summaryrefslogtreecommitdiff
path: root/vendor/github.com/containerd/cgroups/utils.go
blob: f3129b1a3af4d6cb10cbccfb2eb818d7bfc32f9d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
/*
   Copyright The containerd Authors.

   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.
*/

package cgroups

import (
	"bufio"
	"fmt"
	"io"
	"io/ioutil"
	"os"
	"path/filepath"
	"strconv"
	"strings"
	"time"

	units "github.com/docker/go-units"
	specs "github.com/opencontainers/runtime-spec/specs-go"
)

var isUserNS = runningInUserNS()

// runningInUserNS detects whether we are currently running in a user namespace.
// Copied from github.com/lxc/lxd/shared/util.go
func runningInUserNS() bool {
	file, err := os.Open("/proc/self/uid_map")
	if err != nil {
		// This kernel-provided file only exists if user namespaces are supported
		return false
	}
	defer file.Close()

	buf := bufio.NewReader(file)
	l, _, err := buf.ReadLine()
	if err != nil {
		return false
	}

	line := string(l)
	var a, b, c int64
	fmt.Sscanf(line, "%d %d %d", &a, &b, &c)
	/*
	 * We assume we are in the initial user namespace if we have a full
	 * range - 4294967295 uids starting at uid 0.
	 */
	if a == 0 && b == 0 && c == 4294967295 {
		return false
	}
	return true
}

// defaults returns all known groups
func defaults(root string) ([]Subsystem, error) {
	h, err := NewHugetlb(root)
	if err != nil && !os.IsNotExist(err) {
		return nil, err
	}
	s := []Subsystem{
		NewNamed(root, "systemd"),
		NewFreezer(root),
		NewPids(root),
		NewNetCls(root),
		NewNetPrio(root),
		NewPerfEvent(root),
		NewCputset(root),
		NewCpu(root),
		NewCpuacct(root),
		NewMemory(root),
		NewBlkio(root),
		NewRdma(root),
	}
	// only add the devices cgroup if we are not in a user namespace
	// because modifications are not allowed
	if !isUserNS {
		s = append(s, NewDevices(root))
	}
	// add the hugetlb cgroup if error wasn't due to missing hugetlb
	// cgroup support on the host
	if err == nil {
		s = append(s, h)
	}
	return s, nil
}

// remove will remove a cgroup path handling EAGAIN and EBUSY errors and
// retrying the remove after a exp timeout
func remove(path string) error {
	delay := 10 * time.Millisecond
	for i := 0; i < 5; i++ {
		if i != 0 {
			time.Sleep(delay)
			delay *= 2
		}
		if err := os.RemoveAll(path); err == nil {
			return nil
		}
	}
	return fmt.Errorf("cgroups: unable to remove path %q", path)
}

// readPids will read all the pids of processes in a cgroup by the provided path
func readPids(path string, subsystem Name) ([]Process, error) {
	f, err := os.Open(filepath.Join(path, cgroupProcs))
	if err != nil {
		return nil, err
	}
	defer f.Close()
	var (
		out []Process
		s   = bufio.NewScanner(f)
	)
	for s.Scan() {
		if t := s.Text(); t != "" {
			pid, err := strconv.Atoi(t)
			if err != nil {
				return nil, err
			}
			out = append(out, Process{
				Pid:       pid,
				Subsystem: subsystem,
				Path:      path,
			})
		}
	}
	return out, nil
}

// readTasksPids will read all the pids of tasks in a cgroup by the provided path
func readTasksPids(path string, subsystem Name) ([]Task, error) {
	f, err := os.Open(filepath.Join(path, cgroupTasks))
	if err != nil {
		return nil, err
	}
	defer f.Close()
	var (
		out []Task
		s   = bufio.NewScanner(f)
	)
	for s.Scan() {
		if t := s.Text(); t != "" {
			pid, err := strconv.Atoi(t)
			if err != nil {
				return nil, err
			}
			out = append(out, Task{
				Pid:       pid,
				Subsystem: subsystem,
				Path:      path,
			})
		}
	}
	return out, nil
}

