// +build linux package fs import ( "fmt" "io" "io/ioutil" "os" "path/filepath" "strconv" "sync" "github.com/opencontainers/runc/libcontainer/cgroups" "github.com/opencontainers/runc/libcontainer/configs" ) var ( subsystems = map[string]subsystem{ "devices": &DevicesGroup{}, "memory": &MemoryGroup{}, "cpu": &CpuGroup{}, "cpuset": &CpusetGroup{}, "cpuacct": &CpuacctGroup{}, "blkio": &BlkioGroup{}, "hugetlb": &HugetlbGroup{}, "net_cls": &NetClsGroup{}, "net_prio": &NetPrioGroup{}, "perf_event": &PerfEventGroup{}, "freezer": &FreezerGroup{}, } CgroupProcesses = "cgroup.procs" HugePageSizes, _ = cgroups.GetHugePageSize() ) type subsystem interface { // Returns the stats, as 'stats', corresponding to the cgroup under 'path'. GetStats(path string, stats *cgroups.Stats) error // Removes the cgroup represented by 'data'. Remove(*data) error // Creates and joins the cgroup represented by data. Apply(*data) error // Set the cgroup represented by cgroup. Set(path string, cgroup *configs.Cgroup) error } type Manager struct { mu sync.Mutex Cgroups *configs.Cgroup Paths map[string]string } // The absolute path to the root of the cgroup hierarchies. var cgroupRootLock sync.Mutex var cgroupRoot string // Gets the cgroupRoot. func getCgroupRoot() (string, error) { cgroupRootLock.Lock() defer cgroupRootLock.Unlock() if cgroupRoot != "" { return cgroupRoot, nil } root, err := cgroups.FindCgroupMountpointDir() if err != nil { return "", err } if _, err := os.Stat(root); err != nil { return "", err } cgroupRoot = root return cgroupRoot, nil } type data struct { root string cgroup string c *configs.Cgroup pid int } func (m *Manager) Apply(pid int) (err error) { if m.Cgroups == nil { return nil } var c = m.Cgroups d, err := getCgroupData(m.Cgroups, pid) if err != nil { return err } paths := make(map[string]string) defer func() { if err != nil { cgroups.RemovePaths(paths) } }() for name, sys := range subsystems { if err := sys.Apply(d); err != nil { return err } // TODO: Apply should, ideally, be reentrant or be broken up into a separate // create and join phase so that the cgroup hierarchy for a container can be // created then join consists of writing the process pids to cgroup.procs p, err := d.path(name) if err != nil { if cgroups.IsNotFound(err) { continue } return err } paths[name] = p } m.Paths = paths if paths["cpu"] != "" { if err := CheckCpushares(paths["cpu"], c.CpuShares); err != nil { return err } } return nil } func (m *Manager) Destroy() error { m.mu.Lock() defer m.mu.Unlock() if err := cgroups.RemovePaths(m.Paths); err != nil { return err } m.Paths = make(map[string]string) return nil } func (m *Manager) GetPaths() map[string]string { m.mu.Lock() paths := m.Paths m.mu.Unlock() return paths } func (m *Manager) GetStats() (*cgroups.Stats, error) { m.mu.Lock() defer m.mu.Unlock() stats := cgroups.NewStats() for name, path := range m.Paths { sys, ok := subsystems[name] if !ok || !cgroups.PathExists(path) { continue } if err := sys.GetStats(path, stats); err != nil { return nil, err } } return stats, nil } func (m *Manager) Set(container *configs.Config) error { for name, path := range m.Paths { sys, ok := subsystems[name] if !ok || !cgroups.PathExists(path) { continue } if err := sys.Set(path, container.Cgroups); err != nil { return err } } return nil } // Freeze toggles the container's freezer cgroup depending on the state // provided func (m *Manager) Freeze(state configs.FreezerState) error { d, err := getCgroupData(m.Cgroups, 0) if err != nil { return err } dir, err := d.path("freezer") if err != nil { return err } prevState := m.Cgroups.Freezer m.Cgroups.Freezer = state freezer := subsystems["freezer"] err = freezer.Set(dir, m.Cgroups) if err != nil { m.Cgroups.Freezer = prevState return err } return nil } func (m *Manager) GetPids() ([]int, error) { d, err := getCgroupData(m.Cgroups, 0) if err != nil { return nil, err } dir, err := d.path("devices") if err != nil { return nil, err } return cgroups.ReadProcsFile(dir) } func getCgroupData(c *configs.Cgroup, pid int) (*data, error) { root, err := getCgroupRoot() if err != nil { return nil, err } cgroup := c.Name if c.Parent != "" { cgroup = filepath.Join(c.Parent, cgroup) } return &data{ root: root, cgroup: cgroup, c: c, pid: pid, }, nil } func (raw *data) parent(subsystem, mountpoint, root string) (string, error) { initPath, err := cgroups.GetThisCgroupDir(subsystem) if err != nil { return "", err } relDir, err := filepath.Rel(root, initPath) if err != nil { return "", err } return filepath.Join(mountpoint, relDir), nil } func (raw *data) path(subsystem string) (string, error) { mnt, root, err := cgroups.FindCgroupMountpointAndRoot(subsystem) // If we didn't mount the subsystem, there is no point we make the path. if err != nil { return "", err } // If the cgroup name/path is absolute do not look relative to the cgroup of the init process. if filepath.IsAbs(raw.cgroup) { return filepath.Join(raw.root, filepath.Base(mnt), raw.cgroup), nil } parent, err := raw.parent(subsystem, mnt, root) if err != nil { return "", err } return filepath.Join(parent, raw.cgroup), nil } func (raw *data) join(subsystem string) (string, error) { path, err := raw.path(subsystem) if err != nil { return "", err } if err := os.MkdirAll(path, 0755); err != nil { return "", err } if err := writeFile(path, CgroupProcesses, strconv.Itoa(raw.pid)); err != nil { return "", err } return path, nil } func writeFile(dir, file, data string) 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.", file) } return ioutil.WriteFile(filepath.Join(dir, file), []byte(data), 0700) } func readFile(dir, file string) (string, error) { data, err := ioutil.ReadFile(filepath.Join(dir, file)) return string(data), err } func removePath(p string, err error) error { if err != nil { return err } if p != "" { return os.RemoveAll(p) } return nil } func CheckCpushares(path string, c int64) error { var cpuShares int64 if c == 0 { return nil } fd, err := os.Open(filepath.Join(path, "cpu.shares")) if err != nil { return err } defer fd.Close() _, err = fmt.Fscanf(fd, "%d", &cpuShares) if err != nil && err != io.EOF { return err } if c > cpuShares { return fmt.Errorf("The maximum allowed cpu-shares is %d", cpuShares) } else if c < cpuShares { return fmt.Errorf("The minimum allowed cpu-shares is %d", cpuShares) } return nil }