// setupMounts iterates through each of the mount points for a container and
// calls Setup() on each. It also looks to see if is a network mount such as
// /etc/resolv.conf, and if it is not, appends it to the array of mounts.
func (daemon *Daemon) setupMounts(c *container.Container) ([]container.Mount, error) {
var mounts []container.Mount
// TODO: tmpfs mounts should be part of Mountpoints
tmpfsMounts := make(map[string]bool)
tmpfsMountInfo, err := c.TmpfsMounts()
if err != nil {
return nil, err
}
for _, m := range tmpfsMountInfo {
tmpfsMounts[m.Destination] = true
}
for _, m := range c.MountPoints {
if tmpfsMounts[m.Destination] {
continue
}
if err := daemon.lazyInitializeVolume(c.ID, m); err != nil {
return nil, err
}
rootUID, rootGID := daemon.GetRemappedUIDGID()
path, err := m.Setup(c.MountLabel, rootUID, rootGID)
if err != nil {
return nil, err
}
if !c.TrySetNetworkMount(m.Destination, path) {
mnt := container.Mount{
Source: path,
Destination: m.Destination,
Writable: m.RW,
Propagation: string(m.Propagation),
}
if m.Volume != nil {
attributes := map[string]string{
"driver": m.Volume.DriverName(),
"container": c.ID,
"destination": m.Destination,
"read/write": strconv.FormatBool(m.RW),
"propagation": string(m.Propagation),
}
daemon.LogVolumeEvent(m.Volume.Name(), "mount", attributes)
}
mounts = append(mounts, mnt)
}
}
mounts = sortMounts(mounts)
netMounts := c.NetworkMounts()
// if we are going to mount any of the network files from container
// metadata, the ownership must be set properly for potential container
// remapped root (user namespaces)
rootUID, rootGID := daemon.GetRemappedUIDGID()
for _, mount := range netMounts {
if err := os.Chown(mount.Source, rootUID, rootGID); err != nil {
return nil, err
}
}
return append(mounts, netMounts...), nil
}
func (daemon *Daemon) createSpec(c *container.Container) (*specs.Spec, error) {
s := oci.DefaultSpec()
if err := daemon.populateCommonSpec(&s, c); err != nil {
return nil, err
}
if err := setResources(&s, c.HostConfig.Resources); err != nil {
return nil, fmt.Errorf("runtime spec resources: %v", err)
}
if err := setUser(&s, c); err != nil {
return nil, fmt.Errorf("spec user: %v", err)
}
if err := daemon.setNetworkInterface(&s, c); err != nil {
return nil, err
}
if err := daemon.setupIpcDirs(c); err != nil {
return nil, err
}
ms, err := daemon.setupMounts(c)
if err != nil {
return nil, err
}
ms = append(ms, c.IpcMounts()...)
tmpfsMounts, err := c.TmpfsMounts()
if err != nil {
return nil, err
}
ms = append(ms, tmpfsMounts...)
sort.Sort(mounts(ms))
return (*specs.Spec)(&s), nil
}
// containerStart prepares the container to run by setting up everything the
// container needs, such as storage and networking, as well as links
// between containers. The container is left waiting for a signal to
// begin running.
func (daemon *Daemon) containerStart(container *container.Container) (err error) {
container.Lock()
defer container.Unlock()
if container.Running {
return nil
}
if container.RemovalInProgress || container.Dead {
return derr.ErrorCodeContainerBeingRemoved
}
// if we encounter an error during start we need to ensure that any other
// setup has been cleaned up properly
defer func() {
if err != nil {
container.SetError(err)
// if no one else has set it, make sure we don't leave it at zero
if container.ExitCode == 0 {
container.ExitCode = 128
}
container.ToDisk()
daemon.Cleanup(container)
daemon.LogContainerEvent(container, "die")
}
}()
if err := daemon.conditionalMountOnStart(container); err != nil {
return err
}
// Make sure NetworkMode has an acceptable value. We do this to ensure
// backwards API compatibility.
