博客作为学习笔记记录，若有理解或表述错误，欢迎指出
在OpenStack nova创建虚拟机过程中，nova-api收到虚拟机创建请求，然后nova-scheduler完成选择合适计算节点的任务，nova-conductor则开始调用build_instance()来创建虚机。
在conductor.manager.ComputeTaskManager.build_instance()中，通过rpc调用：self.compute_rpcapi.build_and_run_instance()，来调用compute节点上的build_and_run_instance()方法。而build_and_run_instance()方法就完成VM在计算节点上的创建和启动任务。
下面我们来看看Nova compute上的build_and_run_instance()的具体实现。
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, host_list=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:
try:
result = self._do_build_and_run_instance(*args, **kwargs)
except Exception:
# NOTE(mriedem): This should really only happen if
# _decode_files in _do_build_and_run_instance fails, and
# that's before a guest is spawned so it's OK to remove
# allocations for the instance for this node from Placement
# below as there is no guest consuming resources anyway.
# The _decode_files case could be handled more specifically
# but that's left for another day.
result = build_results.FAILED
raise
finally:
if result == build_results.FAILED:
# Remove the allocation records from Placement for the
# instance if the build failed. The instance.host is
# likely set to None in _do_build_and_run_instance
# which means if the user deletes the instance, it
# will be deleted in the API, not the compute service.
# Setting the instance.host to None in
# _do_build_and_run_instance means that the
# ResourceTracker will no longer consider this instance
# to be claiming resources against it, so we want to
# reflect that same thing in Placement. No need to
# call this for a reschedule, as the allocations will
# have already been removed in
# self._do_build_and_run_instance().
self.reportclient.delete_allocation_for_instance(
context, instance.uuid)
if result in (build_results.FAILED,
build_results.RESCHEDULED):
self._build_failed(node)
else:
self._build_succeeded(node)
# 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, host_list)
compute.manager.ComputeManager.build_and_run_instance()方法很简单，里面定义了一个_locked_do_build_and_run_instance()方法，这里真正实现instance的创建和启动的，还有一个spawn方法调用，这是因为nova compute创建VM的时间会比较长，因为其中包括了下载VM镜像、创建和配置VM网卡信息、文件注入等任务，因此调用utils.spawn_n()方法返回RPC线程而不会造成阻塞。
在_locked_do_build_and_run_instance()方法直接调用self._do_build_and_run_instance()。
@hooks.add_hook('build_instance')
@wrap_exception()
@reverts_task_state
@wrap_instance_event(prefix='compute')
@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, host_list=None):
try:
LOG.debug('Starting instance...', 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._get_nodename(instance, refresh=True)
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, request_spec)
LOG.info('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)
self._cleanup_volumes(context, instance,
block_device_mapping, raise_exc=False)
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(mriedem): Always deallocate networking when using Neutron.
# This is to unbind any ports that the user supplied in the server
# create request, or delete any ports that nova created which were
# meant to be bound to this host. This check intentionally bypasses
# the result of deallocate_networks_on_reschedule because the
# default value in the driver is False, but that method was really
# only meant for Ironic and should be removed when nova-network is
# removed (since is_neutron() will then always be True).
# 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
utils.is_neutron() 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()
# The instance will have already claimed resources from this host
# before this build was attempted. Now that it has failed, we need
# to unclaim those resources before casting to the conductor, so
# that if there are alternate hosts available for a retry, it can
# claim resources on that new host for the instance.
self.reportclient.delete_allocation_for_instance(context,
instance.uuid)
self.compute_task_api.build_instances(context, [instance],
image, filter_properties, admin_password,
injected_files, requested_networks, security_groups,
block_device_mapping, request_spec=request_spec,
host_lists=[host_list])
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 as e:
if isinstance(e, exception.BuildAbortException):
LOG.error(e.format_message(), instance=instance)
else:
# Should not reach here.
LOG.exception('Unexpected build failure, not rescheduling '
'build.', instance=instance)
self._cleanup_allocated_networks(context, instance,
requested_networks)
self._cleanup_volumes(context, instance,
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()中完成了几件事情：
- 首先在函数_do_build_and_run_instance()中先设置任务状态：修改vm_state为building，task_state为None，然后调用instance.save()将状态存入数据库中。
- 如果起虚机时有文件注入，将会调用nova.compute.manager.ComputeManager._decode_files()完成文件注入处理。
# b64 decode the files to inject:
decoded_files = self._decode_files(injected_files)
- 接下来是虚机创建的主要任务：
3.1 开始创建VM并启动，调用nova.compute.manager.ComputeManager._build_and_run_instance()开始创建VM，此时vm_stat为building，task_state为spawning，然后调用instance.save()方法将状态存入数据库中。
3.2 VM创建过程中，包括了为虚机申请disk、ram、申请网卡、以及网卡上的IP、MAC信息等。计算节点上创建虚机任务的大头也就是这个地方，这里先简单介绍功能和流程，后面再具体展开各类资源申请过程。
3.3 等虚机各种资源都申请成功后，更新数据库中的状态：vm_state为building, task_state为spawning
3.4. 最后，万事俱备只欠东风，通过调用driver.spawn来完成VM孵化。OpenStack底层调用的是libvirt，因此这里的driver就是libvirt提供的接口。with timeutils.StopWatch() as timer: self.driver.spawn(context, instance, image_meta, injected_files, admin_password, allocs, network_info=network_info, block_device_info=block_device_info)
现在，这里介绍了OpenStack compute节点上，虚机创建的关键步骤和主要流程，后续将会对每个环节具体展开介绍。