Compare commits

..

25 Commits

Author SHA1 Message Date
Thomas Roehl
77fceb17d1 Update rapl collector with powercap limits 2025-04-04 12:04:27 +02:00
Thomas Roehl
b5520efc25 Fix artifacts in netstat collector of not done cc-lib switch 2025-03-15 04:02:26 +01:00
Thomas Roehl
d2b1bad1b8 Fix artifacts of not done cc-lib switch 2025-03-15 04:01:01 +01:00
brinkcoder
0e57c8db1c Add derived_values for numastats (#134)
* Check creation of CCMessage in NATS receiver

* add derived_values for numastats

* change to ccMessage

* remove vim command artefact

---------

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>
Co-authored-by: exterr2f <Robert.Externbrink@rub.de>
Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com>
2025-02-19 11:35:32 +01:00
brinkcoder
f2f38c81af Add exclude_devices to iostat (#133)
* Check creation of CCMessage in NATS receiver

* add exclude_device for iostatMetric

* add md file

---------

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>
Co-authored-by: exterr2f <Robert.Externbrink@rub.de>
Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com>
2025-02-19 11:34:56 +01:00
brinkcoder
f9acc51a50 Add derived values for nfsiostat (#132)
* Check creation of CCMessage in NATS receiver

* add derived_values for nfsiostatMetric

---------

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>
Co-authored-by: exterr2f <Robert.Externbrink@rub.de>
Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com>
2025-02-19 11:34:06 +01:00
brinkcoder
87346e2eae Fix excluded metrics for diskstat and add exclude_mounts (#131)
* Check creation of CCMessage in NATS receiver

* fix excluded metrics and add optional mountpoint exclude

---------

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>
Co-authored-by: exterr2f <Robert.Externbrink@rub.de>
Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com>
2025-02-19 11:33:13 +01:00
brinkcoder
0f92f10b66 Add optional interface alias in netstat (#130)
* Check creation of CCMessage in NATS receiver

* add optional interface aliases for netstatMetric

* small fix

---------

Co-authored-by: Thomas Roehl <thomas.roehl@fau.de>
Co-authored-by: exterr2f <Robert.Externbrink@rub.de>
Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com>
2025-02-19 11:32:15 +01:00
Michael Panzlaff
6901b06e44 Rename 'process_message' to 'process_messages' in metricRouter config
This makes the behavior more consistent with the other modules, which
have their MessageProcessor named 'process_messages'. This most likely
was just a typo.
2025-02-03 15:23:51 +01:00
Thomas Roehl
7b343d0bab Use CCMessage FromBytes instead of Influx's decoder 2024-12-27 15:22:59 +00:00
Thomas Roehl
7d3180b526 Check creation of CCMessage in NATS receiver 2024-12-27 15:00:48 +00:00
Thomas Roehl
70a6afc549 Generate HUGO inputs out of Markdown files 2024-12-23 17:55:48 +01:00
Thomas Roehl
e02a018327 Mark all JSON config fields of message processor as omitempty 2024-12-23 17:52:34 +01:00
Thomas Roehl
bcecdd033b Fix documentation of RAPL collector 2024-12-23 17:51:43 +01:00
Thomas Roehl
2645ffeff3 Merge branch 'main' into develop 2024-12-21 02:39:08 +01:00
Thomas Roehl
ee4e1baf5b Fix Release part 2024-12-20 21:07:33 +01:00
Thomas Roehl
94c80307e8 Fix Release part 2024-12-20 21:03:03 +01:00
Thomas Roehl
e968aa1991 Fix wrongly named packages 2024-12-20 20:33:10 +01:00
Thomas Gruber
d2a38e3844 Merge branch 'main' into develop 2024-12-20 20:27:48 +01:00
Thomas Roehl
1f35f6d3ca Fix wrongly named packages 2024-12-20 20:26:38 +01:00
Thomas Roehl
7e6870c7b3 Add golang-race for UBI9 and Alma9 2024-12-20 20:15:59 +01:00
Thomas Roehl
d881093524 Install go-toolkit to fulfill build requirements for RPM 2024-12-20 20:12:03 +01:00
Thomas Roehl
c01096c157 use go-toolkit for RPM builds 2024-12-20 18:49:28 +01:00
Thomas Roehl
3d70c8afc9 Remove condition around BuildRequires and use go-toolkit for RPM builds 2024-12-20 18:43:21 +01:00
Thomas Roehl
7ee85a07dc Remove go-toolkit as build requirement for RPM builds if run in CI 2024-12-20 18:28:32 +01:00
24 changed files with 774 additions and 435 deletions

View File

@@ -73,21 +73,21 @@ jobs:
NEW_SRPM=${OLD_SRPM/el8/alma8}
mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "EL8_SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "EL8_RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector RPM for AlmaLinux 8
path: ${{ steps.rpmrename.outputs.EL8_RPM }}
path: ${{ steps.rpmrename.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector SRPM for AlmaLinux 8
path: ${{ steps.rpmrename.outputs.EL8_SRPM }}
path: ${{ steps.rpmrename.outputs.SRPM }}
overwrite: true
#
@@ -152,21 +152,21 @@ jobs:
NEW_SRPM=${OLD_SRPM/el9/alma9}
mv "${OLD_RPM}" "${NEW_RPM}"
mv "${OLD_SRPM}" "${NEW_SRPM}"
echo "EL9_SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "EL9_RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
# See: https://github.com/actions/upload-artifact
- name: Save RPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector RPM for AlmaLinux 9
path: ${{ steps.rpmrename.outputs.EL9_RPM }}
path: ${{ steps.rpmrename.outputs.RPM }}
overwrite: true
- name: Save SRPM as artifact
uses: actions/upload-artifact@v4
with:
name: cc-metric-collector SRPM for AlmaLinux 9
path: ${{ steps.rpmrename.outputs.EL9_SRPM }}
path: ${{ steps.rpmrename.outputs.SRPM }}
overwrite: true
#
@@ -235,6 +235,10 @@ jobs:
# See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
container: redhat/ubi9
# The job outputs link to the outputs of the 'rpmbuild' step
# The job outputs link to the outputs of the 'rpmbuild' step
outputs:
rpm : ${{steps.rpmbuild.outputs.RPM}}
srpm : ${{steps.rpmbuild.outputs.SRPM}}
steps:
# Use dnf to install development packages

View File

@@ -33,10 +33,8 @@ In contrast to the configuration files for sinks and receivers, the collectors c
* [`topprocs`](./topprocsMetric.md)
* [`nfs3stat`](./nfs3Metric.md)
* [`nfs4stat`](./nfs4Metric.md)
* [`nfsiostat`](./nfsiostatMetric.md)
* [`cpufreq`](./cpufreqMetric.md)
* [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
* [`schedstat`](./schedstatMetric.md)
* [`numastats`](./numastatsMetric.md)
* [`gpfs`](./gpfsMetric.md)
* [`beegfs_meta`](./beegfsmetaMetric.md)

