VAIF: Variance-driven Automated Instrumentation Framework

VAIF: Variance-driven Automated Instrumentation Framework
复制标题

VAIF:方差驱动的自动化仪表框架

DOI:
10.1145/3544497.3544504
复制
发表时间:
2022
期刊:
ACM SIGOPS Operating Systems Review
影响因子:
--
通讯作者:
Sambasivan, Raja R.
Sambasivan, Raja R.
中科院分区:
--
文献类型:
--
作者:
Toslali, Mert;Ates, Emre;Huye, Darby;Zhang, Zhaoqi;Liu, Lan;Puterman, Samantha;Coskun, Ayse K.;Sambasivan, Raja R.

文献摘要

相似文献

开发人员使用日志来诊断分布式应用程序中的性能问题。但是,很难事先知道在哪里需要日志,以及需要日志中的哪些信息来帮助诊断未来可能发生的问题。我们总结了我们在方差驱动的自动化工具框架(VAIF)上所做的工作,该框架与分布式应用程序一起运行。为了响应新观察到的性能问题,VAIF会自动搜索可能的检测选项空间,以启用帮助诊断这些问题所需的日志。为了工作,VAIF将分布式跟踪(一种增强的日志记录形式)与有关如何在请求跟踪的关键路径部分分解响应时间差异的见解结合在一起。
Developers use logs to diagnose performance problems in distributed applications. But, it is difficult to know a priori where logs are needed and what information in them is needed to help diagnose problems that may occur in the future. We summarize our work on the Variance-driven Automated Instrumentation Framework (VAIF), which runs alongside distributed applications. In response to newly-observed performance problems, VAIF automatically searches the space of possible instrumentation choices to enable the logs needed to help diagnose them. To work, VAIF combines distributed tracing (an enhanced form of logging) with insights about how response-time variance can be decomposed on the criticalpath portions of requests' traces.