cloud-init 源码阅读

网络初始化：

/usr/lib/python2.7/site-packages/cloudinit/stages.py：

    def apply_network_config(self, bring_up):
        netcfg, src = self._find_networking_config()
        if netcfg is None:
            LOG.info("network config is disabled by %s", src)
            return

        try:
            LOG.debug("applying net config names for %s" % netcfg)
            self.distro.apply_network_config_names(netcfg)
        except Exception as e:
            LOG.warn("Failed to rename devices: %s", e)

        if (self.datasource is not NULL_DATA_SOURCE and
                not self.is_new_instance()):
            LOG.debug("not a new instance. network config is not applied.")
            return

        LOG.info("Applying network configuration from %s bringup=%s: %s",
                 src, bring_up, netcfg)
        try:
            return self.distro.apply_network_config(netcfg, bring_up=bring_up)
        except NotImplementedError:
            LOG.warn("distro '%s' does not implement apply_network_config. "
                     "networking may not be configured properly." %
                     self.distro)
            return

def apply_network_config(self, bring_up):

netcfg, src = self._find_networking_config()

if netcfg is None:

LOG.info("network config is disabled by %s", src)

return

try:

LOG.debug("applying net config names for %s" % netcfg)

self.distro.apply_network_config_names(netcfg)

except Exception as e:

LOG.warn("Failed to rename devices: %s", e)

if (self.datasource is not NULL_DATA_SOURCE and

not self.is_new_instance()):

LOG.debug("not a new instance. network config is not applied.")

return

LOG.info("Applying network configuration from %s bringup=%s: %s",

src, bring_up, netcfg)

try:

return self.distro.apply_network_config(netcfg, bring_up=bring_up)

except NotImplementedError:

LOG.warn("distro '%s' does not implement apply_network_config. "

"networking may not be configured properly." %

self.distro)

return

分析：

每次都查找网络配置
如果找到配置，则 self.distro.apply_network_config_names(netcfg)
1. 对于新机器，则 self.distro.apply_network_config(netcfg, bring_up=bring_up) ，包括
  1. 写 ifcfg-eth0 配置文件
  2. if bring_up ,则，启动该网络设备

/usr/lib/python2.7/site-packages/cloudinit/stages.py：

    def _find_networking_config(self):
        disable_file = os.path.join(
            self.paths.get_cpath('data'), 'upgraded-network')
        if os.path.exists(disable_file):
            return (None, disable_file)

        cmdline_cfg = ('cmdline', cmdline.read_kernel_cmdline_config())
        dscfg = ('ds', None)
        if self.datasource and hasattr(self.datasource, 'network_config'):
            dscfg = ('ds', self.datasource.network_config)
        sys_cfg = ('system_cfg', self.cfg.get('network'))

        for loc, ncfg in (cmdline_cfg, sys_cfg, dscfg):
            if net.is_disabled_cfg(ncfg):
                LOG.debug("network config disabled by %s", loc)
                return (None, loc)
            if ncfg:
                return (ncfg, loc)
        return (net.generate_fallback_config(), "fallback")

def _find_networking_config(self):

disable_file = os.path.join(

self.paths.get_cpath('data'), 'upgraded-network')

if os.path.exists(disable_file):

return (None, disable_file)

cmdline_cfg = ('cmdline', cmdline.read_kernel_cmdline_config())

dscfg = ('ds', None)

if self.datasource and hasattr(self.datasource, 'network_config'):

dscfg = ('ds', self.datasource.network_config)

sys_cfg = ('system_cfg', self.cfg.get('network'))

for loc, ncfg in (cmdline_cfg, sys_cfg, dscfg):

if net.is_disabled_cfg(ncfg):

LOG.debug("network config disabled by %s", loc)

return (None, loc)

if ncfg:

return (ncfg, loc)

return (net.generate_fallback_config(), "fallback")

分析：

先尝试从三个不同的地方获取网络配置（注意，这里是有优先级的）：cmdline、system_cfg、datasource中的network_config；只要其中一个地方明确禁用网络或存在配置则返回；