View File

@@ -8,23 +8,21 @@ import (
"syscall"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
// "log"
const MOUNTFILE = `/proc/self/mounts`
type DiskstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeMounts []string `json:"exclude_mounts,omitempty"`
}
type DiskstatCollector struct {
metricCollector
//matches map[string]int
config IOstatCollectorConfig
//devices map[string]IOstatCollectorEntry
config DiskstatCollectorConfig
allowedMetrics map[string]bool
}
func (m *DiskstatCollector) Init(config json.RawMessage) error {
@@ -33,12 +31,21 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
m.meta = map[string]string{"source": m.name, "group": "Disk"}
m.setup()
if len(config) > 0 {
err := json.Unmarshal(config, &m.config)
if err != nil {
if err := json.Unmarshal(config, &m.config); err != nil {
return err
}
}
file, err := os.Open(string(MOUNTFILE))
m.allowedMetrics = map[string]bool{
"disk_total": true,
"disk_free": true,
"part_max_used": true,
}
for _, excl := range m.config.ExcludeMetrics {
if _, ok := m.allowedMetrics[excl]; ok {
m.allowedMetrics[excl] = false
}
}
file, err := os.Open(MOUNTFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return err
@@ -53,7 +60,7 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
return
}
file, err := os.Open(string(MOUNTFILE))
file, err := os.Open(MOUNTFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return
@@ -62,6 +69,7 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
part_max_used := uint64(0)
scanner := bufio.NewScanner(file)
mountLoop:
for scanner.Scan() {
line := scanner.Text()
if len(line) == 0 {
@@ -77,13 +85,17 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
if strings.Contains(linefields[1], "boot") {
continue
}
path := strings.Replace(linefields[1], `\040`, " ", -1)
stat := syscall.Statfs_t{
Blocks: 0,
Bsize: 0,
Bfree: 0,
mountPath := strings.Replace(linefields[1], `\040`, " ", -1)
for _, excl := range m.config.ExcludeMounts {
if strings.Contains(mountPath, excl) {
continue mountLoop
}
}
err := syscall.Statfs(path, &stat)
stat := syscall.Statfs_t{}
err := syscall.Statfs(mountPath, &stat)
if err != nil {
continue
}
@@ -92,16 +104,20 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
}
tags := map[string]string{"type": "node", "device": linefields[0]}
total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
y, err := lp.NewMessage("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
output <- y
if m.allowedMetrics["disk_total"] {
y, err := lp.NewMessage("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
output <- y
}
}
free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
y, err = lp.NewMessage("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
output <- y
if m.allowedMetrics["disk_free"] {
y, err := lp.NewMessage("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
if err == nil {
y.AddMeta("unit", "GBytes")
output <- y
}
}
if total > 0 {
perc := (100 * (total - free)) / total
@@ -110,10 +126,12 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
}
}
}
y, err := lp.NewMessage("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
if err == nil {
y.AddMeta("unit", "percent")
output <- y
if m.allowedMetrics["part_max_used"] {
y, err := lp.NewMessage("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
if err == nil {
y.AddMeta("unit", "percent")
output <- y
}
}
}

