Pilot-Data: An Abstraction for Distributed Data

TL;DR

Pilot-Data introduces an abstraction that enhances the management and scheduling of large-scale data alongside compute resources in distributed environments, addressing interoperability and extensibility challenges.

Contribution

It extends the Pilot-Job abstraction to include data management, enabling efficient data and compute co-placement and scheduling in heterogeneous distributed systems.

Findings

Demonstrated improved application performance with Pilot-Data integration.

Showcased flexible execution modes for data-intensive applications.

Enabled advanced data-compute co-placement and scheduling capabilities.

Abstract

Scientific problems that depend on processing large amounts of data require overcoming challenges in multiple areas: managing large-scale data distribution, controlling co-placement and scheduling of data with compute resources, and storing, transferring, and managing large volumes of data. Although there exist multiple approaches to addressing each of these challenges, an integrative approach is missing; furthermore, extending existing functionality or enabling interoperable capabilities remains difficult at best. We propose the concept of Pilot-Data to address the fundamental challenges of co-placement and scheduling of data and compute in heterogeneous and distributed environments with interoperability and extensibility as first-order concerns. Pilot-Data is an extension of the Pilot-Job abstraction for supporting the management of data in conjunction with compute tasks. Pilot-Data separates logical data units from physical storage, thereby providing the basis for efficient compute/data placement and scheduling. In this paper, we discuss the design and implementation of the Pilot-Data prototype, demonstrate its use by data-intensive applications on multiple production distributed cyberinfrastructure and illustrate the advantages arising from flexible execution modes enabled by Pilot-Data. Our experiments utilize an implementation of Pilot-Data in conjunction with a scalable Pilot-Job (BigJob) to establish the application performance that can be enabled by the use of Pilot-Data. We demonstrate how the concept of Pilot-Data also provides the basis upon which to build tools and support capabilities like affinity which in turn can be used for advanced data-compute co-placement and scheduling.