STAC-24393: Remove timeout for the restore operations (#21)

Author: viliakov

cmd/clickhouse/check_and_finalize.go

@@ -15,8 +15,7 @@ import (
 )
 
 const (
-	defaultRestoreTimeout = 30 * time.Minute
-	defaultPollInterval   = 10 * time.Second
+	defaultPollInterval = 10 * time.Second
 )
 
 // Check-and-finalize command flags
@@ -117,7 +116,7 @@ func waitAndFinalize(appCtx *app.Context, chClient clickhouse.Interface, operati
 		}
 	}
 
-	if err := restore.WaitForAPIRestore(checkStatusFn, defaultPollInterval, defaultRestoreTimeout, appCtx.Logger); err != nil {
+	if err := restore.WaitForAPIRestore(checkStatusFn, defaultPollInterval, appCtx.Logger); err != nil {
 		return err
 	}
 

cmd/elasticsearch/check_and_finalize.go

@@ -105,7 +105,7 @@ func waitAndFinalize(appCtx *app.Context, repository, snapshotName string) error
 		return appCtx.ESClient.GetRestoreStatus(repository, snapshotName)
 	}
 
-	if err := restore.WaitForAPIRestore(checkStatusFn, 0, 0, appCtx.Logger); err != nil {
+	if err := restore.WaitForAPIRestore(checkStatusFn, 0, appCtx.Logger); err != nil {
 		return err
 	}
 

internal/orchestration/restore/apirestore.go

@@ -8,7 +8,6 @@ import (
 )
 
 const (
-	defaultAPIRestoreTimeout      = 30 * time.Minute
 	defaultAPIStatusCheckInterval = 10 * time.Second
 )
 
@@ -18,39 +17,30 @@ const (
 func WaitForAPIRestore(
 	checkStatusFn func() (string, bool, error),
 	interval time.Duration,
-	timeout time.Duration,
 	log *logger.Logger,
 ) error {
 	if interval == 0 {
 		interval = defaultAPIStatusCheckInterval
 	}
-	if timeout == 0 {
-		timeout = defaultAPIRestoreTimeout
-	}
 
-	timeoutChan := time.After(timeout)
 	ticker := time.NewTicker(interval)
 	defer ticker.Stop()
 
 	for {
-		select {
-		case <-timeoutChan:
-			return fmt.Errorf("timeout waiting for restore to complete")
-		case <-ticker.C:
-			statusMsg, isComplete, err := checkStatusFn()
-			if err != nil {
-				return fmt.Errorf("failed to check restore status: %w", err)
-			}
+		<-ticker.C
+		statusMsg, isComplete, err := checkStatusFn()
+		if err != nil {
+			return fmt.Errorf("failed to check restore status: %w", err)
+		}
 
-			log.Debugf("Restore status: %s (complete: %v)", statusMsg, isComplete)
+		log.Debugf("Restore status: %s (complete: %v)", statusMsg, isComplete)
 
-			if isComplete {
-				if statusMsg == "SUCCESS" || statusMsg == "PARTIAL" {
-					log.Debugf("Restore completed successfully")
-					return nil
-				}
-				return fmt.Errorf("restore failed with status: %s", statusMsg)
+		if isComplete {
+			if statusMsg == "SUCCESS" || statusMsg == "PARTIAL" {
+				log.Debugf("Restore completed successfully")
+				return nil
 			}
+			return fmt.Errorf("restore failed with status: %s", statusMsg)
 		}
 	}
 }

internal/orchestration/restore/job.go

@@ -9,44 +9,38 @@ import (
 )
 
 const (
-	defaultJobCompletionTimeout   = 30 * time.Minute
 	defaultJobStatusCheckInterval = 10 * time.Second
 )
 
 // WaitForJobCompletion waits for a Kubernetes job to complete
 func WaitForJobCompletion(k8sClient *k8s.Client, namespace, jobName string, log *logger.Logger) error {
-	timeout := time.After(defaultJobCompletionTimeout)
 	ticker := time.NewTicker(defaultJobStatusCheckInterval)
 	defer ticker.Stop()
 
 	for {
-		select {
-		case <-timeout:
-			return fmt.Errorf("timeout waiting for job to complete")
-		case <-ticker.C:
-			job, err := k8sClient.GetJob(namespace, jobName)
-			if err != nil {
-				return fmt.Errorf("failed to get job status: %w", err)
-			}
+		<-ticker.C
+		job, err := k8sClient.GetJob(namespace, jobName)
+		if err != nil {
+			return fmt.Errorf("failed to get job status: %w", err)
+		}
 
-			if job.Status.Succeeded > 0 {
-				return nil
-			}
+		if job.Status.Succeeded > 0 {
+			return nil
+		}
 
-			if job.Status.Failed > 0 {
-				// Get and print logs from failed job
-				log.Println()
-				log.Errorf("Job failed. Fetching logs...")
-				log.Println()
-				if err := PrintJobLogs(k8sClient, namespace, jobName, log); err != nil {
-					log.Warningf("Failed to fetch job logs: %v", err)
-				}
-				return fmt.Errorf("job failed")
+		if job.Status.Failed > 0 {
+			// Get and print logs from failed job
+			log.Println()
+			log.Errorf("Job failed. Fetching logs...")
+			log.Println()
+			if err := PrintJobLogs(k8sClient, namespace, jobName, log); err != nil {
+				log.Warningf("Failed to fetch job logs: %v", err)
 			}
-
-			log.Debugf("Job status: Active=%d, Succeeded=%d, Failed=%d",
-				job.Status.Active, job.Status.Succeeded, job.Status.Failed)
+			return fmt.Errorf("job failed")
 		}
+
+		log.Debugf("Job status: Active=%d, Succeeded=%d, Failed=%d",
+			job.Status.Active, job.Status.Succeeded, job.Status.Failed)
 	}
 }