迁移学习心得，OpenStack
最近一直在看有关OpenStack里迁移方面的情况，也顺便往下看了下QEMU里关于migration的实现。在这里分享一下自己学习的体会。我看的OpenStack为g版本，不久将至的h版本在migration方面应该没有太大的改变。（至少没有从f到g来的大）OpenStack关于migration可以分为两类，migration和livemigration，migration进入dashboard的管理员模式就使用了，livemigration因为dashboard还没加进这个功能，所以需要敲命令行实现(nova live-migrationinstance_ID)。migration和livemigration无论在功能上还是实现上有很大的不同。migration可以说完全是openstack一手操控的，而livemigration实现大部分依赖了libvirt以及qemu。我们先来看看migration的代码：\nova\compute\manager.py @exception.wrap_exception(notifier=notifier,publisher_id=publisher_id()) @reverts_task_state @wrap_instance_event @wrap_instance_fault defresize_instance(self, context, instance, image, reservations=None, migration=None, migration_id=None, instance_type=None): """Starts the migration of a running instance toanother host.""" if not migration: migration= self.conductor_api.migration_get(context, migration_id) withself._error_out_instance_on_exception(context,instance['uuid'], reservations): if notinstance_type: instance_type =self.conductor_api.instance_type_get(context, migration['new_instance_type_id'])
network_info = self._get_instance_nw_info(context, instance)
migration= self.conductor_api.migration_update(context, migration, 'migrating')
instance =self._instance_update(context, instance['uuid'], task_state=task_states.RESIZE_MIGRATING, expected_task_state=task_states.RESIZE_PREP)
self._notify_about_instance_usage( context, instance,"resize.start", network_info=network_info)
block_device_info =self._get_instance_volume_block_device_info( context, instance)
disk_info= self.driver.migrate_disk_and_power_off( context, instance, migration['dest_host'], instance_type, network_info, block_device_info)
self._terminate_volume_connections(context, instance)
self.conductor_api.network_migrate_instance_start(context, instance, migration)
migration= self.conductor_api.migration_update(context, migration, 'post-migrating')
instance =self._instance_update(context, instance['uuid'], host=migration['dest_compute'], node=migration['dest_node'], task_state=task_states.RESIZE_MIGRATED, expected_task_state=task_states. RESIZE_MIGRATING)
self.compute_rpcapi.finish_resize(context, instance, migration, image, disk_info, migration['dest_compute'], reservations)
self._notify_about_instance_usage(context, instance,"resize.end", network_info=network_info)
非常明显，OpenStack中是通过resize这个命令来实现migration的，那很容易想到migration的实现过程和resize就非常相近了：先shutdown，然后(换个flavor)换个host，接着配置个网络，更新个信息，最后重新启动instance。然后我们看看OpenStack怎么通过libvirt实现migration的。\nova\virt\libvirt\driver.py defmigrate_disk_and_power_off(self, context, instance, dest, instance_type, network_info, block_device_info=None): LOG.debug(_("Startingmigrate_disk_and_power_off"), instance=instance) disk_info_text =self.get_instance_disk_info(instance['name'], block_device_info=block_device_info) disk_info =jsonutils.loads(disk_info_text)
# copy disks to destination # rename instance dir to +_resize at first forusing # shared storage for instance dir (eg.NFS). inst_base =libvirt_utils.get_instance_path(instance) inst_base_resize = inst_base + "_resize" shared_storage =self._is_storage_shared_with(dest, inst_base)
# try to create the directory on the remotecompute node # if this fails we pass the exception up thestack so we can catch # failures here earlier if not shared_storage: utils.execute('ssh', dest, 'mkdir', '-p', inst_base)
self.power_off(instance)
block_device_mapping =driver.block_device_info_get_mapping( block_device_info) for vol in block_device_mapping: connection_info = vol['connection_info'] disk_dev =vol['mount_device'].rpartition("/") self.volume_driver_method('disconnect_volume', connection_info, disk_dev)
try: utils.execute('mv', inst_base, inst_base_resize) # if weare migrating the instance with shared storage then # createthe directory.If it is a remote node thedirectory # hasalready been created ifshared_storage: dest = None utils.execute('mkdir', '-p',inst_base) for infoin disk_info: # assume inst_base ==dirname(info['path']) img_path = info['path'] fname =os.path.basename(img_path) from_path =os.path.join(inst_base_resize, fname) if info['type'] == 'qcow2'and info['backing_file']: tmp_path = from_path + "_rbase" # merge backing file utils.execute('qemu-img', 'convert', '-f','qcow2', '-O', 'qcow2', from_path,tmp_path)
if shared_storage: utils.execute('mv', tmp_path, img_path) else: libvirt_utils.copy_image(tmp_path, img_path, host=dest) utils.execute('rm', '-f', tmp_path)
else:# rawor qcow2 with no backing file libvirt_utils.copy_image(from_path, img_path,host=dest) except Exception: withexcutils.save_and_reraise_exception(): self._cleanup_remote_migration(dest, inst_base, inst_base_resize, shared_storage)
return disk_info_text
可以看到migration的操作就是poweroff该instance，然后建立ssh链接，将image从源主机拷贝到目的主机。是否为共享存储的区别不过在于是否真的将image“拷贝”还是仅仅改变一个地址。所以migration在openstack里面的操作还是简单的，相比之下livemigration操作要复杂得多。livemigration很大的一个变化是g版本把这个操作从nova-compute挪到了nova-conductor里了。废话不多说，上代码。
\nova\compute\api.py
@check_instance_state(vm_state=)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 = self.update(context, instance,task_state=task_states.MIGRATING,expected_task_state=None)
