mudhorn/node_exporter
1
0
Fork 0
mirror of https://github.com/prometheus/node_exporter.git synced 2025-03-05 21:00:12 -08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:prometheus/node_exporter into add-arp-states

Browse source 
Signed-off-by: Emin Umut Gercek <eumutgercek@gmail.com>
This commit is contained in:
Emin Umut Gercek 2025-01-13 20:53:17 +03:00
parent 2246604659 acdd9b813d
commit d679000a11
30 changed files with 1176 additions and 1069 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
.github/workflows/golangci-lint.yml vendored
View file

@ -26,7 +26,7 @@ jobs:
- name: Checkout repository - name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Install Go - name: Install Go
uses: actions/setup-go@41dfa10bad2bb2ae585af6ee5bb4d7d973ad74ed # v5.1.0 uses: actions/setup-go@3041bf56c941b39c61721a86cd11f3bb1338122a # v5.2.0
with: with:
go-version: 1.23.x go-version: 1.23.x
- name: Install snmp_exporter/generator dependencies - name: Install snmp_exporter/generator dependencies
@ -36,4 +36,4 @@ jobs:
uses: golangci/golangci-lint-action@971e284b6050e8a5849b72094c50ab08da042db8 # v6.1.1 uses: golangci/golangci-lint-action@971e284b6050e8a5849b72094c50ab08da042db8 # v6.1.1
with: with:
args: --verbose args: --verbose
version: v1.61.0 version: v1.62.0

10
.golangci.yml
View file

@ -1,17 +1,9 @@
linters: linters:
enable: enable:
- depguard - depguard
- goimports
- misspell - misspell
- revive - revive
disable:
# Disable soon to deprecated[1] linters that lead to false
# positives when build tags disable certain files[2]
# 1: https://github.com/golangci/golangci-lint/issues/1841
# 2: https://github.com/prometheus/node_exporter/issues/1545
- deadcode
- unused
- structcheck
- varcheck
issues: issues:
exclude-rules: exclude-rules:

2
Makefile.common
View file

@ -61,7 +61,7 @@ PROMU_URL := https://github.com/prometheus/promu/releases/download/v$(PROMU_
SKIP_GOLANGCI_LINT := SKIP_GOLANGCI_LINT :=
GOLANGCI_LINT := GOLANGCI_LINT :=
GOLANGCI_LINT_OPTS ?= GOLANGCI_LINT_OPTS ?=
GOLANGCI_LINT_VERSION ?= v1.61.0 GOLANGCI_LINT_VERSION ?= v1.62.0
# golangci-lint only supports linux, darwin and windows platforms on i386/amd64/arm64. # golangci-lint only supports linux, darwin and windows platforms on i386/amd64/arm64.
# windows isn't included here because of the path separator being different. # windows isn't included here because of the path separator being different.
ifeq ($(GOHOSTOS),$(filter $(GOHOSTOS),linux darwin)) ifeq ($(GOHOSTOS),$(filter $(GOHOSTOS),linux darwin))

4
README.md
View file

@ -99,8 +99,8 @@ cpu | flags | --collector.cpu.info.flags-include | N/A
diskstats | device | --collector.diskstats.device-include | --collector.diskstats.device-exclude diskstats | device | --collector.diskstats.device-include | --collector.diskstats.device-exclude
ethtool | device | --collector.ethtool.device-include | --collector.ethtool.device-exclude ethtool | device | --collector.ethtool.device-include | --collector.ethtool.device-exclude
ethtool | metrics | --collector.ethtool.metrics-include | N/A ethtool | metrics | --collector.ethtool.metrics-include | N/A
filesystem | fs-types | N/A | --collector.filesystem.fs-types-exclude filesystem | fs-types | --collector.filesystem.fs-types-include | --collector.filesystem.fs-types-exclude
filesystem | mount-points | N/A | --collector.filesystem.mount-points-exclude filesystem | mount-points | --collector.filesystem.mount-points-include | --collector.filesystem.mount-points-exclude
hwmon | chip | --collector.hwmon.chip-include | --collector.hwmon.chip-exclude hwmon | chip | --collector.hwmon.chip-include | --collector.hwmon.chip-exclude
hwmon | sensor | --collector.hwmon.sensor-include | --collector.hwmon.sensor-exclude hwmon | sensor | --collector.hwmon.sensor-include | --collector.hwmon.sensor-exclude
interrupts | name | --collector.interrupts.name-include | --collector.interrupts.name-exclude interrupts | name | --collector.interrupts.name-include | --collector.interrupts.name-exclude

52
collector/arp_linux.go
View file

@ -17,13 +17,11 @@
package collector package collector
import ( import (
"errors"
"fmt" "fmt"
"log/slog" "log/slog"
"net"
"github.com/alecthomas/kingpin/v2" "github.com/alecthomas/kingpin/v2"
"github.com/jsimonetti/rtnetlink/v2" "github.com/jsimonetti/rtnetlink/v2/rtnl"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs" "github.com/prometheus/procfs"
"golang.org/x/sys/unix" "golang.org/x/sys/unix"
@ -97,53 +95,41 @@ func getTotalArpEntries(deviceEntries []procfs.ARPEntry) map[string]uint32 {
} }
func getArpEntriesRTNL() (map[string]uint32, map[string]map[string]int, error) { func getArpEntriesRTNL() (map[string]uint32, map[string]map[string]int, error) {
conn, err := rtnetlink.Dial(nil) conn, err := rtnl.Dial(nil)
if err != nil { if err != nil {
return nil, nil, err return nil, nil, err
} }
defer conn.Close() defer conn.Close()
neighbors, err := conn.Neigh.List() // Neighbors will also contain IPv6 neighbors, but since this is purely an ARP collector,
// restrict to AF_INET.
neighbors, err := conn.Neighbours(nil, unix.AF_INET)
if err != nil { if err != nil {
return nil, nil, err return nil, nil, err
} }
ifIndexEntries := make(map[uint32]uint32) // Map of interface name to ARP neighbor count.
ifIndexStates := make(map[uint32]map[string]int) entries := make(map[string]uint32)
// Map of map[InterfaceName]map[StateName]int
states := make(map[string]map[string]int)
for _, n := range neighbors { for _, n := range neighbors {
// Neighbors will also contain IPv6 neighbors, but since this is purely an ARP collector, // Skip entries which have state NUD_NOARP to conform to output of /proc/net/arp.
// restrict to AF_INET. Also skip entries which have state NUD_NOARP to conform to output if n.State&unix.NUD_NOARP != unix.NUD_NOARP {
// of /proc/net/arp.
if n.Family == unix.AF_INET && n.State&unix.NUD_NOARP == 0 {
ifIndexEntries[n.Index]++
_, ok := ifIndexStates[n.Index]
if !ok {
ifIndexStates[n.Index] = make(map[string]int)
}
ifIndexStates[n.Index][neighborStatesMap[n.State]]++
}
}
enumEntries := make(map[string]uint32)
enumStates := make(map[string]map[string]int)
// Convert interface indexes to names.
for ifIndex, entryCount := range ifIndexEntries {
iface, err := net.InterfaceByIndex(int(ifIndex))
if err != nil {
if errors.Unwrap(err).Error() == "no such network interface" {
continue continue
} }
return nil, nil, err
entries[n.Interface.Name]++
_, ok := states[n.Interface.Name]
if !ok {
states[n.Interface.Name] = make(map[string]int)
} }
enumEntries[iface.Name] = entryCount states[n.Interface.Name][neighborStatesMap[n.State]]++
enumStates[iface.Name] = ifIndexStates[ifIndex]
} }
return enumEntries, enumStates, nil return entries, states, nil
} }
func (c *arpCollector) Update(ch chan<- prometheus.Metric) error { func (c *arpCollector) Update(ch chan<- prometheus.Metric) error {

59
collector/cpu_linux.go
View file

@ -17,6 +17,7 @@
package collector package collector
import ( import (
"errors"
"fmt" "fmt"
"log/slog" "log/slog"
"os" "os"
@ -26,15 +27,17 @@ import (
"strconv" "strconv"
"sync" "sync"
"golang.org/x/exp/maps"
"github.com/alecthomas/kingpin/v2" "github.com/alecthomas/kingpin/v2"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs" "github.com/prometheus/procfs"
"github.com/prometheus/procfs/sysfs" "github.com/prometheus/procfs/sysfs"
"golang.org/x/exp/maps"
) )
type cpuCollector struct { type cpuCollector struct {
fs procfs.FS procfs procfs.FS
sysfs sysfs.FS
cpu *prometheus.Desc cpu *prometheus.Desc
cpuInfo *prometheus.Desc cpuInfo *prometheus.Desc
cpuFrequencyHz *prometheus.Desc cpuFrequencyHz *prometheus.Desc
@ -45,6 +48,7 @@ type cpuCollector struct {
cpuPackageThrottle *prometheus.Desc cpuPackageThrottle *prometheus.Desc
cpuIsolated *prometheus.Desc cpuIsolated *prometheus.Desc
logger *slog.Logger logger *slog.Logger
cpuOnline *prometheus.Desc
cpuStats map[int64]procfs.CPUStat cpuStats map[int64]procfs.CPUStat
cpuStatsMutex sync.Mutex cpuStatsMutex sync.Mutex
isolatedCpus []uint16 isolatedCpus []uint16
@ -70,17 +74,17 @@ func init() {
// NewCPUCollector returns a new Collector exposing kernel/system statistics. // NewCPUCollector returns a new Collector exposing kernel/system statistics.
func NewCPUCollector(logger *slog.Logger) (Collector, error) { func NewCPUCollector(logger *slog.Logger) (Collector, error) {
fs, err := procfs.NewFS(*procPath) pfs, err := procfs.NewFS(*procPath)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to open procfs: %w", err) return nil, fmt.Errorf("failed to open procfs: %w", err)
} }
sysfs, err := sysfs.NewFS(*sysPath) sfs, err := sysfs.NewFS(*sysPath)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to open sysfs: %w", err) return nil, fmt.Errorf("failed to open sysfs: %w", err)
} }
isolcpus, err := sysfs.IsolatedCPUs() isolcpus, err := sfs.IsolatedCPUs()
if err != nil { if err != nil {
if !os.IsNotExist(err) { if !os.IsNotExist(err) {
return nil, fmt.Errorf("Unable to get isolated cpus: %w", err) return nil, fmt.Errorf("Unable to get isolated cpus: %w", err)
@ -89,7 +93,8 @@ func NewCPUCollector(logger *slog.Logger) (Collector, error) {
} }
c := &cpuCollector{ c := &cpuCollector{
fs: fs, procfs: pfs,
sysfs: sfs,
cpu: nodeCPUSecondsDesc, cpu: nodeCPUSecondsDesc,
cpuInfo: prometheus.NewDesc( cpuInfo: prometheus.NewDesc(
prometheus.BuildFQName(namespace, cpuCollectorSubsystem, "info"), prometheus.BuildFQName(namespace, cpuCollectorSubsystem, "info"),
@ -131,6 +136,11 @@ func NewCPUCollector(logger *slog.Logger) (Collector, error) {
"Whether each core is isolated, information from /sys/devices/system/cpu/isolated.", "Whether each core is isolated, information from /sys/devices/system/cpu/isolated.",
[]string{"cpu"}, nil, []string{"cpu"}, nil,
), ),
cpuOnline: prometheus.NewDesc(
prometheus.BuildFQName(namespace, cpuCollectorSubsystem, "online"),
"CPUs that are online and being scheduled.",
[]string{"cpu"}, nil,
),
logger: logger, logger: logger,
isolatedCpus: isolcpus, isolatedCpus: isolcpus,
cpuStats: make(map[int64]procfs.CPUStat), cpuStats: make(map[int64]procfs.CPUStat),
@ -177,12 +187,21 @@ func (c *cpuCollector) Update(ch chan<- prometheus.Metric) error {
if c.isolatedCpus != nil { if c.isolatedCpus != nil {
c.updateIsolated(ch) c.updateIsolated(ch)
} }
return c.updateThermalThrottle(ch) err := c.updateThermalThrottle(ch)
if err != nil {
return err
}
err = c.updateOnline(ch)
if err != nil {
return err
}
return nil
} }
// updateInfo reads /proc/cpuinfo // updateInfo reads /proc/cpuinfo
func (c *cpuCollector) updateInfo(ch chan<- prometheus.Metric) error { func (c *cpuCollector) updateInfo(ch chan<- prometheus.Metric) error {
info, err := c.fs.CPUInfo() info, err := c.procfs.CPUInfo()
if err != nil { if err != nil {
return err return err
} }
@ -333,9 +352,31 @@ func (c *cpuCollector) updateIsolated(ch chan<- prometheus.Metric) {
} }
} }
// updateOnline reads /sys/devices/system/cpu/cpu*/online through sysfs and exports online status metrics.
func (c *cpuCollector) updateOnline(ch chan<- prometheus.Metric) error {
cpus, err := c.sysfs.CPUs()
if err != nil {
return err
}
// No-op if the system does not support CPU online stats.
cpu0 := cpus[0]
if _, err := cpu0.Online(); err != nil && errors.Is(err, os.ErrNotExist) {
return nil
}
for _, cpu := range cpus {
setOnline := float64(0)
if online, _ := cpu.Online(); online {
setOnline = 1
}
ch <- prometheus.MustNewConstMetric(c.cpuOnline, prometheus.GaugeValue, setOnline, cpu.Number())
}
return nil
}
// updateStat reads /proc/stat through procfs and exports CPU-related metrics. // updateStat reads /proc/stat through procfs and exports CPU-related metrics.
func (c *cpuCollector) updateStat(ch chan<- prometheus.Metric) error { func (c *cpuCollector) updateStat(ch chan<- prometheus.Metric) error {
stats, err := c.fs.Stat() stats, err := c.procfs.Stat()
if err != nil { if err != nil {
return err return err
} }

