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
|
// Copyright 2015 The Prometheus 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.
// +build !nofilesystem
package collector
import (
"bufio"
"fmt"
"io"
"os"
"strings"
"sync"
"syscall"
"time"
"github.com/prometheus/common/log"
)
const (
defIgnoredMountPoints = "^/(dev|proc|run|sys|mnt|media|var/lib/docker/.+)($|/)"
defIgnoredFSTypes = "^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$"
mountTimeout = 30 * time.Second
)
var stuckMounts = make(map[string]struct{})
var stuckMountsMtx = &sync.Mutex{}
// GetStats returns filesystem stats.
func (c *filesystemCollector) GetStats() ([]filesystemStats, error) {
mps, err := mountPointDetails()
if err != nil {
return nil, err
}
stats := []filesystemStats{}
for _, labels := range mps {
if c.ignoredMountPointsPattern.MatchString(labels.mountPoint) {
log.Debugf("Ignoring mount point: %s", labels.mountPoint)
continue
}
if c.ignoredFSTypesPattern.MatchString(labels.fsType) {
log.Debugf("Ignoring fs type: %s", labels.fsType)
continue
}
stuckMountsMtx.Lock()
if _, ok := stuckMounts[labels.mountPoint]; ok {
stats = append(stats, filesystemStats{
labels: labels,
deviceError: 1,
})
log.Debugf("Mount point %q is in an unresponsive state", labels.mountPoint)
stuckMountsMtx.Unlock()
continue
}
stuckMountsMtx.Unlock()
// The success channel is used do tell the "watcher" that the stat
// finished successfully. The channel is closed on success.
success := make(chan struct{})
go stuckMountWatcher(labels.mountPoint, success)
buf := new(syscall.Statfs_t)
err = syscall.Statfs(rootfsFilePath(labels.mountPoint), buf)
stuckMountsMtx.Lock()
close(success)
// If the mount has been marked as stuck, unmark it and log it's recovery.
if _, ok := stuckMounts[labels.mountPoint]; ok {
log.Debugf("Mount point %q has recovered, monitoring will resume", labels.mountPoint)
delete(stuckMounts, labels.mountPoint)
}
stuckMountsMtx.Unlock()
if err != nil {
stats = append(stats, filesystemStats{
labels: labels,
deviceError: 1,
})
log.Debugf("Error on statfs() system call for %q: %s", rootfsFilePath(labels.mountPoint), err)
continue
}
var ro float64
for _, option := range strings.Split(labels.options, ",") {
if option == "ro" {
ro = 1
break
}
}
stats = append(stats, filesystemStats{
labels: labels,
size: float64(buf.Blocks) * float64(buf.Bsize),
free: float64(buf.Bfree) * float64(buf.Bsize),
avail: float64(buf.Bavail) * float64(buf.Bsize),
files: float64(buf.Files),
filesFree: float64(buf.Ffree),
ro: ro,
})
}
return stats, nil
}
// stuckMountWatcher listens on the given success channel and if the channel closes
// then the watcher does nothing. If instead the timeout is reached, the
// mount point that is being watched is marked as stuck.
func stuckMountWatcher(mountPoint string, success chan struct{}) {
select {
case <-success:
// Success
case <-time.After(mountTimeout):
// Timed out, mark mount as stuck
stuckMountsMtx.Lock()
select {
case <-success:
// Success came in just after the timeout was reached, don't label the mount as stuck
default:
log.Debugf("Mount point %q timed out, it is being labeled as stuck and will not be monitored", mountPoint)
stuckMounts[mountPoint] = struct{}{}
}
stuckMountsMtx.Unlock()
}
}
func mountPointDetails() ([]filesystemLabels, error) {
file, err := os.Open(procFilePath("1/mounts"))
if os.IsNotExist(err) {
// Fallback to `/proc/mounts` if `/proc/1/mounts` is missing due hidepid.
log.Debugf("Got %q reading root mounts, falling back to system mounts", err)
file, err = os.Open(procFilePath("mounts"))
}
if err != nil {
return nil, err
}
defer file.Close()
return parseFilesystemLabels(file)
}
func parseFilesystemLabels(r io.Reader) ([]filesystemLabels, error) {
var filesystems []filesystemLabels
scanner := bufio.NewScanner(r)
for scanner.Scan() {
parts := strings.Fields(scanner.Text())
if len(parts) < 4 {
return nil, fmt.Errorf("malformed mount point information: %q", scanner.Text())
}
// Ensure we handle the translation of \040 and \011
// as per fstab(5).
parts[1] = strings.Replace(parts[1], "\\040", " ", -1)
parts[1] = strings.Replace(parts[1], "\\011", "\t", -1)
filesystems = append(filesystems, filesystemLabels{
device: parts[0],
mountPoint: parts[1],
fsType: parts[2],
options: parts[3],
})
}
return filesystems, scanner.Err()
}
|
