Learning to Drive Software-Defined Storage
Learning to Drive Software-Defined Storage
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Jian Huang;Daixuan Li;Jinghan Sun
中科院分区：
文献类型：
--
作者：
Jian Huang;Daixuan Li;Jinghan Sun
由于制造技术的发展，诸如固态驱动器（SSD）的存储设备正变得高度可定制，以满足针对不同应用（即，软件定义存储）。然而，由于复杂的存储堆栈，使用当前的人为驱动的系统构建方法开发优化的存储设备具有挑战性。在本文中，我们提出了基于学习的方法来促进软件定义存储的开发。为了加快高效存储设备的制造，我们支持自动学习优化的硬件规格，以便为特定应用类型开发定制的存储设备。我们的初步研究表明，利用基于学习的技术来推动软件定义存储的发展是有希望的。
Thanks to the development of manufacturing technology, storage devices such as solid-state drives (SSDs) are becoming highly customizable to meet the everincreasing demands on storage performance and capacity for different applications (i.e., software-defined storage). However, it is challenging to develop optimized storage devices with current human-driven systems-building approaches, due to the complicated storage stack. In this paper, we present learning-based approaches to facilitating the development of software-defined storage. To accelerate the manufacturing of efficient storage devices, we enable the automated learning of optimized hardware specifications for developing customized storage devices for specific application types. Our preliminary study shows that utilizing learningbased techniques to drive the development of software-defined storage is promising.