View File

@@ -6,10 +6,13 @@
"exclude_metrics": [
"disk_total"
],
"exclude_mounts": [
"slurm-tmpfs"
]
}
```
The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. Additionally, any mount point containing one of the strings specified in `exclude_mounts` will be skipped during metric collection.
Metrics per device (with `device` tag):
* `disk_total` (unit `GBytes`)

View File

@@ -4,8 +4,8 @@ import (
"fmt"
"os"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
"golang.org/x/sys/unix"
"encoding/json"

View File

@@ -2,24 +2,24 @@ package collectors
import (
"bufio"
"os"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
// "log"
"encoding/json"
"errors"
"os"
"strconv"
"strings"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
// Konstante für den Pfad zu /proc/diskstats
const IOSTATFILE = `/proc/diskstats`
const IOSTAT_SYSFSPATH = `/sys/block`
type IOstatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
// Neues Feld zum Ausschließen von Devices per JSON-Konfiguration
ExcludeDevices []string `json:"exclude_devices,omitempty"`
}
type IOstatCollectorEntry struct {
@@ -76,7 +76,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
if len(m.matches) == 0 {
return errors.New("no metrics to collect")
}
file, err := os.Open(string(IOSTATFILE))
file, err := os.Open(IOSTATFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return err
@@ -87,17 +87,24 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
for scanner.Scan() {
line := scanner.Text()
linefields := strings.Fields(line)
if len(linefields) < 3 {
continue
}
device := linefields[2]
if strings.Contains(device, "loop") {
continue
}
if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
continue
}
values := make(map[string]int64)
for m := range m.matches {
values[m] = 0
}
m.devices[device] = IOstatCollectorEntry{
tags: map[string]string{
"device": linefields[2],
"device": device,
"type": "node",
},
lastValues: values,
@@ -112,7 +119,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
return
}
file, err := os.Open(string(IOSTATFILE))
file, err := os.Open(IOSTATFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return
@@ -126,10 +133,16 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
continue
}
linefields := strings.Fields(line)
if len(linefields) < 3 {
continue
}
device := linefields[2]
if strings.Contains(device, "loop") {
continue
}
if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
continue
}
if _, ok := m.devices[device]; !ok {
continue
}

View File

@@ -4,12 +4,17 @@
```json
"iostat": {
"exclude_metrics": [
"read_ms"
"io_read_ms"
],
"exclude_devices": [
"nvme0n1p1",
"nvme0n1p2",
"md127"
]
}
```
The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric or device is not required, it can be excluded from forwarding it to the sink.
Metrics:
* `io_reads`

View File

@@ -190,8 +190,12 @@ func getBaseFreq() float64 {
}
if math.IsNaN(freq) {
C.timer_init()
freq = float64(C.timer_getCycleClock()) / 1e3
C.power_init(0)
info := C.get_powerInfo()
if float64(info.baseFrequency) != 0 {
freq = float64(info.baseFrequency)
}
C.power_finalize()
}
return freq * 1e3
}

View File

@@ -12,8 +12,8 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
const MEMSTATFILE = "/proc/meminfo"

View File

@@ -9,16 +9,17 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
const NETSTATFILE = "/proc/net/dev"
type NetstatCollectorConfig struct {
IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
InterfaceAliases map[string][]string `json:"interface_aliases,omitempty"`
}
type NetstatCollectorMetric struct {
@@ -32,9 +33,26 @@ type NetstatCollectorMetric struct {
type NetstatCollector struct {
metricCollector
config NetstatCollectorConfig
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
config NetstatCollectorConfig
aliasToCanonical map[string]string
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
}
func (m *NetstatCollector) buildAliasMapping() {
m.aliasToCanonical = make(map[string]string)
for canon, aliases := range m.config.InterfaceAliases {
for _, alias := range aliases {
m.aliasToCanonical[alias] = canon
}
}
}
func getCanonicalName(raw string, aliasToCanonical map[string]string) string {
if canon, ok := aliasToCanonical[raw]; ok {
return canon
}
return raw
}
func (m *NetstatCollector) Init(config json.RawMessage) error {
@@ -77,6 +95,8 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
}
}
m.buildAliasMapping()
// Check access to net statistic file
file, err := os.Open(NETSTATFILE)
if err != nil {
@@ -97,18 +117,20 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
// Split line into fields
f := strings.Fields(l)
// Get net device entry
dev := strings.Trim(f[0], ": ")
// Get raw and canonical names
raw := strings.Trim(f[0], ": ")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
if _, ok := stringArrayContains(m.config.IncludeDevices, canonical); ok {
// Tag will contain original device name (raw).
tags := map[string]string{"stype": "network", "stype-id": raw, "type": "node"}
meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}
meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
m.matches[dev] = []NetstatCollectorMetric{
m.matches[canonical] = []NetstatCollectorMetric{
{
name: "net_bytes_in",
index: fieldReceiveBytes,
@@ -143,7 +165,6 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
},
}
}
}
if len(m.matches) == 0 {
@@ -164,7 +185,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Save current timestamp
m.lastTimestamp = now
file, err := os.Open(string(NETSTATFILE))
file, err := os.Open(NETSTATFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return
@@ -183,11 +204,12 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
// Split line into fields
f := strings.Fields(l)
// Get net device entry
dev := strings.Trim(f[0], ":")
// Get raw and canonical names
raw := strings.Trim(f[0], ":")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device
if devmetrics, ok := m.matches[dev]; ok {
if devmetrics, ok := m.matches[canonical]; ok {
for i := range devmetrics {
metric := &devmetrics[i]

View File

@@ -4,14 +4,19 @@
```json
"netstat": {
"include_devices": [
"eth0"
"eth0",
"eno1"
],
"send_abs_values" : true,
"send_derived_values" : true
"send_abs_values": true,
"send_derived_values": true,
"interface_aliases": {
"eno1": ["eno1np0", "eno1_alt"],
"eth0": ["eth0_alias"]
}
}
```
The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list.
The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list. Optionally, you can define an interface_aliases mapping. For each canonical device (as listed in include_devices), you may provide an array of aliases that may be reported by the system. When an alias is detected, it is preferred for matching, while the output tag stype-id always shows the actual system-reported name.
Metrics:
* `net_bytes_in` (`unit=bytes`)
@@ -23,5 +28,4 @@ Metrics:
* `net_pkts_in_bw` (`unit=packets/sec` if `send_derived_values == true`)
* `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
The device name is added as tag `stype=network,stype-id=<device>`.
The device name is added as tag `stype=network,stype-id=<device>`.

View File

@@ -9,8 +9,8 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
// These are the fields we read from the JSON configuration
@@ -18,17 +18,20 @@ type NfsIOStatCollectorConfig struct {
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
UseServerAddressAsSType bool `json:"use_server_as_stype,omitempty"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
}
// This contains all variables we need during execution and the variables
// defined by metricCollector (name, init, ...)
type NfsIOStatCollector struct {
metricCollector
config NfsIOStatCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
data map[string]map[string]int64 // data storage for difference calculation
