Update go dependencies for kubernetes 1.16.0

This commit is contained in:
Manuel Alejandro de Brito Fontes 2019-09-19 11:01:00 -03:00
parent 280920980d
commit d7b530cb0a
No known key found for this signature in database
GPG key ID: 786136016A8BA02A
510 changed files with 107206 additions and 52551 deletions

View file

@ -27,9 +27,9 @@ type Manager interface {
// Destroys the cgroup set
Destroy() error
// NewCgroupManager() and LoadCgroupManager() require following attributes:
// The option func SystemdCgroups() and Cgroupfs() require following attributes:
// Paths map[string]string
// Cgroups *cgroups.Cgroup
// Cgroups *configs.Cgroup
// Paths maps cgroup subsystem to path at which it is mounted.
// Cgroups specifies specific cgroup settings for the various subsystems
@ -37,7 +37,7 @@ type Manager interface {
// restore the object later.
GetPaths() map[string]string
// Set the cgroup as configured.
// Sets the cgroup as configured.
Set(container *configs.Config) error
}

View file

@ -11,6 +11,7 @@ type ThrottlingData struct {
ThrottledTime uint64 `json:"throttled_time,omitempty"`
}
// CpuUsage denotes the usage of a CPU.
// All CPU stats are aggregate since container inception.
type CpuUsage struct {
// Total CPU time consumed.
@ -50,6 +51,8 @@ type MemoryStats struct {
KernelUsage MemoryData `json:"kernel_usage,omitempty"`
// usage of kernel TCP memory
KernelTCPUsage MemoryData `json:"kernel_tcp_usage,omitempty"`
// if true, memory usage is accounted for throughout a hierarchy of cgroups.
UseHierarchy bool `json:"use_hierarchy"`
Stats map[string]uint64 `json:"stats,omitempty"`
}

