func getContainerSubCgroup(machineID string, canMachinedRegister, unified bool) (string, error) {
var subcgroup string
fromUnit, err := util.RunningFromSystemService()
if err != nil {
return "", errwrap.Wrap(errors.New("could not determine if we're running from a unit file"), err)
}
if fromUnit {
slice, err := util.GetRunningSlice()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get slice name"), err)
}
slicePath, err := common.SliceToPath(slice)
if err != nil {
return "", errwrap.Wrap(errors.New("could not convert slice name to path"), err)
}
unit, err := util.CurrentUnitName()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get unit name"), err)
}
subcgroup = filepath.Join(slicePath, unit)
if unified {
subcgroup = filepath.Join(subcgroup, "payload")
}
} else {
escapedmID := strings.Replace(machineID, "-", "\\x2d", -1)
machineDir := "machine-" + escapedmID + ".scope"
if canMachinedRegister {
// we are not in the final cgroup yet: systemd-nspawn will move us
// to the correct cgroup later during registration so we can't
// look it up in /proc/self/cgroup
subcgroup = filepath.Join("machine.slice", machineDir)
} else {
if unified {
var err error
subcgroup, err = v2.GetOwnCgroupPath()
if err != nil {
return "", errwrap.Wrap(errors.New("could not get own v2 cgroup path"), err)
}
} else {
// when registration is disabled the container will be directly
// under the current cgroup so we can look it up in /proc/self/cgroup
ownV1CgroupPath, err := v1.GetOwnCgroupPath("name=systemd")
if err != nil {
return "", errwrap.Wrap(errors.New("could not get own v1 cgroup path"), err)
}
// systemd-nspawn won't work if we are in the root cgroup. In addition,
// we want all rkt instances to be in distinct cgroups. Create a
// subcgroup and add ourselves to it.
subcgroup = filepath.Join(ownV1CgroupPath, machineDir)
if err := v1.JoinSubcgroup("systemd", subcgroup); err != nil {
return "", errwrap.Wrap(fmt.Errorf("error joining %s subcgroup", ownV1CgroupPath), err)
}
}
}
}
return subcgroup, nil
}
// getArgsEnv returns the nspawn or lkvm args and env according to the flavor used
func getArgsEnv(p *stage1commontypes.Pod, flavor string, debug bool, n *networking.Networking) ([]string, []string, error) {
var args []string
env := os.Environ()
// We store the pod's flavor so we can later garbage collect it correctly
if err := os.Symlink(flavor, filepath.Join(p.Root, stage1initcommon.FlavorFile)); err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to create flavor symlink"), err)
}
// set hostname inside pod
// According to systemd manual (https://www.freedesktop.org/software/systemd/man/hostname.html) :
// "The /etc/hostname file configures the name of the local system that is set
// during boot using the sethostname system call"
if hostname == "" {
hostname = stage1initcommon.GetMachineID(p)
}
hostnamePath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc/hostname")
if err := ioutil.WriteFile(hostnamePath, []byte(hostname), 0644); err != nil {
return nil, nil, fmt.Errorf("error writing %s, %s", hostnamePath, err)
}
switch flavor {
case "kvm":
if privateUsers != "" {
return nil, nil, fmt.Errorf("flag --private-users cannot be used with an lkvm stage1")
}
// kernel and lkvm are relative path, because init has /var/lib/rkt/..../uuid as its working directory
// TODO: move to path.go
kernelPath := filepath.Join(common.Stage1RootfsPath(p.Root), "bzImage")
lkvmPath := filepath.Join(common.Stage1RootfsPath(p.Root), "lkvm")
netDescriptions := kvm.GetNetworkDescriptions(n)
lkvmNetArgs, err := kvm.GetKVMNetArgs(netDescriptions)
if err != nil {
return nil, nil, err
}
cpu, mem := kvm.GetAppsResources(p.Manifest.Apps)
kernelParams := []string{
"console=hvc0",
"init=/usr/lib/systemd/systemd",
"no_timer_check",
"noreplace-smp",
"systemd.default_standard_error=journal+console",
"systemd.default_standard_output=journal+console",
// "systemd.default_standard_output=tty",
"tsc=reliable",
"MACHINEID=" + p.UUID.String(),
}
if debug {
kernelParams = append(kernelParams, []string{
"debug",
"systemd.log_level=debug",
"systemd.show_status=true",
// "systemd.confirm_spawn=true",
}...)