key string // which device info should be used as subtype ID? 'server' or 'mntpoint', see NfsIOStatCollectorConfig.UseServerAddressAsSType
config NfsIOStatCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
data map[string]map[string]int64 // data storage for difference calculation
key string // which device info should be used as subtype ID? 'server' or 'mntpoint'
lastTimestamp time.Time
}
var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
@@ -81,7 +84,6 @@ func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
data[current[m.key]][name] = val
}
}
}
current = nil
}
@@ -98,6 +100,9 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"}
m.tags = map[string]string{"type": "node"}
m.config.UseServerAddressAsSType = false
// Set default configuration
m.config.SendAbsoluteValues = true
m.config.SendDerivedValues = false
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
@@ -110,12 +115,15 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
m.key = "server"
}
m.data = m.readNfsiostats()
m.lastTimestamp = time.Now()
m.init = true
return err
}
func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
timestamp := time.Now()
now := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
// Get the current values for all mountpoints
newdata := m.readNfsiostats()
@@ -123,21 +131,30 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
for mntpoint, values := range newdata {
// Was the mount point already present in the last iteration
if old, ok := m.data[mntpoint]; ok {
// Calculate the difference of old and new values
for i := range values {
x := values[i] - old[i]
y, err := lp.NewMessage(fmt.Sprintf("nfsio_%s", i), m.tags, m.meta, map[string]interface{}{"value": x}, timestamp)
if err == nil {
if strings.HasPrefix(i, "page") {
y.AddMeta("unit", "4K_Pages")
for name, newVal := range values {
if m.config.SendAbsoluteValues {
msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s", name), m.tags, m.meta, map[string]interface{}{"value": newVal}, now)
if err == nil {
msg.AddTag("stype", "filesystem")
msg.AddTag("stype-id", mntpoint)
output <- msg
}
y.AddTag("stype", "filesystem")
y.AddTag("stype-id", mntpoint)
// Send it to output channel
output <- y
}
// Update old to the new value for the next iteration
old[i] = values[i]
if m.config.SendDerivedValues {
rate := float64(newVal-old[name]) / timeDiff
msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s_bw", name), m.tags, m.meta, map[string]interface{}{"value": rate}, now)
if err == nil {
if strings.HasPrefix(name, "page") {
msg.AddMeta("unit", "4K_pages/s")
} else {
msg.AddMeta("unit", "bytes/sec")
}
msg.AddTag("stype", "filesystem")
msg.AddTag("stype-id", mntpoint)
output <- msg
}
}
old[name] = newVal
}
} else {
// First time we see this mount point, store all values
@@ -157,7 +174,6 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
m.data[mntpoint] = nil
}
}
}
func (m *NfsIOStatCollector) Close() {

View File

@@ -3,16 +3,18 @@
```json
"nfsiostat": {
"exclude_metrics": [
"nfsio_oread"
"oread", "pageread"
],
"exclude_filesystems" : [
"/mnt",
"exclude_filesystems": [
"/mnt"
],
"use_server_as_stype": false
"use_server_as_stype": false,
"send_abs_values": false,
"send_derived_values": true
}
```
The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink.
The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink. **Note:** When excluding metrics, you must provide the base metric name (e.g. pageread) without the nfsio_ prefix. This exclusion applies to both absolute and derived values.
Metrics:
* `nfsio_nread`: Bytes transferred by normal `read()` calls
@@ -24,4 +26,9 @@ Metrics:
* `nfsio_nfsread`: Bytes transferred for reading from the server
* `nfsio_nfswrite`: Pages transferred by writing to the server
The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.
For each of these, if derived values are enabled, an additional metric is sent with the `_bw` suffix, which represents the rate:
* For normal byte metrics: `unit=bytes/sec`
* For page metrics: `unit=4K_pages/s`
The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.

View File

@@ -10,10 +10,15 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
type NUMAStatsCollectorConfig struct {
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
}
// Non-Uniform Memory Access (NUMA) policy hit/miss statistics
//
// numa_hit:
@@ -47,13 +52,16 @@ import (
//
// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
type NUMAStatsCollectorTopolgy struct {
file string
tagSet map[string]string
file string
tagSet map[string]string
previousValues map[string]int64
}
type NUMAStatsCollector struct {
metricCollector
topology []NUMAStatsCollectorTopolgy
topology []NUMAStatsCollectorTopolgy
config NUMAStatsCollectorConfig
lastTimestamp time.Time
}
func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
@@ -86,8 +94,9 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
file := filepath.Join(dir, "numastat")
m.topology = append(m.topology,
NUMAStatsCollectorTopolgy{
file: file,
tagSet: map[string]string{"memoryDomain": node},
file: file,
tagSet: map[string]string{"memoryDomain": node},
previousValues: make(map[string]int64),
})
}
@@ -102,23 +111,27 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
return
}
now := time.Now()
timeDiff := now.Sub(m.lastTimestamp).Seconds()
m.lastTimestamp = now
for i := range m.topology {
// Loop for all NUMA domains
t := &m.topology[i]
now := time.Now()
file, err := os.Open(t.file)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
return
continue
}
scanner := bufio.NewScanner(file)
// Read line by line
for scanner.Scan() {
split := strings.Fields(scanner.Text())
line := scanner.Text()
split := strings.Fields(line)
if len(split) != 2 {
continue
}
@@ -130,18 +143,38 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
continue
}
y, err := lp.NewMessage(
"numastats_"+key,
t.tagSet,
m.meta,
map[string]interface{}{"value": value},
now,
)
if err == nil {
output <- y
if m.config.SendAbsoluteValues {
msg, err := lp.NewMessage(
"numastats_"+key,
t.tagSet,
m.meta,
map[string]interface{}{"value": value},
now,
)
if err == nil {
output <- msg
}
}
if m.config.SendDerivedValues {
prev, ok := t.previousValues[key]
if ok {
rate := float64(value-prev) / timeDiff
msg, err := lp.NewMessage(
"numastats_"+key+"_rate",
t.tagSet,
m.meta,
map[string]interface{}{"value": rate},
now,
)
if err == nil {
output <- msg
}
}
t.previousValues[key] = value
}
}
file.Close()
}
}

View File

@@ -2,7 +2,10 @@
## `numastat` collector
```json
"numastats": {}
"numastats": {
"send_abs_values" : true,
"send_derived_values" : true
}
```
The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html>
@@ -15,3 +18,9 @@ Metrics:
* `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
* `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
* `numastats_numa_hit_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_numa_miss_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_numa_foreign_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_local_node_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_other_node_rate` (if `send_derived_values == true`): Derived rate value per second.
* `numastats_interleave_hit_rate` (if `send_derived_values == true`): Derived rate value per second.

View File

@@ -9,20 +9,29 @@ import (
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
)
// running average power limit (RAPL) monitoring attributes for a zone
// Only for Intel systems
type RAPLZoneInfo struct {
energy int64 // current reading of the energy counter in micro joules
maxEnergyRange int64 // Range of the above energy counter in micro-joules
energyTimestamp time.Time // timestamp when energy counter was read
energyFilepath string // path to a file containing the zones current energy counter in micro joules
shortTermFilepath string // path to short term power limit
longTermFilepath string // path to long term power limit
