Merge develop into main (#109)

* Add cpu_used (all-cpu_idle) to CpustatCollector * Update to line-protocol/v2 * Update runonce.yml with Golang 1.20 * Update fsnotify in LIKWID Collector * Use not a pointer to line-protocol.Encoder * Simplify Makefile * Use only as many arguments as required * Allow sum function to handle non float types * Allow values to be a slice of type float64, float32, int, int64, int32, bool * Use generic function to simplify code * Add missing case for type []int32 * Use generic function to compute minimum * Use generic function to compute maximum * Use generic function to compute average * Add error value to sumAnyType * Use generic function to compute median * For older versions of go slices is not part of the installation * Remove old entries from go.sum * Use simpler sort function * Compute metrics ib_total and ib_total_pkts * Add aggregated metrics. Add missing units * Update likwidMetric.go Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error * Completly avoid memory allocations in infinibandMetric read() * Fixed initialization: Initalization and measurements should run in the same thread * Add safe.directory to Release action * Fix path after installation to /usr/bin after installation * ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile * Switch to package slices from the golang 1.21 default library * Read file line by line * Read file line by line * Read file line by line * Use CamelCase * Use CamelCase * Fix function getNumaDomain, it always returned 0 * Avoid type conversion by using Atoi Avoid copying structs by using pointer access Increase readability with CamelCase variable names * Add caching * Cache CpuData * Cleanup * Use init function to initalize cache structure to avoid multi threading problems * Reuse information from /proc/cpuinfo * Avoid slice cloning. Directly use the cache * Add DieList * Add NumaDomainList and SMTList * Cleanup * Add comment * Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Correctly handle lists from /sys * Add Simultaneous Multithreading siblings * Replace deprecated thread_siblings_list by core_cpus_list * Reduce number of required slices * Allow to send total values per core, socket and node * Send all metrics with same time stamp calcEventsetMetrics does only computiation, counter measurement is done before * Input parameters should be float64 when evaluating to float64 * Send all metrics with same time stamp calcGlobalMetrics does only computiation, counter measurement is done before * Remove unused variable gmresults * Add comments * Updated go packages * Add build with golang 1.21 * Switch to checkout action version 4 * Switch to setup-go action version 4 * Add workflow_dispatch to allow manual run of workflow * Add workflow_dispatch to allow manual run of workflow * Add release build jobs to runonce.yml * Switch to golang 1.20 for RHEL based distributions * Use dnf to download golang * Remove golang versions before 1.20 * Upgrade Ubuntu focal -> jammy * Pipe golang tar package directly to tar * Update golang version * Fix Ubuntu version number * Add links to ipmi and redfish receivers * Fix http server addr format * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Corrected spelling * Add some comments * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Allow other fields not only field "value" * Add some basic debugging documentation * Add some basic debugging documentation * Use a lock for the flush timer * Add tags in lexical order as required by AddTag() * Only access meta data, when it gets used as tag * Use slice to store lexialicly orderd key value pairs * Increase golang version requirement to 1.20. * Avoid package cmp to allow builds with golang v1.20 * Fix: Error NVML library not found did crash cc-metric-collector with "SIGSEGV: segmentation violation" * Add config option idle_timeout * Add basic authentication support * Add basic authentication support * Avoid unneccessary memory allocations * Add documentation for send_*_total values * Use generic package maps to clone maps * Reuse flush timer * Add Influx client options * Reuse ccTopology functionality * Do not store unused topology information * Add batch_size config * Cleanup * Use stype and stype-id for the NIC in NetstatCollector * Wait for concurrent flush operations to finish * Be more verbose in error messages * Reverted previous changes. Made the code to complex without much advantages * Use line protocol encoder * Go pkg update * Stop flush timer, when immediatelly flushing * Fix: Corrected unlock access to batch slice * Add config option to specify whether to use GZip compression in influx write requests * Add asynchron send of encoder metrics * Use DefaultServeMux instead of github.com/gorilla/mux * Add config option for HTTP keep-alives * Be more strict, when parsing json * Add config option for HTTP request timeout and Retry interval * Allow more then one background send operation * Fix %sysusers_create_package args (#108) %sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165 * Add nfsiostat to list of collectors --------- Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <holgerob@gmx.de> Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
2025-08-22 18:33:00 +02:00 · 2023-12-04 12:21:26 +01:00
parent 9df1054e32
commit 6ab45dd3ec
39 changed files with 1835 additions and 1030 deletions
--- a/receivers/httpReceiver.go
+++ b/receivers/httpReceiver.go
@@ -5,15 +5,14 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io"
 	"net/http"
 	"strings"
 	"sync"
+	"time"