View file

@ -13,53 +13,58 @@ import (
"strings"
"time"
"github.com/docker/go-units"
units "github.com/docker/go-units"
"golang.org/x/sys/unix"
)
const cgroupNamePrefix = "name="
const (
CgroupNamePrefix = "name="
CgroupProcesses = "cgroup.procs"
)
// https://www.kernel.org/doc/Documentation/cgroups/cgroups.txt
func FindCgroupMountpoint(subsystem string) (string, error) {
// HugePageSizeUnitList is a list of the units used by the linux kernel when
// naming the HugePage control files.
// https://www.kernel.org/doc/Documentation/cgroup-v1/hugetlb.txt
// TODO Since the kernel only use KB, MB and GB; TB and PB should be removed,
// depends on https://github.com/docker/go-units/commit/a09cd47f892041a4fac473133d181f5aea6fa393
var HugePageSizeUnitList = []string{"B", "KB", "MB", "GB", "TB", "PB"}
// https://www.kernel.org/doc/Documentation/cgroup-v1/cgroups.txt
func FindCgroupMountpoint(cgroupPath, subsystem string) (string, error) {
mnt, _, err := FindCgroupMountpointAndRoot(cgroupPath, subsystem)
return mnt, err
}
func FindCgroupMountpointAndRoot(cgroupPath, subsystem string) (string, string, error) {
// We are not using mount.GetMounts() because it's super-inefficient,
// parsing it directly sped up x10 times because of not using Sscanf.
// It was one of two major performance drawbacks in container start.
f, err := os.Open("/proc/self/mountinfo")
if err != nil {
return "", err
}
defer f.Close()
scanner := bufio.NewScanner(f)
for scanner.Scan() {
txt := scanner.Text()
fields := strings.Split(txt, " ")
for _, opt := range strings.Split(fields[len(fields)-1], ",") {
if opt == subsystem {
return fields[4], nil
}
}
}
if err := scanner.Err(); err != nil {
return "", err
if !isSubsystemAvailable(subsystem) {
return "", "", NewNotFoundError(subsystem)
}
return "", NewNotFoundError(subsystem)
}
func FindCgroupMountpointAndRoot(subsystem string) (string, string, error) {
f, err := os.Open("/proc/self/mountinfo")
if err != nil {
return "", "", err
}
defer f.Close()
scanner := bufio.NewScanner(f)
return findCgroupMountpointAndRootFromReader(f, cgroupPath, subsystem)
}
func findCgroupMountpointAndRootFromReader(reader io.Reader, cgroupPath, subsystem string) (string, string, error) {
scanner := bufio.NewScanner(reader)
for scanner.Scan() {
txt := scanner.Text()
fields := strings.Split(txt, " ")
for _, opt := range strings.Split(fields[len(fields)-1], ",") {
if opt == subsystem {
return fields[4], fields[3], nil
fields := strings.Fields(txt)
if len(fields) < 5 {
continue
}
if strings.HasPrefix(fields[4], cgroupPath) {
for _, opt := range strings.Split(fields[len(fields)-1], ",") {
if opt == subsystem {
return fields[4], fields[3], nil
}
}
}
}
@ -70,6 +75,30 @@ func FindCgroupMountpointAndRoot(subsystem string) (string, string, error) {
return "", "", NewNotFoundError(subsystem)
}
func isSubsystemAvailable(subsystem string) bool {
cgroups, err := ParseCgroupFile("/proc/self/cgroup")
if err != nil {
return false
}
_, avail := cgroups[subsystem]
return avail
}
func GetClosestMountpointAncestor(dir, mountinfo string) string {
deepestMountPoint := ""
for _, mountInfoEntry := range strings.Split(mountinfo, "\n") {
mountInfoParts := strings.Fields(mountInfoEntry)
if len(mountInfoParts) < 5 {
continue
}
mountPoint := mountInfoParts[4]
if strings.HasPrefix(mountPoint, deepestMountPoint) && strings.HasPrefix(dir, mountPoint) {
deepestMountPoint = mountPoint
}
}
return deepestMountPoint
}
func FindCgroupMountpointDir() (string, error) {
f, err := os.Open("/proc/self/mountinfo")
if err != nil {
@ -92,7 +121,7 @@ func FindCgroupMountpointDir() (string, error) {
}
if postSeparatorFields[0] == "cgroup" {
// Check that the mount is properly formated.
// Check that the mount is properly formatted.
if numPostFields < 3 {
return "", fmt.Errorf("Error found less than 3 fields post '-' in %q", text)
}
@ -113,7 +142,7 @@ type Mount struct {
Subsystems []string
}
func (m Mount) GetThisCgroupDir(cgroups map[string]string) (string, error) {
func (m Mount) GetOwnCgroup(cgroups map[string]string) (string, error) {
if len(m.Subsystems) == 0 {
return "", fmt.Errorf("no subsystem for mount")
}
@ -121,16 +150,17 @@ func (m Mount) GetThisCgroupDir(cgroups map[string]string) (string, error) {
return getControllerPath(m.Subsystems[0], cgroups)
}
func getCgroupMountsHelper(ss map[string]bool, mi io.Reader) ([]Mount, error) {
func getCgroupMountsHelper(ss map[string]bool, mi io.Reader, all bool) ([]Mount, error) {
res := make([]Mount, 0, len(ss))
scanner := bufio.NewScanner(mi)
for scanner.Scan() {
numFound := 0
for scanner.Scan() && numFound < len(ss) {
txt := scanner.Text()
sepIdx := strings.Index(txt, " - ")
if sepIdx == -1 {
return nil, fmt.Errorf("invalid mountinfo format")
}
if txt[sepIdx+3:sepIdx+9] != "cgroup" {
if txt[sepIdx+3:sepIdx+10] == "cgroup2" || txt[sepIdx+3:sepIdx+9] != "cgroup" {
continue
}
fields := strings.Split(txt, " ")
@ -139,14 +169,20 @@ func getCgroupMountsHelper(ss map[string]bool, mi io.Reader) ([]Mount, error) {
Root: fields[3],
}
for _, opt := range strings.Split(fields[len(fields)-1], ",") {
if strings.HasPrefix(opt, cgroupNamePrefix) {
m.Subsystems = append(m.Subsystems, opt[len(cgroupNamePrefix):])
seen, known := ss[opt]
if !known || (!all && seen) {
continue
}
if ss[opt] {
m.Subsystems = append(m.Subsystems, opt)
ss[opt] = true
if strings.HasPrefix(opt, CgroupNamePrefix) {
opt = opt[len(CgroupNamePrefix):]
}
m.Subsystems = append(m.Subsystems, opt)
numFound++
}
if len(m.Subsystems) > 0 || all {
res = append(res, m)
}
res = append(res, m)
}
if err := scanner.Err(); err != nil {
return nil, err
@ -154,26 +190,28 @@ func getCgroupMountsHelper(ss map[string]bool, mi io.Reader) ([]Mount, error) {
return res, nil
}
func GetCgroupMounts() ([]Mount, error) {
// GetCgroupMounts returns the mounts for the cgroup subsystems.
// all indicates whether to return just the first instance or all the mounts.
func GetCgroupMounts(all bool) ([]Mount, error) {
f, err := os.Open("/proc/self/mountinfo")
if err != nil {
return nil, err
}
defer f.Close()
all, err := GetAllSubsystems()
allSubsystems, err := ParseCgroupFile("/proc/self/cgroup")
if err != nil {
return nil, err
}
allMap := make(map[string]bool)
for _, s := range all {
allMap[s] = true
for s := range allSubsystems {
allMap[s] = false
}
return getCgroupMountsHelper(allMap, f)
return getCgroupMountsHelper(allMap, f, all)
}
// Returns all the cgroup subsystems supported by the kernel
// GetAllSubsystems returns all the cgroup subsystems supported by the kernel
func GetAllSubsystems() ([]string, error) {
f, err := os.Open("/proc/cgroups")
if err != nil {
@ -185,9 +223,6 @@ func GetAllSubsystems() ([]string, error) {
s := bufio.NewScanner(f)
for s.Scan() {
if err := s.Err(); err != nil {
return nil, err
}
text := s.Text()
if text[0] != '#' {
parts := strings.Fields(text)
@ -196,11 +231,14 @@ func GetAllSubsystems() ([]string, error) {
}
}
}
if err := s.Err(); err != nil {
return nil, err
}
return subsystems, nil
}
// Returns the relative path to the cgroup docker is running in.
func GetThisCgroupDir(subsystem string) (string, error) {
// GetOwnCgroup returns the relative path to the cgroup docker is running in.
func GetOwnCgroup(subsystem string) (string, error) {
cgroups, err := ParseCgroupFile("/proc/self/cgroup")
if err != nil {
return "", err
@ -209,8 +247,16 @@ func GetThisCgroupDir(subsystem string) (string, error) {
return getControllerPath(subsystem, cgroups)
}
func GetInitCgroupDir(subsystem string) (string, error) {
func GetOwnCgroupPath(subsystem string) (string, error) {
cgroup, err := GetOwnCgroup(subsystem)
if err != nil {
return "", err
}
return getCgroupPathHelper(subsystem, cgroup)
}
func GetInitCgroup(subsystem string) (string, error) {
cgroups, err := ParseCgroupFile("/proc/1/cgroup")
if err != nil {
return "", err
@ -219,8 +265,33 @@ func GetInitCgroupDir(subsystem string) (string, error) {
return getControllerPath(subsystem, cgroups)
}
func GetInitCgroupPath(subsystem string) (string, error) {
cgroup, err := GetInitCgroup(subsystem)
if err != nil {
return "", err
}
return getCgroupPathHelper(subsystem, cgroup)
}
func getCgroupPathHelper(subsystem, cgroup string) (string, error) {
mnt, root, err := FindCgroupMountpointAndRoot("", subsystem)
if err != nil {
return "", err
}
// This is needed for nested containers, because in /proc/self/cgroup we
// see paths from host, which don't exist in container.
relCgroup, err := filepath.Rel(root, cgroup)
if err != nil {
return "", err
}
return filepath.Join(mnt, relCgroup), nil
}
func readProcsFile(dir string) ([]int, error) {
f, err := os.Open(filepath.Join(dir, "cgroup.procs"))
f, err := os.Open(filepath.Join(dir, CgroupProcesses))
if err != nil {
return nil, err
}
@ -243,6 +314,8 @@ func readProcsFile(dir string) ([]int, error) {
return out, nil
}
// ParseCgroupFile parses the given cgroup file, typically from
// /proc/<pid>/cgroup, into a map of subgroups to cgroup names.
func ParseCgroupFile(path string) (map[string]string, error) {
f, err := os.Open(path)
if err != nil {
@ -250,21 +323,35 @@ func ParseCgroupFile(path string) (map[string]string, error) {
}
defer f.Close()
s := bufio.NewScanner(f)
return parseCgroupFromReader(f)
}
// helper function for ParseCgroupFile to make testing easier
func parseCgroupFromReader(r io.Reader) (map[string]string, error) {
s := bufio.NewScanner(r)
cgroups := make(map[string]string)
for s.Scan() {
if err := s.Err(); err != nil {
return nil, err
}
text := s.Text()
parts := strings.Split(text, ":")
// from cgroups(7):
// /proc/[pid]/cgroup
// ...
// For each cgroup hierarchy ... there is one entry
// containing three colon-separated fields of the form:
// hierarchy-ID:subsystem-list:cgroup-path
parts := strings.SplitN(text, ":", 3)
if len(parts) < 3 {
return nil, fmt.Errorf("invalid cgroup entry: must contain at least two colons: %v", text)
}
for _, subs := range strings.Split(parts[1], ",") {
cgroups[subs] = parts[2]
}
}
if err := s.Err(); err != nil {
return nil, err
}
return cgroups, nil
}
@ -274,7 +361,7 @@ func getControllerPath(subsystem string, cgroups map[string]string) (string, err
return p, nil
}
if p, ok := cgroups[cgroupNamePrefix+subsystem]; ok {
if p, ok := cgroups[CgroupNamePrefix+subsystem]; ok {
return p, nil
}
@ -291,8 +378,7 @@ func PathExists(path string) bool {
func EnterPid(cgroupPaths map[string]string, pid int) error {
for _, path := range cgroupPaths {
if PathExists(path) {
if err := ioutil.WriteFile(filepath.Join(path, "cgroup.procs"),
[]byte(strconv.Itoa(pid)), 0700); err != nil {
if err := WriteCgroupProc(path, pid); err != nil {
return err
}
}
@ -330,19 +416,26 @@ func RemovePaths(paths map[string]string) (err error) {
}
func GetHugePageSize() ([]string, error) {
var pageSizes []string
sizeList := []string{"B", "kB", "MB", "GB", "TB", "PB"}
files, err := ioutil.ReadDir("/sys/kernel/mm/hugepages")
if err != nil {
return pageSizes, err
return []string{}, err
}
var fileNames []string
for _, st := range files {
nameArray := strings.Split(st.Name(), "-")
fileNames = append(fileNames, st.Name())
}
return getHugePageSizeFromFilenames(fileNames)
}
func getHugePageSizeFromFilenames(fileNames []string) ([]string, error) {
var pageSizes []string
for _, fileName := range fileNames {
nameArray := strings.Split(fileName, "-")
pageSize, err := units.RAMInBytes(nameArray[1])
if err != nil {
return []string{}, err
}
sizeString := units.CustomSize("%g%s", float64(pageSize), 1024.0, sizeList)
sizeString := units.CustomSize("%g%s", float64(pageSize), 1024.0, HugePageSizeUnitList)
pageSizes = append(pageSizes, sizeString)
}
@ -361,7 +454,7 @@ func GetAllPids(path string) ([]int, error) {
// collect pids from all sub-cgroups
err := filepath.Walk(path, func(p string, info os.FileInfo, iErr error) error {
dir, file := filepath.Split(p)
if file != "cgroup.procs" {
if file != CgroupProcesses {
return nil
}
if iErr != nil {
@ -376,3 +469,49 @@ func GetAllPids(path string) ([]int, error) {
})
return pids, err
}
// WriteCgroupProc writes the specified pid into the cgroup's cgroup.procs file
func WriteCgroupProc(dir string, pid int) error {
// Normally dir should not be empty, one case is that cgroup subsystem
// is not mounted, we will get empty dir, and we want it fail here.
if dir == "" {
return fmt.Errorf("no such directory for %s", CgroupProcesses)
}
// Dont attach any pid to the cgroup if -1 is specified as a pid
if pid == -1 {
return nil
}
cgroupProcessesFile, err := os.OpenFile(filepath.Join(dir, CgroupProcesses), os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0700)
if err != nil {
return fmt.Errorf("failed to write %v to %v: %v", pid, CgroupProcesses, err)
}
defer cgroupProcessesFile.Close()
for i := 0; i < 5; i++ {
_, err = cgroupProcessesFile.WriteString(strconv.Itoa(pid))
if err == nil {
return nil
}
// EINVAL might mean that the task being added to cgroup.procs is in state
// TASK_NEW. We should attempt to do so again.
if isEINVAL(err) {
time.Sleep(30 * time.Millisecond)
continue
}
return fmt.Errorf("failed to write %v to %v: %v", pid, CgroupProcesses, err)
}
return err
}
func isEINVAL(err error) bool {
switch err := err.(type) {
case *os.PathError:
return err.Err == unix.EINVAL
default:
return false
}
}

