Abstract

The storage subsystem has undergone tremendous innovation in order to keep up with the ever-increasing demand for throughput. Non Volatile Memory Express (NVMe) based solid state devices are the latest development in this domain, delivering unprecedented performance in terms of latency and peak bandwidth. NVMe drives are expected to be particularly beneficial for I/O intensive applications, with databases being one of the prominent use-cases.

This paper provides the first, in-depth performance analysis of NVMe drives. Combining driver instrumentation with system monitoring tools, we present a breakdown of access times for I/O requests throughout the entire system. Furthermore, we present a detailed, quantitative analysis of all the factors contributing to the low-latency, high-throughput characteristics of NVMe drives, including the system software stack. Lastly, we characterize the performance of multiple cloud databases (both relational and NoSQL) on state-of-the-art NVMe drives, and compare that to their performance on enterprise-class SATA-based SSDs. We show that NVMe-backed database applications deliver up to 8× superior client-side performance over enterprise-class, SATA-based SSDs.

Original link: http://www.storagereview.com/sysbench_oltp_benchmark

The Sysbench OLTP application benchmark runs on top of a MySQL database running the InnoDB storage engine. The job of the storage engine is to manage the interface from the on-disk database to the applications reading and writing data to and from the storage engine. The storage engine in turn manages IO threads and logs, and it keeps an in-memory cache to minimize disk access.

为了弥补各层次存储设备之间的性能差距，缓存，在局部性原理的基础上，成为了提高系统性能的一个重要技术手段。CPU缓存就是一个非常有效的技术实现，从中，我们可以看到，缓存实现时的基本要素，比如缓存的映射方式，回写策略，替换策略，缓存一致性等。随着计算机技术的发展，缓存已经不局限于硬件实现了，在软件层的实现越来越多，作用也越来越大。在CPU缓存的实现基础上，我们从软件层的角度出发，梳理出了缓存的基本模型和缓存的一些基本架构，并且探讨了用于实现缓存设计的常见算法和策略。现实例子也非常丰富，从单机缓存系统到分布式缓存系统，我们可以看到缓存的基本要素是如何具体实现的，但同时，我们也看到了缓存设计时的一些常见问题和思考，比如缓存系统的性能问题，更新策略，缓存穿透和失效等。

关于数据库操作和管理的文章，网上文章非常多，但对于数据库系统的工作方式却少有文章介绍。本文将以关系型数据库为主展开，并采用开源的MySQL以及存储引擎InnoDB，对数据库系统的基本工作方式和一些性能考虑因素进行介绍，而对于数据库设计原理，如何实现，以及如何操作和管理数据库等不做展开说明。