Cheetah: An efficient flat addressing scheme for fast query services in cloud computing
Yu Hua · 2016
Cloud computing generally needs to handle large amounts of data in a real-time manner. Typical metrics include fast write and query performance. However, existing cloud systems fail to efficiently offer fast query and write services due to two main reasons. One is the design separation between query and write operations. Most schemes mainly optimize one aspect. The other is the lack of cost-efficient data analytics, which leads to the identical resource consumption for each data item. In order to address the two problems and efficiently support fast query and write services, this paper proposes a novel flat-addressing scheme, called Cheetah. The idea behind Cheetah is to leverage efficient online data compression to reduce the amounts of data to be written, and meantime make use of a flat-addressing cuckoo hashing scheme to support fast query service. In practice, conventional cuckoo hashing schemes suffer from the endless loops, thus not only leading to insertion failure but also causing long operation latency. In order to alleviate the endless loops in item insertion, we use extra space to temporarily store the items that cause hash collisions, which are often shared by multiple loops. In order to further improve system performance, we prefetch the collision data in a batch to further reduce the probability of the occurrence of endless loops, thus offering fast query services to identify the searched items. Extensive experimental results demonstrate that the flat-addressing Cheetah can efficiently support query services in the cloud.