5
collector/cpufreq_linux.go
View file

@ -18,10 +18,11 @@ package collector
import ( import (
"fmt" "fmt"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs/sysfs"
"log/slog" "log/slog"
"strings" "strings"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs/sysfs"
) )
type cpuFreqCollector struct { type cpuFreqCollector struct {

4
collector/filesystem_aix.go
View file

@ -32,12 +32,12 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) {
return nil, err return nil, err
} }
for _, stat := range fsStat { for _, stat := range fsStat {
if c.excludedMountPointsPattern.MatchString(stat.MountPoint) { if c.mountPointFilter.ignored(stat.MountPoint) {
c.logger.Debug("Ignoring mount point", "mountpoint", stat.MountPoint) c.logger.Debug("Ignoring mount point", "mountpoint", stat.MountPoint)
continue continue
} }
fstype := stat.TypeString() fstype := stat.TypeString()
if c.excludedFSTypesPattern.MatchString(fstype) { if c.fsTypeFilter.ignored(fstype) {
c.logger.Debug("Ignoring fs type", "type", fstype) c.logger.Debug("Ignoring fs type", "type", fstype)
continue continue
} }

4
collector/filesystem_bsd.go
View file

@ -48,14 +48,14 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) {
stats = []filesystemStats{} stats = []filesystemStats{}
for i := 0; i < int(count); i++ { for i := 0; i < int(count); i++ {
mountpoint := C.GoString(&mnt[i].f_mntonname[0]) mountpoint := C.GoString(&mnt[i].f_mntonname[0])
if c.excludedMountPointsPattern.MatchString(mountpoint) { if c.mountPointFilter.ignored(mountpoint) {
c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint)
continue continue
} }
device := C.GoString(&mnt[i].f_mntfromname[0]) device := C.GoString(&mnt[i].f_mntfromname[0])
fstype := C.GoString(&mnt[i].f_fstypename[0]) fstype := C.GoString(&mnt[i].f_fstypename[0])
if c.excludedFSTypesPattern.MatchString(fstype) { if c.fsTypeFilter.ignored(fstype) {
c.logger.Debug("Ignoring fs type", "type", fstype) c.logger.Debug("Ignoring fs type", "type", fstype)
continue continue
} }

114
collector/filesystem_common.go
View file

@ -19,8 +19,8 @@ package collector
import ( import (
"errors" "errors"
"fmt"
"log/slog" "log/slog"
"regexp"
"github.com/alecthomas/kingpin/v2" "github.com/alecthomas/kingpin/v2"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
@ -36,7 +36,7 @@ var (
mountPointsExcludeSet bool mountPointsExcludeSet bool
mountPointsExclude = kingpin.Flag( mountPointsExclude = kingpin.Flag(
"collector.filesystem.mount-points-exclude", "collector.filesystem.mount-points-exclude",
"Regexp of mount points to exclude for filesystem collector.", "Regexp of mount points to exclude for filesystem collector. (mutually exclusive to mount-points-include)",
).Default(defMountPointsExcluded).PreAction(func(c *kingpin.ParseContext) error { ).Default(defMountPointsExcluded).PreAction(func(c *kingpin.ParseContext) error {
mountPointsExcludeSet = true mountPointsExcludeSet = true
return nil return nil
@ -45,11 +45,15 @@ var (
"collector.filesystem.ignored-mount-points", "collector.filesystem.ignored-mount-points",
"Regexp of mount points to ignore for filesystem collector.", "Regexp of mount points to ignore for filesystem collector.",
).Hidden().String() ).Hidden().String()
mountPointsInclude = kingpin.Flag(
"collector.filesystem.mount-points-include",
"Regexp of mount points to include for filesystem collector. (mutually exclusive to mount-points-exclude)",
).String()
fsTypesExcludeSet bool fsTypesExcludeSet bool
fsTypesExclude = kingpin.Flag( fsTypesExclude = kingpin.Flag(
"collector.filesystem.fs-types-exclude", "collector.filesystem.fs-types-exclude",
"Regexp of filesystem types to exclude for filesystem collector.", "Regexp of filesystem types to exclude for filesystem collector. (mutually exclusive to fs-types-include)",
).Default(defFSTypesExcluded).PreAction(func(c *kingpin.ParseContext) error { ).Default(defFSTypesExcluded).PreAction(func(c *kingpin.ParseContext) error {
fsTypesExcludeSet = true fsTypesExcludeSet = true
return nil return nil
@ -58,13 +62,17 @@ var (
"collector.filesystem.ignored-fs-types", "collector.filesystem.ignored-fs-types",
"Regexp of filesystem types to ignore for filesystem collector.", "Regexp of filesystem types to ignore for filesystem collector.",
).Hidden().String() ).Hidden().String()
fsTypesInclude = kingpin.Flag(
"collector.filesystem.fs-types-include",
"Regexp of filesystem types to exclude for filesystem collector. (mutually exclusive to fs-types-exclude)",
).String()
filesystemLabelNames = []string{"device", "mountpoint", "fstype", "device_error"} filesystemLabelNames = []string{"device", "mountpoint", "fstype", "device_error"}
) )
type filesystemCollector struct { type filesystemCollector struct {
excludedMountPointsPattern *regexp.Regexp mountPointFilter deviceFilter
excludedFSTypesPattern *regexp.Regexp fsTypeFilter deviceFilter
sizeDesc, freeDesc, availDesc *prometheus.Desc sizeDesc, freeDesc, availDesc *prometheus.Desc
filesDesc, filesFreeDesc *prometheus.Desc filesDesc, filesFreeDesc *prometheus.Desc
roDesc, deviceErrorDesc *prometheus.Desc roDesc, deviceErrorDesc *prometheus.Desc
@ -89,29 +97,7 @@ func init() {
// NewFilesystemCollector returns a new Collector exposing filesystems stats. // NewFilesystemCollector returns a new Collector exposing filesystems stats.
func NewFilesystemCollector(logger *slog.Logger) (Collector, error) { func NewFilesystemCollector(logger *slog.Logger) (Collector, error) {
if *oldMountPointsExcluded != "" { const subsystem = "filesystem"
if !mountPointsExcludeSet {
logger.Warn("--collector.filesystem.ignored-mount-points is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.mount-points-exclude")
*mountPointsExclude = *oldMountPointsExcluded
} else {
return nil, errors.New("--collector.filesystem.ignored-mount-points and --collector.filesystem.mount-points-exclude are mutually exclusive")
}
}
if *oldFSTypesExcluded != "" {
if !fsTypesExcludeSet {
logger.Warn("--collector.filesystem.ignored-fs-types is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.fs-types-exclude")
*fsTypesExclude = *oldFSTypesExcluded
} else {
return nil, errors.New("--collector.filesystem.ignored-fs-types and --collector.filesystem.fs-types-exclude are mutually exclusive")
}
}
subsystem := "filesystem"
logger.Info("Parsed flag --collector.filesystem.mount-points-exclude", "flag", *mountPointsExclude)
mountPointPattern := regexp.MustCompile(*mountPointsExclude)
logger.Info("Parsed flag --collector.filesystem.fs-types-exclude", "flag", *fsTypesExclude)
filesystemsTypesPattern := regexp.MustCompile(*fsTypesExclude)
sizeDesc := prometheus.NewDesc( sizeDesc := prometheus.NewDesc(
prometheus.BuildFQName(namespace, subsystem, "size_bytes"), prometheus.BuildFQName(namespace, subsystem, "size_bytes"),
@ -162,9 +148,19 @@ func NewFilesystemCollector(logger *slog.Logger) (Collector, error) {
nil, nil,
) )
mountPointFilter, err := newMountPointsFilter(logger)
if err != nil {
return nil, fmt.Errorf("unable to parse mount points filter flags: %w", err)
}
fsTypeFilter, err := newFSTypeFilter(logger)
if err != nil {
return nil, fmt.Errorf("unable to parse fs types filter flags: %w", err)
}
return &filesystemCollector{ return &filesystemCollector{
excludedMountPointsPattern: mountPointPattern, mountPointFilter: mountPointFilter,
excludedFSTypesPattern: filesystemsTypesPattern, fsTypeFilter: fsTypeFilter,
sizeDesc: sizeDesc, sizeDesc: sizeDesc,
freeDesc: freeDesc, freeDesc: freeDesc,
availDesc: availDesc, availDesc: availDesc,
@ -230,3 +226,61 @@ func (c *filesystemCollector) Update(ch chan<- prometheus.Metric) error {
} }
return nil return nil
} }
func newMountPointsFilter(logger *slog.Logger) (deviceFilter, error) {
if *oldMountPointsExcluded != "" {
if !mountPointsExcludeSet {
logger.Warn("--collector.filesystem.ignored-mount-points is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.mount-points-exclude")
*mountPointsExclude = *oldMountPointsExcluded
} else {
return deviceFilter{}, errors.New("--collector.filesystem.ignored-mount-points and --collector.filesystem.mount-points-exclude are mutually exclusive")
}
}
if *mountPointsInclude != "" && !mountPointsExcludeSet {
logger.Debug("mount-points-exclude flag not set when mount-points-include flag is set, assuming include is desired")
*mountPointsExclude = ""
}
if *mountPointsExclude != "" && *mountPointsInclude != "" {
return deviceFilter{}, errors.New("--collector.filesystem.mount-points-exclude and --collector.filesystem.mount-points-include are mutually exclusive")
}
if *mountPointsExclude != "" {
logger.Info("Parsed flag --collector.filesystem.mount-points-exclude", "flag", *mountPointsExclude)
}
if *mountPointsInclude != "" {
logger.Info("Parsed flag --collector.filesystem.mount-points-include", "flag", *mountPointsInclude)
}
return newDeviceFilter(*mountPointsExclude, *mountPointsInclude), nil
}
func newFSTypeFilter(logger *slog.Logger) (deviceFilter, error) {
if *oldFSTypesExcluded != "" {
if !fsTypesExcludeSet {
logger.Warn("--collector.filesystem.ignored-fs-types is DEPRECATED and will be removed in 2.0.0, use --collector.filesystem.fs-types-exclude")
*fsTypesExclude = *oldFSTypesExcluded
} else {
return deviceFilter{}, errors.New("--collector.filesystem.ignored-fs-types and --collector.filesystem.fs-types-exclude are mutually exclusive")
}
}
if *fsTypesInclude != "" && !fsTypesExcludeSet {
logger.Debug("fs-types-exclude flag not set when fs-types-include flag is set, assuming include is desired")
*fsTypesExclude = ""
}
if *fsTypesExclude != "" && *fsTypesInclude != "" {
return deviceFilter{}, errors.New("--collector.filesystem.fs-types-exclude and --collector.filesystem.fs-types-include are mutually exclusive")
}
if *fsTypesExclude != "" {
logger.Info("Parsed flag --collector.filesystem.fs-types-exclude", "flag", *fsTypesExclude)
}
if *fsTypesInclude != "" {
logger.Info("Parsed flag --collector.filesystem.fs-types-include", "flag", *fsTypesInclude)
}
return newDeviceFilter(*fsTypesExclude, *fsTypesInclude), nil
}

