arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.10334cs.PFcs.DC
收藏

AutoTune:提高微服务应用程序的端到端性能和资源效率

AutoTune: Improving End-to-end Performance and Resource Efficiency for Microservice Applications

Michael Alan Chang, Aurojit Panda, Hantao Wang, Yuancheng Tsai, Rahul Balakrishnan, Scott Shenker

摘要:

大多数大型Web规模的应用程序现在都是通过组合微服务集合(从几个到100个或1000个)来构建的。运营商需要决定为每个微服务分配多少资源,这些分配可能会对应用程序性能产生很大影响。手动确定既具有成本效益又满足性能要求的分配是一项挑战,即使对于经验丰富的操作员也是如此。在本文中,我们提出了AutoTune,一个端到端的工具,自动最大限度地减少资源利用率,同时保持良好的应用程序性能。

英文摘要:

Most large web-scale applications are now built by composing collections (from a few up to 100s or 1000s) of microservices. Operators need to decide how many resources are allocated to each microservice, and these allocations can have a large impact on application performance. Manually determining allocations that are both cost-efficient and meet performance requirements is challenging, even for experienced operators. In this paper we present AutoTune, an end-to-end tool that automatically minimizes resource utilization while maintaining good application performance.

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。

↑