View file

@ -1,5 +1,3 @@
// +build linux freebsd
package configs
type FreezerState string
@ -22,7 +20,7 @@ type Cgroup struct {
// The path is assumed to be relative to the host system cgroup mountpoint.
Path string `json:"path"`
// ScopePrefix decribes prefix for the scope name
// ScopePrefix describes prefix for the scope name
ScopePrefix string `json:"scope_prefix"`
// Paths represent the absolute cgroups paths to join.
@ -36,7 +34,7 @@ type Cgroup struct {
type Resources struct {
// If this is true allow access to any kind of device within the container. If false, allow access only to devices explicitly listed in the allowed_devices list.
// Deprecated
AllowAllDevices bool `json:"allow_all_devices,omitempty"`
AllowAllDevices *bool `json:"allow_all_devices,omitempty"`
// Deprecated
AllowedDevices []*Device `json:"allowed_devices,omitempty"`
// Deprecated
@ -60,19 +58,19 @@ type Resources struct {
KernelMemoryTCP int64 `json:"kernel_memory_tcp"`
// CPU shares (relative weight vs. other containers)
CpuShares int64 `json:"cpu_shares"`
CpuShares uint64 `json:"cpu_shares"`
// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
CpuQuota int64 `json:"cpu_quota"`
// CPU period to be used for hardcapping (in usecs). 0 to use system default.
CpuPeriod int64 `json:"cpu_period"`
CpuPeriod uint64 `json:"cpu_period"`
// How many time CPU will use in realtime scheduling (in usecs).
CpuRtRuntime int64 `json:"cpu_quota"`
CpuRtRuntime int64 `json:"cpu_rt_quota"`
// CPU period to be used for realtime scheduling (in usecs).
CpuRtPeriod int64 `json:"cpu_period"`
CpuRtPeriod uint64 `json:"cpu_rt_period"`
// CPU to use
CpusetCpus string `json:"cpuset_cpus"`
@ -95,7 +93,7 @@ type Resources struct {
// IO read rate limit per cgroup per device, bytes per second.
BlkioThrottleReadBpsDevice []*ThrottleDevice `json:"blkio_throttle_read_bps_device"`
// IO write rate limit per cgroup per divice, bytes per second.
// IO write rate limit per cgroup per device, bytes per second.
BlkioThrottleWriteBpsDevice []*ThrottleDevice `json:"blkio_throttle_write_bps_device"`
// IO read rate limit per cgroup per device, IO per second.
@ -114,11 +112,11 @@ type Resources struct {
OomKillDisable bool `json:"oom_kill_disable"`
// Tuning swappiness behaviour per cgroup
MemorySwappiness *int64 `json:"memory_swappiness"`
MemorySwappiness *uint64 `json:"memory_swappiness"`
// Set priority of network traffic for container
NetPrioIfpriomap []*IfPrioMap `json:"net_prio_ifpriomap"`
// Set class identifier for container's network packets
NetClsClassid string `json:"net_cls_classid"`
NetClsClassid uint32 `json:"net_cls_classid_u"`
}

View file

@ -1,6 +0,0 @@
// +build !windows,!linux,!freebsd
package configs
type Cgroup struct {
}