} else {
kernelParams = append(kernelParams, "quiet")
}
args = append(args, []string{
"./" + lkvmPath, // relative path
"run",
"--name", "rkt-" + p.UUID.String(),
"--no-dhcp", // speed bootup
"--cpu", strconv.FormatInt(cpu, 10),
"--mem", strconv.FormatInt(mem, 10),
"--console=virtio",
"--kernel", kernelPath,
"--disk", "stage1/rootfs", // relative to run/pods/uuid dir this is a place where systemd resides
// MACHINEID will be available as environment variable
"--params", strings.Join(kernelParams, " "),
}...,
)
args = append(args, lkvmNetArgs...)
if debug {
args = append(args, "--debug")
}
// host volume sharing with 9p
nsargs := stage1initcommon.VolumesToKvmDiskArgs(p.Manifest.Volumes)
args = append(args, nsargs...)
// lkvm requires $HOME to be defined,
// see https://github.com/coreos/rkt/issues/1393
if os.Getenv("HOME") == "" {
env = append(env, "HOME=/root")
}
return args, env, nil
case "coreos":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), interpBin))
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if machinedRegister() {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
// use only dynamic libraries provided in the image
env = append(env, "LD_LIBRARY_PATH="+filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib"))
case "src":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if machinedRegister() {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
case "host":
hostNspawnBin, err := common.LookupPath("systemd-nspawn", os.Getenv("PATH"))
if err != nil {
return nil, nil, err
}
// Check dynamically which version is installed on the host
// Support version >= 220
versionBytes, err := exec.Command(hostNspawnBin, "--version").CombinedOutput()
if err != nil {
return nil, nil, errwrap.Wrap(fmt.Errorf("unable to probe %s version", hostNspawnBin), err)
}
versionStr := strings.SplitN(string(versionBytes), "\n", 2)[0]
var version int
n, err := fmt.Sscanf(versionStr, "systemd %d", &version)
if err != nil {
return nil, nil, fmt.Errorf("cannot parse version: %q", versionStr)
}
if n != 1 || version < 220 {
return nil, nil, fmt.Errorf("rkt needs systemd-nspawn >= 220. %s version not supported: %v", hostNspawnBin, versionStr)
}
// Copy systemd, bash, etc. in stage1 at run-time
if err := installAssets(); err != nil {
return nil, nil, errwrap.Wrap(errors.New("cannot install assets from the host"), err)
}
args = append(args, hostNspawnBin)
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, fmt.Sprintf("--register=true"))
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
default:
return nil, nil, fmt.Errorf("unrecognized stage1 flavor: %q", flavor)
}
// link journal only if the host is running systemd
if util.IsRunningSystemd() {
// we write /etc/machine-id here because systemd-nspawn needs it to link
// the container's journal to the host
mPath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc", "machine-id")
mID := strings.Replace(p.UUID.String(), "-", "", -1)
if err := ioutil.WriteFile(mPath, []byte(mID), 0644); err != nil {
log.FatalE("error writing /etc/machine-id", err)
}
args = append(args, "--link-journal=try-guest")
keepUnit, err := util.RunningFromSystemService()
if err != nil {
if err == util.ErrSoNotFound {
log.Print("warning: libsystemd not found even though systemd is running. Cgroup limits set by the environment (e.g. a systemd service) won't be enforced.")
} else {
return nil, nil, errwrap.Wrap(errors.New("error determining if we're running from a system service"), err)
}
}
if keepUnit {
args = append(args, "--keep-unit")
}
}
if !debug {
args = append(args, "--quiet") // silence most nspawn output (log_warning is currently not covered by this)
env = append(env, "SYSTEMD_LOG_LEVEL=err") // silence log_warning too
}
env = append(env, "SYSTEMD_NSPAWN_CONTAINER_SERVICE=rkt")
if len(privateUsers) > 0 {
args = append(args, "--private-users="+privateUsers)
}
nsargs, err := stage1initcommon.PodToNspawnArgs(p)
if err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to generate nspawn args"), err)
}
args = append(args, nsargs...)
