mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2025-07-28 23:56:08 +02:00
Merge develop branch into main (#123)
* Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
This commit is contained in:
@@ -10,15 +10,16 @@ import (
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
||||
influx "github.com/influxdata/line-protocol/v2/lineprotocol"
|
||||
)
|
||||
|
||||
const HTTP_RECEIVER_PORT = "8080"
|
||||
|
||||
type HttpReceiverConfig struct {
|
||||
Type string `json:"type"`
|
||||
defaultReceiverConfig
|
||||
Addr string `json:"address"`
|
||||
Port string `json:"port"`
|
||||
Path string `json:"path"`
|
||||
@@ -39,7 +40,7 @@ type HttpReceiverConfig struct {
|
||||
|
||||
type HttpReceiver struct {
|
||||
receiver
|
||||
meta map[string]string
|
||||
//meta map[string]string
|
||||
config HttpReceiverConfig
|
||||
server *http.Server
|
||||
wg sync.WaitGroup
|
||||
@@ -85,8 +86,20 @@ func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
|
||||
if r.config.useBasicAuth && len(r.config.Password) == 0 {
|
||||
return errors.New("basic authentication requires password")
|
||||
}
|
||||
msgp, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
return fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
r.mp = msgp
|
||||
if len(r.config.MessageProcessor) > 0 {
|
||||
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
r.mp.AddAddMetaByCondition("true", "source", r.name)
|
||||
|
||||
r.meta = map[string]string{"source": r.name}
|
||||
//r.meta = map[string]string{"source": r.name}
|
||||
p := r.config.Path
|
||||
if !strings.HasPrefix(p, "/") {
|
||||
p = "/" + p
|
||||
@@ -137,80 +150,82 @@ func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
|
||||
return
|
||||
}
|
||||
}
|
||||
if r.sink != nil {
|
||||
d := influx.NewDecoder(req.Body)
|
||||
for d.Next() {
|
||||
|
||||
d := influx.NewDecoder(req.Body)
|
||||
for d.Next() {
|
||||
|
||||
// Decode measurement name
|
||||
measurement, err := d.Measurement()
|
||||
if err != nil {
|
||||
msg := "ServerHttp: Failed to decode measurement: " + 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()
|
||||
// Decode measurement name
|
||||
measurement, err := d.Measurement()
|
||||
if err != nil {
|
||||
msg := "ServerHttp: Failed to decode tag: " + err.Error()
|
||||
msg := "ServerHttp: Failed to decode measurement: " + err.Error()
|
||||
cclog.ComponentError(r.name, msg)
|
||||
http.Error(w, msg, http.StatusInternalServerError)
|
||||
return
|
||||
}
|
||||
if key == nil {
|
||||
break
|
||||
}
|
||||
tags[string(key)] = string(value)
|
||||
}
|
||||
|
||||
// Decode fields
|
||||
fields := make(map[string]interface{})
|
||||
for {
|
||||
key, value, err := d.NextField()
|
||||
// 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
|
||||
}
|
||||
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 field: " + err.Error()
|
||||
msg := "ServerHttp: Failed to decode time stamp: " + 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{})
|
||||
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 time stamp: " + err.Error()
|
||||
msg := "ServerHttp: Failed to decode: " + err.Error()
|
||||
cclog.ComponentError(r.name, msg)
|
||||
http.Error(w, msg, http.StatusInternalServerError)
|
||||
return
|
||||
}
|
||||
|
||||
y, _ := lp.New(
|
||||
string(measurement),
|
||||
tags,
|
||||
r.meta,
|
||||
fields,
|
||||
t,
|
||||
)
|
||||
|
||||
if r.sink != nil {
|
||||
r.sink <- y
|
||||
}
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
w.WriteHeader(http.StatusOK)
|
||||
|
@@ -13,9 +13,10 @@ import (
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
"github.com/ClusterCockpit/cc-metric-collector/pkg/hostlist"
|
||||
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
||||
)
|
||||
|
||||
type IPMIReceiverClientConfig struct {
|
||||
@@ -31,11 +32,13 @@ type IPMIReceiverClientConfig struct {
|
||||
Password string // Password to use for authentication
|
||||
CLIOptions []string // Additional command line options for ipmi-sensors
|
||||
isExcluded map[string]bool // is metric excluded
|
||||
mp mp.MessageProcessor
|
||||
}
|
||||
|
||||
type IPMIReceiver struct {
|
||||
receiver
|
||||
config struct {
|
||||
defaultReceiverConfig
|
||||
Interval time.Duration
|
||||
|
||||
// Client config for each IPMI hosts
|
||||
@@ -43,10 +46,11 @@ type IPMIReceiver struct {
|
||||
}
|
||||
|
||||
// Storage for static information
|
||||
meta map[string]string
|
||||
//meta map[string]string
|
||||
|
||||
done chan bool // channel to finish / stop IPMI receiver
|
||||
wg sync.WaitGroup // wait group for IPMI receiver
|
||||
mp mp.MessageProcessor
|
||||
}
|
||||
|
||||
// doReadMetrics reads metrics from all configure IPMI hosts.
