What-If Analysis of Page Load Time in Web Browsers Using Causal Profiling
What-If Analysis of Page Load Time in Web Browsers Using Causal Profiling
复制标题
DOI：
10.1145/3341617.3326142
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Behnam Pourghassemi;A. A. Sani-A.;Aparna Chandramowlishwaran
中科院分区：
文献类型：
--
作者：
Behnam Pourghassemi;A. A. Sani-A.;Aparna Chandramowlishwaran
Web浏览器已经成为桌面和移动的用户最常用的应用程序之一。尽管最近在网络速度和加速网页加载的若干技术（诸如推测加载、智能缓存和多线程）方面取得了进步，但浏览器仍然遭受相对长的页面加载时间（PLT）。Web应用程序由于其跨平台支持和相对简单的开发过程而受到广泛关注，因此需要具有更高的性能才能与原生应用程序竞争。最近的研究调查了现代Web浏览器的性能瓶颈，并得出结论，网络连接不再是浏览器的瓶颈。尽管对这一说法还没有达成共识，但没有进行后续分析来检查浏览器计算的哪些部分对性能开销有贡献。在本文中，我们应用全面和定量的假设分析的网页浏览器的页面加载过程。与传统的分析方法不同，我们applycauseal分析，以精确地确定每个计算阶段，如HTML解析和布局对PLT的影响。为此，我们开发了COZ+，这是一种高性能的因果分析器，能够分析大型软件系统，如Chromium浏览器。COZ+突出了最有影响力的点，可供浏览器开发人员和/或网站设计人员进一步优化。例如，COZ+显示，在典型的网络条件下，优化JavaScript 40%有望将Chromium桌面浏览器的页面加载性能提高8.5%以上。
Web browsers have become one of the most commonly used applications for desktop and mobile users. Despite recent advances in network speeds and several techniques to speed up web page loading such as speculative loading, smart caching, and multi-threading, browsers still suffer from relatively long page load time (PLT). As web applications are receiving widespread attention owing to their cross-platform support and comparatively straightforward development process, they need to have higher performance to compete with native applications. Recent studies have investigated the bottleneck of the modern web browser's performance and conclude that network connection is not the browser's bottleneck anymore. Even though there is still no consensus on this claim, no subsequent analysis has been conducted to inspect which parts of the browser's computation contribute to the performance overhead. In this paper, we apply comprehensive and quantitative what-if analysis on the web browser's page loading process. Unlike conventional profiling methods, we applycausal profiling to precisely determine the impact of each computation stage such as HTML parsing and Layout on PLT. For this purpose, we develop COZ+, a high-performance causal profiler capable of analyzing large software systems such as the Chromium browser. COZ+ highlights the most influential spots for further optimization, which can be leveraged by browser developers and/or website designers. For instance, COZ+ shows that optimizing JavaScript by 40% is expected to improve the Chromium desktop browser's page loading performance by more than 8.5% under typical network conditions.