View file

@ -7,7 +7,9 @@ import (
"os/exec"
"time"
"github.com/Sirupsen/logrus"
"github.com/opencontainers/runtime-spec/specs-go"
"github.com/sirupsen/logrus"
)
type Rlimit struct {
@ -33,7 +35,7 @@ type Seccomp struct {
Syscalls []*Syscall `json:"syscalls"`
}
// An action to be taken upon rule match in Seccomp
// Action is taken upon rule match in Seccomp
type Action int
const (
@ -44,7 +46,7 @@ const (
Trace
)
// A comparison operator to be used when matching syscall arguments in Seccomp
// Operator is a comparison operator to be used when matching syscall arguments in Seccomp
type Operator int
const (
@ -57,7 +59,7 @@ const (
MaskEqualTo
)
// A rule to match a specific syscall argument in Seccomp
// Arg is a rule to match a specific syscall argument in Seccomp
type Arg struct {
Index uint `json:"index"`
Value uint64 `json:"value"`
@ -65,7 +67,7 @@ type Arg struct {
Op Operator `json:"op"`
}
// An rule to match a syscall in Seccomp
// Syscall is a rule to match a syscall in Seccomp
type Syscall struct {
Name string `json:"name"`
Action Action `json:"action"`
@ -85,11 +87,6 @@ type Config struct {
// that the parent process dies.
ParentDeathSignal int `json:"parent_death_signal"`
// PivotDir allows a custom directory inside the container's root filesystem to be used as pivot, when NoPivotRoot is not set.
// When a custom PivotDir not set, a temporary dir inside the root filesystem will be used. The pivot dir needs to be writeable.
// This is required when using read only root filesystems. In these cases, a read/writeable path can be (bind) mounted somewhere inside the root filesystem to act as pivot.
PivotDir string `json:"pivot_dir"`
// Path to a directory containing the container's root filesystem.
Rootfs string `json:"rootfs"`
@ -117,8 +114,8 @@ type Config struct {
Namespaces Namespaces `json:"namespaces"`
// Capabilities specify the capabilities to keep when executing the process inside the container
// All capbilities not specified will be dropped from the processes capability mask
Capabilities []string `json:"capabilities"`
// All capabilities not specified will be dropped from the processes capability mask
Capabilities *Capabilities `json:"capabilities"`
// Networks specifies the container's network setup to be created
Networks []*Network `json:"networks"`
@ -144,13 +141,10 @@ type Config struct {
// OomScoreAdj specifies the adjustment to be made by the kernel when calculating oom scores
// for a process. Valid values are between the range [-1000, '1000'], where processes with
// higher scores are preferred for being killed.
// higher scores are preferred for being killed. If it is unset then we don't touch the current
// value.
// More information about kernel oom score calculation here: https://lwn.net/Articles/317814/
OomScoreAdj int `json:"oom_score_adj"`
// AdditionalGroups specifies the gids that should be added to supplementary groups
// in addition to those that the user belongs to.
AdditionalGroups []string `json:"additional_groups"`
OomScoreAdj *int `json:"oom_score_adj,omitempty"`
// UidMappings is an array of User ID mappings for User Namespaces
UidMappings []IDMap `json:"uid_mappings"`
@ -187,6 +181,24 @@ type Config struct {
// Labels are user defined metadata that is stored in the config and populated on the state
Labels []string `json:"labels"`
// NoNewKeyring will not allocated a new session keyring for the container. It will use the
// callers keyring in this case.
NoNewKeyring bool `json:"no_new_keyring"`
// IntelRdt specifies settings for Intel RDT group that the container is placed into
// to limit the resources (e.g., L3 cache, memory bandwidth) the container has available
IntelRdt *IntelRdt `json:"intel_rdt,omitempty"`
// RootlessEUID is set when the runc was launched with non-zero EUID.
// Note that RootlessEUID is set to false when launched with EUID=0 in userns.
// When RootlessEUID is set, runc creates a new userns for the container.
// (config.json needs to contain userns settings)
RootlessEUID bool `json:"rootless_euid,omitempty"`
// RootlessCgroups is set when unlikely to have the full access to cgroups.
// When RootlessCgroups is set, cgroups errors are ignored.
RootlessCgroups bool `json:"rootless_cgroups,omitempty"`
}
type Hooks struct {
@ -201,6 +213,19 @@ type Hooks struct {
Poststop []Hook
}
type Capabilities struct {
// Bounding is the set of capabilities checked by the kernel.
Bounding []string
// Effective is the set of capabilities checked by the kernel.
Effective []string
// Inheritable is the capabilities preserved across execve.
Inheritable []string
// Permitted is the limiting superset for effective capabilities.
Permitted []string
// Ambient is the ambient set of capabilities that are kept.
Ambient []string
}
func (hooks *Hooks) UnmarshalJSON(b []byte) error {
var state struct {
Prestart []CommandHook
@ -247,32 +272,23 @@ func (hooks Hooks) MarshalJSON() ([]byte, error) {
})
}
// HookState is the payload provided to a hook on execution.
type HookState struct {
Version string `json:"ociVersion"`
ID string `json:"id"`
Pid int `json:"pid"`
Root string `json:"root"`
BundlePath string `json:"bundlePath"`
}
type Hook interface {
// Run executes the hook with the provided state.
Run(HookState) error
Run(*specs.State) error
}
// NewFunctionHooks will call the provided function when the hook is run.
func NewFunctionHook(f func(HookState) error) FuncHook {
// NewFunctionHook will call the provided function when the hook is run.
func NewFunctionHook(f func(*specs.State) error) FuncHook {
return FuncHook{
run: f,
}
}
type FuncHook struct {
run func(HookState) error
run func(*specs.State) error
}
func (f FuncHook) Run(s HookState) error {
func (f FuncHook) Run(s *specs.State) error {
return f.run(s)
}
@ -284,7 +300,7 @@ type Command struct {
Timeout *time.Duration `json:"timeout"`
}
// NewCommandHooks will execute the provided command when the hook is run.
// NewCommandHook will execute the provided command when the hook is run.
func NewCommandHook(cmd Command) CommandHook {
return CommandHook{
Command: cmd,
@ -295,34 +311,43 @@ type CommandHook struct {
Command
}
func (c Command) Run(s HookState) error {
func (c Command) Run(s *specs.State) error {
b, err := json.Marshal(s)
if err != nil {
return err
}
var stdout, stderr bytes.Buffer
cmd := exec.Cmd{
Path: c.Path,
Args: c.Args,
Env: c.Env,
Stdin: bytes.NewReader(b),
Path: c.Path,
Args: c.Args,
Env: c.Env,
Stdin: bytes.NewReader(b),
Stdout: &stdout,
Stderr: &stderr,
}
if err := cmd.Start(); err != nil {
return err
}
errC := make(chan error, 1)
go func() {
out, err := cmd.CombinedOutput()
err := cmd.Wait()
if err != nil {
err = fmt.Errorf("%s: %s", err, out)
err = fmt.Errorf("error running hook: %v, stdout: %s, stderr: %s", err, stdout.String(), stderr.String())
}
errC <- err
}()
var timerCh <-chan time.Time
if c.Timeout != nil {
select {
case err := <-errC:
return err
case <-time.After(*c.Timeout):
cmd.Process.Kill()
cmd.Wait()
return fmt.Errorf("hook ran past specified timeout of %.1fs", c.Timeout.Seconds())
}
timer := time.NewTimer(*c.Timeout)
defer timer.Stop()
timerCh = timer.C
}
select {
case err := <-errC:
return err
case <-timerCh:
cmd.Process.Kill()
cmd.Wait()
return fmt.Errorf("hook ran past specified timeout of %.1fs", c.Timeout.Seconds())
}
return <-errC
}

View file

@ -0,0 +1,61 @@
package configs
import "fmt"
// HostUID gets the translated uid for the process on host which could be
// different when user namespaces are enabled.
func (c Config) HostUID(containerId int) (int, error) {
if c.Namespaces.Contains(NEWUSER) {
if c.UidMappings == nil {
return -1, fmt.Errorf("User namespaces enabled, but no uid mappings found.")
}
id, found := c.hostIDFromMapping(containerId, c.UidMappings)
if !found {
return -1, fmt.Errorf("User namespaces enabled, but no user mapping found.")
}
return id, nil
}
// Return unchanged id.
return containerId, nil
}
// HostRootUID gets the root uid for the process on host which could be non-zero
// when user namespaces are enabled.
func (c Config) HostRootUID() (int, error) {
return c.HostUID(0)
}
// HostGID gets the translated gid for the process on host which could be
// different when user namespaces are enabled.
func (c Config) HostGID(containerId int) (int, error) {
if c.Namespaces.Contains(NEWUSER) {
if c.GidMappings == nil {
return -1, fmt.Errorf("User namespaces enabled, but no gid mappings found.")
}
id, found := c.hostIDFromMapping(containerId, c.GidMappings)
if !found {
return -1, fmt.Errorf("User namespaces enabled, but no group mapping found.")
}
return id, nil
}
// Return unchanged id.
return containerId, nil
}
// HostRootGID gets the root gid for the process on host which could be non-zero
// when user namespaces are enabled.
func (c Config) HostRootGID() (int, error) {
return c.HostGID(0)
}
// Utility function that gets a host ID for a container ID from user namespace map
// if that ID is present in the map.
func (c Config) hostIDFromMapping(containerID int, uMap []IDMap) (int, bool) {
for _, m := range uMap {
if (containerID >= m.ContainerID) && (containerID <= (m.ContainerID + m.Size - 1)) {
hostID := m.HostID + (containerID - m.ContainerID)
return hostID, true
}
}
return -1, false
}

View file

@ -1,51 +0,0 @@
// +build freebsd linux
package configs
import "fmt"
// Gets the root uid for the process on host which could be non-zero
// when user namespaces are enabled.
func (c Config) HostUID() (int, error) {
if c.Namespaces.Contains(NEWUSER) {
if c.UidMappings == nil {
return -1, fmt.Errorf("User namespaces enabled, but no user mappings found.")
}
id, found := c.hostIDFromMapping(0, c.UidMappings)
if !found {
return -1, fmt.Errorf("User namespaces enabled, but no root user mapping found.")
}
return id, nil
}
// Return default root uid 0
return 0, nil
}
// Gets the root gid for the process on host which could be non-zero
// when user namespaces are enabled.
func (c Config) HostGID() (int, error) {
if c.Namespaces.Contains(NEWUSER) {
if c.GidMappings == nil {
return -1, fmt.Errorf("User namespaces enabled, but no gid mappings found.")
}
id, found := c.hostIDFromMapping(0, c.GidMappings)
if !found {
return -1, fmt.Errorf("User namespaces enabled, but no root group mapping found.")
}
return id, nil
}
// Return default root gid 0
return 0, nil
}
// Utility function that gets a host ID for a container ID from user namespace map
// if that ID is present in the map.
func (c Config) hostIDFromMapping(containerID int, uMap []IDMap) (int, bool) {
for _, m := range uMap {
if (containerID >= m.ContainerID) && (containerID <= (m.ContainerID + m.Size - 1)) {
hostID := m.HostID + (containerID - m.ContainerID)
return hostID, true
}
}
return -1, false
}

View file

@ -1,9 +1,9 @@
// +build linux freebsd
// +build linux
package configs
var (
// These are devices that are to be both allowed and created.
// DefaultSimpleDevices are devices that are to be both allowed and created.
DefaultSimpleDevices = []*Device{
// /dev/null and zero
{
@ -107,19 +107,5 @@ var (
Permissions: "rwm",
},
}, DefaultSimpleDevices...)
DefaultAutoCreatedDevices = append([]*Device{
{
// /dev/fuse is created but not allowed.
// This is to allow java to work. Because java
// Insists on there being a /dev/fuse
// https://github.com/docker/docker/issues/514
// https://github.com/docker/docker/issues/2393
//
Path: "/dev/fuse",
Type: 'c',
Major: 10,
Minor: 229,
Permissions: "rwm",
},
}, DefaultSimpleDevices...)
DefaultAutoCreatedDevices = append([]*Device{}, DefaultSimpleDevices...)
)

