Hera otel integration

.github/workflows/go.yml

@@ -7,7 +7,6 @@ on:
     branches: [ main ]
 
 jobs:
-
   build:
     runs-on: ubuntu-latest
     steps:
@@ -16,7 +15,7 @@ jobs:
       - name: Set up Go
         uses: actions/setup-go@v4
         with:
-          go-version: 1.18.2
+          go-version: 1.20.14
       - name: Install GO Modules
         run: |
           go mod tidy
@@ -37,17 +36,28 @@ jobs:
           - 3306:3306
     steps:
       - uses: actions/checkout@v3
-
       - name: Set up Go
         uses: actions/setup-go@v4
         with:
-          go-version: 1.18.2
+          go-version: 1.20.14
       - name: Install GO Modules
         run: |
           go mod tidy
           go mod download github.com/godror/godror
+      - name: Give Full Permissions to Work Directory
+        run: sudo chmod -R 777 /home/runner/work/
       - name: Build worker
         run: go install github.com/paypal/hera/worker/mysqlworker
+      - name: Check docker version
+        run: |   
+              docker version
+      - name: Install Docker Compose
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y docker-compose
+
+      - name: Verify Docker Compose Installation
+        run: docker-compose --version
       - name: System Test
         run: |
           export GOPATH="/home/runner/go"

go.mod

@@ -1,14 +1,33 @@
 module github.com/paypal/hera
 
-go 1.18
+go 1.20
 
 require (
 	github.com/go-sql-driver/mysql v1.7.1
 	github.com/godror/godror v0.26.3
 	github.com/lib/pq v1.10.3
+	go.opentelemetry.io/otel v1.24.0
+	go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.24.0
+	go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp v1.24.0
+	go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.24.0
+	go.opentelemetry.io/otel/metric v1.24.0
+	go.opentelemetry.io/otel/sdk v1.24.0
+	go.opentelemetry.io/otel/sdk/metric v1.24.0
+	go.opentelemetry.io/proto/otlp v1.2.0
+	google.golang.org/protobuf v1.34.1
 )
 
 require (
+	github.com/cenkalti/backoff/v4 v4.3.0 // indirect
 	github.com/go-logfmt/logfmt v0.5.0 // indirect
-	google.golang.org/protobuf v1.33.0 // indirect
+	github.com/go-logr/logr v1.4.2 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 // indirect
+	go.opentelemetry.io/otel/trace v1.24.0 // indirect
+	golang.org/x/net v0.26.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240520151616-dc85e6b867a5 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240515191416-fc5f0ca64291 // indirect
+	google.golang.org/grpc v1.64.0 // indirect
 )