container.HostConfig = runconfig.SetDefaultNetModeIfBlank(container.HostConfig)
if err := daemon.initializeNetworking(container); err != nil {
return err
}
linkedEnv, err := daemon.setupLinkedContainers(container)
if err != nil {
return err
}
if err := container.SetupWorkingDirectory(); err != nil {
return err
}
env := container.CreateDaemonEnvironment(linkedEnv)
if err := daemon.populateCommand(container, env); err != nil {
return err
}
if !container.HostConfig.IpcMode.IsContainer() && !container.HostConfig.IpcMode.IsHost() {
if err := daemon.setupIpcDirs(container); err != nil {
return err
}
}
mounts, err := daemon.setupMounts(container)
if err != nil {
return err
}
mounts = append(mounts, container.IpcMounts()...)
mounts = append(mounts, container.TmpfsMounts()...)
container.Command.Mounts = mounts
if err := daemon.waitForStart(container); err != nil {
return err
}
container.HasBeenStartedBefore = true
return nil
}
func (daemon *Daemon) createSpec(c *container.Container) (*libcontainerd.Spec, error) {
s := oci.DefaultSpec()
if err := daemon.populateCommonSpec(&s, c); err != nil {
return nil, err
}
var cgroupsPath string
scopePrefix := "docker"
parent := "/docker"
useSystemd := UsingSystemd(daemon.configStore)
if useSystemd {
parent = "system.slice"
}
if c.HostConfig.CgroupParent != "" {
parent = c.HostConfig.CgroupParent
} else if daemon.configStore.CgroupParent != "" {
parent = daemon.configStore.CgroupParent
}
if useSystemd {
cgroupsPath = parent + ":" + scopePrefix + ":" + c.ID
logrus.Debugf("createSpec: cgroupsPath: %s", cgroupsPath)
} else {
cgroupsPath = filepath.Join(parent, c.ID)
}
s.Linux.CgroupsPath = &cgroupsPath
if err := setResources(&s, c.HostConfig.Resources); err != nil {
return nil, fmt.Errorf("linux runtime spec resources: %v", err)
}
s.Linux.Resources.OOMScoreAdj = &c.HostConfig.OomScoreAdj
s.Linux.Sysctl = c.HostConfig.Sysctls
if err := setDevices(&s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec devices: %v", err)
}
if err := setRlimits(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec rlimits: %v", err)
}
if err := setUser(&s, c); err != nil {
return nil, fmt.Errorf("linux spec user: %v", err)
}
if err := setNamespaces(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux spec namespaces: %v", err)
}
if err := setCapabilities(&s, c); err != nil {
return nil, fmt.Errorf("linux spec capabilities: %v", err)
}
if err := setSeccomp(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux seccomp: %v", err)
}
if err := daemon.setupIpcDirs(c); err != nil {
return nil, err
}
ms, err := daemon.setupMounts(c)
if err != nil {
return nil, err
}
ms = append(ms, c.IpcMounts()...)
ms = append(ms, c.TmpfsMounts()...)
sort.Sort(mounts(ms))
if err := setMounts(daemon, &s, c, ms); err != nil {
return nil, fmt.Errorf("linux mounts: %v", err)
}
for _, ns := range s.Linux.Namespaces {
if ns.Type == "network" && ns.Path == "" && !c.Config.NetworkDisabled {
target, err := os.Readlink(filepath.Join("/proc", strconv.Itoa(os.Getpid()), "exe"))
if err != nil {
return nil, err
}
s.Hooks = specs.Hooks{
Prestart: []specs.Hook{{
Path: target, // FIXME: cross-platform
Args: []string{"libnetwork-setkey", c.ID, daemon.netController.ID()},
}},
}
}
}
if apparmor.IsEnabled() {
appArmorProfile := "docker-default"
if len(c.AppArmorProfile) > 0 {
appArmorProfile = c.AppArmorProfile
} else if c.HostConfig.Privileged {
appArmorProfile = "unconfined"
}
s.Process.ApparmorProfile = appArmorProfile
}
s.Process.SelinuxLabel = c.GetProcessLabel()
s.Process.NoNewPrivileges = c.NoNewPrivileges
s.Linux.MountLabel = c.MountLabel
return (*libcontainerd.Spec)(&s), nil