|
||||
@@ -213,7 +217,7 @@ func (r *IPMIReceiver) doReadMetric() {
|
||||
continue
|
||||
}
|
||||
|
||||
y, err := lp.New(
|
||||
y, err := lp.NewMessage(
|
||||
metric,
|
||||
map[string]string{
|
||||
"hostname": host,
|
||||
@@ -230,7 +234,14 @@ func (r *IPMIReceiver) doReadMetric() {
|
||||
},
|
||||
time.Now())
|
||||
if err == nil {
|
||||
r.sink <- y
|
||||
mc, err := clientConfig.mp.ProcessMessage(y)
|
||||
if err == nil && mc != nil {
|
||||
m, err := r.mp.ProcessMessage(mc)
|
||||
if err == nil && m != nil {
|
||||
r.sink <- m
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
@@ -296,11 +307,12 @@ func (r *IPMIReceiver) Close() {
|
||||
// NewIPMIReceiver creates a new instance of the redfish receiver
|
||||
// Initialize the receiver by giving it a name and reading in the config JSON
|
||||
func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
var err error
|
||||
r := new(IPMIReceiver)
|
||||
|
||||
// Config options from config file
|
||||
configJSON := struct {
|
||||
Type string `json:"type"`
|
||||
defaultReceiverConfig
|
||||
|
||||
// How often the IPMI sensor metrics should be read and send to the sink (default: 30 s)
|
||||
IntervalString string `json:"interval,omitempty"`
|
||||
@@ -331,7 +343,8 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
||||
|
||||
// Additional command line options for ipmi-sensors
|
||||
CLIOptions []string `json:"cli_options,omitempty"`
|
||||
CLIOptions []string `json:"cli_options,omitempty"`
|
||||
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
|
||||
} `json:"client_config"`
|
||||
}{
|
||||
// Set defaults values
|
||||
@@ -347,8 +360,15 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
// Create done channel
|
||||
r.done = make(chan bool)
|
||||
|
||||
p, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
r.mp = p
|
||||
|
||||
// Set static information
|
||||
r.meta = map[string]string{"source": r.name}
|
||||
//r.meta = map[string]string{"source": r.name}
|
||||
r.mp.AddAddMetaByCondition("true", "source", r.name)
|
||||
|
||||
// Read the IPMI receiver specific JSON config
|
||||
if len(config) > 0 {
|
||||
@@ -360,12 +380,18 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
}
|
||||
}
|
||||
|
||||
if len(r.config.MessageProcessor) > 0 {
|
||||
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
// Convert interval string representation to duration
|
||||
var err error
|
||||
|
||||
r.config.Interval, err = time.ParseDuration(configJSON.IntervalString)
|
||||
if err != nil {
|
||||
err := fmt.Errorf(
|
||||
"Failed to parse duration string interval='%s': %w",
|
||||
"failed to parse duration string interval='%s': %w",
|
||||
configJSON.IntervalString,
|
||||
err,
|
||||
)
|
||||
@@ -506,6 +532,16 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
for _, key := range configJSON.ExcludeMetrics {
|
||||
isExcluded[key] = true
|
||||
}
|
||||
p, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
if len(clientConfigJSON.MessageProcessor) > 0 {
|
||||
err = p.FromConfigJSON(clientConfigJSON.MessageProcessor)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
r.config.ClientConfigs = append(
|
||||
r.config.ClientConfigs,
|
||||
@@ -520,6 +556,7 @@ func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
Password: password,
|
||||
CLIOptions: cliOptions,
|
||||
isExcluded: isExcluded,
|
||||
mp: p,
|
||||
})
|
||||
}
|
||||
|
||||
|
@@ -1,11 +1,15 @@
|
||||
package receivers
|
||||
|
||||
import (
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