go.sum

@@ -1,19 +1,61 @@
+github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
+github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/go-logfmt/logfmt v0.5.0 h1:TrB8swr/68K7m9CcGut2g3UOihhbcbiMAYiuTXdEih4=
 github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A=
+github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
+github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
+github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
+github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-sql-driver/mysql v1.7.1 h1:lUIinVbN1DY0xBg0eMOzmmtGoHwWBbvnWubQUrtU8EI=
 github.com/go-sql-driver/mysql v1.7.1/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
 github.com/godror/godror v0.26.3 h1:V+z+Q/OBGgmmYzuAwyJzpcn4LsPF4Ev0xHAea68V00c=
 github.com/godror/godror v0.26.3/go.mod h1:1QCn6oXh3r+IlB3DLE8V6qkHXLSHd18a3Hw7szQ9/3Y=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
-github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 h1:bkypFPDjIYGfCYD5mRBvpqxfYX1YCS1PXdKYWi8FsN0=
+github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0/go.mod h1:P+Lt/0by1T8bfcF3z737NnSbmxQAppXMRziHUxPOC8k=
 github.com/lib/pq v1.10.3 h1:v9QZf2Sn6AmjXtQeFpdoq/eaNtYP6IN+7lcrygsIAtg=
 github.com/lib/pq v1.10.3/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
-golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e h1:vcxGaoTs7kV8m5Np9uUNQin4BrLOthgV7252N8V+FwY=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+go.opentelemetry.io/otel v1.24.0 h1:0LAOdjNmQeSTzGBzduGe/rU4tZhMwL5rWgtp9Ku5Jfo=
+go.opentelemetry.io/otel v1.24.0/go.mod h1:W7b9Ozg4nkF5tWI5zsXkaKKDjdVjpD4oAt9Qi/MArHo=
+go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.24.0 h1:f2jriWfOdldanBwS9jNBdeOKAQN7b4ugAMaNu1/1k9g=
+go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.24.0/go.mod h1:B+bcQI1yTY+N0vqMpoZbEN7+XU4tNM0DmUiOwebFJWI=
+go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp v1.24.0 h1:mM8nKi6/iFQ0iqst80wDHU2ge198Ye/TfN0WBS5U24Y=
+go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp v1.24.0/go.mod h1:0PrIIzDteLSmNyxqcGYRL4mDIo8OTuBAOI/Bn1URxac=
+go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.24.0 h1:JYE2HM7pZbOt5Jhk8ndWZTUWYOVift2cHjXVMkPdmdc=
+go.opentelemetry.io/otel/exporters/stdout/stdoutmetric v1.24.0/go.mod h1:yMb/8c6hVsnma0RpsBMNo0fEiQKeclawtgaIaOp2MLY=
+go.opentelemetry.io/otel/metric v1.24.0 h1:6EhoGWWK28x1fbpA4tYTOWBkPefTDQnb8WSGXlc88kI=
+go.opentelemetry.io/otel/metric v1.24.0/go.mod h1:VYhLe1rFfxuTXLgj4CBiyz+9WYBA8pNGJgDcSFRKBco=
+go.opentelemetry.io/otel/sdk v1.24.0 h1:YMPPDNymmQN3ZgczicBY3B6sf9n62Dlj9pWD3ucgoDw=
+go.opentelemetry.io/otel/sdk v1.24.0/go.mod h1:KVrIYw6tEubO9E96HQpcmpTKDVn9gdv35HoYiQWGDFg=
+go.opentelemetry.io/otel/sdk/metric v1.24.0 h1:yyMQrPzF+k88/DbH7o4FMAs80puqd+9osbiBrJrz/w8=
+go.opentelemetry.io/otel/sdk/metric v1.24.0/go.mod h1:I6Y5FjH6rvEnTTAYQz3Mmv2kl6Ek5IIrmwTLqMrrOE0=
+go.opentelemetry.io/otel/trace v1.24.0 h1:CsKnnL4dUAr/0llH9FKuc698G04IrpWV0MQA/Y1YELI=
+go.opentelemetry.io/otel/trace v1.24.0/go.mod h1:HPc3Xr/cOApsBI154IU0OI0HJexz+aw5uPdbs3UCjNU=
+go.opentelemetry.io/proto/otlp v1.2.0 h1:pVeZGk7nXDC9O2hncA6nHldxEjm6LByfA2aN8IOkz94=
+go.opentelemetry.io/proto/otlp v1.2.0/go.mod h1:gGpR8txAl5M03pDhMC79G6SdqNV26naRm/KDsgaHD8A=
+golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ=
+golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
+golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
+golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
+golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
+golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/genproto/googleapis/api v0.0.0-20240520151616-dc85e6b867a5 h1:P8OJ/WCl/Xo4E4zoe4/bifHpSmmKwARqyqE4nW6J2GQ=
+google.golang.org/genproto/googleapis/api v0.0.0-20240520151616-dc85e6b867a5/go.mod h1:RGnPtTG7r4i8sPlNyDeikXF99hMM+hN6QMm4ooG9g2g=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240515191416-fc5f0ca64291 h1:AgADTJarZTBqgjiUzRgfaBchgYB3/WFTC80GPwsMcRI=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240515191416-fc5f0ca64291/go.mod h1:EfXuqaE1J41VCDicxHzUDm+8rk+7ZdXzHV0IhO/I6s0=
+google.golang.org/grpc v1.64.0 h1:KH3VH9y/MgNQg1dE7b3XfVK0GsPSIzJwdF617gUSbvY=
+google.golang.org/grpc v1.64.0/go.mod h1:oxjF8E3FBnjp+/gVFYdWacaLDx9na1aqy9oovLpxQYg=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
-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 v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
+google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=

lib/config.go

@@ -23,6 +23,8 @@ import (
 	"github.com/paypal/hera/cal"
 	"github.com/paypal/hera/config"
 	"github.com/paypal/hera/utility/logger"
+	otelconfig "github.com/paypal/hera/utility/logger/otel/config"
+
 	"os"
 	"path/filepath"
 	"strings"
@@ -235,7 +237,7 @@ func parseMapStrStr(encoded string) map[string]string {
 }
 
