Towards Multi-site Metadata Management for Geographically Distributed Cloud Workflows - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Towards Multi-site Metadata Management for Geographically Distributed Cloud Workflows

Abstract

With their globally distributed datacenters, clouds now provide an opportunity to run complex large-scale applications on dynamically provisioned, networked and federated infrastructures. However, there is a lack of tools supporting data-intensive applications across geographically distributed sites. For instance, scientific workflows which handle many small files can easily saturate state-of-the-art distributed filesystems based on centralized metadata servers (e.g. HDFS, PVFS). In this paper, we explore several alternative design strategies to efficiently support the execution of existing workflow engines across multi-site clouds, by reducing the cost of metadata operations. These strategies leverage workflow semantics in a 2-level metadata partitioning hierarchy that combines distribution and replication. The system was validated on the Microsoft Azure cloud across 4 EU and US datacenters. The experiments were conducted on 128 nodes using synthetic benchmarks and real-life applications. We observe as much as 28% gain in execution time for a parallel, geo-distributed real-world application (Montage) and up to 50% for a metadata-intensive synthetic benchmark, compared to a baseline centralized configuration.
Fichier principal
Vignette du fichier
cluster.pdf (497.83 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01239150 , version 1 (07-12-2015)

Identifiers

Cite

Luis Pineda-Morales, Alexandru Costan, Gabriel Antoniu. Towards Multi-site Metadata Management for Geographically Distributed Cloud Workflows. CLUSTER 2015 - IEEE International Conference on Cluster Computing, Sep 2015, Chicago, United States. ⟨10.1109/CLUSTER.2015.49⟩. ⟨hal-01239150⟩
439 View
392 Download

Altmetric

Share

Gmail Facebook X LinkedIn More