"encoding/json"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
||||
)
|
||||
|
||||
type defaultReceiverConfig struct {
|
||||
Type string `json:"type"`
|
||||
Type string `json:"type"`
|
||||
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
|
||||
}
|
||||
|
||||
// Receiver configuration: Listen address, port
|
||||
@@ -19,14 +23,15 @@ type ReceiverConfig struct {
|
||||
|
||||
type receiver struct {
|
||||
name string
|
||||
sink chan lp.CCMetric
|
||||
sink chan lp.CCMessage
|
||||
mp mp.MessageProcessor
|
||||
}
|
||||
|
||||
type Receiver interface {
|
||||
Start()
|
||||
Close() // Close / finish metric receiver
|
||||
Name() string // Name of the metric receiver
|
||||
SetSink(sink chan lp.CCMetric) // Set sink channel
|
||||
Close() // Close / finish metric receiver
|
||||
Name() string // Name of the metric receiver
|
||||
SetSink(sink chan lp.CCMessage) // Set sink channel
|
||||
}
|
||||
|
||||
// Name returns the name of the metric receiver
|
||||
@@ -35,6 +40,6 @@ func (r *receiver) Name() string {
|
||||
}
|
||||
|
||||
// SetSink set the sink channel
|
||||
func (r *receiver) SetSink(sink chan lp.CCMetric) {
|
||||
func (r *receiver) SetSink(sink chan lp.CCMessage) {
|
||||
r.sink = sink
|
||||
}
|
||||
|
@@ -4,25 +4,30 @@ import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"time"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
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 {
|
||||
Type string `json:"type"`
|
||||
defaultReceiverConfig
|
||||
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"`
|
||||
}
|
||||
|
||||
type NatsReceiver struct {
|
||||
receiver
|
||||
nc *nats.Conn
|
||||
meta map[string]string
|
||||
nc *nats.Conn
|
||||
//meta map[string]string
|
||||
config NatsReceiverConfig
|
||||
}
|
||||
|
||||
@@ -36,65 +41,68 @@ func (r *NatsReceiver) Start() {
|
||||
// _NatsReceive receives subscribed messages from the NATS server
|
||||
func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
|
||||
|
||||
d := influx.NewDecoderWithBytes(m.Data)
|
||||
for d.Next() {
|
||||
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()
|
||||
// Decode measurement name
|
||||
measurement, err := d.Measurement()
|
||||
if err != nil {
|
||||
msg := "_NatsReceive: Failed to decode tag: " + err.Error()
|
||||
msg := "_NatsReceive: Failed to decode measurement: " + 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()
|
||||
// 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 field: " + err.Error()
|
||||
msg := "_NatsReceive: Failed to decode time: " + err.Error()
|
||||
cclog.ComponentError(r.name, msg)
|
||||
return
|
||||
}
|
||||
if key == nil {
|
||||
break
|
||||
|
||||
y, _ := lp.NewMessage(
|
||||
string(measurement),
|
||||
tags,
|
||||
nil,
|
||||
fields,
|
||||
t,
|
||||
)
|
||||
|
||||
m, err := r.mp.ProcessMessage(y)
|
||||
if err == nil && m != nil {
|
||||
r.sink <- m
|
||||
}
|
||||
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, _ := lp.New(
|
||||
string(measurement),
|
||||
tags,
|
||||
r.meta,
|
||||
fields,
|
||||
t,
|
||||
)
|
||||
|
||||
if r.sink != nil {
|
||||
r.sink <- y
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -109,6 +117,7 @@ func (r *NatsReceiver) Close() {
|
||||
|
||||
// NewNatsReceiver creates a new Receiver which subscribes to messages from a NATS server
|
||||
func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
var uinfo nats.Option = nil
|
||||
r := new(NatsReceiver)
|
||||
