With increasing complexity of HPC workflows, data management services need to perform expensive I/O operations asynchronously in the background, aiming to overlap the I/O with the application runtime. However, this may cause interference due to competition for resources: CPU, memory/network bandwidth. The advent of multi-core architectures has exacerbated this problem, as many I/O operations are issued concurrently, thereby competing not only with the application but also among themselves. Furthermore, the interference patterns can dynamically change as a response to variations in application behavior and I/O subsystems (e.g. multiple users sharing a parallel file system). Without a thorough understanding, I/O operations may perform suboptimally, potentially even worse than in the blocking case. To fill this gap, this paper investigates the causes and consequences of interference due to asynchronous I/O on HPC systems. Specifically, we focus on multi-core CPUs and memory bandwidth, isolating the interference due to each resource. Then, we perform an in-depth study to explain the interplay and contention in a variety of resource sharing scenarios such as varying priority and number of background I/O threads and different I/O strategies: sendfile, read/write, mmap/write underlining trade-offs. The insights from this study are important both to enable guided optimizations of existing background I/O, as well as to open new opportunities to design advanced asynchronous I/O strategies.

随着HPC工作流程复杂性的增加，数据管理服务需要在后台异步执行昂贵的I / O操作，以使I / O与应用程序运行时重叠。但是，这可能会由于争用资源而引起干扰：CPU，内存/网络带宽。多核体系结构的出现加剧了这个问题，因为许多I / O操作是同时发出的，因此不仅与应用程序竞争，而且还相互竞争。此外，作为对应用程序行为和I / O子系统（例如，多个用户共享并行文件系统）变化的响应，干扰模式可以动态更改。如果没有透彻的了解，I / O操作可能无法达到最佳效果，甚至可能比阻塞情况下更差。为了填补这一空白，本文研究了HPC系统上异步I / O引起的干扰的原因和后果。具体来说，我们专注于多核CPU和内存带宽，以隔离每种资源造成的干扰。然后，我们进行深入研究，以解释各种资源共享方案中的相互作用和争用，例如，不同的优先级和后台I / O线程数以及不同的I / O策略：sendfile，read / write，mmap / write强调权衡。这项研究的见解对于实现对现有背景I / O的指导性优化以及为设计高级异步I / O策略提供新的机会都非常重要。隔离每种资源造成的干扰。然后，我们进行深入研究，以解释各种资源共享方案中的相互作用和争用，例如，不同的优先级和后台I / O线程数以及不同的I / O策略：sendfile，read / write，mmap / write强调权衡。这项研究的见解对于实现对现有背景I / O的指导性优化以及为设计高级异步I / O策略提供新的机会都非常重要。隔离每种资源造成的干扰。然后，我们进行深入研究，以解释各种资源共享方案中的相互作用和争用，例如，不同的优先级和后台I / O线程数以及不同的I / O策略：sendfile，read / write，mmap / write强调权衡。这项研究的见解对于实现对现有背景I / O的指导性优化以及为设计高级异步I / O策略提供新的机会都非常重要。