4
collector/filesystem_freebsd.go
View file

@ -39,14 +39,14 @@ func (c *filesystemCollector) GetStats() ([]filesystemStats, error) {
stats := []filesystemStats{} stats := []filesystemStats{}
for _, fs := range buf { for _, fs := range buf {
mountpoint := unix.ByteSliceToString(fs.Mntonname[:]) mountpoint := unix.ByteSliceToString(fs.Mntonname[:])
if c.excludedMountPointsPattern.MatchString(mountpoint) { if c.mountPointFilter.ignored(mountpoint) {
c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint)
continue continue
} }
device := unix.ByteSliceToString(fs.Mntfromname[:]) device := unix.ByteSliceToString(fs.Mntfromname[:])
fstype := unix.ByteSliceToString(fs.Fstypename[:]) fstype := unix.ByteSliceToString(fs.Fstypename[:])
if c.excludedFSTypesPattern.MatchString(fstype) { if c.fsTypeFilter.ignored(fstype) {
c.logger.Debug("Ignoring fs type", "type", fstype) c.logger.Debug("Ignoring fs type", "type", fstype)
continue continue
} }

6
collector/filesystem_linux.go
View file

@ -73,12 +73,12 @@ func (c *filesystemCollector) GetStats() ([]filesystemStats, error) {
go func() { go func() {
for _, labels := range mps { for _, labels := range mps {
if c.excludedMountPointsPattern.MatchString(labels.mountPoint) { if c.mountPointFilter.ignored(labels.mountPoint) {
c.logger.Debug("Ignoring mount point", "mountpoint", labels.mountPoint) c.logger.Debug("Ignoring mount point", "mountpoint", labels.mountPoint)
continue continue
} }
if c.excludedFSTypesPattern.MatchString(labels.fsType) { if c.fsTypeFilter.ignored(labels.fsType) {
c.logger.Debug("Ignoring fs", "type", labels.fsType) c.logger.Debug("Ignoring fs type", "type", labels.fsType)
continue continue
} }

4
collector/filesystem_netbsd.go
View file

@ -97,14 +97,14 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) {
stats = []filesystemStats{} stats = []filesystemStats{}
for _, v := range mnt { for _, v := range mnt {
mountpoint := unix.ByteSliceToString(v.F_mntonname[:]) mountpoint := unix.ByteSliceToString(v.F_mntonname[:])
if c.excludedMountPointsPattern.MatchString(mountpoint) { if c.mountPointFilter.ignored(mountpoint) {
c.logger.Debug("msg", "Ignoring mount point", "mountpoint", mountpoint) c.logger.Debug("msg", "Ignoring mount point", "mountpoint", mountpoint)
continue continue
} }
device := unix.ByteSliceToString(v.F_mntfromname[:]) device := unix.ByteSliceToString(v.F_mntfromname[:])
fstype := unix.ByteSliceToString(v.F_fstypename[:]) fstype := unix.ByteSliceToString(v.F_fstypename[:])
if c.excludedFSTypesPattern.MatchString(fstype) { if c.fsTypeFilter.ignored(fstype) {
c.logger.Debug("msg", "Ignoring fs type", "type", fstype) c.logger.Debug("msg", "Ignoring fs type", "type", fstype)
continue continue
} }

4
collector/filesystem_openbsd.go
View file

@ -41,14 +41,14 @@ func (c *filesystemCollector) GetStats() (stats []filesystemStats, err error) {
stats = []filesystemStats{} stats = []filesystemStats{}
for _, v := range mnt { for _, v := range mnt {
mountpoint := unix.ByteSliceToString(v.F_mntonname[:]) mountpoint := unix.ByteSliceToString(v.F_mntonname[:])
if c.excludedMountPointsPattern.MatchString(mountpoint) { if c.mountPointFilter.ignored(mountpoint) {
c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint) c.logger.Debug("Ignoring mount point", "mountpoint", mountpoint)
continue continue
} }
device := unix.ByteSliceToString(v.F_mntfromname[:]) device := unix.ByteSliceToString(v.F_mntfromname[:])
fstype := unix.ByteSliceToString(v.F_fstypename[:]) fstype := unix.ByteSliceToString(v.F_fstypename[:])
if c.excludedFSTypesPattern.MatchString(fstype) { if c.fsTypeFilter.ignored(fstype) {
c.logger.Debug("Ignoring fs type", "type", fstype) c.logger.Debug("Ignoring fs type", "type", fstype)
continue continue
} }

6
collector/fixtures/e2e-64k-page-output.txt
View file

@ -871,6 +871,10 @@ node_hwmon_fan_target_rpm{chip="nct6779",sensor="fan2"} 27000
# HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance # HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance
# TYPE node_hwmon_fan_tolerance gauge # TYPE node_hwmon_fan_tolerance gauge
node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0 node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0
# HELP node_hwmon_freq_freq_mhz Hardware monitor for GPU frequency in MHz
# TYPE node_hwmon_freq_freq_mhz gauge
node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="mclk"} 300
node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="sclk"} 214
# HELP node_hwmon_in_alarm Hardware sensor alarm status (in) # HELP node_hwmon_in_alarm Hardware sensor alarm status (in)
# TYPE node_hwmon_in_alarm gauge # TYPE node_hwmon_in_alarm gauge
node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0 node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0
@ -984,6 +988,8 @@ node_hwmon_pwm_weight_temp_step_tol{chip="nct6779",sensor="pwm1"} 0
# TYPE node_hwmon_sensor_label gauge # TYPE node_hwmon_sensor_label gauge
node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1
node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1
node_hwmon_sensor_label{chip="hwmon4",label="mclk",sensor="freq2"} 1
node_hwmon_sensor_label{chip="hwmon4",label="sclk",sensor="freq1"} 1
node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1 node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1
node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1 node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1
node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1

6
collector/fixtures/e2e-output.txt
View file

@ -893,6 +893,10 @@ node_hwmon_fan_target_rpm{chip="nct6779",sensor="fan2"} 27000
# HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance # HELP node_hwmon_fan_tolerance Hardware monitor fan element tolerance
# TYPE node_hwmon_fan_tolerance gauge # TYPE node_hwmon_fan_tolerance gauge
node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0 node_hwmon_fan_tolerance{chip="nct6779",sensor="fan2"} 0
# HELP node_hwmon_freq_freq_mhz Hardware monitor for GPU frequency in MHz
# TYPE node_hwmon_freq_freq_mhz gauge
node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="mclk"} 300
node_hwmon_freq_freq_mhz{chip="hwmon4",sensor="sclk"} 214
# HELP node_hwmon_in_alarm Hardware sensor alarm status (in) # HELP node_hwmon_in_alarm Hardware sensor alarm status (in)
# TYPE node_hwmon_in_alarm gauge # TYPE node_hwmon_in_alarm gauge
node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0 node_hwmon_in_alarm{chip="nct6779",sensor="in0"} 0
@ -1006,6 +1010,8 @@ node_hwmon_pwm_weight_temp_step_tol{chip="nct6779",sensor="pwm1"} 0
# TYPE node_hwmon_sensor_label gauge # TYPE node_hwmon_sensor_label gauge
node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp1"} 1
node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1 node_hwmon_sensor_label{chip="hwmon4",label="foosensor",sensor="temp2"} 1
node_hwmon_sensor_label{chip="hwmon4",label="mclk",sensor="freq2"} 1
node_hwmon_sensor_label{chip="hwmon4",label="sclk",sensor="freq1"} 1
node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1 node_hwmon_sensor_label{chip="platform_applesmc_768",label="Left side",sensor="fan1"} 1
node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1 node_hwmon_sensor_label{chip="platform_applesmc_768",label="Right side",sensor="fan2"} 1
node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1 node_hwmon_sensor_label{chip="platform_coretemp_0",label="Core 0",sensor="temp2"} 1

20
collector/fixtures/sys.ttar
View file

@ -437,6 +437,26 @@ Lines: 1
100000 100000
Mode: 644 Mode: 644
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Path: sys/class/hwmon/hwmon4/freq1_input
Lines: 1
214000000
Mode: 644
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Path: sys/class/hwmon/hwmon4/freq1_label
Lines: 1
sclk
Mode: 644
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Path: sys/class/hwmon/hwmon4/freq2_input
Lines: 1
300000000
Mode: 644
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Path: sys/class/hwmon/hwmon4/freq2_label
Lines: 1
mclk
Mode: 644
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Path: sys/class/hwmon/hwmon5 Path: sys/class/hwmon/hwmon5
SymlinkTo: ../../devices/platform/bogus.0/hwmon/hwmon5/ SymlinkTo: ../../devices/platform/bogus.0/hwmon/hwmon5/
# ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - # ttar - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

11
collector/hwmon_linux.go
View file

@ -44,7 +44,7 @@ var (
hwmonSensorTypes = []string{ hwmonSensorTypes = []string{
"vrm", "beep_enable", "update_interval", "in", "cpu", "fan", "vrm", "beep_enable", "update_interval", "in", "cpu", "fan",
"pwm", "temp", "curr", "power", "energy", "humidity", "pwm", "temp", "curr", "power", "energy", "humidity",
"intrusion", "intrusion", "freq",
} }
) )
@ -357,6 +357,15 @@ func (c *hwMonCollector) updateHwmon(ch chan<- prometheus.Metric, dir string) er
continue continue
} }
if sensorType == "freq" && element == "input" {
if label, ok := sensorData["label"]; ok {
sensorLabel := cleanMetricName(label)
desc := prometheus.NewDesc(name+"_freq_mhz", "Hardware monitor for GPU frequency in MHz", hwmonLabelDesc, nil)
ch <- prometheus.MustNewConstMetric(
desc, prometheus.GaugeValue, parsedValue/1000000.0, append(labels[:len(labels)-1], sensorLabel)...)
}
continue
}
// fallback, just dump the metric as is // fallback, just dump the metric as is
desc := prometheus.NewDesc(name, "Hardware monitor "+sensorType+" element "+element, hwmonLabelDesc, nil) desc := prometheus.NewDesc(name, "Hardware monitor "+sensorType+" element "+element, hwmonLabelDesc, nil)

3
collector/interrupts_common.go
View file

@ -18,9 +18,10 @@
package collector package collector
import ( import (
"log/slog"
"github.com/alecthomas/kingpin/v2" "github.com/alecthomas/kingpin/v2"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"log/slog"
) )
type interruptsCollector struct { type interruptsCollector struct {

3
collector/runit.go
View file

@ -17,10 +17,11 @@
package collector package collector
import ( import (
"log/slog"
"github.com/alecthomas/kingpin/v2" "github.com/alecthomas/kingpin/v2"
"github.com/prometheus-community/go-runit/runit" "github.com/prometheus-community/go-runit/runit"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"log/slog"
) )
var runitServiceDir = kingpin.Flag("collector.runit.servicedir", "Path to runit service directory.").Default("/etc/service").String() var runitServiceDir = kingpin.Flag("collector.runit.servicedir", "Path to runit service directory.").Default("/etc/service").String()

3
collector/selinux_linux.go
View file

@ -17,9 +17,10 @@
package collector package collector
import ( import (
"log/slog"
"github.com/opencontainers/selinux/go-selinux" "github.com/opencontainers/selinux/go-selinux"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"log/slog"
) )
type selinuxCollector struct { type selinuxCollector struct {

3
collector/softirqs_common.go
View file

@ -18,9 +18,10 @@ package collector
import ( import (
"fmt" "fmt"
"log/slog"
"github.com/prometheus/client_golang/prometheus" "github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/procfs" "github.com/prometheus/procfs"
"log/slog"
) )
type softirqsCollector struct { type softirqsCollector struct {

3
collector/uname.go
View file

@ -18,8 +18,9 @@
package collector package collector
import ( import (
"github.com/prometheus/client_golang/prometheus"
"log/slog" "log/slog"
"github.com/prometheus/client_golang/prometheus"
) )
var unameDesc = prometheus.NewDesc( var unameDesc = prometheus.NewDesc(

