Redynis:分布式键值存储的磁盘感知动态重分区
Redynis: Traffic-aware dynamic repartitioning for a distributed key-value store
摘要:
大多数现代数据存储往往是分布式的,以便跨多个商用硬件实例扩展数据。虽然这确保了几乎无限的存储潜力,但数据本身并不总是理想地分区,并且网络往返的成本可能导致终端用户体验在响应延迟方面的降级。正在解决的问题是使用动态重新分区算法使数据对象更接近频繁的请求源。如果目标是减轻网络延迟的开销,这一点很重要,特别是如果分区是广泛地理分布的。其目的是将这些功能带到现有的分布式键值存储产品Redis中。
英文摘要:
Most modern data stores tend to be distributed, to enable the scaling of the data across multiple instances of commodity hardware. Although this ensures a near unlimited potential for storage, the data itself is not always ideally partitioned, and the cost of a network round-trip may cause a degradation of end-user experience with respect to response latency. The problem being solved is bringing the data objects closer to the frequent sources of requests using a dynamic repartitioning algorithm. This is important if the objective is to mitigate the overhead of network latency, and especially so if the partitions are widely geo-distributed. The intention is to bring these features to an existing distributed key-value store product, Redis.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。