enabledFilepath string // path to check whether limits are enabled
name string
// tags describing the RAPL zone:
// * zone_name, subzone_name: e.g. psys, dram, core, uncore, package-0
// * zone_id: e.g. 0:1 (zone 0 sub zone 1)
tags map[string]string
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
// type=socket for dram, core, uncore, package-* and type=node for psys
// type-id=socket id
tags map[string]string
}
type RAPLCollector struct {
@@ -33,12 +42,40 @@ type RAPLCollector struct {
// * 0:1 for zone 0 subzone 1
ExcludeByID []string `json:"exclude_device_by_id,omitempty"`
// Exclude names for RAPL zones, e.g. psys, dram, core, uncore, package-0
ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
SkipEnergyReading bool `json:"skip_energy_reading,omitempty"`
SkipLimitsReading bool `json:"skip_limits_reading,omitempty"`
OnlyEnabledLimits bool `json:"only_enabled_limits,omitempty"`
}
RAPLZoneInfo []RAPLZoneInfo
raplZoneInfo []RAPLZoneInfo
meta map[string]string // default meta information
}
// Get the path to the power limit file for zone selectable by limit name
// Common limit names for Intel systems are
// - long_term
// - short_term
// Does not support AMD as AMD systems do not provide the power limits
// through sysfs
func ZoneLimitFile(folder string, limit_name string) string {
nameGlob := filepath.Join(folder, "constraint_*_name")
candidates, err := filepath.Glob(nameGlob)
if err == nil {
for _, c := range candidates {
if v, err := os.ReadFile(c); err == nil {
if strings.TrimSpace(string(v)) == limit_name {
var i int
n, err := fmt.Sscanf(filepath.Base(c), "constraint_%d_name", &i)
if err == nil && n == 1 {
return filepath.Join(folder, fmt.Sprintf("constraint_%d_power_limit_uw", i))
}
}
}
}
}
return ""
}
// Init initializes the running average power limit (RAPL) collector
func (m *RAPLCollector) Init(config json.RawMessage) error {
@@ -58,6 +95,9 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
}
// Read in the JSON configuration
m.config.SkipEnergyReading = false
m.config.SkipLimitsReading = false
m.config.OnlyEnabledLimits = true
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
@@ -83,50 +123,62 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// readZoneInfo reads RAPL monitoring attributes for a zone given by zonePath
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
readZoneInfo := func(zonePath string) (z struct {
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
ok bool // Are all information available?
name string // zones name e.g. psys, dram, core, uncore, package-0
energyFilepath string // path to a file containing the zones current energy counter in micro joules
energy int64 // current reading of the energy counter in micro joules
energyTimestamp time.Time // timestamp when energy counter was read
maxEnergyRange int64 // Range of the above energy counter in micro-joules
shortTermFilepath string
longTermFilepath string
enabledFilepath string
}) {
// zones name e.g. psys, dram, core, uncore, package-0
foundName := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "name")); err == nil {
foundName = true
z.name = strings.TrimSpace(string(v))
}
// path to a file containing the zones current energy counter in micro joules
z.energyFilepath = filepath.Join(zonePath, "energy_uj")
// current reading of the energy counter in micro joules
foundEnergy := false
if v, err := os.ReadFile(z.energyFilepath); err == nil {
// timestamp when energy counter was read
z.energyTimestamp = time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
foundEnergy = true
z.energy = i
if os.Geteuid() == 0 && (!m.config.SkipEnergyReading) {
// path to a file containing the zones current energy counter in micro joules
z.energyFilepath = filepath.Join(zonePath, "energy_uj")
// current reading of the energy counter in micro joules
if v, err := os.ReadFile(z.energyFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
z.energy = i
// timestamp when energy counter was read
z.energyTimestamp = time.Now()
}
} else {
cclog.ComponentError(m.name, "Cannot read energy file for ", z.name, ":", err.Error())
}
// Range of the above energy counter in micro-joules
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
z.maxEnergyRange = i
}
}
} else {
cclog.ComponentInfo(m.name, "Energy readings for", zonePath, "disabled")
}
// Range of the above energy counter in micro-joules
foundMaxEnergyRange := false
if v, err :=
os.ReadFile(
filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
foundMaxEnergyRange = true
z.maxEnergyRange = i
if !m.config.SkipLimitsReading {
z.shortTermFilepath = ZoneLimitFile(zonePath, "short_term")
if _, err := os.Stat(z.shortTermFilepath); err != nil {
z.shortTermFilepath = ""
}
z.longTermFilepath = ZoneLimitFile(zonePath, "long_term")
if _, err := os.Stat(z.longTermFilepath); err != nil {
z.longTermFilepath = ""
}
z.enabledFilepath = filepath.Join(zonePath, "enabled")
} else {
cclog.ComponentInfo(m.name, "Power limit readings for", zonePath, "disabled")
}
// Are all information available?
z.ok = foundName && foundEnergy && foundMaxEnergyRange
return
}
@@ -143,25 +195,42 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
for _, zonePath := range zonesPath {
zoneID := strings.TrimPrefix(zonePath, zonePrefix)
zonetags := make(map[string]string)
z := readZoneInfo(zonePath)
if z.ok &&
!isIDExcluded[zoneID] &&
if !isIDExcluded[zoneID] &&
!isNameExcluded[z.name] {
si := RAPLZoneInfo{
tags: make(map[string]string),
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
shortTermFilepath: z.shortTermFilepath,
longTermFilepath: z.longTermFilepath,
enabledFilepath: z.enabledFilepath,
name: z.name,
}
si.tags["type"] = "node"
si.tags["type-id"] = "0"
var pid int = 0
if strings.HasPrefix(z.name, "package-") {
n, err := fmt.Sscanf(z.name, "package-%d", &pid)
if err == nil && n == 1 {
si.tags["type-id"] = fmt.Sprintf("%d", pid)
si.tags["type"] = "socket"
}
si.name = "pkg"
}
// Add RAPL monitoring attributes for a zone
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID,
"zone_name": z.name,
},
energyFilepath: z.energyFilepath,
energy: z.energy,
energyTimestamp: z.energyTimestamp,
maxEnergyRange: z.maxEnergyRange,
})
if _, ok1 := si.tags["type"]; ok1 {
if _, ok2 := si.tags["type-id"]; ok2 {
m.raplZoneInfo = append(m.raplZoneInfo, si)
zonetags["type"] = si.tags["type"]
zonetags["type-id"] = si.tags["type-id"]
}
}
}
// find all sub zones for the given zone
@@ -174,29 +243,32 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
for _, subZonePath := range subZonesPath {
subZoneID := strings.TrimPrefix(subZonePath, subZonePrefix)
sz := readZoneInfo(subZonePath)
if len(zoneID) > 0 && len(z.name) > 0 &&
sz.ok &&
!isIDExcluded[zoneID+":"+subZoneID] &&
!isNameExcluded[sz.name] {
m.RAPLZoneInfo =
append(
m.RAPLZoneInfo,
RAPLZoneInfo{
tags: map[string]string{
"id": zoneID + ":" + subZoneID,
"zone_name": z.name,
"sub_zone_name": sz.name,
},
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
})
si := RAPLZoneInfo{
tags: zonetags,
energyFilepath: sz.energyFilepath,
energy: sz.energy,
energyTimestamp: sz.energyTimestamp,
maxEnergyRange: sz.maxEnergyRange,
shortTermFilepath: sz.shortTermFilepath,
longTermFilepath: sz.longTermFilepath,
enabledFilepath: sz.enabledFilepath,
name: sz.name,
}
if _, ok1 := si.tags["type"]; ok1 {
if _, ok2 := si.tags["type-id"]; ok2 {
m.raplZoneInfo = append(m.raplZoneInfo, si)
}
}
}
}
}
if m.RAPLZoneInfo == nil {
if m.raplZoneInfo == nil {
return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
}
@@ -205,7 +277,7 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
cclog.ComponentDebug(
m.name,
"initialized",
len(m.RAPLZoneInfo),
len(m.raplZoneInfo),
"zones with running average power limit (RAPL) monitoring attributes")
m.init = true
@@ -216,40 +288,89 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
