论文标题

Rosetta:一个以容器为中心的科学平台,用于资源密集,交互式数据分析

Rosetta: a container-centric science platform for resource-intensive, interactive data analysis

论文作者

Russo, Stefano Alberto, Bertocco, Sara, Gheller, Claudio, Taffoni, Giuliano

论文摘要

Rosetta是一个科学平台,用于资源密集型,交互式数据分析,可将用户任务作为软件容器运行。它建立在基于框架用户任务的新型体系结构之上,作为微服务 - 独立和独立的单元 - 允许完全支持自定义和用户定义的软件包,库和环境。除了通用分析环境作为Jupyter笔记本电脑外,其中包括完整的远程桌面和GUI应用程序。罗塞塔(Rosetta)依靠开放的容器倡议容器,该容器允许安全,有效和可重复执行的执行;可以使用许多容器引擎和运行时间;并无缝支持几个工作负载管理系统,从而在广泛的计算资源上实现了容器化的工作负载。尽管在天文学和天体物理学领域开发,但罗塞塔(Rosetta)几乎可以支持需要资源密集的,交互式数据分析的任何科学和技术领域。

Rosetta is a science platform for resource-intensive, interactive data analysis which runs user tasks as software containers. It is built on top of a novel architecture based on framing user tasks as microservices - independent and self-contained units - which allows to fully support custom and user-defined software packages, libraries and environments. These include complete remote desktop and GUI applications, besides common analysis environments as the Jupyter Notebooks. Rosetta relies on Open Container Initiative containers, which allow for safe, effective and reproducible code execution; can use a number of container engines and runtimes; and seamlessly supports several workload management systems, thus enabling containerized workloads on a wide range of computing resources. Although developed in the astronomy and astrophysics space, Rosetta can virtually support any science and technology domain where resource-intensive, interactive data analysis is required.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源