feat: implement otel telemetry sdk for distributed tracing (#221)

* feat: implement otel sdk

Signed-off-by: namkyu1999 <lak9348@konkuk.ac.kr>

* fix: update endpoint

Signed-off-by: namkyu1999 <lak9348@konkuk.ac.kr>

* fix: fix context logic

Signed-off-by: namkyu1999 <lak9348@konkuk.ac.kr>

* fix: make otel optional

Signed-off-by: namkyu1999 <lak9348@konkuk.ac.kr>

* (chore): Fix the release pipeline (#224)

Signed-off-by: Shubham Chaudhary <shubham.chaudhary@harness.io>

* fix: add logs

Signed-off-by: namkyu1999 <lak9348@gmail.com>

* chore

Signed-off-by: namkyu1999 <lak9348@gmail.com>

* feat: go version from 1.20 to 1.22

Signed-off-by: namkyu1999 <lak9348@gmail.com>

---------

Signed-off-by: namkyu1999 <lak9348@konkuk.ac.kr>
Signed-off-by: Shubham Chaudhary <shubham.chaudhary@harness.io>
Signed-off-by: namkyu1999 <lak9348@gmail.com>
Co-authored-by: Shubham Chaudhary <shubham.chaudhary@harness.io>

Author: namkyu1999

.github/workflows/build.yml

@@ -84,7 +84,7 @@ jobs:
       # Install golang
       - uses: actions/setup-go@v2
         with:
-          go-version: 1.20.0
+          go-version: 1.22.0
 
       # Checkout to the latest commit
       # On specific directory/path

.github/workflows/push.yml

@@ -13,7 +13,7 @@ jobs:
       # Install golang
       - uses: actions/setup-go@v2
         with:
-          go-version: 1.20.0
+          go-version: 1.22.0
 
       # Checkout to the latest commit
       # On specific directory/path

.github/workflows/release.yml

@@ -11,7 +11,7 @@ jobs:
       # Install golang
       - uses: actions/setup-go@v2
         with:
-          go-version: 1.20.0
+          go-version: 1.22.0
 
       # Checkout to the latest commit
       # On specific directory/path

bin/runner.go

@@ -1,10 +1,16 @@
 package main
 
 import (
+	"context"
+	"errors"
+	"os"
+
 	"github.com/litmuschaos/chaos-runner/pkg/log"
+	"github.com/litmuschaos/chaos-runner/pkg/telemetry"
 	"github.com/litmuschaos/chaos-runner/pkg/utils"
 	"github.com/litmuschaos/chaos-runner/pkg/utils/analytics"
 	"github.com/sirupsen/logrus"
+	"go.opentelemetry.io/otel"
 )
 
 func init() {
@@ -17,9 +23,26 @@ func init() {
 }
 
 func main() {
+	ctx := context.Background()
+	// Set up Observability.
+	if otelExporterEndpoint := os.Getenv(telemetry.OTELExporterOTLPEndpoint); otelExporterEndpoint != "" {
+		shutdown, err := telemetry.InitOTelSDK(ctx, otelExporterEndpoint)
+		if err != nil {
+			log.Errorf("Failed to initialize OTel SDK: %v", err)
+			return
+		}
+		defer func() {
+			err = errors.Join(err, shutdown(ctx))
+		}()
+		ctx = telemetry.GetTraceParentContext()
+	}
 
 	engineDetails := utils.EngineDetails{}
 	clients := utils.ClientSets{}
+
+	ctx, span := otel.Tracer(telemetry.TracerName).Start(ctx, "ExecuteChaosRunner")
+	defer span.End()
+
 	// Getting kubeConfig and Generate ClientSets
 	if err := clients.GenerateClientSetFromKubeConfig(); err != nil {
 		log.Errorf("unable to create ClientSets, error: %v", err)
@@ -66,7 +89,7 @@ func main() {
 			continue
 		}
 		// derive the envs from the chaos experiment and override their values from chaosengine if any
-		if err := experiment.SetENV(engineDetails, clients); err != nil {
+		if err := experiment.SetENV(ctx, engineDetails, clients); err != nil {
 			log.Errorf("unable to patch ENV, error: %v", err)
 			experiment.ExperimentSkipped(utils.ExperimentEnvParseErrorReason, engineDetails, clients)
 			engineDetails.ExperimentSkippedPatchEngine(&experiment, clients)
@@ -92,7 +115,7 @@ func main() {
 		experiment.ExperimentDependencyCheck(engineDetails, clients)
 