20
docs/node-mixin/alerts/alerts.libsonnet
View file

@ -10,7 +10,7 @@
( (
node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpWarningThreshold)d node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpWarningThreshold)d
and and
predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[%(fsSpaceFillingUpPredictionWindow)s], 24*60*60) < 0 predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[%(fsSpaceFillingUpPredictionWindow)s], %(nodeWarningWindowHours)s*60*60) < 0
and and
node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0
) )
@ -20,7 +20,7 @@
severity: 'warning', severity: 'warning',
}, },
annotations: { annotations: {
summary: 'Filesystem is predicted to run out of space within the next 24 hours.', summary: 'Filesystem is predicted to run out of space within the next %(nodeWarningWindowHours)s hours.' % $._config,
description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.', description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.',
}, },
}, },
@ -30,7 +30,7 @@
( (
node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpCriticalThreshold)d node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_size_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < %(fsSpaceFillingUpCriticalThreshold)d
and and
predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 4*60*60) < 0 predict_linear(node_filesystem_avail_bytes{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeCriticalWindowHours)s*60*60) < 0
and and
node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0
) )
@ -40,7 +40,7 @@
severity: '%(nodeCriticalSeverity)s' % $._config, severity: '%(nodeCriticalSeverity)s' % $._config,
}, },
annotations: { annotations: {
summary: 'Filesystem is predicted to run out of space within the next 4 hours.', summary: 'Filesystem is predicted to run out of space within the next %(nodeCriticalWindowHours)s hours.' % $._config,
description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.', description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.',
}, },
}, },
@ -86,7 +86,7 @@
( (
node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 40 node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 40
and and
predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 24*60*60) < 0 predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeWarningWindowHours)s*60*60) < 0
and and
node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0
) )
@ -96,7 +96,7 @@
severity: 'warning', severity: 'warning',
}, },
annotations: { annotations: {
summary: 'Filesystem is predicted to run out of inodes within the next 24 hours.', summary: 'Filesystem is predicted to run out of inodes within the next %(nodeWarningWindowHours)s hours.' % $._config,
description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.', description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.',
}, },
}, },
@ -106,7 +106,7 @@
( (
node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 20 node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} / node_filesystem_files{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} * 100 < 20
and and
predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], 4*60*60) < 0 predict_linear(node_filesystem_files_free{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s}[6h], %(nodeCriticalWindowHours)s*60*60) < 0
and and
node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0 node_filesystem_readonly{%(nodeExporterSelector)s,%(fsSelector)s,%(fsMountpointSelector)s} == 0
) )
@ -116,7 +116,7 @@
severity: '%(nodeCriticalSeverity)s' % $._config, severity: '%(nodeCriticalSeverity)s' % $._config,
}, },
annotations: { annotations: {
summary: 'Filesystem is predicted to run out of inodes within the next 4 hours.', summary: 'Filesystem is predicted to run out of inodes within the next %(nodeCriticalWindowHours)s hours.' % $._config,
description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.', description: 'Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.',
}, },
}, },
@ -191,7 +191,7 @@
||| % $._config, ||| % $._config,
annotations: { annotations: {
summary: 'Number of conntrack are getting close to the limit.', summary: 'Number of conntrack are getting close to the limit.',
description: '{{ $value | humanizePercentage }} of conntrack entries are used.', description: '{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.',
}, },
labels: { labels: {
severity: 'warning', severity: 'warning',
@ -312,7 +312,7 @@
{ {
alert: 'NodeCPUHighUsage', alert: 'NodeCPUHighUsage',
expr: ||| expr: |||
sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode!="idle"}[2m]))) * 100 > %(cpuHighUsageThreshold)d sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode!~"idle|iowait"}[2m]))) * 100 > %(cpuHighUsageThreshold)d
||| % $._config, ||| % $._config,
'for': '15m', 'for': '15m',
labels: { labels: {

10
docs/node-mixin/config.libsonnet
View file

@ -50,6 +50,16 @@
// 'NodeSystemSaturation' alert. // 'NodeSystemSaturation' alert.
systemSaturationPerCoreThreshold: 2, systemSaturationPerCoreThreshold: 2,
// Some of the alerts use predict_linear() to fire alerts ahead of time to
// prevent unrecoverable situations (eg. no more disk space). However, the
// node may have automatic processes (cronjobs) in place to prevent that
// within a certain time window, this may not align with the default time
// window of these alerts. This can cause these alerts to start flapping.
// By reducing the time window, the system gets more time to
// resolve this before problems occur.
nodeWarningWindowHours: '24',
nodeCriticalWindowHours: '4',
// Available disk space (%) thresholds on which to trigger the // Available disk space (%) thresholds on which to trigger the
// 'NodeFilesystemSpaceFillingUp' alerts. These alerts fire if the disk // 'NodeFilesystemSpaceFillingUp' alerts. These alerts fire if the disk
// usage grows in a way that it is predicted to run out in 4h or 1d // usage grows in a way that it is predicted to run out in 4h or 1d