}
func (daemon *Daemon) createSpec(c *container.Container) (*specs.Spec, error) {
s := oci.DefaultSpec()
if err := daemon.populateCommonSpec(&s, c); err != nil {
return nil, err
}
var cgroupsPath string
scopePrefix := "docker"
parent := "/docker"
useSystemd := UsingSystemd(daemon.configStore)
if useSystemd {
parent = "system.slice"
}
if c.HostConfig.CgroupParent != "" {
parent = c.HostConfig.CgroupParent
} else if daemon.configStore.CgroupParent != "" {
parent = daemon.configStore.CgroupParent
}
if useSystemd {
cgroupsPath = parent + ":" + scopePrefix + ":" + c.ID
logrus.Debugf("createSpec: cgroupsPath: %s", cgroupsPath)
} else {
cgroupsPath = filepath.Join(parent, c.ID)
}
s.Linux.CgroupsPath = &cgroupsPath
if err := setResources(&s, c.HostConfig.Resources); err != nil {
return nil, fmt.Errorf("linux runtime spec resources: %v", err)
}
s.Linux.Resources.OOMScoreAdj = &c.HostConfig.OomScoreAdj
s.Linux.Sysctl = c.HostConfig.Sysctls
p := *s.Linux.CgroupsPath
if useSystemd {
initPath, err := cgroups.GetInitCgroupDir("cpu")
if err != nil {
return nil, err
}
p, _ = cgroups.GetThisCgroupDir("cpu")
if err != nil {
return nil, err
}
p = filepath.Join(initPath, p)
}
// Clean path to guard against things like ../../../BAD
parentPath := filepath.Dir(p)
if !filepath.IsAbs(parentPath) {
parentPath = filepath.Clean("/" + parentPath)
}
if err := daemon.initCgroupsPath(parentPath); err != nil {
return nil, fmt.Errorf("linux init cgroups path: %v", err)
}
if err := setDevices(&s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec devices: %v", err)
}
if err := setRlimits(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec rlimits: %v", err)
}
if err := setUser(&s, c); err != nil {
return nil, fmt.Errorf("linux spec user: %v", err)
}
if err := setNamespaces(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux spec namespaces: %v", err)
}
if err := setCapabilities(&s, c); err != nil {
return nil, fmt.Errorf("linux spec capabilities: %v", err)
}
if err := setSeccomp(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux seccomp: %v", err)
}
if err := daemon.setupIpcDirs(c); err != nil {
return nil, err
}
if err := daemon.setupSecretDir(c); err != nil {
return nil, err
}
ms, err := daemon.setupMounts(c)
if err != nil {
return nil, err
}
ms = append(ms, c.IpcMounts()...)
tmpfsMounts, err := c.TmpfsMounts()
if err != nil {
return nil, err
}
ms = append(ms, tmpfsMounts...)
if m := c.SecretMount(); m != nil {
ms = append(ms, *m)
}
sort.Sort(mounts(ms))
if err := setMounts(daemon, &s, c, ms); err != nil {
return nil, fmt.Errorf("linux mounts: %v", err)
}
for _, ns := range s.Linux.Namespaces {
if ns.Type == "network" && ns.Path == "" && !c.Config.NetworkDisabled {
target, err := os.Readlink(filepath.Join("/proc", strconv.Itoa(os.Getpid()), "exe"))
if err != nil {
return nil, err
}
s.Hooks = specs.Hooks{
Prestart: []specs.Hook{{
Path: target, // FIXME: cross-platform
Args: []string{"libnetwork-setkey", c.ID, daemon.netController.ID()},
}},
}
}
}
if apparmor.IsEnabled() {
var appArmorProfile string
if c.AppArmorProfile != "" {
appArmorProfile = c.AppArmorProfile
} else if c.HostConfig.Privileged {
appArmorProfile = "unconfined"
} else {
appArmorProfile = "docker-default"
}
if appArmorProfile == "docker-default" {
// Unattended upgrades and other fun services can unload AppArmor
// profiles inadvertently. Since we cannot store our profile in
// /etc/apparmor.d, nor can we practically add other ways of
// telling the system to keep our profile loaded, in order to make
// sure that we keep the default profile enabled we dynamically
// reload it if necessary.
