arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.03066cs.SE
收藏

从DevOps到DevDataOps:DevOps过程中的数据管理

From DevOps to DevDataOps: Data Management in DevOps processes

Antonio Capizzi, Salvatore Distefano, Manuel Mazzara

摘要:

DevOps是管理软件开发和运营的一种非常有效的方法,正如实际应用和案例研究中的大量成功案例所证实的那样。DevOps现在正在成为软件行业在开发中采用的主流解决方案,能够缩短上市时间和成本,同时提高质量并确保最终软件架构的可演化性和适应性。在DevOps过程中需要考虑的方面中,数据具有战略重要性,因为它可以从运营中直接获得洞察力,从而直接进入开发,这是DevOps方法的主要目标。因此,数据可以被视为DevOps过程的燃料,需要适当的解决方案来管理。根据生成的数据量、其种类、速度、可变性、价值和其他相关特征,DevOps数据管理主要可以归入大数据类别。这允许利用大数据解决方案来管理整个过程中生成的DevOps数据,包括工件,代码,文档,日志等。本文旨在调查DevOps过程中的数据管理,识别相关问题,挑战和潜在的解决方案,这些解决方案来自大数据世界以及采用和适应DevOps方法进行数据管理的新趋势,即DataOps。

英文摘要:

DevOps is a quite effective approach for managing software development and operation, as confirmed by plenty of success stories in real applications and case studies. DevOps is now becoming the main-stream solution adopted by the software industry in development, able to reduce the time to market and costs while improving quality and ensuring evolvability and adaptability of the resulting software architecture. Among the aspects to take into account in a DevOps process, data is assuming strategic importance, since it allows to gain insights from the operation directly into the development, the main objective of a DevOps approach. Data can be therefore considered as the fuel of the DevOps process, requiring proper solutions for its management. Based on the amount of data generated, its variety, velocity, variability, value and other relevant features, DevOps data management can be mainly framed into the BigData category. This allows exploiting BigData solutions for the management of DevOps data generated throughout the process, including artefacts, code, documentation, logs and so on. This paper aims at investigating data management in DevOps processes, identifying related issues, challenges and potential solutions taken from the BigData world as well as from new trends adopting and adapting DevOps approaches in data management, i.e. DataOps.

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。

↑