View file

@ -0,0 +1,13 @@
package configs
type IntelRdt struct {
// The schema for L3 cache id and capacity bitmask (CBM)
// Format: "L3:<cache_id0>=<cbm0>;<cache_id1>=<cbm1>;..."
L3CacheSchema string `json:"l3_cache_schema,omitempty"`
// The schema of memory bandwidth per L3 cache id
// Format: "MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;..."
// The unit of memory bandwidth is specified in "percentages" by
// default, and in "MBps" if MBA Software Controller is enabled.
MemBwSchema string `json:"memBwSchema,omitempty"`
}

View file

@ -1,5 +1,11 @@
package configs
const (
// EXT_COPYUP is a directive to copy up the contents of a directory when
// a tmpfs is mounted over it.
EXT_COPYUP = 1 << iota
)
type Mount struct {
// Source path for the mount.
Source string `json:"source"`
@ -22,6 +28,9 @@ type Mount struct {
// Relabel source if set, "z" indicates shared, "Z" indicates unshared.
Relabel string `json:"relabel"`
// Extensions are additional flags that are specific to runc.
Extensions int `json:"extensions"`
// Optional Command to be run before Source is mounted.
PremountCmds []Command `json:"premount_cmds"`

View file

@ -1,5 +1,3 @@
// +build linux freebsd
package configs
import (
@ -9,12 +7,13 @@ import (
)
const (
NEWNET NamespaceType = "NEWNET"
NEWPID NamespaceType = "NEWPID"
NEWNS NamespaceType = "NEWNS"
NEWUTS NamespaceType = "NEWUTS"
NEWIPC NamespaceType = "NEWIPC"
NEWUSER NamespaceType = "NEWUSER"
NEWNET NamespaceType = "NEWNET"
NEWPID NamespaceType = "NEWPID"
NEWNS NamespaceType = "NEWNS"
NEWUTS NamespaceType = "NEWUTS"
NEWIPC NamespaceType = "NEWIPC"
NEWUSER NamespaceType = "NEWUSER"
NEWCGROUP NamespaceType = "NEWCGROUP"
)
var (
@ -22,8 +21,8 @@ var (
supportedNamespaces = make(map[NamespaceType]bool)
)
// nsToFile converts the namespace type to its filename
func nsToFile(ns NamespaceType) string {
// NsName converts the namespace type to its filename
func NsName(ns NamespaceType) string {
switch ns {
case NEWNET:
return "net"
@ -37,6 +36,8 @@ func nsToFile(ns NamespaceType) string {
return "user"
case NEWUTS:
return "uts"
case NEWCGROUP:
return "cgroup"
}
return ""
}
@ -50,7 +51,7 @@ func IsNamespaceSupported(ns NamespaceType) bool {
if ok {
return supported
}
nsFile := nsToFile(ns)
nsFile := NsName(ns)
// if the namespace type is unknown, just return false
if nsFile == "" {
return false
@ -64,12 +65,13 @@ func IsNamespaceSupported(ns NamespaceType) bool {
func NamespaceTypes() []NamespaceType {
return []NamespaceType{
NEWUSER, // Keep user NS always first, don't move it.
NEWIPC,
NEWUTS,
NEWNET,
NEWPID,
NEWNS,
NEWUTS,
NEWIPC,
NEWUSER,
NEWCGROUP,
}
}
@ -81,10 +83,7 @@ type Namespace struct {
}
func (n *Namespace) GetPath(pid int) string {
if n.Path != "" {
return n.Path
}
return fmt.Sprintf("/proc/%d/ns/%s", pid, nsToFile(n.Type))
return fmt.Sprintf("/proc/%d/ns/%s", pid, NsName(n.Type))
}
func (n *Namespaces) Remove(t NamespaceType) bool {

View file

@ -2,19 +2,20 @@
package configs
import "syscall"
import "golang.org/x/sys/unix"
func (n *Namespace) Syscall() int {
return namespaceInfo[n.Type]
}
var namespaceInfo = map[NamespaceType]int{
NEWNET: syscall.CLONE_NEWNET,
NEWNS: syscall.CLONE_NEWNS,
NEWUSER: syscall.CLONE_NEWUSER,
NEWIPC: syscall.CLONE_NEWIPC,
NEWUTS: syscall.CLONE_NEWUTS,
NEWPID: syscall.CLONE_NEWPID,
NEWNET: unix.CLONE_NEWNET,
NEWNS: unix.CLONE_NEWNS,
NEWUSER: unix.CLONE_NEWUSER,
NEWIPC: unix.CLONE_NEWIPC,
NEWUTS: unix.CLONE_NEWUTS,
NEWPID: unix.CLONE_NEWPID,
NEWCGROUP: unix.CLONE_NEWCGROUP,
}
// CloneFlags parses the container's Namespaces options to set the correct

View file

@ -4,12 +4,10 @@ package configs
func (n *Namespace) Syscall() int {
panic("No namespace syscall support")
return 0
}
// CloneFlags parses the container's Namespaces options to set the correct
// flags on clone, unshare. This function returns flags only for new namespaces.
func (n *Namespaces) CloneFlags() uintptr {
panic("No namespace syscall support")
return uintptr(0)
}

View file

@ -1,4 +1,4 @@
// +build !linux,!freebsd
// +build !linux
package configs

191
vendor/github.com/opencontainers/runtime-spec/LICENSE generated vendored Normal file
View file

@ -0,0 +1,191 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
Copyright 2015 The Linux Foundation.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

