Improving Collective I/O Performance Using Non-volatile Memory Devices

Congiu, Giuseppe; Narasimhamurthy, Sai; SuB, Tim; Brinkmann, André

doi:10.1109/cluster.2016.37

Cited by 20 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their motivation is to satisfy the need to overlap computation and I/O and to hide the synchronization cost imposed by standard blocking collective I/O operations. In [25] a set of MPI-IO hints extension is proposed so users can harness locally attached SSDs to boost collective I/O performance by increasing parallelism and reducing global synchronization impact in the ROMIO implementation. In [26], the communication phase of the collective I/O operations is tuned for a Blue Gene/L supercomputer by exploring the specific network features of the machine.…”

Section: Related Workmentioning

confidence: 99%

Collective I/O Performance on the Santos Dumont Supercomputer

Carneiro

Bez

Boito

et al. 2018

2018 26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

View full text Add to dashboard Cite

The historical gap between processing and data access speeds causes many applications to spend a large portion of their execution on I/O operations. From the point of view of a large-scale, expensive, supercomputer, it is important to ensure applications achieve the best I/O performance to promote an efficient usage of the machine. In this paper, we evaluate the I/O infrastructure of the Santos Dumont supercomputer, the largest one from Latin America. More specifically, we investigate the performance of collective I/O operations. By conducting an analysis of a scientific application that uses the machine, we identify large performance differences between the available MPI implementations. We then further study the observed phenomenon using the BT-IO and IOR benchmarks, in addition to a custom microbenchmark. We conclude that the customized MPI implementation by Bull (used by more than 20% of the jobs) presents the worst performance for small collective write operations. Our results are being used to help the Santos Dumont users to achieve the best performance for their applications. Additionally, by investigating the observed phenomenon, we provide information to help improve future MPI-IO collective write implementations.

show abstract

Section: Related Workmentioning

confidence: 99%

Collective I/O Performance on the Santos Dumont Supercomputer

Carneiro

Bez

Boito

et al. 2018

2018 26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)

View full text Add to dashboard Cite

show abstract

“…Caching is an alternative approach for organizing the node-local fast storage. Congiu et al (2016) proposed a set of message passing interface I/O (MPI-IO) hints to cache data in locally attached fast storage. Dong et al (2011) used SSDs in compute nodes as write-back cache to store huge numbers of checkpoint data.…”

Section: Solid State Drive Based and Memory-based Storage Tiersmentioning

confidence: 99%

ONFS: a hierarchical hybrid file system based on memory, SSD, and HDD for high performance computers

Liu

Yu³

et al. 2017

Frontiers Inf Technol Electronic Eng

View full text Add to dashboard Cite

With supercomputers developing towards exascale, the number of compute cores increases dramatically, making more complex and larger-scale applications possible. The input/output (I/O) requirements of large-scale applications, workflow applications, and their checkpointing include substantial bandwidth and an extremely low latency, posing a serious challenge to high performance computing (HPC) storage systems. Current hard disk drive (HDD) based underlying storage systems are becoming more and more incompetent to meet the requirements of next-generation exascale supercomputers. To rise to the challenge, we propose a hierarchical hybrid storage system, on-line and near-line file system (ONFS). It leverages dynamic random access memory (DRAM) and solid state drive (SSD) in compute nodes, and HDD in storage servers to build a three-level storage system in a unified namespace. It supports portable operating system interface (POSIX) semantics, and provides high bandwidth, low latency, and huge storage capacity. In this paper, we present the technical details on distributed metadata management, the strategy of memory borrow and return, data consistency, parallel access control, and mechanisms guiding downward and upward migration in ONFS. We implement an ONFS prototype on the TH-1A supercomputer, and conduct experiments to test its I/O performance and scalability. The results show that the bandwidths of single-thread and multi-thread 'read'/'write' are 6-fold and 5-fold better than HDD-based Lustre, respectively. The I/O bandwidth of data-intensive applications in ONFS can be 6.35 times that in Lustre.

show abstract

“…We generated multiple benchmarks with the MPI-IO Test benchmarking tool 3 to cover representative access patterns. They are the combination of parameters such as number of files, spatiality, request size, operation (read or write), etc.…”

Section: A Methodology For the Generation Of The Tracesmentioning

confidence: 99%

On server-side file access pattern matching

Boito

Nou

Pilla

et al. 2019

2019 International Conference on High Performance Computing &Amp; Simulation (HPCS)

View full text Add to dashboard Cite

In this paper, we propose a pattern matching approach for server-side access pattern detection for the HPC I/O stack. More specifically, our proposal concerns file-level accesses, such as the ones made to I/O libraries, I/O nodes, and the parallel file system servers. The goal of this detection is to allow the system to adapt to the current workload. Compared to existing detection techniques, ours differ by working at run-time and on the server side, where detailed application information is not available since HPC I/O systems are stateless, and without relying on previous traces. We build a time series to represent accesses spatiality, and use a pattern matching algorithm, in addition to an heuristic, to compare it to known patterns. We detail our proposal and evaluate it with two case studies-situations where detecting the current access pattern is important to select the best scheduling algorithm or to tune a fixed algorithm parameter. We show our approach has good detection capabilities, with precision of up to 93% and recall of up to 99%, and discuss all design choices.

show abstract

Improving Collective I/O Performance Using Non-volatile Memory Devices

Cited by 20 publications

References 15 publications

Collective I/O Performance on the Santos Dumont Supercomputer

Collective I/O Performance on the Santos Dumont Supercomputer

ONFS: a hierarchical hybrid file system based on memory, SSD, and HDD for high performance computers

On server-side file access pattern matching

Contact Info

Product

Resources

About