603
docs/node-mixin/dashboards/use.libsonnet
View file

@ -1,201 +1,178 @@
local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet'; local grafana = import 'github.com/grafana/grafonnet/gen/grafonnet-latest/main.libsonnet';
local dashboard = grafana.dashboard; local dashboard = grafana.dashboard;
local row = grafana.row; local variable = dashboard.variable;
local prometheus = grafana.prometheus; local row = grafana.panel.row;
local template = grafana.template; local prometheus = grafana.query.prometheus;
local graphPanel = grafana.graphPanel;
local timeSeriesPanel = grafana.panel.timeSeries;
local tsOptions = timeSeriesPanel.options;
local tsStandardOptions = timeSeriesPanel.standardOptions;
local tsQueryOptions = timeSeriesPanel.queryOptions;
local tsCustom = timeSeriesPanel.fieldConfig.defaults.custom;
local tsLegend = tsOptions.legend;
local c = import '../config.libsonnet'; local c = import '../config.libsonnet';
local datasourceTemplate = { local datasource = variable.datasource.new(
current: { 'datasource', 'prometheus'
text: 'default', );
value: 'default',
}, local tsCommonPanelOptions =
hide: 0, variable.query.withDatasourceFromVariable(datasource)
label: 'Data Source', + tsCustom.stacking.withMode('normal')
name: 'datasource', + tsCustom.withFillOpacity(100)
options: [], + tsCustom.withShowPoints('never')
query: 'prometheus', + tsLegend.withShowLegend(false)
refresh: 1, + tsOptions.tooltip.withMode('multi')
regex: '', + tsOptions.tooltip.withSort('desc');
type: 'datasource',
};
local CPUUtilisation = local CPUUtilisation =
graphPanel.new( timeSeriesPanel.new(
'CPU Utilisation', 'CPU Utilisation',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
local CPUSaturation = local CPUSaturation =
// TODO: Is this a useful panel? At least there should be some explanation how load // TODO: Is this a useful panel? At least there should be some explanation how load
// average relates to the "CPU saturation" in the title. // average relates to the "CPU saturation" in the title.
graphPanel.new( timeSeriesPanel.new(
'CPU Saturation (Load1 per CPU)', 'CPU Saturation (Load1 per CPU)',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
local memoryUtilisation = local memoryUtilisation =
graphPanel.new( timeSeriesPanel.new(
'Memory Utilisation', 'Memory Utilisation',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
local memorySaturation = local memorySaturation =
graphPanel.new( timeSeriesPanel.new(
'Memory Saturation (Major Page Faults)', 'Memory Saturation (Major Page Faults)',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='rds', + tsStandardOptions.withUnit('rds');
stack=true,
fill=10, local networkOverrides = tsStandardOptions.withOverrides(
legend_show=false, [
) { tooltip+: { sort: 2 } }; tsStandardOptions.override.byRegexp.new('/Transmit/')
+ tsStandardOptions.override.byRegexp.withPropertiesFromOptions(
tsCustom.withTransform('negative-Y')
),
]
);
local networkUtilisation = local networkUtilisation =
graphPanel.new( timeSeriesPanel.new(
'Network Utilisation (Bytes Receive/Transmit)', 'Network Utilisation (Bytes Receive/Transmit)',
datasource='$datasource',
span=6,
format='Bps',
stack=true,
fill=10,
legend_show=false,
) )
.addSeriesOverride({ alias: '/Receive/', stack: 'A' }) + tsCommonPanelOptions
.addSeriesOverride({ alias: '/Transmit/', stack: 'B', transform: 'negative-Y' }) + tsStandardOptions.withUnit('Bps')
{ tooltip+: { sort: 2 } }; + networkOverrides;
local networkSaturation = local networkSaturation =
graphPanel.new( timeSeriesPanel.new(
'Network Saturation (Drops Receive/Transmit)', 'Network Saturation (Drops Receive/Transmit)',
datasource='$datasource',
span=6,
format='Bps',
stack=true,
fill=10,
legend_show=false,
) )
.addSeriesOverride({ alias: '/ Receive/', stack: 'A' }) + tsCommonPanelOptions
.addSeriesOverride({ alias: '/ Transmit/', stack: 'B', transform: 'negative-Y' }) + tsStandardOptions.withUnit('Bps')
{ tooltip+: { sort: 2 } }; + networkOverrides;
local diskIOUtilisation = local diskIOUtilisation =
graphPanel.new( timeSeriesPanel.new(
'Disk IO Utilisation', 'Disk IO Utilisation',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
local diskIOSaturation = local diskIOSaturation =
graphPanel.new( timeSeriesPanel.new(
'Disk IO Saturation', 'Disk IO Saturation',
datasource='$datasource', )
span=6, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
local diskSpaceUtilisation = local diskSpaceUtilisation =
graphPanel.new( timeSeriesPanel.new(
'Disk Space Utilisation', 'Disk Space Utilisation',
datasource='$datasource', )
span=12, + tsCommonPanelOptions
format='percentunit', + tsStandardOptions.withUnit('percentunit');
stack=true,
fill=10,
legend_show=false,
) { tooltip+: { sort: 2 } };
{ {
_clusterTemplate:: template.new( _clusterVariable::
name='cluster', variable.query.new('cluster')
datasource='$datasource', + variable.query.withDatasourceFromVariable(datasource)
query='label_values(node_time_seconds, %s)' % $._config.clusterLabel, + variable.query.queryTypes.withLabelValues(
current='', $._config.clusterLabel,
hide=if $._config.showMultiCluster then '' else '2', 'node_time_seconds',
refresh=2, )
includeAll=false, + (if $._config.showMultiCluster then variable.query.generalOptions.showOnDashboard.withLabelAndValue() else variable.query.generalOptions.showOnDashboard.withNothing())
sort=1 + variable.query.refresh.onTime()
), + variable.query.selectionOptions.withIncludeAll(false)
+ variable.query.withSort(asc=true),
grafanaDashboards+:: { grafanaDashboards+:: {
'node-rsrc-use.json': 'node-rsrc-use.json':
dashboard.new( dashboard.new(
'%sUSE Method / Node' % $._config.dashboardNamePrefix, '%sUSE Method / Node' % $._config.dashboardNamePrefix,
time_from='now-1h',
tags=($._config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair',
uid=std.md5('node-rsrc-use.json')
) )
.addTemplate(datasourceTemplate) + dashboard.time.withFrom('now-1h')
.addTemplate($._clusterTemplate) + dashboard.withTags($._config.dashboardTags)
.addTemplate( + dashboard.withTimezone('utc')
template.new( + dashboard.withRefresh('30s')
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withUid(std.md5('node-rsrc-use.json'))
+ dashboard.withVariables([
datasource,
$._clusterVariable,
variable.query.new('instance')
+ variable.query.withDatasourceFromVariable(datasource)
+ variable.query.queryTypes.withLabelValues(
'instance', 'instance',
'$datasource', 'node_exporter_build_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config,
'label_values(node_exporter_build_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}, instance)' % $._config,
refresh='time',
sort=1
) )
) + variable.query.refresh.onTime()
.addRow( + variable.query.withSort(asc=true),
])
+ dashboard.withPanels(
grafana.util.grid.makeGrid([
row.new('CPU') row.new('CPU')
.addPanel(CPUUtilisation.addTarget(prometheus.target('instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Utilisation'))) + row.withPanels([
.addPanel(CPUSaturation.addTarget(prometheus.target('instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Saturation'))) CPUUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Utilisation')]),
) CPUSaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Saturation')]),
.addRow( ]),
row.new('Memory') row.new('Memory')
.addPanel(memoryUtilisation.addTarget(prometheus.target('instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Utilisation'))) + row.withPanels([
.addPanel(memorySaturation.addTarget(prometheus.target('instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Major page Faults'))) memoryUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Utilisation')]),
) memorySaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Major page Faults')]),
.addRow( ]),
row.new('Network') row.new('Network')
.addPanel( + row.withPanels([
networkUtilisation networkUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target('instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Receive')) prometheus.new('$datasource', 'instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Receive'),
.addTarget(prometheus.target('instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Transmit')) prometheus.new('$datasource', 'instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Transmit'),
) ]),
.addPanel( networkSaturation + tsQueryOptions.withTargets([
networkSaturation prometheus.new('$datasource', 'instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Receive'),
.addTarget(prometheus.target('instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Receive')) prometheus.new('$datasource', 'instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('Transmit'),
.addTarget(prometheus.target('instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='Transmit')) ]),
) ]),
)
.addRow(
row.new('Disk IO') row.new('Disk IO')
.addPanel(diskIOUtilisation.addTarget(prometheus.target('instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{device}}'))) + row.withPanels([
.addPanel(diskIOSaturation.addTarget(prometheus.target('instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{device}}'))) diskIOUtilisation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('{{device}}')]),
) diskIOSaturation + tsQueryOptions.withTargets([prometheus.new('$datasource', 'instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} != 0' % $._config) + prometheus.withLegendFormat('{{device}}')]),
.addRow( ]),
], panelWidth=12, panelHeight=7)
+ grafana.util.grid.makeGrid([
row.new('Disk Space') row.new('Disk Space')
.addPanel( + row.withPanels([
diskSpaceUtilisation.addTarget(prometheus.target( diskSpaceUtilisation + tsQueryOptions.withTargets([
prometheus.new(
'$datasource',
||| |||
sort_desc(1 - sort_desc(1 -
( (
@ -204,28 +181,36 @@ local diskSpaceUtilisation =
max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"}) max without (mountpoint, fstype) (node_filesystem_size_bytes{%(nodeExporterSelector)s, fstype!="", instance="$instance", %(clusterLabel)s="$cluster"})
) != 0 ) != 0
) )
||| % $._config, legendFormat='{{device}}' ||| % $._config
)) ) + prometheus.withLegendFormat('{{device}}'),
) ]),
]),
], panelWidth=24, panelHeight=7, startY=34),
), ),
'node-cluster-rsrc-use.json': 'node-cluster-rsrc-use.json':
dashboard.new( dashboard.new(
'%sUSE Method / Cluster' % $._config.dashboardNamePrefix, '%sUSE Method / Cluster' % $._config.dashboardNamePrefix,
time_from='now-1h',
tags=($._config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair',
uid=std.md5('node-cluster-rsrc-use.json')
) )
.addTemplate(datasourceTemplate) + dashboard.time.withFrom('now-1h')
.addTemplate($._clusterTemplate) + dashboard.withTags($._config.dashboardTags)
.addRow( + dashboard.withTimezone('utc')
+ dashboard.withRefresh('30s')
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withUid(std.md5('node-cluster-rsrc-use.json'))
+ dashboard.withVariables([
datasource,
$._clusterVariable,
variable.query.withDatasourceFromVariable(datasource)
+ variable.query.refresh.onTime()
+ variable.query.withSort(asc=true),
])
+ dashboard.withPanels(
grafana.util.grid.makeGrid([
row.new('CPU') row.new('CPU')
.addPanel( + row.withPanels([
CPUUtilisation CPUUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
(( ((
instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance:node_cpu_utilisation:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
@ -233,79 +218,90 @@ local diskSpaceUtilisation =
instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
) != 0 ) ) != 0 )
/ scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}))
||| % $._config, legendFormat='{{ instance }}' ||| % $._config
)) ) + prometheus.withLegendFormat('{{ instance }}'),
) ]),
.addPanel( CPUSaturation + tsQueryOptions.withTargets([
CPUSaturation prometheus.new(
.addTarget(prometheus.target( '$datasource',
||| |||
( (
instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
/ scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}))
) != 0 ) != 0
||| % $._config, legendFormat='{{instance}}' ||| % $._config
)) ) + prometheus.withLegendFormat('{{ instance }}'),
) ]),
) ]),
.addRow(
row.new('Memory') row.new('Memory')
.addPanel( + row.withPanels([
memoryUtilisation memoryUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
( (
instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
/ scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}))
) != 0 ) != 0
||| % $._config, legendFormat='{{instance}}', ||| % $._config
)) ) + prometheus.withLegendFormat('{{ instance }}'),
) ]),
.addPanel(memorySaturation.addTarget(prometheus.target('instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config, legendFormat='{{instance}}'))) memorySaturation + tsQueryOptions.withTargets([
) prometheus.new(
.addRow( '$datasource',
'instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}' % $._config
) + prometheus.withLegendFormat('{{ instance }}'),
]),
]),
row.new('Network') row.new('Network')
.addPanel( + row.withPanels([
networkUtilisation networkUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target('instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Receive')) prometheus.new(
.addTarget(prometheus.target('instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Transmit')) '$datasource',
) 'instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config
.addPanel( ) + prometheus.withLegendFormat('{{ instance }} Receive'),
networkSaturation prometheus.new(
.addTarget(prometheus.target('instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Receive')) '$datasource',
.addTarget(prometheus.target('instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config, legendFormat='{{instance}} Transmit')) 'instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config
) ) + prometheus.withLegendFormat('{{ instance }} Transmit'),
) ]),
.addRow( networkSaturation + tsQueryOptions.withTargets([
prometheus.new(
'$datasource',
'instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config
) + prometheus.withLegendFormat('{{ instance }} Receive'),
prometheus.new(
'$datasource',
'instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} != 0' % $._config
) + prometheus.withLegendFormat('{{ instance }} Transmit'),
]),
]),
row.new('Disk IO') row.new('Disk IO')
.addPanel( + row.withPanels([
diskIOUtilisation diskIOUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
(
instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
/ scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}))
) != 0 ||| % $._config
||| % $._config, legendFormat='{{instance}} {{device}}' ) + prometheus.withLegendFormat('{{ instance }} {{device}}'),
)) ]),
) diskIOSaturation + tsQueryOptions.withTargets([prometheus.new(
.addPanel( '$datasource',
diskIOSaturation
.addTarget(prometheus.target(
||| |||
(
instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"} instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}
/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"})) / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster"}))
) != 0 ||| % $._config
||| % $._config, legendFormat='{{instance}} {{device}}' ) + prometheus.withLegendFormat('{{ instance }} {{device}}')]),
)) ]),
) ], panelWidth=12, panelHeight=7)
) + grafana.util.grid.makeGrid([
.addRow(
row.new('Disk Space') row.new('Disk Space')
.addPanel( + row.withPanels([
diskSpaceUtilisation diskSpaceUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum without (device) ( sum without (device) (
max without (fstype, mountpoint) (( max without (fstype, mountpoint) ((
@ -315,28 +311,37 @@ local diskSpaceUtilisation =
) != 0) ) != 0)
) )
/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"}))) / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s, %(clusterLabel)s="$cluster"})))
||| % $._config, legendFormat='{{instance}}' ||| % $._config
)) ) + prometheus.withLegendFormat('{{ instance }}'),
) ]),
]),
], panelWidth=24, panelHeight=7, startY=34),
), ),
} + } +
if $._config.showMultiCluster then { if $._config.showMultiCluster then {
'node-multicluster-rsrc-use.json': 'node-multicluster-rsrc-use.json':
dashboard.new( dashboard.new(
'%sUSE Method / Multi-cluster' % $._config.dashboardNamePrefix, '%sUSE Method / Multi-cluster' % $._config.dashboardNamePrefix,
time_from='now-1h',
tags=($._config.dashboardTags),
timezone='utc',
refresh='30s',
graphTooltip='shared_crosshair',
uid=std.md5('node-multicluster-rsrc-use.json')
) )
.addTemplate(datasourceTemplate) + dashboard.time.withFrom('now-1h')
.addRow( + dashboard.withTags($._config.dashboardTags)
+ dashboard.withTimezone('utc')
+ dashboard.withRefresh('30s')
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withUid(std.md5('node-multicluster-rsrc-use.json'))
+ dashboard.withVariables([
datasource,
variable.query.withDatasourceFromVariable(datasource)
+ variable.query.refresh.onTime()
+ variable.query.withSort(asc=true),
])
+ dashboard.withPanels(
grafana.util.grid.makeGrid([
row.new('CPU') row.new('CPU')
.addPanel( + row.withPanels([
CPUUtilisation CPUUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum( sum(
(( ((
@ -346,112 +351,116 @@ local diskSpaceUtilisation =
) != 0) ) != 0)
/ scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s})) / scalar(sum(instance:node_num_cpu:sum{%(nodeExporterSelector)s}))
) by (%(clusterLabel)s) ) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'),
) ]),
.addPanel( CPUSaturation + tsQueryOptions.withTargets([
CPUSaturation prometheus.new(
.addTarget(prometheus.target( '$datasource',
||| |||
sum(( sum((
instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s} instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s}
/ scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s})) / scalar(count(instance:node_load1_per_cpu:ratio{%(nodeExporterSelector)s}))
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'),
) ]),
) ]),
.addRow(
row.new('Memory') row.new('Memory')
.addPanel( + row.withPanels([
memoryUtilisation memoryUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum(( sum((
instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s} instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s}
/ scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s})) / scalar(count(instance:node_memory_utilisation:ratio{%(nodeExporterSelector)s}))
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'),
) ]),
.addPanel( memorySaturation + tsQueryOptions.withTargets([
memorySaturation prometheus.new(
.addTarget(prometheus.target( '$datasource',
||| |||
sum(( sum((
instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s} instance:node_vmstat_pgmajfault:rate%(rateInterval)s{%(nodeExporterSelector)s}
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config |||
)) % $._config
) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'),
) ]),
.addRow( ]),
row.new('Network') row.new('Network')
.addPanel( + row.withPanels([
networkUtilisation networkUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum(( sum((
instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s}
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}} Receive' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Receive'),
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum(( sum((
instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s}
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}} Transmit' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Transmit'),
) ]),
.addPanel( networkSaturation + tsQueryOptions.withTargets([
networkSaturation prometheus.new(
.addTarget(prometheus.target( '$datasource',
||| |||
sum(( sum((
instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s}
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}} Receive' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Receive'),
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum(( sum((
instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s} instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s{%(nodeExporterSelector)s}
) != 0) by (%(clusterLabel)s) ) != 0) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}} Transmit' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} Transmit'),
) ]),
) ]),
.addRow(
row.new('Disk IO') row.new('Disk IO')
.addPanel( + row.withPanels([
diskIOUtilisation diskIOUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum(( sum((
instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s}
/ scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) / scalar(count(instance_device:node_disk_io_time_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s}))
) != 0) by (%(clusterLabel)s, device) ) != 0) by (%(clusterLabel)s, device)
||| % $._config, legendFormat='{{%(clusterLabel)s}} {{device}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} {{device}}'),
) ]),
.addPanel( diskIOSaturation + tsQueryOptions.withTargets([prometheus.new(
diskIOSaturation '$datasource',
.addTarget(prometheus.target(
||| |||
sum(( sum((
instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s} instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s}
/ scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s})) / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s{%(nodeExporterSelector)s}))
) != 0) by (%(clusterLabel)s, device) ) != 0) by (%(clusterLabel)s, device)
||| % $._config, legendFormat='{{%(clusterLabel)s}} {{device}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}} {{device}}')]),
) ]),
)
.addRow( ], panelWidth=12, panelHeight=7)
+ grafana.util.grid.makeGrid([
row.new('Disk Space') row.new('Disk Space')
.addPanel( + row.withPanels([
diskSpaceUtilisation diskSpaceUtilisation + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
sum ( sum (
sum without (device) ( sum without (device) (
@ -461,9 +470,11 @@ local diskSpaceUtilisation =
) )
/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s}))) / scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, %(fsSelector)s, %(fsMountpointSelector)s})))
) by (%(clusterLabel)s) ) by (%(clusterLabel)s)
||| % $._config, legendFormat='{{%(clusterLabel)s}}' % $._config ||| % $._config
)) ) + prometheus.withLegendFormat('{{%(clusterLabel)s}}'),
) ]),
]),
], panelWidth=24, panelHeight=7, startY=34),
), ),
} else {}, } else {},
} }

