Deepstitch: Deep Learning for Cross-Layer Stitching in Microservices

Deepstitch: Deep Learning for Cross-Layer Stitching in Microservices
复制标题

Deepstitch:微服务中跨层拼接的深度学习

DOI:
10.1145/3429885.3429965
复制
发表时间:
2020
期刊:
WOC'20: Proceedings of the 2020 6th International Workshop on Container Technologies and Container Clouds
影响因子:
--
通讯作者:
Eide, Eric
Eide, Eric
中科院分区:
--
文献类型:
--
作者:
Li, Richard;Du, Min;Chang, Hyunseok;Mukherjee, Sarit;Eide, Eric

文献摘要

参考文献

相似文献

虽然分布式应用层跟踪广泛用于微服务中的性能诊断,但其在服务级别的粗粒度限制了其在检测更细粒度的系统级问题方面的适用性。为了解决这个问题,已经提出了跟踪信息的跨层拼接。然而,所有现有的跨层拼接方法要么需要修改内核,要么需要更新应用层跟踪库来传播拼接信息,这两者都对现有的跟踪工具添加了进一步的复杂修改。本文介绍了Deepstitch,这是一种基于深度学习的方法,可以缝合跨层跟踪信息,而无需对现有的应用层跟踪工具进行任何更改。Deepstitch利用由多个服务组成的分布式应用程序的全局视图,并学习所有相关服务的全局系统调用序列。然后使用这些知识将系统调用序列与从已部署应用程序获得的服务级别跟踪缝合在一起。我们的概念验证实验表明,所提出的方法成功地映射到系统调用序列的应用程序级的交互,并可以识别线程级的交互。
While distributed application-layer tracing is widely used for performance diagnosis in microservices, its coarse granularity at the service level limits its applicability towards detecting more fine-grained system level issues. To address this problem, cross-layer stitching of tracing information has been proposed. However, all existing cross-layer stitching approaches either require modification of the kernel or need updates in the application-layer tracing library to propagate stitching information, both of which add further complex modifications to existing tracing tools. This paper introduces Deepstitch, a deep learning based approach to stitch cross-layer tracing information without requiring any changes to existing application layer tracing tools. Deepstitch leverages a global view of a distributed application composed of multiple services and learns the global system call sequences across all services involved. This knowledge is then used to stitch system call sequences with service-level traces obtained from a deployed application. Our proof of concept experiments show that the proposed approach successfully maps application-level interaction into the system call sequences and can identify thread-level interactions.
西蒙·德耶格
DOI: --
发表时间: 2019
期刊: Authors group
影响因子: --
作者:
S. De Jaeger
通讯作者: S. De Jaeger
DOI: --
发表时间: 2010
期刊: --
影响因子: --
作者:
B. Sigelman;L. Barroso;M. Burrows;Patrick Stephenson;Manoj Plakal;Donald Beaver;Saul Jaspan;C. Shanbh
通讯作者: B. Sigelman;L. Barroso;M. Burrows;Patrick Stephenson;Manoj Plakal;Donald Beaver;Saul Jaspan;C. Shanbh
Linux 4.X 跟踪工具:使用 {BPF} 超能力
DOI: --
发表时间: 2016
期刊:
影响因子: --
作者:
B. Gregg
通讯作者: B. Gregg
基于协作虚拟机社区的云异常检测结构
DOI: --
发表时间: 2017
期刊: IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing
影响因子: --
作者:
Rashid Tahir;M. Caesar;Ali Raza;Mazhar Naqvi;Fareed Zaffar
通讯作者: Fareed Zaffar