info)
self.firewall_driver.setup_basic_filtering(instance,
network_info)
self.firewall_driver.prepare_instance_filter(instance,
network_info)
with self._lxc_disk_handler(instance, instance.image_meta,
block_device_info, disk_info):
guest = self._create_domain(
xml, pause=pause, power_on=power_on)
self.firewall_driver.apply_instance_filter(instance,
network_info)
except exception.VirtualInterfaceCreateException:
# Neutron reported failure and we didn't swallow it, so
# bail here
with excutils.save_and_reraise_exception():
if guest:
guest.poweroff()
self.cleanup(context, instance, network_info=network_info,
block_device_info=block_device_info)
except eventlet.timeout.Timeout:
# We never heard from Neutron
LOG.warn(_LW('Timeout waiting for vif plugging callback for '
'instance %(uuid)s'), {'uuid': instance.uuid},
instance=instance)
if CONF.vif_plugging_is_fatal:
if guest:
guest.poweroff()
self.cleanup(context, instance, network_info=network_info,
block_device_info=block_device_info)
raise exception.VirtualInterfaceCreateException()
# Resume only if domain has been paused
if pause:
guest.resume()
return guest
执行的工作有
- 准备网络设备及硬盘设备
- 执行_create_domain创建domain
3、nova.virt.libvirt.driver.py执行_create_domain()
def _create_domain(self, xml=None, domain=None,
power_on=True, pause=False):
"""Create a domain.
Either domain or xml must be passed in. If both are passed, then
the domain definition is overwritten from the xml.
:returns guest.Guest: Guest just created
"""
if xml:
guest = libvirt_guest.Guest.create(xml, self._host)
else:
guest = libvirt_guest.Guest(domain)
if power_on or pause:
guest.launch(pause=pause)
if not utils.is_neutron():
guest.enable_hairpin()
return guest
执行的工作任务有
- 根据xml信息define虚拟机对象(必须首先定义才能启动)
- 根据定义的虚拟机对象启动创建,
4、nova.virt.libvirt.guest.py文件执行底层操作
其中启动创建虚拟机使用的接口为createWithFlags
@classmethod
def create(cls, xml, host):
"""Create a new Guest
:param xml: XML definition of the domain to create
:param host: host.Host connection to define the guest on
:returns guest.Guest: Guest ready to be launched
"""
try:
# TODO(sahid): Host.write_instance_config should return
# an instance of Guest
domain = host.write_instance_config(xml)
except Exception:
with excutils.save_and_reraise_exception():
LOG.error(_LE('Error defining a domain with XML: %s'),
encodeutils.safe_decode(xml))
return cls(domain)
def launch(self, pause=False):
"""Starts a created guest.
:param pause: Indicates whether to start and pause the guest
"""
flags = pause and libvirt.VIR_DOMAIN_START_PAUSED or 0
try:
return self._domain.createWithFlags(flags)
except Exception:
with excutils.save_and_reraise_exception():
LOG.error(_LE('Error launching a defined domain '
'with XML: %s'),
self._encoded_xml, errors='ignore')
五,虚拟机调度
在第二节中提到,虚拟机通过scheduler进行调度
def _schedule_instances(self, context, request_spec, filter_properties):
scheduler_utils.setup_instance_group(context, request_spec,
filter_properties)
# TODO(sbauza): Hydrate here the object until we modify the
# scheduler.utils methods to directly use the RequestSpec object
spec_obj = objects.RequestSpec.from_primitives(
context, request_spec, filter_properties)
hosts = self.scheduler_client.select_destinations(context, spec_obj)
return hosts
会执行到nova.scheduler.rpcapi进行调度的调用过程
def select_destinations(self, ctxt, spec_obj):
version = '4.3'
msg_args = {'spec_obj': spec_obj}
if not self.client.can_send_version(version):
del msg_args['spec_obj']
msg_args['request_spec'] = spec_obj.to_legacy_request_spec_dict()
msg_args['filter_properties'
] = spec_obj.to_legacy_filter_properties_dict()
version = '4.0'
cctxt = self.client.prepare(version=version)
return cctxt.call(ctxt, 'select_destinations', **msg_args)
其中需要注意的是此次的rpc调用时call同步调用
关于scheduler过程此处不详细描述,可以见《OpenStack nova-scheduler调度过程》分析