r.name = fmt.Sprintf("NatsReceiver(%s)", name)
|
||||
|
||||
@@ -127,16 +136,40 @@ func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
len(r.config.Subject) == 0 {
|
||||
return nil, errors.New("not all configuration variables set required by NatsReceiver")
|
||||
}
|
||||
p, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
r.mp = p
|
||||
if len(r.config.MessageProcessor) > 0 {
|
||||
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
// Set metadata
|
||||
r.meta = map[string]string{
|
||||
"source": r.name,
|
||||
// r.meta = map[string]string{
|
||||
// "source": r.name,
|
||||
// }
|
||||
r.mp.AddAddMetaByCondition("true", "source", r.name)
|
||||
|
||||
if len(r.config.User) > 0 && len(r.config.Password) > 0 {
|
||||
uinfo = nats.UserInfo(r.config.User, r.config.Password)
|
||||
} else if len(r.config.NkeyFile) > 0 {
|
||||
_, err := os.Stat(r.config.NkeyFile)
|
||||
if err == nil {
|
||||
uinfo = nats.UserCredentials(r.config.NkeyFile)
|
||||
} else {
|
||||
cclog.ComponentError(r.name, "NKEY file", r.config.NkeyFile, "does not exist: %v", err.Error())
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
// Connect to NATS server
|
||||
url := fmt.Sprintf("nats://%s:%s", r.config.Addr, r.config.Port)
|
||||
cclog.ComponentDebug(r.name, "NewNatsReceiver", url, "Subject", r.config.Subject)
|
||||
if nc, err := nats.Connect(url); err == nil {
|
||||
if nc, err := nats.Connect(url, uinfo); err == nil {
|
||||
r.nc = nc
|
||||
} else {
|
||||
r.nc = nil
|
||||
|
@@ -10,7 +10,10 @@ The `nats` receiver can be used receive metrics from the NATS network. The `nats
|
||||
"type": "nats",
|
||||
"address" : "nats-server.example.org",
|
||||
"port" : "4222",
|
||||
"subject" : "subject"
|
||||
"subject" : "subject",
|
||||
"user": "natsuser",
|
||||
"password": "natssecret",
|
||||
"nkey_file": "/path/to/nkey_file"
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -19,6 +22,9 @@ The `nats` receiver can be used receive metrics from the NATS network. The `nats
|
||||
- `address`: Address of the NATS control server
|
||||
- `port`: Port of the NATS control server
|
||||
- `subject`: Subscribes to this subject and receive metrics
|
||||
- `user`: Connect to nats using this user
|
||||
- `password`: Connect to nats using this password
|
||||
- `nkey_file`: Path to credentials file with NKEY
|
||||
|
||||
### Debugging
|
||||
|
||||
|
@@ -13,7 +13,7 @@ import (
|
||||
"time"
|
||||
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
)
|
||||
|
||||
type PrometheusReceiverConfig struct {
|
||||
@@ -74,7 +74,7 @@ func (r *PrometheusReceiver) Start() {
|
||||
}
|
||||
value, err := strconv.ParseFloat(lineSplit[1], 64)
|
||||
if err == nil {
|
||||
y, err := lp.New(name, tags, r.meta, map[string]interface{}{"value": value}, t)
|
||||
y, err := lp.NewMessage(name, tags, r.meta, map[string]interface{}{"value": value}, t)
|
||||
if err == nil {
|
||||
r.sink <- y
|
||||
}
|
||||
|
@@ -7,7 +7,7 @@ import (
|
||||
"sync"
|
||||
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
)
|
||||
|
||||
var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
|
||||
@@ -19,14 +19,14 @@ var AvailableReceivers = map[string]func(name string, config json.RawMessage) (R
|
||||
|
||||
type receiveManager struct {
|
||||
inputs []Receiver
|
||||
output chan lp.CCMetric
|
||||
output chan lp.CCMessage
|
||||
config []json.RawMessage
|
||||
}
|
||||
|
||||
type ReceiveManager interface {
|
||||
Init(wg *sync.WaitGroup, receiverConfigFile string) error