func hugePageSizes() ([]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 nil, err
	}
	for _, st := range files {
		nameArray := strings.Split(st.Name(), "-")
		pageSize, err := units.RAMInBytes(nameArray[1])
		if err != nil {
			return nil, err
		}
		pageSizes = append(pageSizes, units.CustomSize("%g%s", float64(pageSize), 1024.0, sizeList))
	}
	return pageSizes, nil
}

func readUint(path string) (uint64, error) {
	v, err := ioutil.ReadFile(path)
	if err != nil {
		return 0, err
	}
	return parseUint(strings.TrimSpace(string(v)), 10, 64)
}

func parseUint(s string, base, bitSize int) (uint64, error) {
	v, err := strconv.ParseUint(s, base, bitSize)
	if err != nil {
		intValue, intErr := strconv.ParseInt(s, base, bitSize)
		// 1. Handle negative values greater than MinInt64 (and)
		// 2. Handle negative values lesser than MinInt64
		if intErr == nil && intValue < 0 {
			return 0, nil
		} else if intErr != nil &&
			intErr.(*strconv.NumError).Err == strconv.ErrRange &&
			intValue < 0 {
			return 0, nil
		}
		return 0, err
	}
	return v, nil
}

func parseKV(raw string) (string, uint64, error) {
	parts := strings.Fields(raw)
	switch len(parts) {
	case 2:
		v, err := parseUint(parts[1], 10, 64)
		if err != nil {
			return "", 0, err
		}
		return parts[0], v, nil
	default:
		return "", 0, ErrInvalidFormat
	}
}

func parseCgroupFile(path string) (map[string]string, error) {
	f, err := os.Open(path)
	if err != nil {
		return nil, err
	}
	defer f.Close()
	return parseCgroupFromReader(f)
}

func parseCgroupFromReader(r io.Reader) (map[string]string, error) {
	var (
		cgroups = make(map[string]string)
		s       = bufio.NewScanner(r)
	)
	for s.Scan() {
		if err := s.Err(); err != nil {
			return nil, err
		}
		var (
			text  = s.Text()
			parts = strings.SplitN(text, ":", 3)
		)
		if len(parts) < 3 {
			return nil, fmt.Errorf("invalid cgroup entry: %q", text)
		}
		for _, subs := range strings.Split(parts[1], ",") {
			if subs != "" {
				cgroups[subs] = parts[2]
			}
		}
	}
	return cgroups, nil
}

func getCgroupDestination(subsystem string) (string, error) {
	f, err := os.Open("/proc/self/mountinfo")
	if err != nil {
		return "", err
	}
	defer f.Close()
	s := bufio.NewScanner(f)
	for s.Scan() {
		if err := s.Err(); err != nil {
			return "", err
		}
		fields := strings.Fields(s.Text())
		for _, opt := range strings.Split(fields[len(fields)-1], ",") {
			if opt == subsystem {
				return fields[3], nil
			}
		}
	}
	return "", ErrNoCgroupMountDestination
}

func pathers(subystems []Subsystem) []pather {
	var out []pather
	for _, s := range subystems {
		if p, ok := s.(pather); ok {
			out = append(out, p)
		}
	}
	return out
}

func initializeSubsystem(s Subsystem, path Path, resources *specs.LinuxResources) error {
	if c, ok := s.(creator); ok {
		p, err := path(s.Name())
		if err != nil {
			return err
		}
		if err := c.Create(p, resources); err != nil {
			return err
		}
	} else if c, ok := s.(pather); ok {
		p, err := path(s.Name())
		if err != nil {
			return err
		}
		// do the default create if the group does not have a custom one
		if err := os.MkdirAll(c.Path(p), defaultDirPerm); err != nil {
			return err
		}
	}
	return nil
}

func cleanPath(path string) string {
	if path == "" {
		return ""
	}
	path = filepath.Clean(path)
	if !filepath.IsAbs(path) {
		path, _ = filepath.Rel(string(os.PathSeparator), filepath.Clean(string(os.PathSeparator)+path))
	}
	return filepath.Clean(path)
}