The core idea of Multi-Path Transmission Control Protocol (MPTCP) is to share network resources by distributing payload data transmission among multiple subflows. Then, multiple paths in the underlying network can be used to maximize the overall connection throughput. However, the concurrent transmission of not all subflows aggregation can improve network performance, because of the performance difference of each subflow. In this paper, we propose a new FullMesh algorithm based on Path Characteristic and Data Characteristic (PCDC), in which the Subflow Impact Factor (IF) is used as a subflow characteristic to predict the impact of the subflow on the overall throughput. Then, different path sets are adopted for different sizes of traffic. The PCDC algorithm is evaluated in the NorNet Core testbed, compared with the FullMesh algorithm. Our research results show that the PCDC algorithm can improve the network throughput, and reduce the overall completion time of small data streams.