|
||||
AddInput(name string, rawConfig json.RawMessage) error
|
||||
AddOutput(output chan lp.CCMetric)
|
||||
AddOutput(output chan lp.CCMessage)
|
||||
Start()
|
||||
Close()
|
||||
}
|
||||
@@ -93,7 +93,7 @@ func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error
|
||||
return nil
|
||||
}
|
||||
|
||||
func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
|
||||
func (rm *receiveManager) AddOutput(output chan lp.CCMessage) {
|
||||
rm.output = output
|
||||
for _, r := range rm.inputs {
|
||||
r.SetSink(rm.output)
|
||||
|
@@ -13,9 +13,10 @@ import (
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
||||
"github.com/ClusterCockpit/cc-metric-collector/pkg/hostlist"
|
||||
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
||||
|
||||
// See: https://pkg.go.dev/github.com/stmcginnis/gofish
|
||||
"github.com/stmcginnis/gofish"
|
||||
@@ -42,6 +43,8 @@ type RedfishReceiverClientConfig struct {
|
||||
readSensorURLs map[string][]string
|
||||
|
||||
gofish gofish.ClientConfig
|
||||
|
||||
mp mp.MessageProcessor
|
||||
}
|
||||
|
||||
// RedfishReceiver configuration:
|
||||
@@ -49,6 +52,7 @@ type RedfishReceiver struct {
|
||||
receiver
|
||||
|
||||
config struct {
|
||||
defaultReceiverConfig
|
||||
fanout int
|
||||
Interval time.Duration
|
||||
HttpTimeout time.Duration
|
||||
@@ -79,13 +83,19 @@ func setMetricValue(value any) map[string]interface{} {
|
||||
}
|
||||
|
||||
// sendMetric sends the metric through the sink channel
|
||||
func (r *RedfishReceiver) sendMetric(name string, tags map[string]string, meta map[string]string, value any, timestamp time.Time) {
|
||||
func (r *RedfishReceiver) sendMetric(mp mp.MessageProcessor, name string, tags map[string]string, meta map[string]string, value any, timestamp time.Time) {
|
||||
|
||||
deleteEmptyTags(tags)
|
||||
deleteEmptyTags(meta)
|
||||
y, err := lp.New(name, tags, meta, setMetricValue(value), timestamp)
|
||||
y, err := lp.NewMessage(name, tags, meta, setMetricValue(value), timestamp)
|
||||
if err == nil {
|
||||
r.sink <- y
|
||||
mc, err := mp.ProcessMessage(y)
|
||||
if err == nil && mc != nil {
|
||||
m, err := r.mp.ProcessMessage(mc)
|
||||
if err == nil && m != nil {
|
||||
r.sink <- m
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -119,7 +129,7 @@ func (r *RedfishReceiver) readSensors(
|
||||
"unit": "degC",
|
||||
}
|
||||
|
||||
r.sendMetric("temperature", tags, meta, sensor.Reading, time.Now())
|
||||
r.sendMetric(clientConfig.mp, "temperature", tags, meta, sensor.Reading, time.Now())
|
||||
}
|
||||
|
||||
writeFanSpeedSensor := func(sensor *redfish.Sensor) {
|
||||
@@ -145,7 +155,7 @@ func (r *RedfishReceiver) readSensors(
|
||||
"unit": string(sensor.ReadingUnits),
|
||||
}
|
||||
|
||||
r.sendMetric("fan_speed", tags, meta, sensor.Reading, time.Now())
|
||||
r.sendMetric(clientConfig.mp, "fan_speed", tags, meta, sensor.Reading, time.Now())
|
||||
}
|
||||
|
||||
writePowerSensor := func(sensor *redfish.Sensor) {
|
||||
@@ -172,7 +182,7 @@ func (r *RedfishReceiver) readSensors(
|
||||
"unit": "watts",
|
||||
}
|
||||
|
||||
r.sendMetric("power", tags, meta, sensor.Reading, time.Now())
|
||||
r.sendMetric(clientConfig.mp, "power", tags, meta, sensor.Reading, time.Now())
|
||||
}
|
||||
|
||||
if _, ok := clientConfig.readSensorURLs[chassis.ID]; !ok {
|
||||
@@ -340,7 +350,7 @@ func (r *RedfishReceiver) readThermalMetrics(
|
||||
// ReadingCelsius shall be the current value of the temperature sensor's reading.