// Arguments to systemd
args = append(args, "--")
args = append(args, "--default-standard-output=tty") // redirect all service logs straight to tty
if !debug {
args = append(args, "--log-target=null") // silence systemd output inside pod
args = append(args, "--show-status=0") // silence systemd initialization status output
}
return args, env, nil
}
// getArgsEnv returns the nspawn or lkvm args and env according to the flavor
// as the first two return values respectively.
func getArgsEnv(p *stage1commontypes.Pod, flavor string, canMachinedRegister bool, debug bool, n *networking.Networking, insecureOptions stage1initcommon.Stage1InsecureOptions) ([]string, []string, error) {
var args []string
env := os.Environ()
// We store the pod's flavor so we can later garbage collect it correctly
if err := os.Symlink(flavor, filepath.Join(p.Root, stage1initcommon.FlavorFile)); err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to create flavor symlink"), err)
}
// set hostname inside pod
// According to systemd manual (https://www.freedesktop.org/software/systemd/man/hostname.html) :
// "The /etc/hostname file configures the name of the local system that is set
// during boot using the sethostname system call"
if hostname == "" {
hostname = stage1initcommon.GetMachineID(p)
}
hostnamePath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc/hostname")
if err := ioutil.WriteFile(hostnamePath, []byte(hostname), 0644); err != nil {
return nil, nil, fmt.Errorf("error writing %s, %s", hostnamePath, err)
}
// systemd-nspawn needs /etc/machine-id to link the container's journal
// to the host. Since systemd-v230, /etc/machine-id is mandatory, see
// https://github.com/systemd/systemd/commit/e01ff70a77e781734e1e73a2238af2e9bf7967a8
mPath := filepath.Join(common.Stage1RootfsPath(p.Root), "etc", "machine-id")
machineID := strings.Replace(p.UUID.String(), "-", "", -1)
switch flavor {
case "kvm":
if privateUsers != "" {
return nil, nil, fmt.Errorf("flag --private-users cannot be used with an lkvm stage1")
}
// kernel and hypervisor binaries are located relative to the working directory
// of init (/var/lib/rkt/..../uuid)
// TODO: move to path.go
kernelPath := filepath.Join(common.Stage1RootfsPath(p.Root), "bzImage")
netDescriptions := kvm.GetNetworkDescriptions(n)
cpu, mem := kvm.GetAppsResources(p.Manifest.Apps)
// Parse hypervisor
hv, err := KvmCheckHypervisor(common.Stage1RootfsPath(p.Root))
if err != nil {
return nil, nil, err
}
// Set start command for hypervisor
StartCmd := hvlkvm.StartCmd
switch hv {
case "lkvm":
StartCmd = hvlkvm.StartCmd
case "qemu":
StartCmd = hvqemu.StartCmd
default:
return nil, nil, fmt.Errorf("unrecognized hypervisor")
}
hvStartCmd := StartCmd(
common.Stage1RootfsPath(p.Root),
p.UUID.String(),
kernelPath,
netDescriptions,
cpu,
mem,
debug,
)
if hvStartCmd == nil {
return nil, nil, fmt.Errorf("no hypervisor")
}
args = append(args, hvStartCmd...)
