Design and Evaluation of a Collective IO Model for Loosely Coupled Petascale Programming

TL;DR

This paper presents a collective IO model for petascale loosely coupled programming that improves data distribution and collection efficiency, reducing manual tuning and enhancing ease of programming on large-scale systems.

Contribution

The paper introduces a prototype collective IO model that leverages local file systems and broadcast techniques to optimize data handling in loosely coupled petascale applications.

Findings

Achieved high-speed data distribution and collection on Blue Gene/P

Reduced manual tuning in file-based many-task computing

Demonstrated performance improvements with synthetic benchmarks and molecular dynamics application

Abstract

Loosely coupled programming is a powerful paradigm for rapidly creating higher-level applications from scientific programs on petascale systems, typically using scripting languages. This paradigm is a form of many-task computing (MTC) which focuses on the passing of data between programs as ordinary files rather than messages. While it has the significant benefits of decoupling producer and consumer and allowing existing application programs to be executed in parallel with no recoding, its typical implementation using shared file systems places a high performance burden on the overall system and on the user who will analyze and consume the downstream data. Previous efforts have achieved great speedups with loosely coupled programs, but have done so with careful manual tuning of all shared file system access. In this work, we evaluate a prototype collective IO model for file-based MTC. The model enables efficient and easy distribution of input data files to computing nodes and gathering of output results from them. It eliminates the need for such manual tuning and makes the programming of large-scale clusters using a loosely coupled model easier. Our approach, inspired by in-memory approaches to collective operations for parallel programming, builds on fast local file systems to provide high-speed local file caches for parallel scripts, uses a broadcast approach to handle distribution of common input data, and uses efficient scatter/gather and caching techniques for input and output. We describe the design of the prototype model, its implementation on the Blue Gene/P supercomputer, and present preliminary measurements of its performance on synthetic benchmarks and on a large-scale molecular dynamics application.