We present a software tool, the Container Profiler, that measures and records the resource usage of any containerized task. Our tool profiles the CPU, memory, disk, and network utilization of a containerized job by collecting Linux operating system metrics at the virtual machine, container, and process levels. The Container Profiler can produce utilization snapshots at multiple time points, allowing for continuous monitoring of the resources consumed by a container workflow. To investigate the utility of the Container Profiler we profiled the resource utilization requirements of a multi-stage bioinformatics analytical workflow (RNA sequencing using unique molecular identifiers). We examined the collected profile metrics and confirmed that they were consistent with the expected CPU, disk, network resource utilization patterns for the different stages of the workflow. We also quantified the profiling overhead and found that this was negligible. The Container Profiler is a useful tool that can be used to continuously monitor the resource consumption of long and complex containerized workflows that run locally or on the cloud. This can identify bottlenecks where more resources are needed to improve performance.

中文翻译：

---

分析生物信息学工作流的资源利用

我们提供了一个软件工具 Container Profiler，它可以测量和记录任何容器化任务的资源使用情况。我们的工具通过在虚拟机、容器和进程级别收集 Linux 操作系统指标来分析容器化作业的 CPU、内存、磁盘和网络利用率。Container Profiler 可以在多个时间点生成利用率快照，从而可以持续监控容器工作流消耗的资源。为了研究 Container Profiler 的实用性，我们分析了多阶段生物信息学分析工作流程（使用唯一分子标识符的 RNA 测序）的资源利用要求。我们检查了收集的配置文件指标并确认它们与预期的 CPU、磁盘、工作流不同阶段的网络资源利用模式。我们还量化了分析开销，发现这是可以忽略不计的。Container Profiler 是一个有用的工具，可用于持续监控在本地或云上运行的长而复杂的容器化工作流的资源消耗。这可以确定需要更多资源来提高性能的瓶颈。