Numerous IoT devices in IoT systems collect data concurrently, which brings great challenges to IoT time series databases to store and manage these data. NVM device has high read-write speed compared with HDD and Flash-based SSD, and it is a possible way to solve the storage bottleneck. However, there are some limitations that should be solved such as the overhead of the I/O software stack for NVM devices and the lack of optimization for IoT time series databases in a Linux environment. By analyzing the characteristics of IoT time series databases and NVM devices, we optimized the device driver of NVM in Linux and provide a new structure of a NVM device driver for IoT time series databases. A multi-queue management strategy and a lightweight load balance mechanism based on frequency were designed to improve the concurrency and efficiency of NVM device drivers. The prototype of an IoT-oriented NVM device driver named TS-PMEM was implemented based on an open-source NVM device driver. Six prototypes were used for evaluation with YCSB-TS, a test tool for time series databases. Results showed that TS-PMEM can improve write throughput of the time series databases by 18.6%, query throughput by 10.6%, and reduce the write latency by 8.3% and query latency by 6.4%.
Keywords: I/O software stack; IoT; IoT time series database; NVM storage system; storage device driver.