Kubernetes has become the leading container orchestration platform due to its powerful scalability features, enabling dynamic resource management and efficient workload handling in cloud-native environments. This review examines Kubernetes scaling mechanisms at both the application and cluster levels, focusing on Horizontal Pod Autoscaler (HPA), Vertical Pod Autoscaler (VPA), and event-driven scaling with KEDA for adaptive application scaling. At the cluster level, Cluster Autoscaler (CA), Karpenter, Cluster Proportional Autoscaler (CPA), and Cluster Proportional Vertical Autoscaler (CPVA) optimize node provisioning and resource allocation. Despite these advancements, challenges persist, including reactive scaling delays, resource fragmentation, inconsistent scaling decisions across multiple autoscalers, and security vulnerabilities like Economic Denial of Sustainability (EDoS) attacks. To address these issues, emerging trends in AI-driven observability, predictive analytics, and unified autoscaling frameworks offer proactive scaling, anomaly detection, and self-healing capabilities. This review synthesizes academic research and industry practices to highlight the current state, challenges, and future directions of Kubernetes scalability, emphasizing the need for intelligent, adaptive, and secure scaling solutions.