if err := ensureDefaultAppArmorProfile(); err != nil {
return nil, err
}
}
s.Process.ApparmorProfile = appArmorProfile
}
s.Process.SelinuxLabel = c.GetProcessLabel()
s.Process.NoNewPrivileges = c.NoNewPrivileges
s.Linux.MountLabel = c.MountLabel
return (*specs.Spec)(&s), nil
}
//创建容器的namespace以及cgroups等相关。
func (daemon *Daemon) createSpec(c *container.Container) (*libcontainerd.Spec, error) {
s := oci.DefaultSpec()
//populateCommand(container, env) 主要是为container的execdriver(最终启动容器的)
//设置网络模式、设置namespace(pid,ipc,uts)等、资源(resources)限制等，并且设置
//在容器内执行的Command，Command中含有容器内进程的启动命令；
if err := daemon.populateCommonSpec(&s, c); err != nil {
return nil, err
}
var cgroupsPath string
scopePrefix := "docker"
parent := "/docker"
useSystemd := UsingSystemd(daemon.configStore)
if useSystemd {
parent = "system.slice"
}
if c.HostConfig.CgroupParent != "" {
parent = c.HostConfig.CgroupParent
} else if daemon.configStore.CgroupParent != "" {
parent = daemon.configStore.CgroupParent
}
//是否支持systemd？
if useSystemd {
cgroupsPath = parent + ":" + scopePrefix + ":" + c.ID
logrus.Debugf("createSpec: cgroupsPath: %s", cgroupsPath)
} else {
cgroupsPath = filepath.Join(parent, c.ID)
}
s.Linux.CgroupsPath = &cgroupsPath
//设置一系列的参数
if err := setResources(&s, c.HostConfig.Resources); err != nil {
return nil, fmt.Errorf("linux runtime spec resources: %v", err)
}
s.Linux.Resources.OOMScoreAdj = &c.HostConfig.OomScoreAdj
if err := setDevices(&s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec devices: %v", err)
}
if err := setRlimits(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux runtime spec rlimits: %v", err)
}
if err := setUser(&s, c); err != nil {
return nil, fmt.Errorf("linux spec user: %v", err)
}
//设置namespace
if err := setNamespaces(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux spec namespaces: %v", err)
}
//设置cgroup。
if err := setCapabilities(&s, c); err != nil {
return nil, fmt.Errorf("linux spec capabilities: %v", err)
}
//?
if err := setSeccomp(daemon, &s, c); err != nil {
return nil, fmt.Errorf("linux seccomp: %v", err)
}
//?
if err := daemon.setupIpcDirs(c); err != nil {
return nil, err
}
//container.setupMounts() 返回container的所有挂载点；
mounts, err := daemon.setupMounts(c)
if err != nil {
return nil, err
}
mounts = append(mounts, c.IpcMounts()...)
mounts = append(mounts, c.TmpfsMounts()...)
//设置容器的所有挂载点。
if err := setMounts(daemon, &s, c, mounts); err != nil {
return nil, fmt.Errorf("linux mounts: %v", err)
}
//和网络的设置有关，但是这一点究竟是干什么的呢？
//设置到进程的钩子，通过进程/proc/XXX/exe的链接文件获取到。
for _, ns := range s.Linux.Namespaces {
if ns.Type == "network" && ns.Path == "" && !c.Config.NetworkDisabled {
target, err := os.Readlink(filepath.Join("/proc", strconv.Itoa(os.Getpid()), "exe"))
if err != nil {
return nil, err
}
s.Hooks = specs.Hooks{
//// Hooks are the commands run at various lifecycle events of the container.
Prestart: []specs.Hook{{
Path: target, // FIXME: cross-platform
Args: []string{"libnetwork-setkey", c.ID, daemon.netController.ID()},
}},
}
}
}
//apparmor相关配置
if apparmor.IsEnabled() {
appArmorProfile := "docker-default"
if len(c.AppArmorProfile) > 0 {
appArmorProfile = c.AppArmorProfile
} else if c.HostConfig.Privileged {
appArmorProfile = "unconfined"
}
s.Process.ApparmorProfile = appArmorProfile
}
//设置容器的selinux,privilege,moutlabel等特性。
s.Process.SelinuxLabel = c.GetProcessLabel()
s.Process.NoNewPrivileges = c.NoNewPrivileges
s.Linux.MountLabel = c.MountLabel
return (*libcontainerd.Spec)(&s), nil
}