Merge pull request #6824 from devtron-labs/ea-fail-fix-main

fix: error handler correction

Author: prkhrkat

client/telemetry/TelemetryEventClient.go

@@ -133,17 +133,29 @@ func NewTelemetryEventClientImpl(logger *zap.SugaredLogger, client *http.Client,
 
 func (impl *TelemetryEventClientImpl) GetCloudProvider() (string, error) {
 	// assumption: the IMDS server will be reachable on startup
+	// Return cached value or "unknown" if identification is still in progress
 	if len(impl.telemetryConfig.cloudProvider) == 0 {
-		provider, err := impl.cloudProviderIdentifierService.IdentifyProvider()
-		if err != nil {
-			impl.logger.Errorw("exception while getting cluster provider", "error", err)
-			return "", err
-		}
-		impl.telemetryConfig.cloudProvider = provider
+		// Return unknown for now, background identification will update this
+		return "unknown", nil
 	}
 	return impl.telemetryConfig.cloudProvider, nil
 }
 
+// identifyCloudProviderAsync runs cloud provider identification in background
+func (impl *TelemetryEventClientImpl) identifyCloudProviderAsync() {
+	impl.logger.Info("Starting cloud provider identification in background")
+
+	provider, err := impl.cloudProviderIdentifierService.IdentifyProvider()
+	if err != nil {
+		impl.logger.Errorw("exception while getting cluster provider", "error", err)
+		impl.telemetryConfig.cloudProvider = "unknown"
+		return
+	}
+
+	impl.telemetryConfig.cloudProvider = provider
+	impl.logger.Infow("Cloud provider identified", "provider", provider)
+}
+
 func (impl *TelemetryEventClientImpl) StopCron() {
 	impl.cron.Stop()
 }
@@ -341,6 +353,10 @@ func (impl *TelemetryEventClientImpl) GetTelemetryMetaInfo() (*TelemetryMetaInfo
 
 func (impl *TelemetryEventClientImpl) SendTelemetryInstallEventEA() (*TelemetryEventType, error) {
 	ucid, err := impl.getUCIDAndCheckIsOptedOut(context.Background())
+
+	// Start cloud provider identification in background to avoid blocking startup
+	go impl.identifyCloudProviderAsync()
+
 	if err != nil {
 		impl.logger.Errorw("exception while getting unique client id", "error", err)
 		return nil, err

cmd/external-app/externalApp.go

@@ -20,11 +20,12 @@ import (
 	"context"
 	"errors"
 	"fmt"
-	posthogTelemetry "github.com/devtron-labs/common-lib/telemetry"
 	"net/http"
 	"os"
 	"time"
 
+	posthogTelemetry "github.com/devtron-labs/common-lib/telemetry"
+
 	authMiddleware "github.com/devtron-labs/authenticator/middleware"
 	"github.com/devtron-labs/common-lib/middlewares"
 	"github.com/devtron-labs/devtron/client/telemetry"
@@ -71,21 +72,31 @@ func (app *App) Start() {
 	app.MuxRouter.Init()
 	//authEnforcer := casbin2.Create()
 
-	_, err := app.telemetry.SendTelemetryInstallEventEA()
-
-	if err != nil {
-		app.Logger.Warnw("telemetry installation success event failed", "err", err)
-	}
+	// Send telemetry event asynchronously to avoid blocking startup
+	go func() {
+		_, err := app.telemetry.SendTelemetryInstallEventEA()
+		if err != nil {
+			app.Logger.Warnw("telemetry installation success event failed", "err", err)
+		}
+	}()
 	server := &http.Server{Addr: fmt.Sprintf(":%d", port), Handler: authMiddleware.Authorizer(app.sessionManager, user.WhitelistChecker, app.userService.CheckUserStatusAndUpdateLoginAudit)(app.MuxRouter.Router)}
 	app.MuxRouter.Router.Use(middleware.PrometheusMiddleware)
 	app.MuxRouter.Router.Use(middlewares.Recovery)
 	app.server = server
 
-	err = server.ListenAndServe()
-	if err != nil && !errors.Is(err, http.ErrServerClosed) {
-		app.Logger.Errorw("error in startup", "err", err)
-		os.Exit(2)
-	}
+	// Start server in goroutine to make it non-blocking
+	go func() {
+		app.Logger.Info("HTTP server starting to listen")
+		err := server.ListenAndServe()
+		if err != nil && !errors.Is(err, http.ErrServerClosed) {
+			app.Logger.Errorw("error in startup", "err", err)
+			os.Exit(2)
+		}
+	}()
+
+	// Give server a moment to start listening
+	time.Sleep(1 * time.Second)
+	app.Logger.Info("HTTP server should be ready for health checks")
 }
 
 func (app *App) Stop() {
@@ -98,7 +109,10 @@ func (app *App) Stop() {
 
 	timeoutContext, _ := context.WithTimeout(context.Background(), 5*time.Second)
 	app.Logger.Infow("closing router")
-	err := app.server.Shutdown(timeoutContext)
+	var err error
+	if app.server != nil {
+		err = app.server.Shutdown(timeoutContext)
+	}
 	if err != nil {
 		app.Logger.Errorw("error in mux router shutdown", "err", err)
 	}