for i := range m.RAPLZoneInfo {
p := &m.RAPLZoneInfo[i]
for i := range m.raplZoneInfo {
p := &m.raplZoneInfo[i]
// Read current value of the energy counter in micro joules
if v, err := os.ReadFile(p.energyFilepath); err == nil {
energyTimestamp := time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
energy := i
if os.Geteuid() == 0 && (!m.config.SkipEnergyReading) {
// Read current value of the energy counter in micro joules
if v, err := os.ReadFile(p.energyFilepath); err == nil {
energyTimestamp := time.Now()
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
energy := i
// Compute average power (Δ energy / Δ time)
energyDiff := energy - p.energy
if energyDiff < 0 {
// Handle overflow:
// ( p.maxEnergyRange - p.energy ) + energy
// = p.maxEnergyRange + ( energy - p.energy )
// = p.maxEnergyRange + diffEnergy
energyDiff += p.maxEnergyRange
// Compute average power (Δ energy / Δ time)
energyDiff := energy - p.energy
if energyDiff < 0 {
// Handle overflow:
// ( p.maxEnergyRange - p.energy ) + energy
// = p.maxEnergyRange + ( energy - p.energy )
// = p.maxEnergyRange + diffEnergy
energyDiff += p.maxEnergyRange
}
timeDiff := energyTimestamp.Sub(p.energyTimestamp)
averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
y, err := lp.NewMetric(
fmt.Sprintf("rapl_%s_average_power", p.name),
p.tags,
m.meta,
averagePower,
energyTimestamp)
if err == nil {
output <- y
}
e, err := lp.NewMetric(
fmt.Sprintf("rapl_%s_energy", p.name),
p.tags,
m.meta,
float64(energyDiff)*1e-3,
energyTimestamp)
if err == nil {
e.AddMeta("unit", "Joules")
output <- e
}
// Save current energy counter state
p.energy = energy
p.energyTimestamp = energyTimestamp
}
timeDiff := energyTimestamp.Sub(p.energyTimestamp)
averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
y, err := lp.NewMessage(
"rapl_average_power",
p.tags,
m.meta,
map[string]interface{}{"value": averagePower},
energyTimestamp)
if err == nil {
output <- y
}
}
// https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#constraints
if !m.config.SkipLimitsReading {
skip := false
if m.config.OnlyEnabledLimits {
if v, err := os.ReadFile(p.enabledFilepath); err == nil {
if strings.TrimSpace(string(v)) == "0" {
skip = true
}
}
}
if !skip {
if len(p.shortTermFilepath) > 0 {
if v, err := os.ReadFile(p.shortTermFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
name := fmt.Sprintf("rapl_%s_limit_short_term", p.name)
y, err := lp.NewMetric(name, p.tags, m.meta, i/1e6, time.Now())
if err == nil {
output <- y
}
}
}
}
// Save current energy counter state
p.energy = energy
p.energyTimestamp = energyTimestamp
if len(p.longTermFilepath) > 0 {
if v, err := os.ReadFile(p.longTermFilepath); err == nil {
if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
name := fmt.Sprintf("rapl_%s_limit_long_term", p.name)
y, err := lp.NewMetric(name, p.tags, m.meta, i/1e6, time.Now())
if err == nil {
output <- y
}
}
}
}
}
}
}

View File

@@ -1,18 +1,23 @@
# Running average power limit (RAPL) metric collector
## `rapl` collector
This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>.
The Likwid metric collector provides similar functionality.
## Configuration
This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html>.
```json
"rapl": {
"exclude_device_by_id": ["0:1", "0:2"],
"exclude_device_by_name": ["psys"]
"exclude_device_by_name": ["psys"],
"skip_energy_reading": false,
"skip_limits_reading": false,
"only_enabled_limits": true
}
```
## Metrics
Metrics:
* `rapl_<domain>_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement
* `rapl_<domain>_energy`: Difference from the last measurement
* `rapl_<domain>_limit_short_term`: Short term powercap setting for the domain
* `rapl_<domain>_limit_long_term`: Long term powercap setting for the domain
* `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement
Only the `rapl_<domain>_average_power` and `rapl_<domain>_energy` metrics require root-permissions. The limits can be read as user. Some domains have limits available but they are not enabled. By default, only enabled domain limits are collected.
Energy and power measurments can also be done with the Likwid metric collector.

36
go.mod
View File

@@ -1,11 +1,12 @@
module github.com/ClusterCockpit/cc-metric-collector
go 1.21.1
go 1.23.0
toolchain go1.22.1
toolchain go1.23.2
require (
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1
github.com/ClusterCockpit/cc-units v0.4.0
github.com/ClusterCockpit/go-rocm-smi v0.3.0
github.com/NVIDIA/go-nvml v0.12.0-2
@@ -13,33 +14,36 @@ require (
github.com/expr-lang/expr v1.16.9
github.com/fsnotify/fsnotify v1.7.0
github.com/gorilla/mux v1.8.1
github.com/influxdata/influxdb-client-go/v2 v2.13.0
github.com/influxdata/influxdb-client-go/v2 v2.14.0
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
github.com/influxdata/line-protocol/v2 v2.2.1
github.com/nats-io/nats.go v1.36.0
github.com/prometheus/client_golang v1.19.0
github.com/nats-io/nats.go v1.39.0
github.com/prometheus/client_golang v1.20.5
github.com/stmcginnis/gofish v0.15.0
github.com/tklauser/go-sysconf v0.3.13
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8
golang.org/x/sys v0.18.0
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f
golang.org/x/sys v0.28.0
)
require (
github.com/ClusterCockpit/cc-backend v1.4.2 // indirect
github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/cespare/xxhash/v2 v2.2.0 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/google/uuid v1.6.0 // indirect
github.com/klauspost/compress v1.17.7 // indirect
github.com/nats-io/nkeys v0.4.7 // indirect
github.com/klauspost/compress v1.17.9 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/nats-io/nkeys v0.4.9 // indirect
github.com/nats-io/nuid v1.0.1 // indirect
github.com/oapi-codegen/runtime v1.1.1 // indirect
github.com/prometheus/client_model v0.6.0 // indirect
github.com/prometheus/common v0.49.0 // indirect
github.com/prometheus/procfs v0.12.0 // indirect
github.com/prometheus/client_model v0.6.1 // indirect
github.com/prometheus/common v0.55.0 // indirect
github.com/prometheus/procfs v0.15.1 // indirect
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
github.com/shopspring/decimal v1.3.1 // indirect
github.com/tklauser/numcpus v0.7.0 // indirect
golang.org/x/crypto v0.21.0 // indirect
golang.org/x/net v0.22.0 // indirect
google.golang.org/protobuf v1.33.0 // indirect
golang.org/x/crypto v0.31.0 // indirect
golang.org/x/net v0.31.0 // indirect
google.golang.org/protobuf v1.35.2 // indirect
)

69
go.sum
View File

@@ -1,5 +1,9 @@
github.com/ClusterCockpit/cc-backend v1.4.2 h1:kTOzqkh9N0564N9nqQThnSs7TAfg8RLgvSm00e5HtIc=
github.com/ClusterCockpit/cc-backend v1.4.2/go.mod h1:g8TNHXe4AXej26snu2//jO3mUF980elT93iV/k11O/c=
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900 h1:6+WNav16uWTEDC09hkZKEHfBhtc91p/ZcjgCtyntuIg=
github.com/ClusterCockpit/cc-energy-manager v0.0.0-20240709142550-dd446f7ab900/go.mod h1:EbYeC5t+Y0kW1Q1pP2n9zMqbeYEJITG8YGvAUihXVn4=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1 h1:dz9j0g2cod8+SMDjuoIY6ISpiHHeekhX6yQaeiwiwJw=
github.com/ClusterCockpit/cc-lib v0.1.0-beta.1/go.mod h1:kXMskla1i5ZSfXW0vVRIHgGeXMU5zu2PzYOYnUaOr80=
github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
@@ -17,8 +21,8 @@ github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -39,8 +43,8 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
github.com/influxdata/influxdb-client-go/v2 v2.13.0 h1:ioBbLmR5NMbAjP4UVA5r9b5xGjpABD7j65pI8kFphDM=
github.com/influxdata/influxdb-client-go/v2 v2.13.0/go.mod h1:k+spCbt9hcvqvUiz0sr5D8LolXHqAAOfPw9v/RIRHl4=
github.com/influxdata/influxdb-client-go/v2 v2.14.0 h1:AjbBfJuq+QoaXNcrova8smSjwJdUHnwvfjMF71M1iI4=
github.com/influxdata/influxdb-client-go/v2 v2.14.0/go.mod h1:Ahpm3QXKMJslpXl3IftVLVezreAUtBOTZssDrjZEFHI=
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