15
docs/node-mixin/jsonnetfile.json
View file

@ -4,20 +4,11 @@
{ {
"source": { "source": {
"git": { "git": {
"remote": "https://github.com/grafana/grafonnet-lib.git", "remote": "https://github.com/grafana/grafonnet.git",
"subdir": "grafonnet" "subdir": "gen/grafonnet-latest"
} }
}, },
"version": "master" "version": "main"
},
{
"source": {
"git": {
"remote": "https://github.com/grafana/grafonnet-lib.git",
"subdir": "grafonnet-7.0"
}
},
"version": "master"
} }
], ],
"legacyImports": false "legacyImports": false

691
docs/node-mixin/lib/prom-mixin.libsonnet
View file

@ -1,76 +1,85 @@
local grafana = import 'github.com/grafana/grafonnet-lib/grafonnet/grafana.libsonnet'; local grafana = import 'github.com/grafana/grafonnet/gen/grafonnet-latest/main.libsonnet';
local dashboard = grafana.dashboard; local dashboard = grafana.dashboard;
local row = grafana.row; local row = grafana.panel.row;
local prometheus = grafana.prometheus; local prometheus = grafana.query.prometheus;
local template = grafana.template; local variable = dashboard.variable;
local graphPanel = grafana.graphPanel;
local grafana70 = import 'github.com/grafana/grafonnet-lib/grafonnet-7.0/grafana.libsonnet'; local timeSeriesPanel = grafana.panel.timeSeries;
local gaugePanel = grafana70.panel.gauge; local tsOptions = timeSeriesPanel.options;
local table = grafana70.panel.table; local tsStandardOptions = timeSeriesPanel.standardOptions;
local tsQueryOptions = timeSeriesPanel.queryOptions;
local tsCustom = timeSeriesPanel.fieldConfig.defaults.custom;
local gaugePanel = grafana.panel.gauge;
local gaugeStep = gaugePanel.standardOptions.threshold.step;
local table = grafana.panel.table;
local tableStep = table.standardOptions.threshold.step;
local tableOverride = table.standardOptions.override;
local tableTransformation = table.queryOptions.transformation;
{ {
new(config=null, platform=null, uid=null):: { new(config=null, platform=null, uid=null):: {
local prometheusDatasourceTemplate = { local prometheusDatasourceVariable = variable.datasource.new(
current: { 'datasource', 'prometheus'
text: 'default',
value: 'default',
},
hide: 0,
label: 'Data Source',
name: 'datasource',
options: [],
query: 'prometheus',
refresh: 1,
regex: '',
type: 'datasource',
},
local clusterTemplatePrototype =
template.new(
'cluster',
'$datasource',
'',
hide=if config.showMultiCluster then '' else '2',
refresh='time',
label='Cluster',
), ),
local clusterTemplate =
if platform == 'Darwin' then
clusterTemplatePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname="Darwin"}, %(clusterLabel)s)' % config }
else
clusterTemplatePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, sysname!="Darwin"}, %(clusterLabel)s)' % config },
local instanceTemplatePrototype = local clusterVariablePrototype =
template.new( variable.query.new('cluster')
+ variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
+ (if config.showMultiCluster then variable.query.generalOptions.showOnDashboard.withLabelAndValue() else variable.query.generalOptions.showOnDashboard.withNothing())
+ variable.query.refresh.onTime()
+ variable.query.generalOptions.withLabel('Cluster'),
local clusterVariable =
if platform == 'Darwin' then
clusterVariablePrototype
+ variable.query.queryTypes.withLabelValues(
' %(clusterLabel)s' % config,
'node_uname_info{%(nodeExporterSelector)s, sysname="Darwin"}' % config,
)
else
clusterVariablePrototype
+ variable.query.queryTypes.withLabelValues(
'%(clusterLabel)s' % config,
'node_uname_info{%(nodeExporterSelector)s, sysname!="Darwin"}' % config,
),
local instanceVariablePrototype =
variable.query.new('instance')
+ variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
+ variable.query.refresh.onTime()
+ variable.query.generalOptions.withLabel('Instance'),
local instanceVariable =
if platform == 'Darwin' then
instanceVariablePrototype
+ variable.query.queryTypes.withLabelValues(
'instance', 'instance',
'$datasource', 'node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname="Darwin"}' % config,
'', )
refresh='time',
label='Instance',
),
local instanceTemplate =
if platform == 'Darwin' then
instanceTemplatePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname="Darwin"}, instance)' % config }
else else
instanceTemplatePrototype instanceVariablePrototype
{ query: 'label_values(node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname!="Darwin"}, instance)' % config }, + variable.query.queryTypes.withLabelValues(
'instance',
'node_uname_info{%(nodeExporterSelector)s, %(clusterLabel)s="$cluster", sysname!="Darwin"}' % config,
),
local idleCPU = local idleCPU =
graphPanel.new( timeSeriesPanel.new('CPU Usage')
'CPU Usage', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withUnit('percentunit')
span=6, + tsCustom.stacking.withMode('normal')
format='percentunit', + tsStandardOptions.withMax(1)
max=1, + tsStandardOptions.withMin(0)
min=0, + tsOptions.tooltip.withMode('multi')
stack=true, + tsCustom.withFillOpacity(10)
) + tsCustom.withShowPoints('never')
.addTarget(prometheus.target( + tsQueryOptions.withTargets([
prometheus.new(
'$datasource',
||| |||
( (
(1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance", %(clusterLabel)s="$cluster"}[$__rate_interval]))) (1 - sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal", instance="$instance", %(clusterLabel)s="$cluster"}[$__rate_interval])))
@ -78,36 +87,42 @@ local table = grafana70.panel.table;
count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance", %(clusterLabel)s="$cluster"}) count without (cpu, mode) (node_cpu_seconds_total{%(nodeExporterSelector)s, mode="idle", instance="$instance", %(clusterLabel)s="$cluster"})
) )
||| % config, ||| % config,
legendFormat='{{cpu}}', )
intervalFactor=5, + prometheus.withLegendFormat('{{cpu}}')
)), + prometheus.withIntervalFactor(5),
]),
local systemLoad = local systemLoad =
graphPanel.new( timeSeriesPanel.new('Load Average')
'Load Average', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withUnit('short')
span=6, + tsStandardOptions.withMin(0)
format='short', + tsCustom.withFillOpacity(0)
min=0, + tsCustom.withShowPoints('never')
fill=0, + tsOptions.tooltip.withMode('multi')
) + tsQueryOptions.withTargets([
.addTarget(prometheus.target('node_load1{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='1m load average')) prometheus.new('$datasource', 'node_load1{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('1m load average'),
.addTarget(prometheus.target('node_load5{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='5m load average')) prometheus.new('$datasource', 'node_load5{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('5m load average'),
.addTarget(prometheus.target('node_load15{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='15m load average')) prometheus.new('$datasource', 'node_load15{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('15m load average'),
.addTarget(prometheus.target('count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", mode="idle"})' % config, legendFormat='logical cores')), prometheus.new('$datasource', 'count(node_cpu_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", mode="idle"})' % config) + prometheus.withLegendFormat('logical cores'),
]),
local memoryGraphPanelPrototype = local memoryGraphPanelPrototype =
graphPanel.new( timeSeriesPanel.new('Memory Usage')
'Memory Usage', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withUnit('bytes')
span=9, + tsStandardOptions.withMin(0)
format='bytes', + tsOptions.tooltip.withMode('multi')
min=0, + tsCustom.withFillOpacity(10)
), + tsCustom.withShowPoints('never'),
local memoryGraph = local memoryGraph =
if platform == 'Linux' then if platform == 'Linux' then
memoryGraphPanelPrototype { stack: true } memoryGraphPanelPrototype
.addTarget(prometheus.target( + tsCustom.stacking.withMode('normal')
+ tsQueryOptions.withTargets([
prometheus.new(
'$datasource',
||| |||
( (
node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} node_memory_MemTotal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}
@ -119,16 +134,19 @@ local table = grafana70.panel.table;
node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}
) )
||| % config, ||| % config,
legendFormat='memory used' ) + prometheus.withLegendFormat('memory used'),
)) prometheus.new('$datasource', 'node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory buffers'),
.addTarget(prometheus.target('node_memory_Buffers_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory buffers')) prometheus.new('$datasource', 'node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory cached'),
.addTarget(prometheus.target('node_memory_Cached_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory cached')) prometheus.new('$datasource', 'node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('memory free'),
.addTarget(prometheus.target('node_memory_MemFree_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='memory free')) ])
else if platform == 'Darwin' then else if platform == 'Darwin' then
// not useful to stack // not useful to stack
memoryGraphPanelPrototype { stack: false } memoryGraphPanelPrototype
.addTarget(prometheus.target('node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Physical Memory')) + tsCustom.stacking.withMode('none')
.addTarget(prometheus.target( + tsQueryOptions.withTargets([
prometheus.new('$datasource', 'node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Physical Memory'),
prometheus.new(
'$datasource',
||| |||
( (
node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} -
@ -136,50 +154,61 @@ local table = grafana70.panel.table;
node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} + node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} +
node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}
) )
||| % config, legendFormat='Memory Used' ||| % config
)) ) + prometheus.withLegendFormat(
.addTarget(prometheus.target( 'Memory Used'
),
prometheus.new(
'$datasource',
||| |||
( (
node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - node_memory_internal_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} -
node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} node_memory_purgeable_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}
) )
||| % config, legendFormat='App Memory' ||| % config
)) ) + prometheus.withLegendFormat(
.addTarget(prometheus.target('node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Wired Memory')) 'App Memory'
.addTarget(prometheus.target('node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Compressed')) ),
prometheus.new('$datasource', 'node_memory_wired_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Wired Memory'),
prometheus.new('$datasource', 'node_memory_compressed_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Compressed'),
])
else if platform == 'AIX' then else if platform == 'AIX' then
memoryGraphPanelPrototype { stack: false } memoryGraphPanelPrototype
.addTarget(prometheus.target('node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config, legendFormat='Physical Memory')) + tsCustom.stacking.withMode('none')
.addTarget(prometheus.target( + tsQueryOptions.withTargets([
prometheus.new('$datasource', 'node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}' % config) + prometheus.withLegendFormat('Physical Memory'),
prometheus.new(
'$datasource',
||| |||
( (
node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} - node_memory_total_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} -
node_memory_available_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"} node_memory_available_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster"}
) )
||| % config, legendFormat='Memory Used' ||| % config
)), ) + prometheus.withLegendFormat('Memory Used'),
]),
// NOTE: avg() is used to circumvent a label change caused by a node_exporter rollout. // NOTE: avg() is used to circumvent a label change caused by a node_exporter rollout.
local memoryGaugePanelPrototype = local memoryGaugePanelPrototype =
gaugePanel.new( gaugePanel.new('Memory Usage')
title='Memory Usage', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + gaugePanel.standardOptions.thresholds.withSteps([
) gaugeStep.withColor('rgba(50, 172, 45, 0.97)'),
.addThresholdStep('rgba(50, 172, 45, 0.97)') gaugeStep.withColor('rgba(237, 129, 40, 0.89)') + gaugeStep.withValue(80),
.addThresholdStep('rgba(237, 129, 40, 0.89)', 80) gaugeStep.withColor('rgba(245, 54, 54, 0.9)') + gaugeStep.withValue(90),
.addThresholdStep('rgba(245, 54, 54, 0.9)', 90) ])
.setFieldConfig(max=100, min=0, unit='percent') + gaugePanel.standardOptions.withMax(100)
+ { + gaugePanel.standardOptions.withMin(0)
span: 3, + gaugePanel.standardOptions.withUnit('percent'),
},
local memoryGauge = local memoryGauge =
if platform == 'Linux' then if platform == 'Linux' then