View file

@ -0,0 +1,570 @@
package specs
import "os"
// Spec is the base configuration for the container.
type Spec struct {
// Version of the Open Container Runtime Specification with which the bundle complies.
Version string `json:"ociVersion"`
// Process configures the container process.
Process *Process `json:"process,omitempty"`
// Root configures the container's root filesystem.
Root *Root `json:"root,omitempty"`
// Hostname configures the container's hostname.
Hostname string `json:"hostname,omitempty"`
// Mounts configures additional mounts (on top of Root).
Mounts []Mount `json:"mounts,omitempty"`
// Hooks configures callbacks for container lifecycle events.
Hooks *Hooks `json:"hooks,omitempty" platform:"linux,solaris"`
// Annotations contains arbitrary metadata for the container.
Annotations map[string]string `json:"annotations,omitempty"`
// Linux is platform-specific configuration for Linux based containers.
Linux *Linux `json:"linux,omitempty" platform:"linux"`
// Solaris is platform-specific configuration for Solaris based containers.
Solaris *Solaris `json:"solaris,omitempty" platform:"solaris"`
// Windows is platform-specific configuration for Windows based containers.
Windows *Windows `json:"windows,omitempty" platform:"windows"`
}
// Process contains information to start a specific application inside the container.
type Process struct {
// Terminal creates an interactive terminal for the container.
Terminal bool `json:"terminal,omitempty"`
// ConsoleSize specifies the size of the console.
ConsoleSize *Box `json:"consoleSize,omitempty"`
// User specifies user information for the process.
User User `json:"user"`
// Args specifies the binary and arguments for the application to execute.
Args []string `json:"args"`
// Env populates the process environment for the process.
Env []string `json:"env,omitempty"`
// Cwd is the current working directory for the process and must be
// relative to the container's root.
Cwd string `json:"cwd"`
// Capabilities are Linux capabilities that are kept for the process.
Capabilities *LinuxCapabilities `json:"capabilities,omitempty" platform:"linux"`
// Rlimits specifies rlimit options to apply to the process.
Rlimits []POSIXRlimit `json:"rlimits,omitempty" platform:"linux,solaris"`
// NoNewPrivileges controls whether additional privileges could be gained by processes in the container.
NoNewPrivileges bool `json:"noNewPrivileges,omitempty" platform:"linux"`
// ApparmorProfile specifies the apparmor profile for the container.
ApparmorProfile string `json:"apparmorProfile,omitempty" platform:"linux"`
// Specify an oom_score_adj for the container.
OOMScoreAdj *int `json:"oomScoreAdj,omitempty" platform:"linux"`
// SelinuxLabel specifies the selinux context that the container process is run as.
SelinuxLabel string `json:"selinuxLabel,omitempty" platform:"linux"`
}
// LinuxCapabilities specifies the whitelist of capabilities that are kept for a process.
// http://man7.org/linux/man-pages/man7/capabilities.7.html
type LinuxCapabilities struct {
// Bounding is the set of capabilities checked by the kernel.
Bounding []string `json:"bounding,omitempty" platform:"linux"`
// Effective is the set of capabilities checked by the kernel.
Effective []string `json:"effective,omitempty" platform:"linux"`
// Inheritable is the capabilities preserved across execve.
Inheritable []string `json:"inheritable,omitempty" platform:"linux"`
// Permitted is the limiting superset for effective capabilities.
Permitted []string `json:"permitted,omitempty" platform:"linux"`
// Ambient is the ambient set of capabilities that are kept.
Ambient []string `json:"ambient,omitempty" platform:"linux"`
}
// Box specifies dimensions of a rectangle. Used for specifying the size of a console.
type Box struct {
// Height is the vertical dimension of a box.
Height uint `json:"height"`
// Width is the horizontal dimension of a box.
Width uint `json:"width"`
}
// User specifies specific user (and group) information for the container process.
type User struct {
// UID is the user id.
UID uint32 `json:"uid" platform:"linux,solaris"`
// GID is the group id.
GID uint32 `json:"gid" platform:"linux,solaris"`
// AdditionalGids are additional group ids set for the container's process.
AdditionalGids []uint32 `json:"additionalGids,omitempty" platform:"linux,solaris"`
// Username is the user name.
Username string `json:"username,omitempty" platform:"windows"`
}
// Root contains information about the container's root filesystem on the host.
type Root struct {
// Path is the absolute path to the container's root filesystem.
Path string `json:"path"`
// Readonly makes the root filesystem for the container readonly before the process is executed.
Readonly bool `json:"readonly,omitempty"`
}
// Mount specifies a mount for a container.
type Mount struct {
// Destination is the absolute path where the mount will be placed in the container.
Destination string `json:"destination"`
// Type specifies the mount kind.
Type string `json:"type,omitempty" platform:"linux,solaris"`
// Source specifies the source path of the mount.
Source string `json:"source,omitempty"`
// Options are fstab style mount options.
Options []string `json:"options,omitempty"`
}
// Hook specifies a command that is run at a particular event in the lifecycle of a container
type Hook struct {
Path string `json:"path"`
Args []string `json:"args,omitempty"`
Env []string `json:"env,omitempty"`
Timeout *int `json:"timeout,omitempty"`
}
// Hooks for container setup and teardown
type Hooks struct {
// Prestart is a list of hooks to be run before the container process is executed.
Prestart []Hook `json:"prestart,omitempty"`
// Poststart is a list of hooks to be run after the container process is started.
Poststart []Hook `json:"poststart,omitempty"`
// Poststop is a list of hooks to be run after the container process exits.
Poststop []Hook `json:"poststop,omitempty"`
}
// Linux contains platform-specific configuration for Linux based containers.
type Linux struct {
// UIDMapping specifies user mappings for supporting user namespaces.
UIDMappings []LinuxIDMapping `json:"uidMappings,omitempty"`
// GIDMapping specifies group mappings for supporting user namespaces.
GIDMappings []LinuxIDMapping `json:"gidMappings,omitempty"`
// Sysctl are a set of key value pairs that are set for the container on start
Sysctl map[string]string `json:"sysctl,omitempty"`
// Resources contain cgroup information for handling resource constraints
// for the container
Resources *LinuxResources `json:"resources,omitempty"`
// CgroupsPath specifies the path to cgroups that are created and/or joined by the container.
// The path is expected to be relative to the cgroups mountpoint.
// If resources are specified, the cgroups at CgroupsPath will be updated based on resources.
CgroupsPath string `json:"cgroupsPath,omitempty"`
// Namespaces contains the namespaces that are created and/or joined by the container
Namespaces []LinuxNamespace `json:"namespaces,omitempty"`
// Devices are a list of device nodes that are created for the container
Devices []LinuxDevice `json:"devices,omitempty"`
// Seccomp specifies the seccomp security settings for the container.
Seccomp *LinuxSeccomp `json:"seccomp,omitempty"`
// RootfsPropagation is the rootfs mount propagation mode for the container.
RootfsPropagation string `json:"rootfsPropagation,omitempty"`
// MaskedPaths masks over the provided paths inside the container.
MaskedPaths []string `json:"maskedPaths,omitempty"`
// ReadonlyPaths sets the provided paths as RO inside the container.
ReadonlyPaths []string `json:"readonlyPaths,omitempty"`
// MountLabel specifies the selinux context for the mounts in the container.
MountLabel string `json:"mountLabel,omitempty"`
// IntelRdt contains Intel Resource Director Technology (RDT) information
// for handling resource constraints (e.g., L3 cache) for the container
IntelRdt *LinuxIntelRdt `json:"intelRdt,omitempty"`
}
// LinuxNamespace is the configuration for a Linux namespace
type LinuxNamespace struct {
// Type is the type of namespace
Type LinuxNamespaceType `json:"type"`
// Path is a path to an existing namespace persisted on disk that can be joined
// and is of the same type
Path string `json:"path,omitempty"`
}
// LinuxNamespaceType is one of the Linux namespaces
type LinuxNamespaceType string
const (
// PIDNamespace for isolating process IDs