|
||||
value := temperature.ReadingCelsius
|
||||
|
||||
r.sendMetric("temperature", tags, meta, value, timestamp)
|
||||
r.sendMetric(clientConfig.mp, "temperature", tags, meta, value, timestamp)
|
||||
}
|
||||
|
||||
for _, fan := range thermal.Fans {
|
||||
@@ -381,7 +391,7 @@ func (r *RedfishReceiver) readThermalMetrics(
|
||||
"unit": string(fan.ReadingUnits),
|
||||
}
|
||||
|
||||
r.sendMetric("fan_speed", tags, meta, fan.Reading, timestamp)
|
||||
r.sendMetric(clientConfig.mp, "fan_speed", tags, meta, fan.Reading, timestamp)
|
||||
}
|
||||
|
||||
return nil
|
||||
@@ -479,7 +489,7 @@ func (r *RedfishReceiver) readPowerMetrics(
|
||||
}
|
||||
|
||||
for name, value := range metrics {
|
||||
r.sendMetric(name, tags, meta, value, timestamp)
|
||||
r.sendMetric(clientConfig.mp, name, tags, meta, value, timestamp)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -561,7 +571,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
|
||||
if !clientConfig.isExcluded[namePower] &&
|
||||
// Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null
|
||||
processorMetrics.ConsumedPowerWatt != 65535 {
|
||||
r.sendMetric(namePower, tags, metaPower, processorMetrics.ConsumedPowerWatt, timestamp)
|
||||
r.sendMetric(clientConfig.mp, namePower, tags, metaPower, processorMetrics.ConsumedPowerWatt, timestamp)
|
||||
}
|
||||
// Set meta data tags
|
||||
metaThermal := map[string]string{
|
||||
@@ -573,7 +583,7 @@ func (r *RedfishReceiver) readProcessorMetrics(
|
||||
nameThermal := "temperature"
|
||||
|
||||
if !clientConfig.isExcluded[nameThermal] {
|
||||
r.sendMetric(nameThermal, tags, metaThermal, processorMetrics.TemperatureCelsius, timestamp)
|
||||
r.sendMetric(clientConfig.mp, nameThermal, tags, metaThermal, processorMetrics.TemperatureCelsius, timestamp)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
@@ -776,11 +786,13 @@ func (r *RedfishReceiver) Close() {
|
||||
// NewRedfishReceiver creates a new instance of the redfish receiver
|
||||
// Initialize the receiver by giving it a name and reading in the config JSON
|
||||
func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
var err error
|
||||
r := new(RedfishReceiver)
|
||||
|
||||
// Config options from config file
|
||||
configJSON := struct {
|
||||
Type string `json:"type"`
|
||||
Type string `json:"type"`
|
||||
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
|
||||
|
||||
// Maximum number of simultaneous redfish connections (default: 64)
|
||||
Fanout int `json:"fanout,omitempty"`
|
||||
@@ -820,7 +832,8 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
DisableThermalMetrics bool `json:"disable_thermal_metrics"`
|
||||
|
||||
// Per client excluded metrics
|
||||
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
||||
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
||||
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
|
||||
} `json:"client_config"`
|
||||
}{
|
||||
// Set defaults values
|
||||
@@ -846,13 +859,24 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
p, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
r.mp = p
|
||||
if len(r.config.MessageProcessor) > 0 {
|
||||
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
// Convert interval string representation to duration
|
||||
var err error
|
||||
|
||||
r.config.Interval, err = time.ParseDuration(configJSON.IntervalString)
|
||||
if err != nil {
|
||||
err := fmt.Errorf(
|
||||
"Failed to parse duration string interval='%s': %w",
|
||||
"failed to parse duration string interval='%s': %w",
|
||||
configJSON.IntervalString,
|
||||
err,
|
||||
)
|
||||
@@ -864,7 +888,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
r.config.HttpTimeout, err = time.ParseDuration(configJSON.HttpTimeoutString)
|
||||
if err != nil {
|
||||
err := fmt.Errorf(
|
||||
"Failed to parse duration string http_timeout='%s': %w",
|
||||
"failed to parse duration string http_timeout='%s': %w",
