The high density, low power consumption non-volatile memory (NVM) provides a promising DRAM alternative for the in-memory big-data processing applications, e.g., Spark, It is significant to simulate the behaviors when NVMs are deployed into the area of big-data processing before their widespread use in market. However, existing simulation approaches are not applicable for big-data processing due to two reasons. First, some approaches require complicated hardware and/or OS supports. Second, cycle-level or function-level simulations are too time-consuming to simulate the whole software stack of big-data processing. Therefore, the complexity and expensive time cost in NVM simulation have dramatically dragged down the integrated research of big data with NVM. This paper proposes a fast and reconfigurable simulation method, called NVM Streaker, which does not need complex hardware or OS supports. It simulates NVM access costs using disturbed DRAM accesses and commonly configurable hardware parameters. It is fast since we use DRAM accesses and change its access costs to simulate NVM access costs, thus enabling to simulate the whole software stack to run Spark applications. It is reconfigurable since we enable users to configure the disturbed memory access costs, in order to simulate different NVM access costs. The experimental results show that we can simulate Spark applications with almost negligible cost and high efficiency.