PIDNamespace LinuxNamespaceType = "pid"
// NetworkNamespace for isolating network devices, stacks, ports, etc
NetworkNamespace = "network"
// MountNamespace for isolating mount points
MountNamespace = "mount"
// IPCNamespace for isolating System V IPC, POSIX message queues
IPCNamespace = "ipc"
// UTSNamespace for isolating hostname and NIS domain name
UTSNamespace = "uts"
// UserNamespace for isolating user and group IDs
UserNamespace = "user"
// CgroupNamespace for isolating cgroup hierarchies
CgroupNamespace = "cgroup"
)
// LinuxIDMapping specifies UID/GID mappings
type LinuxIDMapping struct {
// HostID is the starting UID/GID on the host to be mapped to 'ContainerID'
HostID uint32 `json:"hostID"`
// ContainerID is the starting UID/GID in the container
ContainerID uint32 `json:"containerID"`
// Size is the number of IDs to be mapped
Size uint32 `json:"size"`
}
// POSIXRlimit type and restrictions
type POSIXRlimit struct {
// Type of the rlimit to set
Type string `json:"type"`
// Hard is the hard limit for the specified type
Hard uint64 `json:"hard"`
// Soft is the soft limit for the specified type
Soft uint64 `json:"soft"`
}
// LinuxHugepageLimit structure corresponds to limiting kernel hugepages
type LinuxHugepageLimit struct {
// Pagesize is the hugepage size
Pagesize string `json:"pageSize"`
// Limit is the limit of "hugepagesize" hugetlb usage
Limit uint64 `json:"limit"`
}
// LinuxInterfacePriority for network interfaces
type LinuxInterfacePriority struct {
// Name is the name of the network interface
Name string `json:"name"`
// Priority for the interface
Priority uint32 `json:"priority"`
}
// linuxBlockIODevice holds major:minor format supported in blkio cgroup
type linuxBlockIODevice struct {
// Major is the device's major number.
Major int64 `json:"major"`
// Minor is the device's minor number.
Minor int64 `json:"minor"`
}
// LinuxWeightDevice struct holds a `major:minor weight` pair for weightDevice
type LinuxWeightDevice struct {
linuxBlockIODevice
// Weight is the bandwidth rate for the device.
Weight *uint16 `json:"weight,omitempty"`
// LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, CFQ scheduler only
LeafWeight *uint16 `json:"leafWeight,omitempty"`
}
// LinuxThrottleDevice struct holds a `major:minor rate_per_second` pair
type LinuxThrottleDevice struct {
linuxBlockIODevice
// Rate is the IO rate limit per cgroup per device
Rate uint64 `json:"rate"`
}
// LinuxBlockIO for Linux cgroup 'blkio' resource management
type LinuxBlockIO struct {
// Specifies per cgroup weight
Weight *uint16 `json:"weight,omitempty"`
// Specifies tasks' weight in the given cgroup while competing with the cgroup's child cgroups, CFQ scheduler only
LeafWeight *uint16 `json:"leafWeight,omitempty"`
// Weight per cgroup per device, can override BlkioWeight
WeightDevice []LinuxWeightDevice `json:"weightDevice,omitempty"`
// IO read rate limit per cgroup per device, bytes per second
ThrottleReadBpsDevice []LinuxThrottleDevice `json:"throttleReadBpsDevice,omitempty"`
// IO write rate limit per cgroup per device, bytes per second
ThrottleWriteBpsDevice []LinuxThrottleDevice `json:"throttleWriteBpsDevice,omitempty"`
// IO read rate limit per cgroup per device, IO per second
ThrottleReadIOPSDevice []LinuxThrottleDevice `json:"throttleReadIOPSDevice,omitempty"`
// IO write rate limit per cgroup per device, IO per second
ThrottleWriteIOPSDevice []LinuxThrottleDevice `json:"throttleWriteIOPSDevice,omitempty"`
}
// LinuxMemory for Linux cgroup 'memory' resource management
type LinuxMemory struct {
// Memory limit (in bytes).
Limit *int64 `json:"limit,omitempty"`
// Memory reservation or soft_limit (in bytes).
Reservation *int64 `json:"reservation,omitempty"`
// Total memory limit (memory + swap).
Swap *int64 `json:"swap,omitempty"`
// Kernel memory limit (in bytes).
Kernel *int64 `json:"kernel,omitempty"`
// Kernel memory limit for tcp (in bytes)
KernelTCP *int64 `json:"kernelTCP,omitempty"`
// How aggressive the kernel will swap memory pages.
Swappiness *uint64 `json:"swappiness,omitempty"`
// DisableOOMKiller disables the OOM killer for out of memory conditions
DisableOOMKiller *bool `json:"disableOOMKiller,omitempty"`
}
// LinuxCPU for Linux cgroup 'cpu' resource management
type LinuxCPU struct {
// CPU shares (relative weight (ratio) vs. other cgroups with cpu shares).
Shares *uint64 `json:"shares,omitempty"`
// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
Quota *int64 `json:"quota,omitempty"`
// CPU period to be used for hardcapping (in usecs).
Period *uint64 `json:"period,omitempty"`
// How much time realtime scheduling may use (in usecs).
RealtimeRuntime *int64 `json:"realtimeRuntime,omitempty"`
// CPU period to be used for realtime scheduling (in usecs).
RealtimePeriod *uint64 `json:"realtimePeriod,omitempty"`
// CPUs to use within the cpuset. Default is to use any CPU available.
Cpus string `json:"cpus,omitempty"`
// List of memory nodes in the cpuset. Default is to use any available memory node.
Mems string `json:"mems,omitempty"`
}
// LinuxPids for Linux cgroup 'pids' resource management (Linux 4.3)
type LinuxPids struct {
// Maximum number of PIDs. Default is "no limit".
Limit int64 `json:"limit"`
}
// LinuxNetwork identification and priority configuration
type LinuxNetwork struct {
// Set class identifier for container's network packets
ClassID *uint32 `json:"classID,omitempty"`
// Set priority of network traffic for container
Priorities []LinuxInterfacePriority `json:"priorities,omitempty"`
}
// LinuxResources has container runtime resource constraints
type LinuxResources struct {
// Devices configures the device whitelist.
Devices []LinuxDeviceCgroup `json:"devices,omitempty"`
// Memory restriction configuration
Memory *LinuxMemory `json:"memory,omitempty"`
// CPU resource restriction configuration
CPU *LinuxCPU `json:"cpu,omitempty"`
// Task resource restriction configuration.
Pids *LinuxPids `json:"pids,omitempty"`
// BlockIO restriction configuration
BlockIO *LinuxBlockIO `json:"blockIO,omitempty"`
// Hugetlb limit (in bytes)
HugepageLimits []LinuxHugepageLimit `json:"hugepageLimits,omitempty"`
// Network restriction configuration
Network *LinuxNetwork `json:"network,omitempty"`
}
// LinuxDevice represents the mknod information for a Linux special device file
type LinuxDevice struct {
// Path to the device.
Path string `json:"path"`
// Device type, block, char, etc.
Type string `json:"type"`
// Major is the device's major number.
Major int64 `json:"major"`
// Minor is the device's minor number.
Minor int64 `json:"minor"`
// FileMode permission bits for the device.
FileMode *os.FileMode `json:"fileMode,omitempty"`
// UID of the device.
UID *uint32 `json:"uid,omitempty"`
// Gid of the device.
GID *uint32 `json:"gid,omitempty"`
}
// LinuxDeviceCgroup represents a device rule for the whitelist controller
type LinuxDeviceCgroup struct {
// Allow or deny
Allow bool `json:"allow"`
// Device type, block, char, etc.
Type string `json:"type,omitempty"`
// Major is the device's major number.
Major *int64 `json:"major,omitempty"`
// Minor is the device's minor number.
Minor *int64 `json:"minor,omitempty"`
// Cgroup access permissions format, rwm.
Access string `json:"access,omitempty"`
}
// Solaris contains platform-specific configuration for Solaris application containers.
type Solaris struct {
// SMF FMRI which should go "online" before we start the container process.
Milestone string `json:"milestone,omitempty"`
// Maximum set of privileges any process in this container can obtain.
LimitPriv string `json:"limitpriv,omitempty"`
// The maximum amount of shared memory allowed for this container.
MaxShmMemory string `json:"maxShmMemory,omitempty"`
// Specification for automatic creation of network resources for this container.
Anet []SolarisAnet `json:"anet,omitempty"`
// Set limit on the amount of CPU time that can be used by container.
CappedCPU *SolarisCappedCPU `json:"cappedCPU,omitempty"`
// The physical and swap caps on the memory that can be used by this container.
CappedMemory *SolarisCappedMemory `json:"cappedMemory,omitempty"`
}
// SolarisCappedCPU allows users to set limit on the amount of CPU time that can be used by container.
type SolarisCappedCPU struct {
Ncpus string `json:"ncpus,omitempty"`
}
// SolarisCappedMemory allows users to set the physical and swap caps on the memory that can be used by this container.
type SolarisCappedMemory struct {