|
||||
configJSON.HttpTimeoutString,
|
||||
err,
|
||||
)
|
||||
@@ -948,6 +972,18 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
for _, key := range configJSON.ExcludeMetrics {
|
||||
isExcluded[key] = true
|
||||
}
|
||||
p, err = mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
cclog.ComponentError(r.name, err.Error())
|
||||
return nil, err
|
||||
}
|
||||
if len(clientConfigJSON.MessageProcessor) > 0 {
|
||||
err = p.FromConfigJSON(clientConfigJSON.MessageProcessor)
|
||||
if err != nil {
|
||||
cclog.ComponentError(r.name, err.Error())
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
hostList, err := hostlist.Expand(clientConfigJSON.HostList)
|
||||
if err != nil {
|
||||
@@ -978,6 +1014,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
Endpoint: endpoint,
|
||||
HTTPClient: httpClient,
|
||||
},
|
||||
mp: p,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -1002,7 +1039,7 @@ func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
for i := range r.config.ClientConfigs {
|
||||
host := r.config.ClientConfigs[i].Hostname
|
||||
if isDuplicate[host] {
|
||||
err := fmt.Errorf("Found duplicate client config for host %s", host)
|
||||
err := fmt.Errorf("found duplicate client config for host %s", host)
|
||||
cclog.ComponentError(r.name, err)
|
||||
return nil, err
|
||||
}
|
||||
|
@@ -5,11 +5,13 @@ import (
|
||||
"fmt"
|
||||
|
||||
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
||||
mp "github.com/ClusterCockpit/cc-metric-collector/pkg/messageProcessor"
|
||||
)
|
||||
|
||||
// SampleReceiver configuration: receiver type, listen address, port
|
||||
// The defaultReceiverConfig contains the keys 'type' and 'process_messages'
|
||||
type SampleReceiverConfig struct {
|
||||
Type string `json:"type"`
|
||||
defaultReceiverConfig
|
||||
Addr string `json:"address"`
|
||||
Port string `json:"port"`
|
||||
}
|
||||
@@ -19,7 +21,6 @@ type SampleReceiver struct {
|
||||
config SampleReceiverConfig
|
||||
|
||||
// Storage for static information
|
||||
meta map[string]string
|
||||
// Use in case of own go routine
|
||||
// done chan bool
|
||||
// wg sync.WaitGroup
|
||||
@@ -79,8 +80,19 @@ func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
// The name should be chosen in such a way that different instances of SampleReceiver can be distinguished
|
||||
r.name = fmt.Sprintf("SampleReceiver(%s)", name)
|
||||
|
||||
// create new message processor
|
||||
p, err := mp.NewMessageProcessor()
|
||||
if err != nil {
|
||||
cclog.ComponentError(r.name, "Initialization of message processor failed:", err.Error())
|
||||
return nil, fmt.Errorf("initialization of message processor failed: %v", err.Error())
|
||||
}
|
||||
r.mp = p
|
||||
// Set static information
|
||||
r.meta = map[string]string{"source": r.name}
|
||||
err = r.mp.AddAddMetaByCondition("true", "source", r.name)
|
||||
if err != nil {
|
||||
cclog.ComponentError(r.name, fmt.Sprintf("Failed to add static information source=%s:", r.name), err.Error())
|
||||
return nil, fmt.Errorf("failed to add static information source=%s: %v", r.name, err.Error())
|
||||
}
|
||||
|
||||
// Set defaults in r.config
|
||||
// Allow overwriting these defaults by reading config JSON
|
||||
@@ -94,6 +106,15 @@ func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
|
||||
}
|
||||
}
|
||||
|
||||
// Add message processor config
|
||||
if len(r.config.MessageProcessor) > 0 {
|
||||
err = r.mp.FromConfigJSON(r.config.MessageProcessor)
|
||||
if err != nil {
|
||||
cclog.ComponentError(r.name, "Failed parsing JSON for message processor:", err.Error())
|
||||
return nil, fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
|
||||
}
|
||||
}
|
||||
|
||||
// Check that all required fields in the configuration are set
|
||||
// Use 'if len(r.config.Option) > 0' for strings
|
||||
|
||||
|
Reference in New Issue
Block a user