memoryGaugePanelPrototype memoryGaugePanelPrototype
+ gaugePanel.queryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new(
'$datasource',
||| |||
100 - 100 -
( (
@ -188,11 +217,14 @@ local table = grafana70.panel.table;
* 100 * 100
) )
||| % config, ||| % config,
)) ),
])
else if platform == 'Darwin' then else if platform == 'Darwin' then
memoryGaugePanelPrototype memoryGaugePanelPrototype
.addTarget(prometheus.target( + gaugePanel.queryOptions.withTargets([
prometheus.new(
'$datasource',
||| |||
( (
( (
@ -206,10 +238,14 @@ local table = grafana70.panel.table;
* *
100 100
||| % config ||| % config
)) ),
])
else if platform == 'AIX' then else if platform == 'AIX' then
memoryGaugePanelPrototype memoryGaugePanelPrototype
.addTarget(prometheus.target( + gaugePanel.queryOptions.withTargets([
prometheus.new(
'$datasource',
||| |||
100 - 100 -
( (
@ -218,156 +254,94 @@ local table = grafana70.panel.table;
* 100 * 100
) )
||| % config ||| % config
)), ),
]),
local diskIO = local diskIO =
graphPanel.new( timeSeriesPanel.new('Disk I/O')
'Disk I/O', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withMin(0)
span=6, + tsCustom.withFillOpacity(0)
min=0, + tsCustom.withShowPoints('never')
fill=0, + tsOptions.tooltip.withMode('multi')
) + tsQueryOptions.withTargets([
// TODO: Does it make sense to have those three in the same panel? // TODO: Does it make sense to have those three in the same panel?
.addTarget(prometheus.target( prometheus.new('$datasource', 'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config)
'rate(node_disk_read_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, + prometheus.withLegendFormat('{{device}} read')
legendFormat='{{device}} read', + prometheus.withIntervalFactor(1),
intervalFactor=1, prometheus.new('$datasource', 'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config)
)) + prometheus.withLegendFormat('{{device}} written')
.addTarget(prometheus.target( + prometheus.withIntervalFactor(1),
'rate(node_disk_written_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, prometheus.new('$datasource', 'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config)
legendFormat='{{device}} written', + prometheus.withLegendFormat('{{device}} io time')
intervalFactor=1, + prometheus.withIntervalFactor(1),
)) ])
.addTarget(prometheus.target( + tsStandardOptions.withOverrides(
'rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(diskDeviceSelector)s}[$__rate_interval])' % config, [
legendFormat='{{device}} io time', tsStandardOptions.override.byRegexp.new('/ read| written/')
intervalFactor=1, + tsStandardOptions.override.byRegexp.withPropertiesFromOptions(
)) + tsStandardOptions.withUnit('Bps')
{ ),
seriesOverrides: [ tsStandardOptions.override.byRegexp.new('/ io time/')
{ + tsStandardOptions.override.byRegexp.withPropertiesFromOptions(tsStandardOptions.withUnit('percentunit')),
alias: '/ read| written/', ]
yaxis: 1, ),
},
{
alias: '/ io time/',
yaxis: 2,
},
],
yaxes: [
self.yaxe(format='Bps'),
self.yaxe(format='percentunit'),
],
},
local diskSpaceUsage = local diskSpaceUsage =
table.new( table.new('Disk Space Usage')
title='Disk Space Usage', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + table.standardOptions.withUnit('decbytes')
) + table.standardOptions.thresholds.withSteps(
.setFieldConfig(unit='decbytes') [
.addThresholdStep(color='green', value=null) tableStep.withColor('green'),
.addThresholdStep(color='yellow', value=0.8) tableStep.withColor('yellow') + gaugeStep.withValue(0.8),
.addThresholdStep(color='red', value=0.9) tableStep.withColor('red') + gaugeStep.withValue(0.9),
.addTarget(prometheus.target(
|||
max by (mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s})
||| % config,
legendFormat='',
instant=true,
format='table'
))
.addTarget(prometheus.target(
|||
max by (mountpoint) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s})
||| % config,
legendFormat='',
instant=true,
format='table'
))
.addOverride(
matcher={
id: 'byName',
options: 'Mounted on',
},
properties=[
{
id: 'custom.width',
value: 260,
},
],
)
.addOverride(
matcher={
id: 'byName',
options: 'Size',
},
properties=[
{
id: 'custom.width',
value: 93,
},
],
)
.addOverride(
matcher={
id: 'byName',
options: 'Used',
},
properties=[
{
id: 'custom.width',
value: 72,
},
],
)
.addOverride(
matcher={
id: 'byName',
options: 'Available',
},
properties=[
{
id: 'custom.width',
value: 88,
},
],
)
.addOverride(
matcher={
id: 'byName',
options: 'Used, %',
},
properties=[
{
id: 'unit',
value: 'percentunit',
},
{
id: 'custom.displayMode',
value: 'gradient-gauge',
},
{
id: 'max',
value: 1,
},
{
id: 'min',
value: 0,
},
] ]
) )
+ { span: 6 } + table.queryOptions.withTargets([
+ { prometheus.new(
transformations: [ '$datasource',
|||
max by (mountpoint) (node_filesystem_size_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s})
||| % config
)
+ prometheus.withLegendFormat('')
+ prometheus.withInstant()
+ prometheus.withFormat('table'),
prometheus.new(
'$datasource',
|||
max by (mountpoint) (node_filesystem_avail_bytes{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", %(fsSelector)s, %(fsMountpointSelector)s})
||| % config
)
+ prometheus.withLegendFormat('')
+ prometheus.withInstant()
+ prometheus.withFormat('table'),
])
+ table.standardOptions.withOverrides([
tableOverride.byName.new('Mounted on')
+ tableOverride.byName.withProperty('custom.width', 260),
tableOverride.byName.new('Size')
+ tableOverride.byName.withProperty('custom.width', 93),
tableOverride.byName.new('Used')
+ tableOverride.byName.withProperty('custom.width', 72),
tableOverride.byName.new('Available')
+ tableOverride.byName.withProperty('custom.width', 88),
tableOverride.byName.new('Used, %')
+ tableOverride.byName.withProperty('unit', 'percentunit')
+ tableOverride.byName.withPropertiesFromOptions(
table.fieldConfig.defaults.custom.withCellOptions(
{ type: 'gauge' },
)
)
+ tableOverride.byName.withProperty('max', 1)
+ tableOverride.byName.withProperty('min', 0),
])
+ table.queryOptions.withTransformations([
tableTransformation.withId('groupBy')
+ tableTransformation.withOptions(
{ {
id: 'groupBy',
options: {
fields: { fields: {
'Value #A': { 'Value #A': {
aggregations: [ aggregations: [
@ -386,15 +360,12 @@ local table = grafana70.panel.table;
operation: 'groupby', operation: 'groupby',
}, },
}, },
}, }
}, ),
tableTransformation.withId('merge'),
tableTransformation.withId('calculateField')
+ tableTransformation.withOptions(
{ {
id: 'merge',
options: {},
},
{
id: 'calculateField',
options: {
alias: 'Used', alias: 'Used',
binary: { binary: {
left: 'Value #A (lastNotNull)', left: 'Value #A (lastNotNull)',
@ -406,11 +377,11 @@ local table = grafana70.panel.table;
reduce: { reduce: {
reducer: 'sum', reducer: 'sum',
}, },
}, }
}, ),
tableTransformation.withId('calculateField')
+ tableTransformation.withOptions(
{ {
id: 'calculateField',
options: {
alias: 'Used, %', alias: 'Used, %',
binary: { binary: {
left: 'Used', left: 'Used',
@ -422,11 +393,11 @@ local table = grafana70.panel.table;
reduce: { reduce: {
reducer: 'sum', reducer: 'sum',
}, },
}, }
}, ),
tableTransformation.withId('organize')
+ tableTransformation.withOptions(
{ {
id: 'organize',
options: {
excludeByName: {}, excludeByName: {},
indexByName: {}, indexByName: {},
renameByName: { renameByName: {
@ -434,127 +405,131 @@ local table = grafana70.panel.table;
'Value #B (lastNotNull)': 'Available', 'Value #B (lastNotNull)': 'Available',
mountpoint: 'Mounted on', mountpoint: 'Mounted on',
}, },
}, }
}, ),
tableTransformation.withId('sortBy')
+ tableTransformation.withOptions(
{ {
id: 'sortBy',
options: {
fields: {}, fields: {},
sort: [ sort: [
{ {
field: 'Mounted on', field: 'Mounted on',
}, },
], ],
}, }
}, ),
],
},
]),
local networkReceived = local networkReceived =
graphPanel.new( timeSeriesPanel.new('Network Received')
'Network Received', + timeSeriesPanel.panelOptions.withDescription('Network received (bits/s)')
description='Network received (bits/s)', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withUnit('bps')
span=6, + tsStandardOptions.withMin(0)
format='bps', + tsCustom.withFillOpacity(0)
min=0, + tsCustom.withShowPoints('never')
fill=0, + tsOptions.tooltip.withMode('multi')
) + tsQueryOptions.withTargets([
.addTarget(prometheus.target( prometheus.new('$datasource', 'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config)
'rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config, + prometheus.withLegendFormat('{{device}}')
legendFormat='{{device}}', + prometheus.withIntervalFactor(1),
intervalFactor=1, ]),
)),
local networkTransmitted = local networkTransmitted =
graphPanel.new( timeSeriesPanel.new('Network Transmitted')
'Network Transmitted', + timeSeriesPanel.panelOptions.withDescription('Network transmitted (bits/s)')
description='Network transmitted (bits/s)', + variable.query.withDatasourceFromVariable(prometheusDatasourceVariable)
datasource='$datasource', + tsStandardOptions.withUnit('bps')
span=6, + tsStandardOptions.withMin(0)
format='bps', + tsCustom.withFillOpacity(0)
min=0, + tsOptions.tooltip.withMode('multi')
fill=0, + tsQueryOptions.withTargets([
) prometheus.new('$datasource', 'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config)
.addTarget(prometheus.target( + prometheus.withLegendFormat('{{device}}')
'rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, instance="$instance", %(clusterLabel)s="$cluster", device!="lo"}[$__rate_interval]) * 8' % config, + prometheus.withIntervalFactor(1),
legendFormat='{{device}}', ]),
intervalFactor=1,
)),
local cpuRow = local cpuRow =
row.new('CPU') row.new('CPU')
.addPanel(idleCPU) + row.withPanels([
.addPanel(systemLoad), idleCPU,
systemLoad,
]),
local memoryRow = local memoryRow = [
row.new('Memory') row.new('Memory') + row.gridPos.withY(8),
.addPanel(memoryGraph) memoryGraph + row.gridPos.withX(0) + row.gridPos.withY(9) + row.gridPos.withH(7) + row.gridPos.withW(18),
.addPanel(memoryGauge), memoryGauge + row.gridPos.withX(18) + row.gridPos.withY(9) + row.gridPos.withH(7) + row.gridPos.withW(6),
],
local diskRow = local diskRow =
row.new('Disk') row.new('Disk')
.addPanel(diskIO) + row.withPanels([
.addPanel(diskSpaceUsage), diskIO,
diskSpaceUsage,
]),
local networkRow = local networkRow =
row.new('Network') row.new('Network')
.addPanel(networkReceived) + row.withPanels([
.addPanel(networkTransmitted), networkReceived,
networkTransmitted,
]),
local rows = local panels =
[ grafana.util.grid.makeGrid([
cpuRow, cpuRow,
memoryRow, ], panelWidth=12, panelHeight=7)
+ memoryRow
+ grafana.util.grid.makeGrid([
diskRow, diskRow,
networkRow, networkRow,
], ], panelWidth=12, panelHeight=7, startY=18),
local templates = local variables =
[ [
prometheusDatasourceTemplate, prometheusDatasourceVariable,
clusterTemplate, clusterVariable,
instanceTemplate, instanceVariable,
], ],
dashboard: if platform == 'Linux' then dashboard: if platform == 'Linux' then
dashboard.new( dashboard.new(
'%sNodes' % config.dashboardNamePrefix, '%sNodes' % config.dashboardNamePrefix,
time_from='now-1h',
tags=(config.dashboardTags),
timezone='utc',
refresh='30s',
uid=std.md5(uid),
graphTooltip='shared_crosshair'
) )
.addTemplates(templates) + dashboard.time.withFrom('now-1h')
.addRows(rows) + dashboard.withTags(config.dashboardTags)
+ dashboard.withTimezone('utc')
+ dashboard.withRefresh('30s')
+ dashboard.withUid(std.md5(uid))
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withVariables(variables)
+ dashboard.withPanels(panels)
else if platform == 'Darwin' then else if platform == 'Darwin' then
dashboard.new( dashboard.new(
'%sMacOS' % config.dashboardNamePrefix, '%sMacOS' % config.dashboardNamePrefix,
time_from='now-1h',
tags=(config.dashboardTags),
timezone='utc',
refresh='30s',
uid=std.md5(uid),
graphTooltip='shared_crosshair'
) )
.addTemplates(templates) + dashboard.time.withFrom('now-1h')
.addRows(rows) + dashboard.withTags(config.dashboardTags)
+ dashboard.withTimezone('utc')
+ dashboard.withRefresh('30s')
+ dashboard.withUid(std.md5(uid))
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withVariables(variables)
+ dashboard.withPanels(panels)
else if platform == 'AIX' then else if platform == 'AIX' then
dashboard.new( dashboard.new(
'%sAIX' % config.dashboardNamePrefix, '%sAIX' % config.dashboardNamePrefix,
time_from='now-1h',
tags=(config.dashboardTags),
timezone='utc',
refresh='30s',
uid=std.md5(uid),
graphTooltip='shared_crosshair'
) )
.addTemplates(templates) + dashboard.time.withFrom('now-1h')
.addRows(rows), + dashboard.withTags(config.dashboardTags)
+ dashboard.withTimezone('utc')
+ dashboard.withRefresh('30s')
+ dashboard.withUid(std.md5(uid))
+ dashboard.graphTooltip.withSharedCrosshair()
+ dashboard.withVariables(variables)
+ dashboard.withPanels(panels),
}, },
} }

