Merge pull request #608 from inatatsu/reduce-parsing-mountinfo

Eliminate redundant parsing of mountinfo

libcontainer/cgroups/utils.go

@@ -23,6 +23,9 @@ func FindCgroupMountpoint(subsystem 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.
+	if !isSubsystemAvailable(subsystem) {
+		return "", NewNotFoundError(subsystem)
+	}
 	f, err := os.Open("/proc/self/mountinfo")
 	if err != nil {
 		return "", err
@@ -47,6 +50,9 @@ func FindCgroupMountpoint(subsystem string) (string, error) {
 }
 
 func FindCgroupMountpointAndRoot(subsystem string) (string, string, error) {
+	if !isSubsystemAvailable(subsystem) {
+		return "", "", NewNotFoundError(subsystem)
+	}
 	f, err := os.Open("/proc/self/mountinfo")
 	if err != nil {
 		return "", "", err
@@ -70,6 +76,15 @@ 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 FindCgroupMountpointDir() (string, error) {
 	f, err := os.Open("/proc/self/mountinfo")
 	if err != nil {
@@ -124,7 +139,8 @@ func (m Mount) GetThisCgroupDir(cgroups map[string]string) (string, error) {
 func getCgroupMountsHelper(ss map[string]bool, mi io.Reader) ([]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 {
@@ -139,12 +155,15 @@ func getCgroupMountsHelper(ss map[string]bool, mi io.Reader) ([]Mount, error) {
 			Root:       fields[3],
 		}
 		for _, opt := range strings.Split(fields[len(fields)-1], ",") {
+			if !ss[opt] {
+				continue
+			}
 			if strings.HasPrefix(opt, cgroupNamePrefix) {
 				m.Subsystems = append(m.Subsystems, opt[len(cgroupNamePrefix):])
-			}
-			if ss[opt] {
+			} else {
 				m.Subsystems = append(m.Subsystems, opt)
 			}
+			numFound++
 		}
 		res = append(res, m)
 	}
@@ -161,13 +180,13 @@ func GetCgroupMounts() ([]Mount, error) {
 	}
 	defer f.Close()
 
-	all, err := GetAllSubsystems()
+	all, err := ParseCgroupFile("/proc/self/cgroup")
 	if err != nil {
 		return nil, err
 	}
 
 	allMap := make(map[string]bool)
-	for _, s := range all {
+	for s := range all {
 		allMap[s] = true
 	}
 	return getCgroupMountsHelper(allMap, f)

libcontainer/rootfs_linux.go

@@ -515,10 +515,10 @@ func getParentMount(rootfs string) (string, string, error) {
 }
 
 // Make parent mount private if it was shared
-func rootfsParentMountPrivate(config *configs.Config) error {
+func rootfsParentMountPrivate(rootfs string) error {
 	sharedMount := false
 
-	parentMount, optionalOpts, err := getParentMount(config.Rootfs)
+	parentMount, optionalOpts, err := getParentMount(rootfs)
 	if err != nil {
 		return err
 	}
@@ -550,9 +550,10 @@ func prepareRoot(config *configs.Config) error {
 	if err := syscall.Mount("", "/", "", uintptr(flag), ""); err != nil {
 		return err
 	}
-
-	if err := rootfsParentMountPrivate(config); err != nil {
-		return err
+	if config.NoPivotRoot {
+		if err := rootfsParentMountPrivate(config.Rootfs); err != nil {
+			return err
+		}
 	}
 
 	return syscall.Mount(config.Rootfs, config.Rootfs, "bind", syscall.MS_BIND|syscall.MS_REC, "")
@@ -595,7 +596,14 @@ func pivotRoot(rootfs, pivotBaseDir string) (err error) {
 		}
 	}()
 	if err := syscall.PivotRoot(rootfs, pivotDir); err != nil {
-		return fmt.Errorf("pivot_root %s", err)
+		// Make the parent mount private
+		if err := rootfsParentMountPrivate(rootfs); err != nil {
+			return err
+		}
+		// Try again
+		if err := syscall.PivotRoot(rootfs, pivotDir); err != nil {
+			return fmt.Errorf("pivot_root %s", err)
+		}
 	}
 	if err := syscall.Chdir("/"); err != nil {
 		return fmt.Errorf("chdir / %s", err)

libcontainer/selinux/selinux.go

@@ -16,7 +16,6 @@ import (
 	"sync"
 	"syscall"
 
-	"github.com/docker/docker/pkg/mount"
 	"github.com/opencontainers/runc/libcontainer/system"
 )
 
@@ -60,16 +59,31 @@ func getSelinuxMountPoint() string {
 	}
 	selinuxfs = ""
 
-	mounts, err := mount.GetMounts()
+	f, err := os.Open("/proc/self/mountinfo")
 	if err != nil {
 		return selinuxfs
 	}
-	for _, mount := range mounts {
-		if mount.Fstype == "selinuxfs" {
-			selinuxfs = mount.Mountpoint
-			break
+	defer f.Close()
+
+	scanner := bufio.NewScanner(f)
+	for scanner.Scan() {
+		txt := scanner.Text()
+		// Safe as mountinfo encodes mountpoints with spaces as \040.
+		sepIdx := strings.Index(txt, " - ")
+		if sepIdx == -1 {
+			continue
 		}
+		if !strings.Contains(txt[sepIdx:], "selinuxfs") {
+			continue
+		}
+		fields := strings.Split(txt, " ")
+		if len(fields) < 5 {
+			continue
+		}
+		selinuxfs = fields[4]
+		break
 	}
+
 	if selinuxfs != "" {
 		var buf syscall.Statfs_t
 		syscall.Statfs(selinuxfs, &buf)