@@ -51,8 +55,8 @@ github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxks
github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
github.com/klauspost/compress v1.17.7 h1:ehO88t2UGzQK66LMdE8tibEd1ErmzZjNEqWkjLAKQQg=
github.com/klauspost/compress v1.17.7/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA=
github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
@@ -60,10 +64,14 @@ github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/nats-io/nats.go v1.36.0 h1:suEUPuWzTSse/XhESwqLxXGuj8vGRuPRoG7MoRN/qyU=
github.com/nats-io/nats.go v1.36.0/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
github.com/nats-io/nkeys v0.4.7 h1:RwNJbbIdYCoClSDNY7QVKZlyb/wfT6ugvFCiKy6vDvI=
github.com/nats-io/nkeys v0.4.7/go.mod h1:kqXRgRDPlGy7nGaEDMuYzmiJCIAAWDK0IMBtDmGD0nc=
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
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/nats-io/nats.go v1.39.0 h1:2/yg2JQjiYYKLwDuBzV0FbB2sIV+eFNkEevlRi4n9lI=
github.com/nats-io/nats.go v1.39.0/go.mod h1:MgRb8oOdigA6cYpEPhXJuRVH6UE/V4jblJ2jQ27IXYM=
github.com/nats-io/nkeys v0.4.9 h1:qe9Faq2Gxwi6RZnZMXfmGMZkg3afLLOtrU+gDZJ35b0=
github.com/nats-io/nkeys v0.4.9/go.mod h1:jcMqs+FLG+W5YO36OX6wFIFcmpdAns+w1Wm6D3I/evE=
github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
@@ -71,16 +79,18 @@ github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmt
github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU=
github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k=
github.com/prometheus/client_model v0.6.0 h1:k1v3CzpSRUTrKMppY35TLwPvxHqBu0bYgxZzqGIgaos=
github.com/prometheus/client_model v0.6.0/go.mod h1:NTQHnmxFpouOD0DpvP4XujX3CdOAGQPoaGhyTchlyt8=
github.com/prometheus/common v0.49.0 h1:ToNTdK4zSnPVJmh698mGFkDor9wBI/iGaJy5dbH1EgI=
github.com/prometheus/common v0.49.0/go.mod h1:Kxm+EULxRbUkjGU6WFsQqo3ORzB4tyKvlWFOE9mB2sE=
github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y=
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/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc=
github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8=
github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
github.com/prometheus/procfs v0.15.1/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/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4=
github.com/santhosh-tekuri/jsonschema/v5 v5.3.1/go.mod h1:uToXkOrWAZ6/Oc07xWQrPOhJotwFIyu2bBVN41fcDUY=
github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
@@ -92,26 +102,27 @@ github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpE
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4=
github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8 h1:yixxcjnhBmY0nkL253HFVIm0JsFHwrHdT3Yh6szTnfY=
golang.org/x/exp v0.0.0-20240613232115-7f521ea00fb8/go.mod h1:jj3sYF3dwk5D+ghuXyeI3r5MFf+NT2An6/9dOA95KSI=
golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f h1:oFMYAjX0867ZD2jcNiLBrI9BdpmEkvPyi5YrBGXbamg=
golang.org/x/exp v0.0.0-20250215185904-eff6e970281f/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
golang.org/x/net v0.31.0 h1:68CPQngjLL0r2AlUKiSxtQFKvzRVbnzLwMUn5SzcLHo=
golang.org/x/net v0.31.0/go.mod h1:P4fl1q7dY2hnZFxEk4pPSkDHF+QqjitcnDjUQyMM+pM=
golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
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 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@@ -40,7 +40,7 @@ type metricRouterConfig struct {
NormalizeUnits bool `json:"normalize_units"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix"` // Add prefix that should be applied to the metrics
// dropMetrics map[string]bool // Internal map for O(1) lookup
MessageProcessor json.RawMessage `json:"process_message,omitempty"`
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
}
// Metric router data structure

View File

@@ -22,27 +22,27 @@ type messageProcessorTagConfig struct {
}
type messageProcessorConfig struct {
StageOrder []string `json:"stage_order,omitempty"` // List of stages to execute them in the specified order and to skip unrequired ones
DropMessages []string `json:"drop_messages,omitempty"` // List of metric names to drop. For fine-grained dropping use drop_messages_if
DropMessagesIf []string `json:"drop_messages_if,omitempty"` // List of evaluatable terms to drop messages
RenameMessages map[string]string `json:"rename_messages,omitempty"` // Map of metric names to rename
RenameMessagesIf map[string]string `json:"rename_messages_if,omitempty"` // Map to rename metric name based on a condition
NormalizeUnits bool `json:"normalize_units,omitempty"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix,omitempty"` // Add prefix that should be applied to the messages
AddTagsIf []messageProcessorTagConfig `json:"add_tags_if"` // List of tags that are added when the condition is met
DelTagsIf []messageProcessorTagConfig `json:"delete_tags_if"` // List of tags that are removed when the condition is met
AddMetaIf []messageProcessorTagConfig `json:"add_meta_if"` // List of meta infos that are added when the condition is met
DelMetaIf []messageProcessorTagConfig `json:"delete_meta_if"` // List of meta infos that are removed when the condition is met
AddFieldIf []messageProcessorTagConfig `json:"add_field_if"` // List of fields that are added when the condition is met
DelFieldIf []messageProcessorTagConfig `json:"delete_field_if"` // List of fields that are removed when the condition is met
DropByType []string `json:"drop_by_message_type"` // List of message types that should be dropped
MoveTagToMeta []messageProcessorTagConfig `json:"move_tag_to_meta_if"`
MoveTagToField []messageProcessorTagConfig `json:"move_tag_to_field_if"`
MoveMetaToTag []messageProcessorTagConfig `json:"move_meta_to_tag_if"`
MoveMetaToField []messageProcessorTagConfig `json:"move_meta_to_field_if"`
MoveFieldToTag []messageProcessorTagConfig `json:"move_field_to_tag_if"`
MoveFieldToMeta []messageProcessorTagConfig `json:"move_field_to_meta_if"`
AddBaseEnv map[string]interface{} `json:"add_base_env"`
StageOrder []string `json:"stage_order,omitempty"` // List of stages to execute them in the specified order and to skip unrequired ones
DropMessages []string `json:"drop_messages,omitempty"` // List of metric names to drop. For fine-grained dropping use drop_messages_if
DropMessagesIf []string `json:"drop_messages_if,omitempty"` // List of evaluatable terms to drop messages
RenameMessages map[string]string `json:"rename_messages,omitempty"` // Map of metric names to rename
RenameMessagesIf map[string]string `json:"rename_messages_if,omitempty"` // Map to rename metric name based on a condition
NormalizeUnits bool `json:"normalize_units,omitempty"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix,omitempty"` // Add prefix that should be applied to the messages
AddTagsIf []messageProcessorTagConfig `json:"add_tags_if,omitempty"` // List of tags that are added when the condition is met
DelTagsIf []messageProcessorTagConfig `json:"delete_tags_if,omitempty"` // List of tags that are removed when the condition is met
AddMetaIf []messageProcessorTagConfig `json:"add_meta_if,omitempty"` // List of meta infos that are added when the condition is met
DelMetaIf []messageProcessorTagConfig `json:"delete_meta_if,omitempty"` // List of meta infos that are removed when the condition is met
AddFieldIf []messageProcessorTagConfig `json:"add_field_if,omitempty"` // List of fields that are added when the condition is met
DelFieldIf []messageProcessorTagConfig `json:"delete_field_if,omitempty"` // List of fields that are removed when the condition is met
DropByType []string `json:"drop_by_message_type,omitempty"` // List of message types that should be dropped
MoveTagToMeta []messageProcessorTagConfig `json:"move_tag_to_meta_if,omitempty"`
MoveTagToField []messageProcessorTagConfig `json:"move_tag_to_field_if,omitempty"`
