Consistent hasing has played a fundamental role as a data router and a load balancer in various fields, such as distributed database, cloud infrastructure, and peer-to-peer network. However, the existing consistent hashing schemes can't meet the requirements simultaneously, including full consistency, scalability, small memory footprint, low update time and low query complexity. Thus, We propose DxHash, a scalable consistent hashing algorithm based on the pseudo-random sequence. For the scenario of distributed storage, there are two optimizations based on DXHash are proposed. First, the Weighted DxHash can adjust the workloads on arbitrary nodes. Second, the Asymmetric Replica Strategy (ARS) is combining the replica strategy in distributed storage with the scaleup process to improve the availability of the system and reduce the remapping rate. The evaluation indicates that compared with the state-of-art works, DxHash achieves significant improvements on the 5 requirements. Even with 50% failure ratio, DxHash still can complete 16.5 million queries per second. What's more, the two optimizations both achieve their own results.

Flash-based disk cache has been widely used in indurstry in the last decade, such as flashcache (facebook, 2010) [9], bcache (opensource, 2013) [1]. These cache systems typically use commercial SSDs to store and manage cache data. However, these flash-based disk cache systems are unfriendly to write-intensive application because of the special physical characteristic of the NAND flash memory. Recently, more and more new storage devices and emulators have come out. Benifiting from these works, the paper introduces a write-friendly flash-based disk cache system, called WLFC (Write Less in Flash-based Cache) which mainly makes three contributions. First is proposing a new flash-based disk cache system by combining the Open channel SSDs with log structure. Second is proposing a new replacement algorithm for OCSSD cache to determine weather the data should be evicted by the unused area size of the data bucket. Third is that WLFC saves as little metadata as possible both to ensure the consistency after power failure and to reduce the overhead of SSD and DRAM. Our experiments show that WLFC can significantly reduce the write latency by 70%, increase the throughput up to 4.5x, and remove 88.9% unnecessary erase operations at most.