如果没有找到任何配置，则进入预定义的配置逻辑net/__init__.py: net.generate_fallback_config() ：

def generate_fallback_config():
    """Determine which attached net dev is most likely to have a connection and
       generate network state to run dhcp on that interface"""
    # get list of interfaces that could have connections
    invalid_interfaces = set(['lo'])
    potential_interfaces = set(get_devicelist())
    potential_interfaces = potential_interfaces.difference(invalid_interfaces)
    # sort into interfaces with carrier, interfaces which could have carrier,
    # and ignore interfaces that are definitely disconnected
    connected = []
    possibly_connected = []
    for interface in potential_interfaces:
        if interface.startswith("veth"):
            continue
        if os.path.exists(sys_dev_path(interface, "bridge")):
            # skip any bridges
            continue
        carrier = read_sys_net_int(interface, 'carrier')
        if carrier:
            connected.append(interface)
            continue
        # check if nic is dormant or down, as this may make a nick appear to
        # not have a carrier even though it could acquire one when brought
        # online by dhclient
        dormant = read_sys_net_int(interface, 'dormant')
        if dormant:
            possibly_connected.append(interface)
            continue
        operstate = read_sys_net_safe(interface, 'operstate')
        if operstate in ['dormant', 'down', 'lowerlayerdown', 'unknown']:
            possibly_connected.append(interface)
            continue

    # don't bother with interfaces that might not be connected if there are
    # some that definitely are
    if connected:
        potential_interfaces = connected
    else:
        potential_interfaces = possibly_connected

    # if eth0 exists use it above anything else, otherwise get the interface
    # that we can read 'first' (using the sorted defintion of first).
    names = list(sorted(potential_interfaces))
    if DEFAULT_PRIMARY_INTERFACE in names:
        names.remove(DEFAULT_PRIMARY_INTERFACE)
        names.insert(0, DEFAULT_PRIMARY_INTERFACE)
    target_name = None
    target_mac = None
    for name in names:
        mac = read_sys_net_safe(name, 'address')
        if mac:
            target_name = name
            target_mac = mac
            break
    if target_mac and target_name:
        nconf = {'config': [], 'version': 1}
        nconf['config'].append(
            {'type': 'physical', 'name': target_name,
             'mac_address': target_mac, 'subnets': [{'type': 'dhcp'}]})
        return nconf
    else:
        # can't read any interfaces addresses (or there are none); give up
        return None

def generate_fallback_config():

"""Determine which attached net dev is most likely to have a connection and

generate network state to run dhcp on that interface"""

# get list of interfaces that could have connections

invalid_interfaces = set(['lo'])

potential_interfaces = set(get_devicelist())

potential_interfaces = potential_interfaces.difference(invalid_interfaces)

# sort into interfaces with carrier, interfaces which could have carrier,

# and ignore interfaces that are definitely disconnected

connected = []

possibly_connected = []

for interface in potential_interfaces:

if interface.startswith("veth"):

continue

if os.path.exists(sys_dev_path(interface, "bridge")):

# skip any bridges

continue

carrier = read_sys_net_int(interface, 'carrier')

if carrier:

connected.append(interface)

continue

# check if nic is dormant or down, as this may make a nick appear to

# not have a carrier even though it could acquire one when brought

# online by dhclient

dormant = read_sys_net_int(interface, 'dormant')

if dormant:

possibly_connected.append(interface)

continue

operstate = read_sys_net_safe(interface, 'operstate')

if operstate in ['dormant', 'down', 'lowerlayerdown', 'unknown']:

possibly_connected.append(interface)

continue

# don't bother with interfaces that might not be connected if there are

# some that definitely are

if connected:

potential_interfaces = connected

else:

potential_interfaces = possibly_connected

# if eth0 exists use it above anything else, otherwise get the interface

# that we can read 'first' (using the sorted defintion of first).

names = list(sorted(potential_interfaces))

if DEFAULT_PRIMARY_INTERFACE in names:

names.remove(DEFAULT_PRIMARY_INTERFACE)

names.insert(0, DEFAULT_PRIMARY_INTERFACE)

target_name = None

target_mac = None

for name in names:

mac = read_sys_net_safe(name, 'address')

if mac:

target_name = name

target_mac = mac

break

if target_mac and target_name:

nconf = {'config': [], 'version': 1}

nconf['config'].append(

{'type': 'physical', 'name': target_name,

'mac_address': target_mac, 'subnets': [{'type': 'dhcp'}]})

return nconf

else:

