Prediction of the impact of network switch utilization on application performance via active measurement

Autor: Greg Bronevetsky, Marc Casas
Přispěvatelé: Barcelona Supercomputing Center
Rok vydání: 2017
Předmět:
Programari
business.product_category
Computer Networks and Communications
Computer science
Distributed computing
Real-time computing
02 engineering and technology
Bottleneck
Performance modeling
Theoretical Computer Science
Network simulation
Supercomputadors
Artificial Intelligence
0202 electrical engineering
electronic engineering
information engineering
Network computers
Resource sharing
Software architecture
Enginyeria electrònica [Àrees temàtiques de la UPC]
020206 networking & telecommunications
021001 nanoscience & nanotechnology
Supercomputer
Computer Graphics and Computer-Aided Design
Network traffic control
Shared resource
Hardware and Architecture
Measurement techniques
Component-based software engineering
Key (cryptography)
Network switch
High performance computing
0210 nano-technology
business
Software
Zdroj: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
ISSN: 0167-8191
DOI: 10.1016/j.parco.2017.06.005
Popis: Although one of the key characteristics of High Performance Computing (HPC) infrastructures are their fast interconnecting networks, the increasingly large computational capacity of HPC nodes and the subsequent growth of data exchanges between them constitute a potential performance bottleneck. To achieve high performance in parallel executions despite network limitations, application developers require tools to measure their codes’ network utilization and to correlate the network’s communication capacity with the performance of their applications. This paper presents a new methodology to measure and understand network behavior. The approach is based in two different techniques that inject extra network communication. The first technique aims to measure the fraction of the network that is utilized by a software component (an application or an individual task) to determine the existence and severity of network contention. The second injects large amounts of network traffic to study how applications behave on less capable or fully utilized networks. The measurements obtained by these techniques are combined to predict the performance slowdown suffered by a particular software component when it shares the network with others. Predictions are obtained by considering several training sets that use raw data from the two measurement techniques. The sensitivity of the training set size is evaluated by considering 12 different scenarios. Our results find the optimum training set size to be around 200 training points. When optimal data sets are used, the proposed methodology provides predictions with an average error of 9.6% considering 36 scenarios. With the support of the Secretary for Universities and Research of the Ministry of Economy and Knowledge of the Government of Catalonia and the Cofund programme of the Marie Curie Actions of the 7th R&D Framework Programme of the European Union (Expedient 2013BP_B00243). The research leading to these results has received funding from the European Research Council under the European Union’s 7th FP (FP/2007-2013) /ERC GA n. 321253. Work partially supported by the Spanish Ministry of Science and Innovation (TIN2012-34557)
Databáze: OpenAIRE
Externí odkaz: