Improving the Performance of Distributed Storage Algorithms in Cloud Computing Environments

In response to the performance bottlenecks and challenges brought about by the integration of cloud computing, big data, the Internet of Things and other technologies, this study proposes a storage system optimization solution that integrates dynamic load balancing, elastic expansion and latency optimization. The current distributed storage system has typical problems such as load imbalance, resource waste, and high latency. It is urgent to solve the performance bottleneck problem and improve scalability and response speed. Therefore, this paper proposes a dynamic load balancing mechanism design to intelligently adjust request allocation by real-time monitoring of node resource utilization. Experiments show that the optimized system has immediate improvements in throughput, latency and scalability. The optimized system throughput increased by an average of 58.4MB/s, the average latency increased by 47.1ms, and the scalability increased by an average of 42.1s. These improvements show that the optimization measures effectively improved processing power, response time, and stability, enabling the system to better cope with high loads and large-scale applications. Based on the above research data, this paper solves the bottleneck performance characteristics of the storage system and provides an efficient and reliable solution.