node_exporter/collector/filesystem_linux.go

// 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"
	"os"
	"strings"
	"sync"
	"syscall"
	"time"

	"github.com/prometheus/common/log"
)

const (
	defIgnoredMountPoints = "^/(dev|proc|sys|var/lib/docker)($|/)"
	defIgnoredFSTypes     = "^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$"
	readOnly              = 0x1 // ST_RDONLY
	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(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", 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("mounts"))
	if err != nil {
		return nil, err
	}
	defer file.Close()

	filesystems := []filesystemLabels{}
	scanner := bufio.NewScanner(file)
	for scanner.Scan() {
		parts := strings.Fields(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()
}