Physical string `json:"physical,omitempty"`
Swap string `json:"swap,omitempty"`
}
// SolarisAnet provides the specification for automatic creation of network resources for this container.
type SolarisAnet struct {
// Specify a name for the automatically created VNIC datalink.
Linkname string `json:"linkname,omitempty"`
// Specify the link over which the VNIC will be created.
Lowerlink string `json:"lowerLink,omitempty"`
// The set of IP addresses that the container can use.
Allowedaddr string `json:"allowedAddress,omitempty"`
// Specifies whether allowedAddress limitation is to be applied to the VNIC.
Configallowedaddr string `json:"configureAllowedAddress,omitempty"`
// The value of the optional default router.
Defrouter string `json:"defrouter,omitempty"`
// Enable one or more types of link protection.
Linkprotection string `json:"linkProtection,omitempty"`
// Set the VNIC's macAddress
Macaddress string `json:"macAddress,omitempty"`
}
// Windows defines the runtime configuration for Windows based containers, including Hyper-V containers.
type Windows struct {
// LayerFolders contains a list of absolute paths to directories containing image layers.
LayerFolders []string `json:"layerFolders"`
// Resources contains information for handling resource constraints for the container.
Resources *WindowsResources `json:"resources,omitempty"`
// CredentialSpec contains a JSON object describing a group Managed Service Account (gMSA) specification.
CredentialSpec interface{} `json:"credentialSpec,omitempty"`
// Servicing indicates if the container is being started in a mode to apply a Windows Update servicing operation.
Servicing bool `json:"servicing,omitempty"`
// IgnoreFlushesDuringBoot indicates if the container is being started in a mode where disk writes are not flushed during its boot process.
IgnoreFlushesDuringBoot bool `json:"ignoreFlushesDuringBoot,omitempty"`
// HyperV contains information for running a container with Hyper-V isolation.
HyperV *WindowsHyperV `json:"hyperv,omitempty"`
// Network restriction configuration.
Network *WindowsNetwork `json:"network,omitempty"`
}
// WindowsResources has container runtime resource constraints for containers running on Windows.
type WindowsResources struct {
// Memory restriction configuration.
Memory *WindowsMemoryResources `json:"memory,omitempty"`
// CPU resource restriction configuration.
CPU *WindowsCPUResources `json:"cpu,omitempty"`
// Storage restriction configuration.
Storage *WindowsStorageResources `json:"storage,omitempty"`
}
// WindowsMemoryResources contains memory resource management settings.
type WindowsMemoryResources struct {
// Memory limit in bytes.
Limit *uint64 `json:"limit,omitempty"`
}
// WindowsCPUResources contains CPU resource management settings.
type WindowsCPUResources struct {
// Number of CPUs available to the container.
Count *uint64 `json:"count,omitempty"`
// CPU shares (relative weight to other containers with cpu shares).
Shares *uint16 `json:"shares,omitempty"`
// Specifies the portion of processor cycles that this container can use as a percentage times 100.
Maximum *uint16 `json:"maximum,omitempty"`
}
// WindowsStorageResources contains storage resource management settings.
type WindowsStorageResources struct {
// Specifies maximum Iops for the system drive.
Iops *uint64 `json:"iops,omitempty"`
// Specifies maximum bytes per second for the system drive.
Bps *uint64 `json:"bps,omitempty"`
// Sandbox size specifies the minimum size of the system drive in bytes.
SandboxSize *uint64 `json:"sandboxSize,omitempty"`
}
// WindowsNetwork contains network settings for Windows containers.
type WindowsNetwork struct {
// List of HNS endpoints that the container should connect to.
EndpointList []string `json:"endpointList,omitempty"`
// Specifies if unqualified DNS name resolution is allowed.
AllowUnqualifiedDNSQuery bool `json:"allowUnqualifiedDNSQuery,omitempty"`
// Comma separated list of DNS suffixes to use for name resolution.
DNSSearchList []string `json:"DNSSearchList,omitempty"`
// Name (ID) of the container that we will share with the network stack.
NetworkSharedContainerName string `json:"networkSharedContainerName,omitempty"`
}
// WindowsHyperV contains information for configuring a container to run with Hyper-V isolation.
type WindowsHyperV struct {
// UtilityVMPath is an optional path to the image used for the Utility VM.
UtilityVMPath string `json:"utilityVMPath,omitempty"`
}
// LinuxSeccomp represents syscall restrictions
type LinuxSeccomp struct {
DefaultAction LinuxSeccompAction `json:"defaultAction"`
Architectures []Arch `json:"architectures,omitempty"`
Syscalls []LinuxSyscall `json:"syscalls,omitempty"`
}
// Arch used for additional architectures
type Arch string
// Additional architectures permitted to be used for system calls
// By default only the native architecture of the kernel is permitted
const (
ArchX86 Arch = "SCMP_ARCH_X86"
ArchX86_64 Arch = "SCMP_ARCH_X86_64"
ArchX32 Arch = "SCMP_ARCH_X32"
ArchARM Arch = "SCMP_ARCH_ARM"
ArchAARCH64 Arch = "SCMP_ARCH_AARCH64"
ArchMIPS Arch = "SCMP_ARCH_MIPS"
ArchMIPS64 Arch = "SCMP_ARCH_MIPS64"
ArchMIPS64N32 Arch = "SCMP_ARCH_MIPS64N32"
ArchMIPSEL Arch = "SCMP_ARCH_MIPSEL"
ArchMIPSEL64 Arch = "SCMP_ARCH_MIPSEL64"
ArchMIPSEL64N32 Arch = "SCMP_ARCH_MIPSEL64N32"
ArchPPC Arch = "SCMP_ARCH_PPC"
ArchPPC64 Arch = "SCMP_ARCH_PPC64"
ArchPPC64LE Arch = "SCMP_ARCH_PPC64LE"
ArchS390 Arch = "SCMP_ARCH_S390"
ArchS390X Arch = "SCMP_ARCH_S390X"
ArchPARISC Arch = "SCMP_ARCH_PARISC"
ArchPARISC64 Arch = "SCMP_ARCH_PARISC64"
)
// LinuxSeccompAction taken upon Seccomp rule match
type LinuxSeccompAction string
// Define actions for Seccomp rules
const (
ActKill LinuxSeccompAction = "SCMP_ACT_KILL"
ActTrap LinuxSeccompAction = "SCMP_ACT_TRAP"
ActErrno LinuxSeccompAction = "SCMP_ACT_ERRNO"
ActTrace LinuxSeccompAction = "SCMP_ACT_TRACE"
ActAllow LinuxSeccompAction = "SCMP_ACT_ALLOW"
)
// LinuxSeccompOperator used to match syscall arguments in Seccomp
type LinuxSeccompOperator string
// Define operators for syscall arguments in Seccomp
const (
OpNotEqual LinuxSeccompOperator = "SCMP_CMP_NE"
OpLessThan LinuxSeccompOperator = "SCMP_CMP_LT"
OpLessEqual LinuxSeccompOperator = "SCMP_CMP_LE"
OpEqualTo LinuxSeccompOperator = "SCMP_CMP_EQ"
OpGreaterEqual LinuxSeccompOperator = "SCMP_CMP_GE"
OpGreaterThan LinuxSeccompOperator = "SCMP_CMP_GT"
OpMaskedEqual LinuxSeccompOperator = "SCMP_CMP_MASKED_EQ"
)
// LinuxSeccompArg used for matching specific syscall arguments in Seccomp
type LinuxSeccompArg struct {
Index uint `json:"index"`
Value uint64 `json:"value"`
ValueTwo uint64 `json:"valueTwo,omitempty"`
Op LinuxSeccompOperator `json:"op"`
}
// LinuxSyscall is used to match a syscall in Seccomp
type LinuxSyscall struct {
Names []string `json:"names"`
Action LinuxSeccompAction `json:"action"`
Args []LinuxSeccompArg `json:"args,omitempty"`
}
// LinuxIntelRdt has container runtime resource constraints
// for Intel RDT/CAT which introduced in Linux 4.10 kernel
type LinuxIntelRdt struct {
// The schema for L3 cache id and capacity bitmask (CBM)
// Format: "L3:<cache_id0>=<cbm0>;<cache_id1>=<cbm1>;..."
L3CacheSchema string `json:"l3CacheSchema,omitempty"`
}

View file

@ -0,0 +1,17 @@
package specs
// State holds information about the runtime state of the container.
type State struct {
// Version is the version of the specification that is supported.
Version string `json:"ociVersion"`
// ID is the container ID
ID string `json:"id"`
// Status is the runtime status of the container.
Status string `json:"status"`
// Pid is the process ID for the container process.
Pid int `json:"pid,omitempty"`
// Bundle is the path to the container's bundle directory.
Bundle string `json:"bundle"`
// Annotations are key values associated with the container.
Annotations map[string]string `json:"annotations,omitempty"`
}

View file

@ -0,0 +1,18 @@
package specs
import "fmt"
const (
// VersionMajor is for an API incompatible changes
VersionMajor = 1
// VersionMinor is for functionality in a backwards-compatible manner
VersionMinor = 0
// VersionPatch is for backwards-compatible bug fixes
VersionPatch = 0
// VersionDev indicates development branch. Releases will be empty string.
VersionDev = ""
)
// Version is the specification version that the package types support.
var Version = fmt.Sprintf("%d.%d.%d%s", VersionMajor, VersionMinor, VersionPatch, VersionDev)