self.compute_task_api.migrate_server(context, instance,scheduler_hint={'host': host_name},live=True, rebuild=False, flavor=None,block_migration=block_migration,disk_over_commit=disk_over_commit)
这里的compute_task_api就是指conductor，我们接着看conductor。
\nova\conductor\manager.pydef migrate_server(self, context, instance, scheduler_hint,live, rebuild, flavor, block_migration,disk_over_commit):if not live or rebuild or (flavor != None):raise NotImplementedError()
destination = scheduler_hint.get("host")self.scheduler_rpcapi.live_migration(context,block_migration,disk_over_commit, instance, destination)
好吧，conductor把皮球踢给了scheduler，在这里限于篇幅，我们简单看一下scheduler里面做的是什么。try:self._schedule_live_migration(context, instance, dest,block_migration, disk_over_commit)except (exception.NoValidHost,exception.ComputeServiceUnavailable,exception.InvalidHypervisorType,exception.UnableToMigrateToSelf,exception.DestinationHypervisorTooOld,exception.InvalidLocalStorage,exception.InvalidSharedStorage,exception.MigrationPreCheckError) as ex:request_spec = {'instance_properties': {'uuid': instance['uuid'], },}scheduler无非检查一下destination的情况，storage的情况等，然后接着把皮球踢还conductor。\conductor\tasks\live_migrate.pyclass LiveMigrationTask(object):def __init__(self, context, instance, destination,block_migration, disk_over_commit,select_hosts_callback):self.context = contextself.instance = instanceself.destination = destinationself.block_migration = block_migrationself.disk_over_commit = disk_over_commitself.select_hosts_callback = select_hosts_callbackself.source = instance['host']self.migrate_data = Noneself.compute_rpcapi = compute_rpcapi.ComputeAPI()self.servicegroup_api = servicegroup.API()self.image_service = glance.get_default_image_service()
def execute(self):self._check_instance_is_running()self._check_host_is_up(self.source)
if not self.destination:self.destination = self._find_destination()else:self._check_requested_destination()
#TODO(johngarbutt) need to move complexity out of computemanagerreturn self.compute_rpcapi.live_migration(self.context,host=self.source,instance=self.instance,dest=self.destination,block_migration=self.block_migration,migrate_data=self.migrate_data)
终于干正事了，conductor通过MQ把livemigration的消息告诉了源主机的nova-compute。咱们开始迁移吧！老规矩，还是让libvirt来干活～\nova\virt\libvirt\driver.pydef live_migration(self, context, instance, dest,post_method, recover_method,block_migration=False,migrate_data=None):"""Spawning live_migration operation for distributinghigh-load.
:params context: security context:params instance:nova.db.sqlalchemy.models.Instance objectinstance object that is migrated.:params dest: destination host:params block_migration: destination host:params post_method:post operation method.expected nova.compute.manager.post_live_migration.:params recover_method:recovery method when any exception occurs.expected nova.compute.manager.recover_live_migration.:params block_migration: if true, do block migration.:params migrate_data: implementation specific params
"""
greenthread.spawn(self._live_migration, context, instance,dest, post_method, recover_method,block_migration, migrate_data)
def _live_migration(self, context, instance, dest,post_method,recover_method, block_migration=False,migrate_data=None):"""Do live migration.
:params context: security context:params instance:nova.db.sqlalchemy.models.Instance objectinstance object that is migrated.:params dest: destination host:params post_method:post operation method.expected nova.compute.manager.post_live_migration.:params recover_method:recovery method when any exception occurs.expected nova.compute.manager.recover_live_migration.:params migrate_data: implementation specific params"""
# Do live migration.try:if block_migration:flaglist = CONF.block_migration_flag.split(',')else:flaglist = CONF.live_migration_flag.split(',')flagvals = logical_sum = reduce(lambda x, y: x | y, flagvals)
dom = self._lookup_by_name(instance["name"])dom.migrateToURI(CONF.live_migration_uri % dest,logical_sum,None,CONF.live_migration_bandwidth)
except Exception as e:with excutils.save_and_reraise_exception():LOG.error(_("Live Migration failure: %s"), e, instance=instance)recover_method(context, instance, dest, block_migration)
# Waiting for completion of live_migration.timer = loopingcall.FixedIntervalLoopingCall(f=None)
接着就要调用libvirt以及他下面的QEMU了，也就是dom.migrateToURI()这个函数。如果玩过类似virtmanager的东西，对于这个命令里的参数应该不会陌生。事实上，OpenStack里面的live-migration和在virtmanager里做migration没什么本质的区别。到这里总结一下，OpenStack首先在qemu上面找了个libvirt这样的函数库，封装他的API。毕竟OpenStack除了KVM外，还要支持Xen，ESX这样的虚拟化工具。然后相比于单机上的虚拟化，作为云平台的管理工具，OpenStack当然要负责完成把instance的信息在数据库里更新（也就是conductor的任务）、搭建起网络、选择一个目的主机等一系列工序。至于是不是sharedstorage，其实OpenStack不会太关注，因为libvirt或者更准确的说，QEMU完全能自己搞定这件事了。OpenStack通知他一声就成～另外，值得一提的是，OpenStack默认是不支持live-migration的，因为OpenStack认为live-migration会因为内存中dirtypagerate大于网络的brandwidth而不能停止（详细解释请关注之后QEMU的部分）。因此如果不进行相关设置的话，OpenStack默认会用migration代替（live-migration是不是有种需要打开隐藏关卡才能看到的赶脚）。总体感觉OpenStack在livemigration方面做得还是挺不错的，我在实践中也没发现什么问题。毕竟OpenStack也就是个管理工具，livemigration活怎么样（downtime多少，总迁移时间多少，性能下降多少等），和他也没什么直接关系。反正写到这里OpenStack方面关于迁移的事情我觉得交代的差不多了
页:
[1]