 	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	"github.com/gorilla/mux"
-	influx "github.com/influxdata/line-protocol"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
 )

 const HTTP_RECEIVER_PORT = "8080"
@@ -23,22 +22,39 @@ type HttpReceiverConfig struct {
 	Addr string `json:"address"`
 	Port string `json:"port"`
 	Path string `json:"path"`
+
+	// Maximum amount of time to wait for the next request when keep-alives are enabled
+	// should be larger than the measurement interval to keep the connection open
+	IdleTimeout string `json:"idle_timeout"`
+	idleTimeout time.Duration
+
+	// Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled
+	KeepAlivesEnabled bool `json:"keep_alives_enabled"`
+
+	// Basic authentication
+	Username     string `json:"username"`
+	Password     string `json:"password"`
+	useBasicAuth bool
 }

 type HttpReceiver struct {
 	receiver
-	handler *influx.MetricHandler
-	parser  *influx.Parser
-	meta    map[string]string
-	config  HttpReceiverConfig
-	router  *mux.Router
-	server  *http.Server
-	wg      sync.WaitGroup
+	meta   map[string]string
+	config HttpReceiverConfig
+	server *http.Server
+	wg     sync.WaitGroup
 }

 func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
 	r.name = fmt.Sprintf("HttpReceiver(%s)", name)
+
+	// Set default values
 	r.config.Port = HTTP_RECEIVER_PORT
+	r.config.KeepAlivesEnabled = true
+	// should be larger than the measurement interval to keep the connection open
+	r.config.IdleTimeout = "120s"
+
+	// Read config
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &r.config)
 		if err != nil {
@@ -49,20 +65,47 @@ func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
 	if len(r.config.Port) == 0 {
 		return errors.New("not all configuration variables set required by HttpReceiver")
 	}
+
+	// Check idle timeout config
+	if len(r.config.IdleTimeout) > 0 {
+		t, err := time.ParseDuration(r.config.IdleTimeout)
+		if err == nil {
+			cclog.ComponentDebug(r.name, "idleTimeout", t)
+			r.config.idleTimeout = t
+		}
+	}
+
+	// Check basic authentication config
+	if len(r.config.Username) > 0 || len(r.config.Password) > 0 {
+		r.config.useBasicAuth = true
+	}
+	if r.config.useBasicAuth && len(r.config.Username) == 0 {
+		return errors.New("basic authentication requires username")
+	}
+	if r.config.useBasicAuth && len(r.config.Password) == 0 {
+		return errors.New("basic authentication requires password")
+	}
+
 	r.meta = map[string]string{"source": r.name}
 	p := r.config.Path
 	if !strings.HasPrefix(p, "/") {
 		p = "/" + p
 	}
-	uri := fmt.Sprintf("%s:%s%s", r.config.Addr, r.config.Port, p)
-	cclog.ComponentDebug(r.name, "INIT", uri)
-	r.handler = influx.NewMetricHandler()
-	r.parser = influx.NewParser(r.handler)
-	r.parser.SetTimeFunc(DefaultTime)
+	addr := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
+	uri := addr + p
+	cclog.ComponentDebug(r.name, "INIT", "listen on:", uri)
+
+	// Register handler function r.ServerHttp for path p in the DefaultServeMux
+	http.HandleFunc(p, r.ServerHttp)
+
+	// Create http server
+	r.server = &http.Server{
+		Addr:        addr,
+		Handler:     nil, // handler to invoke, http.DefaultServeMux if nil
+		IdleTimeout: r.config.idleTimeout,
+	}
+	r.server.SetKeepAlivesEnabled(r.config.KeepAlivesEnabled)

-	r.router = mux.NewRouter()
-	r.router.Path(p).HandlerFunc(r.ServerHttp)
-	r.server = &http.Server{Addr: uri, Handler: r.router}
 	return nil
 }

@@ -79,31 +122,97 @@ func (r *HttpReceiver) Start() {
 }

 func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
+
+	// Check request method, only post method is handled
 	if req.Method != http.MethodPost {
 		http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
 		return
 	}

-	body, err := io.ReadAll(req.Body)
-	if err != nil {
-		http.Error(w, err.Error(), http.StatusInternalServerError)
-		return
-	}
-	metrics, err := r.parser.Parse(body)
-	if err != nil {
-		http.Error(w, err.Error(), http.StatusBadRequest)
+	// Check basic authentication
+	if r.config.useBasicAuth {
+		username, password, ok := req.BasicAuth()
+		if !ok || username != r.config.Username || password != r.config.Password {
+			http.Error(w, "Unauthorized", http.StatusUnauthorized)
+			return
+		}
 	}

-	for _, m := range metrics {
-		y := lp.FromInfluxMetric(m)
-		for k, v := range r.meta {
-			y.AddMeta(k, v)
+	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()
+			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 time stamp: " + 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)
 }