// lkvm requires $HOME to be defined,
// see https://github.com/coreos/rkt/issues/1393
if os.Getenv("HOME") == "" {
env = append(env, "HOME=/root")
}
if err := linkJournal(common.Stage1RootfsPath(p.Root), machineID); err != nil {
return nil, nil, errwrap.Wrap(errors.New("error linking pod's journal"), err)
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
return args, env, nil
case "coreos":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), interpBin))
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, "--notify-ready=yes") // From systemd v231
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if canMachinedRegister {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib")+":"+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
case "src":
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), interpBin))
args = append(args, filepath.Join(common.Stage1RootfsPath(p.Root), nspawnBin))
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, "--notify-ready=yes") // From systemd v231
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
if canMachinedRegister {
args = append(args, fmt.Sprintf("--register=true"))
} else {
args = append(args, fmt.Sprintf("--register=false"))
}
// use only dynamic libraries provided in the image
// from systemd v231 there's a new internal libsystemd-shared-v231.so
// which is present in /usr/lib/systemd
env = append(env, "LD_LIBRARY_PATH="+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib")+":"+
filepath.Join(common.Stage1RootfsPath(p.Root), "usr/lib/systemd"))
case "host":
hostNspawnBin, err := common.LookupPath("systemd-nspawn", os.Getenv("PATH"))
if err != nil {
return nil, nil, err
}
// Check dynamically which version is installed on the host
// Support version >= 220
versionBytes, err := exec.Command(hostNspawnBin, "--version").CombinedOutput()
if err != nil {
return nil, nil, errwrap.Wrap(fmt.Errorf("unable to probe %s version", hostNspawnBin), err)
}
versionStr := strings.SplitN(string(versionBytes), "\n", 2)[0]
var version int
n, err := fmt.Sscanf(versionStr, "systemd %d", &version)
if err != nil {
return nil, nil, fmt.Errorf("cannot parse version: %q", versionStr)
}
if n != 1 || version < 220 {
return nil, nil, fmt.Errorf("rkt needs systemd-nspawn >= 220. %s version not supported: %v", hostNspawnBin, versionStr)
}
// Copy systemd, bash, etc. in stage1 at run-time
if err := installAssets(); err != nil {
return nil, nil, errwrap.Wrap(errors.New("cannot install assets from the host"), err)
}
args = append(args, hostNspawnBin)
args = append(args, "--boot") // Launch systemd in the pod
args = append(args, fmt.Sprintf("--register=true"))
if version >= 231 {
args = append(args, "--notify-ready=yes") // From systemd v231
}
if context := os.Getenv(common.EnvSELinuxContext); context != "" {
args = append(args, fmt.Sprintf("-Z%s", context))
}
if context := os.Getenv(common.EnvSELinuxMountContext); context != "" {
args = append(args, fmt.Sprintf("-L%s", context))
}
default:
return nil, nil, fmt.Errorf("unrecognized stage1 flavor: %q", flavor)
}
machineIDBytes := append([]byte(machineID), '\n')
if err := ioutil.WriteFile(mPath, machineIDBytes, 0644); err != nil {
log.FatalE("error writing /etc/machine-id", err)
}
// link journal only if the host is running systemd
if util.IsRunningSystemd() {
args = append(args, "--link-journal=try-guest")
keepUnit, err := util.RunningFromSystemService()
if err != nil {
if err == dlopen.ErrSoNotFound {
log.Print("warning: libsystemd not found even though systemd is running. Cgroup limits set by the environment (e.g. a systemd service) won't be enforced.")
} else {
return nil, nil, errwrap.Wrap(errors.New("error determining if we're running from a system service"), err)
}
}
if keepUnit {
args = append(args, "--keep-unit")
}
} else {
args = append(args, "--link-journal=no")
}
if !debug {
args = append(args, "--quiet") // silence most nspawn output (log_warning is currently not covered by this)
env = append(env, "SYSTEMD_LOG_LEVEL=err") // silence log_warning too
}
env = append(env, "SYSTEMD_NSPAWN_CONTAINER_SERVICE=rkt")
// TODO (alepuccetti) remove this line when rkt will use cgroup namespace
// If the kernel has the cgroup namespace enabled, systemd v232 will use it by default.
// This was introduced by https://github.com/systemd/systemd/pull/3809 and it will cause
// problems in rkt when cgns is enabled and cgroup-v1 is used. For more information see
// https://github.com/systemd/systemd/pull/3589#discussion_r70277625.
// The following line tells systemd-nspawn not to use cgroup namespace using the environment variable
// introduced by https://github.com/systemd/systemd/pull/3809.
env = append(env, "SYSTEMD_NSPAWN_USE_CGNS=no")
if insecureOptions.DisablePaths {
env = append(env, "SYSTEMD_NSPAWN_API_VFS_WRITABLE=yes")
}
if len(privateUsers) > 0 {
args = append(args, "--private-users="+privateUsers)
}
nsargs, err := stage1initcommon.PodToNspawnArgs(p, insecureOptions)
if err != nil {
return nil, nil, errwrap.Wrap(errors.New("failed to generate nspawn args"), err)
}
args = append(args, nsargs...)
// Arguments to systemd
args = append(args, "--")
args = append(args, "--default-standard-output=tty") // redirect all service logs straight to tty
if !debug {
args = append(args, "--log-target=null") // silence systemd output inside pod
args = append(args, "--show-status=0") // silence systemd initialization status output
}
return args, env, nil
}