# can't read any interfaces addresses (or there are none); give up

return None

分析：

lo 排除在外
list目录 SYS_CLASS_NET = “/sys/class/net/” ，可以找到多个网络设备，如：

分析现有的网络设备，看看哪个最适合连网
“””Determine which attached net dev is most likely to have a connection and
generate network state to run dhcp on that interface”””

如果是veth开头的，认为是设备对，不考虑
如果存在 /sys/class/net/{$name}/bridge 则认为是（肯定是）网桥，也不考虑

如果是插着线(carrier)的，则加入可以考虑的接口列表，如何判断是否插着线呢？
参考：

def read_sys_net_int(iface, field):
    val = read_sys_net_safe(iface, field)
    if val is False:
        return None
    try:
        return int(val)
    except TypeError:
        return None

def read_sys_net_int(iface, field):

val = read_sys_net_safe(iface, field)

if val is False:

return None

try:

return int(val)

except TypeError:

return None

简单说就是： cat /sys/class/net/{$name}/carrier 如果结果是整数，则是插着线呢，否则就没插线，如下：

注意：
插着线的意思是，线的两端都是加了电的网络设备，即：数据链路层是UP的;
有些网络设备的该文件是不能cat的，如：

如果cat /sys/class/net/{$name}/dormant 是一个大于0的整型值，也可以考虑
参考文件 /sys/class/net/{$name}/operstate ，这里记录了设备的状态，如果状态是： ‘dormant’, ‘down’, ‘lowerlayerdown’, ‘unknown’，也可以考虑
最后，对可以考虑的列表进行排序；排在前面的优先考虑；不过还有个例外，程序里面定义了一个默认的网络设备 DEFAULT_PRIMARY_INTERFACE，就是 eth0，排序后被特意添加到了列表的最前面；不出意外的话，后续胜出的基本就是eth0了

根据上面得到的列表，查找设备的mac地址，只要有一个设备有mac地址，该设备就胜出了，后面的就没戏了

最后，返回网络配置

    if target_mac and target_name:
        nconf = {'config': [], 'version': 1}
        nconf['config'].append(
            {'type': 'physical', 'name': target_name,
             'mac_address': target_mac, 'subnets': [{'type': 'dhcp'}]})
        return nconf

if target_mac and target_name:

nconf = {'config': [], 'version': 1}

nconf['config'].append(

{'type': 'physical', 'name': target_name,

'mac_address': target_mac, 'subnets': [{'type': 'dhcp'}]})

return nconf

总结：

分析可知，如果不对网络进行特殊配置的话，cloud-init只能帮我们配置一个网卡；一般来讲，大部分需求已经满足了。

我们如果看 cloud-init （ /var/log/cloud-init.log ）的日志的话，会发现，在多个网卡的时候，虽然其他网卡的信息也被read了，但是最终却没有得到和eth0相同的待遇，现在也就真相大白了

堆栈：

关于cmdline的获取方法：（util.py)

容器的话，cat /proc/1/cmdline
非容器的话， cat /proc/cmdline

结果：

BOOT_IMAGE=/boot/vmlinuz-4.10.10-1.el7.elrepo.x86_64 root=UUID=0356e691-d6fb-4f8b-a905-4230dbe62a32 ro console=tty0 console=ttyS0,115200n8 crashkernel=auto console=ttyS0,115200 LANG=en_US.UTF-8

1	BOOT_IMAGE=/boot/vmlinuz-4.10.10-1.el7.elrepo.x86_64 root=UUID=0356e691-d6fb-4f8b-a905-4230dbe62a32 ro console=tty0 console=ttyS0,115200n8 crashkernel=auto console=ttyS0,115200 LANG=en_US.UTF-8

留下评论

取消回复