 // InitConfig initializes the configuration, both the static configuration (from hera.txt) and the dynamic configuration
-func InitConfig() error {
+func InitConfig(poolName string) error {
 	currentDir, abserr := filepath.Abs(filepath.Dir(os.Args[0]))
 
 	if abserr != nil {
@@ -486,9 +488,39 @@ func InitConfig() error {
 		gAppConfig.MaxDesiredHealthyWorkerPct = 90
 	}
 
+	//Initialize OTEL configs
+	initializeOTELConfigs(cdb, poolName)
+	if logger.GetLogger().V(logger.Info) {
+		otelconfig.OTelConfigData.Dump()
+	}
 	return nil
 }
 
+// This function takes care of initialize OTEL configuration
+func initializeOTELConfigs(cdb config.Config, poolName string) {
+	otelconfig.OTelConfigData = &otelconfig.OTelConfig{}
+	//TODO initialize the values
+	otelconfig.OTelConfigData.Enabled = cdb.GetOrDefaultBool("enable_otel", false)
+	otelconfig.OTelConfigData.SkipCalStateLog = cdb.GetOrDefaultBool("skip_cal_statelog", false)
+	otelconfig.OTelConfigData.MetricNamePrefix = cdb.GetOrDefaultString("otel_metric_prefix", "pp.occ")
+	otelconfig.OTelConfigData.Host = cdb.GetOrDefaultString("otel_agent_host", "localhost")
+	otelconfig.OTelConfigData.MetricsPort = cdb.GetOrDefaultInt("otel_agent_metrics_port", 4318)
+	otelconfig.OTelConfigData.TracePort = cdb.GetOrDefaultInt("otel_agent_trace_port", 4318)
+	otelconfig.OTelConfigData.OtelMetricGRPC = cdb.GetOrDefaultBool("otel_agent_use_grpc_metric", false)
+	otelconfig.OTelConfigData.OtelTraceGRPC = cdb.GetOrDefaultBool("otel_agent_use_grpc_trace", false)
+	otelconfig.OTelConfigData.MetricsURLPath = cdb.GetOrDefaultString("otel_agent_metrics_uri", "")
+	otelconfig.OTelConfigData.TraceURLPath = cdb.GetOrDefaultString("otel_agent_trace_uri", "")
+	otelconfig.OTelConfigData.PoolName = poolName
+	otelconfig.OTelConfigData.UseTls = cdb.GetOrDefaultBool("otel_use_tls", false)
+	otelconfig.OTelConfigData.TLSCertPath = cdb.GetOrDefaultString("otel_tls_cert_path", "")
+	otelconfig.OTelConfigData.ResolutionTimeInSec = cdb.GetOrDefaultInt("otel_resolution_time_in_sec", 1)
+	otelconfig.OTelConfigData.ExporterTimeout = cdb.GetOrDefaultInt("otel_exporter_time_in_sec", 30)
+	otelconfig.OTelConfigData.EnableRetry = cdb.GetOrDefaultBool("otel_enable_exporter_retry", false)
+	otelconfig.OTelConfigData.ResourceType = gAppConfig.StateLogPrefix
+	otelconfig.OTelConfigData.OTelErrorReportingInterval = cdb.GetOrDefaultInt("otel_error_reporting_interval_in_sec", 60)
+	otelconfig.SetOTelIngestToken(cdb.GetOrDefaultString("otel_ingest_token", ""))
+}
+
 func LogOccConfigs() {
 	whiteListConfigs := map[string]map[string]interface{}{
 		"BACKLOG": {
@@ -501,6 +533,18 @@ func LogOccConfigs() {
 			"bouncer_startup_delay":    gAppConfig.BouncerStartupDelay,
 			"bouncer_poll_interval_ms": gAppConfig.BouncerPollInterval,
 		},
+		"OTEL": {
+			"enable_otel":                          otelconfig.OTelConfigData.Enabled,
+			"otel_use_tls":                         otelconfig.OTelConfigData.UseTls,
+			"skip_cal_statelog":                    otelconfig.OTelConfigData.SkipCalStateLog,
+			"otel_agent_host":                      otelconfig.OTelConfigData.Host,
+			"otel_agent_metrics_port":              otelconfig.OTelConfigData.MetricsPort,
+			"otel_agent_trace_port":                otelconfig.OTelConfigData.TracePort,
+			"otel_agent_metrics_uri":               otelconfig.OTelConfigData.MetricsURLPath,
+			"otel_agent_trace_uri":                 otelconfig.OTelConfigData.TraceURLPath,
+			"otel_resolution_time_in_sec":          otelconfig.OTelConfigData.ResolutionTimeInSec,
+			"otel_error_reporting_interval_in_sec": otelconfig.OTelConfigData.OTelErrorReportingInterval,
+		},
 		"PROFILE": {
 			"enable_profile":      gAppConfig.EnableProfile,
 			"profile_http_port":   gAppConfig.ProfileHTTPPort,
@@ -616,6 +660,10 @@ func LogOccConfigs() {
 			if !gAppConfig.BouncerEnabled {
 				continue
 			}
+		case "OTEL":
+			if !otelconfig.OTelConfigData.Enabled {
+				continue
+			}
 		case "PROFILE":
 			if !gAppConfig.EnableProfile {
 				continue
@@ -677,7 +725,6 @@ func LogOccConfigs() {
 		}
 		evt.Completed()
 	}
-
 }
 