 		// Creation of PodTemplateSpec, and Final Job
-		if err := utils.BuildingAndLaunchJob(&experiment, clients); err != nil {
+		if err := utils.BuildingAndLaunchJob(ctx, &experiment, clients); err != nil {
 			log.Errorf("unable to construct chaos experiment job, error: %v", err)
 			experiment.ExperimentSkipped(utils.ExperimentDependencyCheckReason, engineDetails, clients)
 			engineDetails.ExperimentSkippedPatchEngine(&experiment, clients)

go.mod

@@ -1,6 +1,6 @@
 module github.com/litmuschaos/chaos-runner
 
-go 1.20
+go 1.22
 
 require (
 	github.com/AdaLogics/go-fuzz-headers v0.0.0-20230811130428-ced1acdcaa24
@@ -12,39 +12,50 @@ require (
 	github.com/onsi/gomega v1.15.0
 	github.com/pkg/errors v0.9.1
 	github.com/sirupsen/logrus v1.9.3
-	github.com/stretchr/testify v1.7.0
+	github.com/stretchr/testify v1.9.0
+	go.opentelemetry.io/otel v1.27.0
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.27.0
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.27.0
+	go.opentelemetry.io/otel/sdk v1.27.0
 	k8s.io/api v0.26.0
 	k8s.io/apimachinery v0.26.0
 	k8s.io/client-go v12.0.0+incompatible
 )
 
 require (
+	github.com/cenkalti/backoff/v4 v4.3.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/evanphx/json-patch v4.11.0+incompatible // indirect
 	github.com/fsnotify/fsnotify v1.4.9 // indirect
-	github.com/go-logr/logr v1.2.3 // indirect
+	github.com/go-logr/logr v1.4.1 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/google/go-cmp v0.5.6 // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/google/gofuzz v1.1.0 // indirect
 	github.com/googleapis/gnostic v0.5.5 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 // indirect
 	github.com/imdario/mergo v0.3.12 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/kr/pretty v0.2.1 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/nxadm/tail v1.4.8 // indirect
 	github.com/palantir/stacktrace v0.0.0-20161112013806-78658fd2d177 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
-	golang.org/x/net v0.19.0 // indirect
-	golang.org/x/oauth2 v0.0.0-20210514164344-f6687ab2804c // indirect
-	golang.org/x/sys v0.15.0 // indirect
+	go.opentelemetry.io/otel/metric v1.27.0 // indirect
+	go.opentelemetry.io/otel/trace v1.27.0 // indirect
+	go.opentelemetry.io/proto/otlp v1.2.0 // indirect
+	golang.org/x/net v0.25.0 // indirect
+	golang.org/x/oauth2 v0.21.0 // indirect
+	golang.org/x/sys v0.20.0 // indirect
 	golang.org/x/term v0.15.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	golang.org/x/time v0.0.0-20210723032227-1f47c861a9ac // indirect
-	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/protobuf v1.26.0 // indirect
+	golang.org/x/text v0.15.0 // indirect
+	golang.org/x/time v0.5.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240610135401-a8a62080eff3 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240610135401-a8a62080eff3 // indirect
+	google.golang.org/grpc v1.64.0 // indirect
+	google.golang.org/protobuf v1.34.1 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
@@ -60,14 +71,11 @@ require (
 // Pinned to kubernetes-1.21.2
 replace (
 	k8s.io/api => k8s.io/api v0.21.2
-	k8s.io/apiextensions-apiserver => k8s.io/apiextensions-apiserver v0.21.2
 	k8s.io/apimachinery => k8s.io/apimachinery v0.21.2
-	k8s.io/apiserver => k8s.io/apiserver v0.21.2
 	k8s.io/cli-runtime => k8s.io/cli-runtime v0.21.2
 	k8s.io/client-go => k8s.io/client-go v0.21.2
 	k8s.io/cloud-provider => k8s.io/cloud-provider v0.21.2
 	k8s.io/cluster-bootstrap => k8s.io/cluster-bootstrap v0.21.2
-	k8s.io/code-generator => k8s.io/code-generator v0.21.2
 	k8s.io/component-base => k8s.io/component-base v0.21.2
 	k8s.io/cri-api => k8s.io/cri-api v0.21.2
 	k8s.io/csi-translation-lib => k8s.io/csi-translation-lib v0.21.2