With the rapid development of IoT technology, sensors are widely used for monitoring environmental parameters. The data collected by sensors needs to be stored, and distributed storage systems provide an excellent platform to handle this vast amount of data. To enhance data reliability and reduce storage costs, erasure coding technology can be employed within distributed storage systems. However, the process of recovering lost or damaged data inevitably generates significant cross-rack traffic. In recent years, various batch recovery methods have been designed to improve data recovery speed and reduce cross-rack recovery traffic, but they have limitations in different aspects, such as less consideration for heterogeneous cross-rack bandwidth and insufficient handling of recovery link scheduling. This paper proposes the HBRepair recovery framework, aimed at improving data recovery speed by balancing the recovery load and reducing cross-rack recovery traffic. Firstly, HBRepair strategically selects helper blocks and nodes for storing recovery blocks to find the optimal batch recovery plan. Then, it selectively and rationally schedules recovery links to saturate idle bandwidth resources and avoid network congestion. Experimental results show that by optimizing the use of cross-rack bandwidth, HBRepair can reduce cross-rack recovery time by up to 26.74%, effectively addressing the shortcomings of existing methods.