To address the problems that the resource is surplus, the resource utilization rate is low and the cost is unreasonably high for virtual machines in the scientific application of DAG(directed acyclic graph), a novel DAG scientific workflow scheduling algorithm based on CPC(critical path cut) was proposed. In the algorithm, the CPC technology was adopted to circularly find the unallocated task which is finished at last; the biggest connected subgraph was found from the graph constructed by the whole unallocated tasks; the critical path of this subgraph was calculated and the task set on the critical path was scheduled to the performance-matched virtual machine to execute. Meanwhile, the isolated tasks were used to fill in the idle slots of the virtual machines, such that the resource utilization could be improved. Experimental results demonstrate that, the proposed CPC algorithm can effectively reduce the execution cost of the scientific workflows while satisfying the deadline constraint in mean time. 