A Parallel MPI I/O Solution Supported by Byte-addressable Non-volatile RAM Distributed Cache

Abstract

Abstract-While many scientific, large-scale applications are data-intensive, fast and efficient I/O operations have become of key importance for HPC environments. We propose an MPI I/O extension based on in-system distributed cache with data located in Non-volatile Random Access Memory (NVRAM) available in each cluster node. The presented architecture makes effective use of NVRAM properties such as persistence and byte-level access behind the MPI I/O API. Another advantage of the proposed solution is making development of a parallel application easy and efficient as a programmer just needs to use the well known MPI I/O data model and API while efficient file access is automatically provided without a need for application level optimizations like avoiding frequent operations on a small data.Results of experiments obtained with three different applications suggest, that the extension significantly reduces file access time, especially for small I/O operations. By locating cache facilities on computing nodes, the extension decreases load of file system servers and makes I/O scalable.

Distributed NVRAM Cache – Optimization and Evaluation with Power of Adjacency Matrix

“…Moreover, the solution is aimed at applications that access small chunks of data (gain from byte addressing of NVRAM) from spread file locations (no drawback from omitting staging algorithms). As it was shown in previous papers [16,17], for long running and data intensive HPC applications that operate on small data parts, our solution performs better than unmodified MPI I/O. In this paper, we want to evaluate it with an application that does not meet those criteria strictly.…”

“…In 2016 we proposed the idea of NVRAM distributed cache located as an additional layer between a file system and a parallel distributed application [16]. The extension was transparent to the developer, because of its compatibility with the well-known Message Passing Interface (MPI) I/O API [18].…”

A Solution to Image Processing with Parallel MPI I/O and Distributed NVRAM Cache

“…As we will show in experiments, performance of specific operations in regular MPI I/O and PFS could be significantly improved using our byte-addressable NVRAM distributed cache [23].…”

“…The main distinguishing features of the cache are fully decentralized management, prefetching the whole file during opening, synchronizing the whole file during closing and keeping minimal metadata. A set of tests with synthetic benchmarks and real-life applications like map searching, crowd simulation or graph processing proved I/O improved performance, especially for long running applications [21,22,23]. An additional feature of the cache that naturally benefits from NVRAM persistence is safety of the data during processing [24].…”