Using Balanced Data Placement to Address I/O Contention in Production Environments

• Sarah Neuwirth University of Heidelberg
• Feiyi Wang National Center for Computational Sciences, Oak Ridge National Laboratory
• Sarp Oral National Center for Computational Sciences, Oak Ridge National Laboratory
• Sudharshan Vazhkudai National Center for Computational Sciences, Oak Ridge National Laboratory
• James Rogers National Center for Computational Sciences, Oak Ridge National Laboratory
• Ulrich Bruening University of Heidelberg

Abstract

Designed for capacity and capability, HPC I/O systems are inherently complex and shared among multiple, concurrent jobs competing for resources. Lack of centralized coordination and control often render the end-to-end I/O paths vulnerable to load imbalance and contention. With the emergence of data-intensive HPC applications, storage systems are further contended for performance and scalability. This paper proposes to unify two key approaches to tackle the imbalanced use of I/O resources and to achieve an end-to-end I/O performance improvement in the most transparent way. First, it utilizes a topology-aware, Balanced Placement I/O method (BPIO) for mitigating resource contention. Second, it takes advantage of the platform-neutral ADIOS middleware, which provides a flexible I/O mechanism for scientific applications. By integrating BPIO with ADIOS, referred to as Aequilibro, we obtain an end-to-end and per job I/O performance improvement for ADIOS-enabled HPC applications without requiring any code changes. Aequilibro can be applied to almost any HPC platform and is mostly suitable for systems that lack a centralized file system resource manager. We demonstrate the effectiveness of our integration on the Titan system at the Oak Ridge National Laboratory. Our experiments with a synthetic benchmark and real-world HPC workload show that, even in a noisy production environment, Aequilibro can improve large-scale application performance significantly.

Keywords: Libraries, Load management, Scalability, Resource management, Aggregates, Production, Performance evaluation, Parallel File System, High Performance Computing, Load Balancing, Performance Evaluation