Distributed In-memory Data Management for Workflow Executions

TL;DR

This paper introduces SchalaDB, a distributed in-memory data management architecture for efficient workflow execution and user steering in large-scale scientific experiments, demonstrating its scalability and minimal overhead.

Contribution

The paper presents SchalaDB, a novel distributed in-memory data management approach tailored for scalable workflow control and user steering, validated through an extensive HPC cluster evaluation.

Findings

SchalaDB achieves negligible overhead with hundreds of concurrent tasks.

Distributed in-memory data management improves workflow scheduling and user steering.

Experimental results show high scalability on up to 960 cores.

Abstract

Complex scientific experiments from various domains are typically modeled as workflows and executed on large-scale machines using a Parallel Workflow Management System (WMS). Since such executions usually last for hours or days, some WMSs provide user steering support, i.e., they allow users to run data analyses and, depending on the results, adapt the workflows at runtime. A challenge in the parallel execution control design is to manage workflow data for efficient executions while enabling user steering support. Data access for high scalability is typically transaction-oriented, while for data analysis, it is online analytical-oriented so that managing such hybrid workloads makes the challenge even harder. In this work, we present SchalaDB, an architecture with a set of design principles and techniques based on distributed in-memory data management for efficient workflow execution control and user steering. We propose a distributed data design for scalable workflow task scheduling and high availability driven by a parallel and distributed in-memory DBMS. To evaluate our proposal, we develop d-Chiron, a WMS designed according to SchalaDB's principles. We carry out an extensive experimental evaluation on an HPC cluster with up to 960 computing cores. Among other analyses, we show that even when running data analyses for user steering, SchalaDB's overhead is negligible for workloads composed of hundreds of concurrent tasks on shared data. Our results encourage workflow engine developers to follow a parallel and distributed data-oriented approach not only for scheduling and monitoring but also for user steering.