MoveMetaToTag []messageProcessorTagConfig `json:"move_meta_to_tag_if,omitempty"`
MoveMetaToField []messageProcessorTagConfig `json:"move_meta_to_field_if,omitempty"`
MoveFieldToTag []messageProcessorTagConfig `json:"move_field_to_tag_if,omitempty"`
MoveFieldToMeta []messageProcessorTagConfig `json:"move_field_to_meta_if,omitempty"`
AddBaseEnv map[string]interface{} `json:"add_base_env,omitempty"`
}
type messageProcessor struct {

View File

@@ -13,7 +13,6 @@ import (
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
)
const HTTP_RECEIVER_PORT = "8080"
@@ -151,80 +150,22 @@ func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
}
}
if r.sink != nil {
d := influx.NewDecoder(req.Body)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
buf := make([]byte, 0, req.ContentLength)
len, err := req.Body.Read(buf)
if err == nil && len > 0 {
messages, err := lp.FromBytes(buf)
if err != nil {
msg := "ServerHttp: Failed to decode measurement: " + err.Error()
msg := "ServerHttp: Failed to decode messages: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "ServerHttp: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
for _, y := range messages {
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil {
r.sink <- m
}
if key == nil {
break
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "ServerHttp: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "ServerHttp: Failed to decode time stamp: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
y, _ := lp.NewMessage(
string(measurement),
tags,
nil,
fields,
t,
)
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil {
r.sink <- m
}
}
// Check for IO errors
err := d.Err()
if err != nil {
msg := "ServerHttp: Failed to decode: " + err.Error()
cclog.ComponentError(r.name, msg)
http.Error(w, msg, http.StatusInternalServerError)
return
}
}

View File

@@ -5,20 +5,18 @@ import (
"errors"
"fmt"
"os"
"time"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
nats "github.com/nats-io/nats.go"
)
type NatsReceiverConfig struct {
defaultReceiverConfig
Addr string `json:"address"`
Port string `json:"port"`
Subject string `json:"subject"`
Addr string `json:"address"`
Port string `json:"port"`
Subject string `json:"subject"`
User string `json:"user,omitempty"`
Password string `json:"password,omitempty"`
NkeyFile string `json:"nkey_file,omitempty"`
@@ -42,67 +40,15 @@ func (r *NatsReceiver) Start() {
func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
if r.sink != nil {
d := influx.NewDecoderWithBytes(m.Data)
for d.Next() {
// Decode measurement name
measurement, err := d.Measurement()
if err != nil {
msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
// Decode tags
tags := make(map[string]string)
for {
key, value, err := d.NextTag()
if err != nil {
msg := "_NatsReceive: Failed to decode tag: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
if key == nil {
break
}
tags[string(key)] = string(value)
}
// Decode fields
fields := make(map[string]interface{})
for {
key, value, err := d.NextField()
if err != nil {
msg := "_NatsReceive: Failed to decode field: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
if key == nil {
break
}
fields[string(key)] = value.Interface()
}
// Decode time stamp
t, err := d.Time(influx.Nanosecond, time.Time{})
if err != nil {
msg := "_NatsReceive: Failed to decode time: " + err.Error()
cclog.ComponentError(r.name, msg)
return
}
y, err := lp.NewMessage(
string(measurement),
tags,
nil,
fields,
t,
)
if err == nil {
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil && r.sink != nil {
r.sink <- m
}
messages, err := lp.FromBytes(m.Data)
if err != nil {
msg := "_NatsReceive: Failed to decode messages: " + err.Error()
cclog.ComponentError(r.name, msg)
}
for _, y := range messages {
m, err := r.mp.ProcessMessage(y)
if err == nil && m != nil && r.sink != nil {
r.sink <- m
}
}
}

175
scripts/generate_docs.sh Executable file
View File

@@ -0,0 +1,175 @@
#!/bin/bash -l
SRCDIR="$(pwd)"
DESTDIR="$1"
if [ -z "$DESTDIR" ]; then
echo "Destination folder not provided"
exit 1
fi
COLLECTORS=$(find "${SRCDIR}/collectors" -name "*Metric.md")
SINKS=$(find "${SRCDIR}/sinks" -name "*Sink.md")
RECEIVERS=$(find "${SRCDIR}/receivers" -name "*Receiver.md")
# Collectors
mkdir -p "${DESTDIR}/collectors"
for F in $COLLECTORS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/collectors/${FNAME}"
cat << EOF >> "${DESTDIR}/collectors/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Collector, ${FNAME/Metric.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/collectors/${FNAME}"
done
if [ -e "${SRCDIR}/collectors/README.md" ]; then
cat << EOF > "${DESTDIR}/collectors/_index.md"
---
title: cc-metric-collector's collectors
description: Documentation of cc-metric-collector's collectors
categories: [cc-metric-collector]
tags: [cc-metric-collector, Collector, General]
weight: 40
---
EOF
cat "${SRCDIR}/collectors/README.md" >> "${DESTDIR}/collectors/_index.md"
fi
# Sinks
mkdir -p "${DESTDIR}/sinks"
for F in $SINKS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/sinks/${FNAME}"
cat << EOF >> "${DESTDIR}/sinks/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Sink, ${FNAME/Sink.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/sinks/${FNAME}"
done
if [ -e "${SRCDIR}/collectors/README.md" ]; then
cat << EOF > "${DESTDIR}/sinks/_index.md"
---
title: cc-metric-collector's sinks
description: Documentation of cc-metric-collector's sinks
categories: [cc-metric-collector]
tags: [cc-metric-collector, Sink, General]
weight: 40
---
EOF
cat "${SRCDIR}/sinks/README.md" >> "${DESTDIR}/sinks/_index.md"
fi
# Receivers
mkdir -p "${DESTDIR}/receivers"
for F in $RECEIVERS; do
echo "$F"
FNAME=$(basename "$F")
TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
echo "'${TITLE//\`/}'"
if [ "${TITLE}" == "" ]; then continue; fi
rm --force "${DESTDIR}/receivers/${FNAME}"
cat << EOF >> "${DESTDIR}/receivers/${FNAME}"
---
title: ${TITLE//\`/}
description: >
Toplevel ${FNAME/.md/}
categories: [cc-metric-collector]
tags: [cc-metric-collector, Receiver, ${FNAME/Receiver.md/}]
weight: 2
---
EOF
cat "$F" >> "${DESTDIR}/receivers/${FNAME}"
done
if [ -e "${SRCDIR}/receivers/README.md" ]; then
cat << EOF > "${DESTDIR}/receivers/_index.md"
---
title: cc-metric-collector's receivers
description: Documentation of cc-metric-collector's receivers
categories: [cc-metric-collector]
tags: [cc-metric-collector, Receiver, General]
weight: 40
---
EOF
cat "${SRCDIR}/receivers/README.md" >> "${DESTDIR}/receivers/_index.md"
fi
mkdir -p "${DESTDIR}/internal/metricRouter"
if [ -e "${SRCDIR}/internal/metricRouter/README.md" ]; then
cat << EOF > "${DESTDIR}/internal/metricRouter/_index.md"
---
title: cc-metric-collector's router
description: Documentation of cc-metric-collector's router
categories: [cc-metric-collector]
tags: [cc-metric-collector, Router, General]
weight: 40
---
EOF
cat "${SRCDIR}/internal/metricRouter/README.md" >> "${DESTDIR}/internal/metricRouter/_index.md"
fi
if [ -e "${SRCDIR}/README.md" ]; then
cat << EOF > "${DESTDIR}/_index.md"
---
title: cc-metric-collector
description: Documentation of cc-metric-collector
categories: [cc-metric-collector]
tags: [cc-metric-collector, General]
weight: 40
---
EOF
cat "${SRCDIR}/README.md" >> "${DESTDIR}/_index.md"
sed -i -e 's+README.md+_index.md+g' "${DESTDIR}/_index.md"
fi
mkdir -p "${DESTDIR}/pkg/messageProcessor"
if [ -e "${SRCDIR}/pkg/messageProcessor/README.md" ]; then
cat << EOF > "${DESTDIR}/pkg/messageProcessor/_index.md"
---
title: cc-metric-collector's message processor
description: Documentation of cc-metric-collector's message processor
categories: [cc-metric-collector]
tags: [cc-metric-collector, Message Processor]
weight: 40
---
EOF
cat "${SRCDIR}/pkg/messageProcessor/README.md" >> "${DESTDIR}/pkg/messageProcessor/_index.md"
fi