 // CheckOpsConfigChange checks if the ops config file needs to be reloaded and reloads it if necessary.

lib/main.go

@@ -18,8 +18,11 @@
 package lib
 
 import (
+	"context"
 	"flag"
 	"fmt"
+	otellogger "github.com/paypal/hera/utility/logger/otel"
+	otelconfig "github.com/paypal/hera/utility/logger/otel/config"
 	"math/rand"
 	"os"
 	"os/signal"
@@ -36,6 +39,9 @@ func Run() {
 	signal.Ignore(syscall.SIGPIPE)
 	mux_process_id := syscall.Getpid()
 
+	// Defer release resource in case of any abnormal exit of for application
+	defer handlePanicAndReleaseResource(mux_process_id)
+
 	namePtr := flag.String("name", "", "module name in v$session table")
 	flag.Parse()
 
@@ -50,7 +56,7 @@ func Run() {
 
 	rand.Seed(time.Now().Unix())
 
-	err := InitConfig()
+	err := InitConfig(*namePtr)
 	if err != nil {
 		if logger.GetLogger().V(logger.Alert) {
 			logger.GetLogger().Log(logger.Alert, "failed to initialize configuration:", err.Error())
@@ -106,7 +112,24 @@ func Run() {
 	caltxn.SetCorrelationID("runtxn")
 	caltxn.Completed()
 
-	GetStateLog().SetStartTime(time.Now())
+	//Initialize OTEL
+	if otelconfig.OTelConfigData.Enabled {
+		shutdownFunc, err := otellogger.Init(context.Background())
+		if err != nil {
+			logger.GetLogger().Log(logger.Alert, fmt.Sprintf("failed to initialize OTEL, err: %v", err))
+			evt := cal.NewCalEvent("OTEL_INIT", *namePtr, "2", fmt.Sprintf("erro: %v", err))
+			evt.Completed()
+			if otelconfig.OTelConfigData.SkipCalStateLog {
+				logger.GetLogger().Log(logger.Alert, fmt.Sprintf("OTEL initialization failed. Only the OTEL state-log has been enabled. It is not safe to start the server"))
+				FullShutdown()
+			}
+		}
+		GetStateLog().SetStartTime(time.Now())
+		defer otellogger.StopMetricCollection()  //Stop sending metrics data
+		defer shutdownFunc(context.Background()) //During exit from mux, this will takecare of OTEL providers clean-up
+	} else {
+		GetStateLog().SetStartTime(time.Now())
+	}
 
 	go func() {
 		sleep := time.Duration(GetConfig().ConfigReloadTimeMs)
@@ -192,9 +215,6 @@ func Run() {
 		cal.ReleaseCxtResource()
 	}()
 
-	// Defer release resource in case of any abnormal exit of for application
-	defer handlePanicAndReleaseResource(mux_process_id)
-
 	<-GetWorkerBrokerInstance().Stopped()
 }