feat: queue workspace reconcile if workspace health check encounters an error

fix #1325

Signed-off-by: Max batleforc <[email protected]>

Author: batleforc

controllers/workspace/devworkspace_controller.go

@@ -491,8 +491,10 @@ func (r *DevWorkspaceReconciler) Reconcile(ctx context.Context, req ctrl.Request
 	reconcileStatus.setConditionTrue(conditions.DeploymentReady, "DevWorkspace deployment ready")
 
 	serverReady, serverStatusCode, err := checkServerStatus(clusterWorkspace)
-	if err != nil {
-		return reconcile.Result{}, err
+	if shouldReturn, reconcileResult, reconcileErr := r.checkDWError(workspace, err, "Error checking server status", metrics.ReasonInfrastructureFailure, reqLogger, &reconcileStatus); shouldReturn {
+		reqLogger.Info("Waiting for DevWorkspace health check endpoint to become available")
+		reconcileStatus.setConditionFalse(dw.DevWorkspaceReady, "Waiting for workspace health check to become available")
+		return reconcileResult, reconcileErr
 	}
 	if !serverReady {
 		reqLogger.Info("Main URL server not ready", "status-code", serverStatusCode)

controllers/workspace/status.go

@@ -26,6 +26,7 @@ import (
 
 	dw "github.com/devfile/api/v2/pkg/apis/workspaces/v1alpha2"
 	"github.com/devfile/devworkspace-operator/pkg/common"
+	"github.com/devfile/devworkspace-operator/pkg/dwerrors"
 	"github.com/devfile/devworkspace-operator/pkg/provision/sync"
 
 	"github.com/go-logr/logr"
@@ -211,7 +212,7 @@ func checkServerStatus(workspace *common.DevWorkspaceWithConfig) (ok bool, respo
 
 	resp, err := healthCheckHttpClient.Get(healthz.String())
 	if err != nil {
-		return false, nil, err
+		return false, nil, &dwerrors.RetryError{Err: err, Message: "Failed to check server status", RequeueAfter: 1 * time.Second}
 	}
 	if (resp.StatusCode / 100) == 4 {
 		// Assume endpoint is unimplemented and/or * is covered with authentication.