24
go.mod
View file

@ -18,18 +18,18 @@ require (
github.com/mattn/go-xmlrpc v0.0.3 github.com/mattn/go-xmlrpc v0.0.3
github.com/mdlayher/ethtool v0.2.0 github.com/mdlayher/ethtool v0.2.0
github.com/mdlayher/netlink v1.7.2 github.com/mdlayher/netlink v1.7.2
github.com/mdlayher/wifi v0.3.0 github.com/mdlayher/wifi v0.3.1
github.com/opencontainers/selinux v1.11.1 github.com/opencontainers/selinux v1.11.1
github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55
github.com/prometheus-community/go-runit v0.1.0 github.com/prometheus-community/go-runit v0.1.0
github.com/prometheus/client_golang v1.20.5 github.com/prometheus/client_golang v1.20.5
github.com/prometheus/client_model v0.6.1 github.com/prometheus/client_model v0.6.1
github.com/prometheus/common v0.60.1 github.com/prometheus/common v0.61.0
github.com/prometheus/exporter-toolkit v0.13.1 github.com/prometheus/exporter-toolkit v0.13.2
github.com/prometheus/procfs v0.15.1 github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b // == v0.15.1 + https://github.com/prometheus/procfs/commit/1754b780536bb81082baa913e04cc4fff4d2baea
github.com/safchain/ethtool v0.4.1 github.com/safchain/ethtool v0.5.9
golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 golang.org/x/exp v0.0.0-20240909161429-701f63a606c0
golang.org/x/sys v0.26.0 golang.org/x/sys v0.28.0
howett.net/plist v1.0.1 howett.net/plist v1.0.1
) )
@ -51,11 +51,11 @@ require (
github.com/xhit/go-str2duration/v2 v2.1.0 // indirect github.com/xhit/go-str2duration/v2 v2.1.0 // indirect
go.uber.org/atomic v1.7.0 // indirect go.uber.org/atomic v1.7.0 // indirect
go.uber.org/multierr v1.6.0 // indirect go.uber.org/multierr v1.6.0 // indirect
golang.org/x/crypto v0.28.0 // indirect golang.org/x/crypto v0.31.0 // indirect
golang.org/x/net v0.29.0 // indirect golang.org/x/net v0.32.0 // indirect
golang.org/x/oauth2 v0.23.0 // indirect golang.org/x/oauth2 v0.24.0 // indirect
golang.org/x/sync v0.8.0 // indirect golang.org/x/sync v0.10.0 // indirect
golang.org/x/text v0.19.0 // indirect golang.org/x/text v0.21.0 // indirect
google.golang.org/protobuf v1.34.2 // indirect google.golang.org/protobuf v1.35.2 // indirect
gopkg.in/yaml.v2 v2.4.0 // indirect gopkg.in/yaml.v2 v2.4.0 // indirect
) )

54
go.sum
View file

@ -61,8 +61,8 @@ github.com/mdlayher/socket v0.4.1 h1:eM9y2/jlbs1M615oshPQOHZzj6R6wMT7bX5NPiQvn2U
github.com/mdlayher/socket v0.4.1/go.mod h1:cAqeGjoufqdxWkD7DkpyS+wcefOtmu5OQ8KuoJGIReA= github.com/mdlayher/socket v0.4.1/go.mod h1:cAqeGjoufqdxWkD7DkpyS+wcefOtmu5OQ8KuoJGIReA=
github.com/mdlayher/vsock v1.2.1 h1:pC1mTJTvjo1r9n9fbm7S1j04rCgCzhCOS5DY0zqHlnQ= github.com/mdlayher/vsock v1.2.1 h1:pC1mTJTvjo1r9n9fbm7S1j04rCgCzhCOS5DY0zqHlnQ=
github.com/mdlayher/vsock v1.2.1/go.mod h1:NRfCibel++DgeMD8z/hP+PPTjlNJsdPOmxcnENvE+SE= github.com/mdlayher/vsock v1.2.1/go.mod h1:NRfCibel++DgeMD8z/hP+PPTjlNJsdPOmxcnENvE+SE=
github.com/mdlayher/wifi v0.3.0 h1:ZfS81w/7xTWBJfhM77K0k6m3sJckwoNOoZUwOW34omo= github.com/mdlayher/wifi v0.3.1 h1:bZDuMI1f7z5BtUUO3NgHRdR/R88YtywIe6dsEFI0Txs=
github.com/mdlayher/wifi v0.3.0/go.mod h1:/bdkqKYl+lD4recmQM6bTHxMrEUW70reibTyr93CAd0= github.com/mdlayher/wifi v0.3.1/go.mod h1:ODQaObvsglghTuNhezD9grkTB4shVNc28aJfTXmvSi8=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA= github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ= github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU= github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
@ -79,48 +79,48 @@ github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+
github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE= github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E= github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY= github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
github.com/prometheus/common v0.60.1 h1:FUas6GcOw66yB/73KC+BOZoFJmbo/1pojoILArPAaSc= github.com/prometheus/common v0.61.0 h1:3gv/GThfX0cV2lpO7gkTUwZru38mxevy90Bj8YFSRQQ=
github.com/prometheus/common v0.60.1/go.mod h1:h0LYf1R1deLSKtD4Vdg8gy4RuOvENW2J/h19V5NADQw= github.com/prometheus/common v0.61.0/go.mod h1:zr29OCN/2BsJRaFwG8QOBr41D6kkchKbpeNH7pAjb/s=
github.com/prometheus/exporter-toolkit v0.13.1 h1:Evsh0gWQo2bdOHlnz9+0Nm7/OFfIwhE2Ws4A2jIlR04= github.com/prometheus/exporter-toolkit v0.13.2 h1:Z02fYtbqTMy2i/f+xZ+UK5jy/bl1Ex3ndzh06T/Q9DQ=
github.com/prometheus/exporter-toolkit v0.13.1/go.mod h1:ujdv2YIOxtdFxxqtloLpbqmxd5J0Le6IITUvIRSWjj0= github.com/prometheus/exporter-toolkit v0.13.2/go.mod h1:tCqnfx21q6qN1KA4U3Bfb8uWzXfijIrJz3/kTIqMV7g=
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc= github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b h1:4EJkx3vycI+n5JY5ht+bnSUGamkmmXkpcNeO/OBT/0A=
github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk= github.com/prometheus/procfs v0.15.2-0.20240603130017-1754b780536b/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ= github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog= github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/safchain/ethtool v0.4.1 h1:S6mEleTADqgynileXoiapt/nKnatyR6bmIHoF+h2ADo= github.com/safchain/ethtool v0.5.9 h1://6RvaOKFf3nQ0rl5+8zBbE4/72455VC9Jq61pfq67E=
github.com/safchain/ethtool v0.4.1/go.mod h1:XLLnZmy4OCRTkksP/UiMjij96YmIsBfmBQcs7H6tA48= github.com/safchain/ethtool v0.5.9/go.mod h1:w8oSsZeowyRaM7xJJBAbubzzrOkwO8TBgPSEqPP/5mg=
github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973 h1:GfSdC6wKfTGcgCS7BtzF5694Amne1pGCSTY252WhlEY= github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973 h1:GfSdC6wKfTGcgCS7BtzF5694Amne1pGCSTY252WhlEY=
github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973/go.mod h1:G81aIFAMS9ECrwBYR9YxhlPjWgrItd+Kje78O6+uqm8= github.com/siebenmann/go-kstat v0.0.0-20210513183136-173c9b0a9973/go.mod h1:G81aIFAMS9ECrwBYR9YxhlPjWgrItd+Kje78O6+uqm8=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg= github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/xhit/go-str2duration/v2 v2.1.0 h1:lxklc02Drh6ynqX+DdPyp5pCKLUQpRT8bp8Ydu2Bstc= github.com/xhit/go-str2duration/v2 v2.1.0 h1:lxklc02Drh6ynqX+DdPyp5pCKLUQpRT8bp8Ydu2Bstc=
github.com/xhit/go-str2duration/v2 v2.1.0/go.mod h1:ohY8p+0f07DiV6Em5LKB0s2YpLtXVyJfNt1+BlmyAsU= github.com/xhit/go-str2duration/v2 v2.1.0/go.mod h1:ohY8p+0f07DiV6Em5LKB0s2YpLtXVyJfNt1+BlmyAsU=
go.uber.org/atomic v1.7.0 h1:ADUqmZGgLDDfbSL9ZmPxKTybcoEYHgpYfELNoN+7hsw= go.uber.org/atomic v1.7.0 h1:ADUqmZGgLDDfbSL9ZmPxKTybcoEYHgpYfELNoN+7hsw=
go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc= go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
go.uber.org/multierr v1.6.0 h1:y6IPFStTAIT5Ytl7/XYmHvzXQ7S3g/IeZW9hyZ5thw4= go.uber.org/multierr v1.6.0 h1:y6IPFStTAIT5Ytl7/XYmHvzXQ7S3g/IeZW9hyZ5thw4=
go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9iU= go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9iU=
golang.org/x/crypto v0.28.0 h1:GBDwsMXVQi34v5CCYUm2jkJvu4cbtru2U4TN2PSyQnw= golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
golang.org/x/crypto v0.28.0/go.mod h1:rmgy+3RHxRZMyY0jjAJShp2zgEdOqj2AO7U0pYmeQ7U= golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 h1:e66Fs6Z+fZTbFBAxKfP3PALWBtpfqks2bwGcexMxgtk= golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 h1:e66Fs6Z+fZTbFBAxKfP3PALWBtpfqks2bwGcexMxgtk=
golang.org/x/exp v0.0.0-20240909161429-701f63a606c0/go.mod h1:2TbTHSBQa924w8M6Xs1QcRcFwyucIwBGpK1p2f1YFFY= golang.org/x/exp v0.0.0-20240909161429-701f63a606c0/go.mod h1:2TbTHSBQa924w8M6Xs1QcRcFwyucIwBGpK1p2f1YFFY=
golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo= golang.org/x/net v0.32.0 h1:ZqPmj8Kzc+Y6e0+skZsuACbx+wzMgo5MQsJh9Qd6aYI=
golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0= golang.org/x/net v0.32.0/go.mod h1:CwU0IoeOlnQQWJ6ioyFrfRuomB8GKF6KbYXZVyeXNfs=
golang.org/x/oauth2 v0.23.0 h1:PbgcYx2W7i4LvjJWEbf0ngHV6qJYr86PkAV3bXdLEbs= golang.org/x/oauth2 v0.24.0 h1:KTBBxWqUa0ykRPLtV69rRto9TLXcqYkeswu48x/gvNE=
golang.org/x/oauth2 v0.23.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI= golang.org/x/oauth2 v0.24.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ= golang.org/x/sync v0.10.0 h1:3NQrjDixjgGwUOCaF8w2+VYHv0Ve/vGYSbdkTa98gmQ=
golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20211031064116-611d5d643895/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.0.0-20211031064116-611d5d643895/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.27.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.26.0 h1:KHjCJyddX0LoSTb3J+vWpupP9p0oznkqVk/IfjymZbo= golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
golang.org/x/sys v0.26.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/text v0.19.0 h1:kTxAhCbGbxhK0IwgSKiMO5awPoDQ0RpfiVYBfK860YM= golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
golang.org/x/text v0.19.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY= golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg= google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw= google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=