Critical embedded software, such as spacecraft flight software, requires high reliability, efficiency, and real-time performance while being capable enough to meet application needs. The increasing prevalence of Linux, and in particular Linux containers, presents opportunities for space systems but also poses potential risks since Linux was not designed to be a real-time operating system. In this study, we conducted a variety of experiments to look at both the overhead imposed by containers and the latency experienced in Linux using various combinations of patched OS and containers running on a Raspberry Pi 4. We found that containers have little impact on CPU utilization but do incur penalties in RAM, disk storage, and startup time. We also found the unpatched Linux kernel performs well for real time; and that, while the real-time kernel patch reduces both overall and maximum latency, it can negatively impact performance, particularly on single-core systems running non-real-time tasks.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Container Performance in Space Systems

  • Shariar M. Alamgir,
  • Dhruv L. Bohra,
  • Elisabeth A. Nguyen

摘要

Critical embedded software, such as spacecraft flight software, requires high reliability, efficiency, and real-time performance while being capable enough to meet application needs. The increasing prevalence of Linux, and in particular Linux containers, presents opportunities for space systems but also poses potential risks since Linux was not designed to be a real-time operating system. In this study, we conducted a variety of experiments to look at both the overhead imposed by containers and the latency experienced in Linux using various combinations of patched OS and containers running on a Raspberry Pi 4. We found that containers have little impact on CPU utilization but do incur penalties in RAM, disk storage, and startup time. We also found the unpatched Linux kernel performs well for real time; and that, while the real-time kernel patch reduces both overall and maximum latency, it can negatively impact performance, particularly on single-core systems running non-real-time tasks.