Enhancing the SDTMA-NDN architecture for transferring the scientific data software using named data networking

Mohammad Alhowaidi, Byrav Ramamurthy, Brian Bockelman, David Swanson

Research output: Contribution to journalArticle

Abstract

Named Data Networking (NDN) is one of the promising future internet architectures, which focuses on the data rather than its location (IP/host-based system). NDN has several characteristics which facilitate addressing and routing the data: fail-over, in-network caching and load balancing. This makes it useful in areas such as managing scientific data across a distributed infrastructure. The Compact Muon Solenoid (CMS) experiment on the Large Hadron Collider (LHC) runs such an infrastructure and has a data access pattern amenable to Information-Centric Networking (ICN). In this paper, we propose SDTMA-NDN (Scientific Data Transfer Management Architecture using NDN) to distribute CMS's software to worker-nodes and end-users. We provide several strategies to enhance the performance of NDN in transferring the scientific data. We build this on top of CERN Virtual Machine File System (CVMFS), a global, distributed filesystem designed to be used with cache-friendly workloads. CVMFS maintains its data by using content-addressable storage, which makes it suitable for NDN and a reasonable starting point for CMS. We examine the effect of in-network caching of NDN on the latency, how NDN provides transparent path selection to avoid high latency in the path, and how it balances several paths for retrieving the data. We compare SDTMA-NDN to the HTTP proxies used in the existing CVMFS-Content Distribution Network (CDN). Also, we propose two NDN forwarding strategies for retrieving the data; NDN Best-Path strategy (NDN-BP) and NDN Multi-path strategy (NDN-MP). SDTMA-NDN shows a better performance than the existing HTTP protocol in transferring the data. Further, it shows more resiliency and outperforms CVMFS-CDN under different network conditions.

Original languageEnglish (US)
Article number106954
JournalComputer Networks
Volume166
DOIs
StatePublished - Jan 15 2020

Fingerprint

Data transfer
HTTP
Solenoids
Electric power distribution
Associative storage
Colliding beam accelerators
Resource allocation
Internet
Network protocols
Virtual machine
Experiments

Keywords

  • CERN virtual machine file system (CVMFS)
  • Named data networking
  • Scientific data

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Enhancing the SDTMA-NDN architecture for transferring the scientific data software using named data networking. / Alhowaidi, Mohammad; Ramamurthy, Byrav; Bockelman, Brian; Swanson, David.

In: Computer Networks, Vol. 166, 106954, 15.01.2020.

Research output: Contribution to journalArticle

@article{79bd8f8c9eed4540afe0f9969f71e39c,
title = "Enhancing the SDTMA-NDN architecture for transferring the scientific data software using named data networking",
abstract = "Named Data Networking (NDN) is one of the promising future internet architectures, which focuses on the data rather than its location (IP/host-based system). NDN has several characteristics which facilitate addressing and routing the data: fail-over, in-network caching and load balancing. This makes it useful in areas such as managing scientific data across a distributed infrastructure. The Compact Muon Solenoid (CMS) experiment on the Large Hadron Collider (LHC) runs such an infrastructure and has a data access pattern amenable to Information-Centric Networking (ICN). In this paper, we propose SDTMA-NDN (Scientific Data Transfer Management Architecture using NDN) to distribute CMS's software to worker-nodes and end-users. We provide several strategies to enhance the performance of NDN in transferring the scientific data. We build this on top of CERN Virtual Machine File System (CVMFS), a global, distributed filesystem designed to be used with cache-friendly workloads. CVMFS maintains its data by using content-addressable storage, which makes it suitable for NDN and a reasonable starting point for CMS. We examine the effect of in-network caching of NDN on the latency, how NDN provides transparent path selection to avoid high latency in the path, and how it balances several paths for retrieving the data. We compare SDTMA-NDN to the HTTP proxies used in the existing CVMFS-Content Distribution Network (CDN). Also, we propose two NDN forwarding strategies for retrieving the data; NDN Best-Path strategy (NDN-BP) and NDN Multi-path strategy (NDN-MP). SDTMA-NDN shows a better performance than the existing HTTP protocol in transferring the data. Further, it shows more resiliency and outperforms CVMFS-CDN under different network conditions.",
keywords = "CERN virtual machine file system (CVMFS), Named data networking, Scientific data",
author = "Mohammad Alhowaidi and Byrav Ramamurthy and Brian Bockelman and David Swanson",
year = "2020",
month = "1",
day = "15",
doi = "10.1016/j.comnet.2019.106954",
language = "English (US)",
volume = "166",
journal = "Computer Networks",
issn = "1389-1286",
publisher = "Elsevier",

}

TY - JOUR

T1 - Enhancing the SDTMA-NDN architecture for transferring the scientific data software using named data networking

AU - Alhowaidi, Mohammad

AU - Ramamurthy, Byrav

AU - Bockelman, Brian

AU - Swanson, David

PY - 2020/1/15

Y1 - 2020/1/15

N2 - Named Data Networking (NDN) is one of the promising future internet architectures, which focuses on the data rather than its location (IP/host-based system). NDN has several characteristics which facilitate addressing and routing the data: fail-over, in-network caching and load balancing. This makes it useful in areas such as managing scientific data across a distributed infrastructure. The Compact Muon Solenoid (CMS) experiment on the Large Hadron Collider (LHC) runs such an infrastructure and has a data access pattern amenable to Information-Centric Networking (ICN). In this paper, we propose SDTMA-NDN (Scientific Data Transfer Management Architecture using NDN) to distribute CMS's software to worker-nodes and end-users. We provide several strategies to enhance the performance of NDN in transferring the scientific data. We build this on top of CERN Virtual Machine File System (CVMFS), a global, distributed filesystem designed to be used with cache-friendly workloads. CVMFS maintains its data by using content-addressable storage, which makes it suitable for NDN and a reasonable starting point for CMS. We examine the effect of in-network caching of NDN on the latency, how NDN provides transparent path selection to avoid high latency in the path, and how it balances several paths for retrieving the data. We compare SDTMA-NDN to the HTTP proxies used in the existing CVMFS-Content Distribution Network (CDN). Also, we propose two NDN forwarding strategies for retrieving the data; NDN Best-Path strategy (NDN-BP) and NDN Multi-path strategy (NDN-MP). SDTMA-NDN shows a better performance than the existing HTTP protocol in transferring the data. Further, it shows more resiliency and outperforms CVMFS-CDN under different network conditions.

AB - Named Data Networking (NDN) is one of the promising future internet architectures, which focuses on the data rather than its location (IP/host-based system). NDN has several characteristics which facilitate addressing and routing the data: fail-over, in-network caching and load balancing. This makes it useful in areas such as managing scientific data across a distributed infrastructure. The Compact Muon Solenoid (CMS) experiment on the Large Hadron Collider (LHC) runs such an infrastructure and has a data access pattern amenable to Information-Centric Networking (ICN). In this paper, we propose SDTMA-NDN (Scientific Data Transfer Management Architecture using NDN) to distribute CMS's software to worker-nodes and end-users. We provide several strategies to enhance the performance of NDN in transferring the scientific data. We build this on top of CERN Virtual Machine File System (CVMFS), a global, distributed filesystem designed to be used with cache-friendly workloads. CVMFS maintains its data by using content-addressable storage, which makes it suitable for NDN and a reasonable starting point for CMS. We examine the effect of in-network caching of NDN on the latency, how NDN provides transparent path selection to avoid high latency in the path, and how it balances several paths for retrieving the data. We compare SDTMA-NDN to the HTTP proxies used in the existing CVMFS-Content Distribution Network (CDN). Also, we propose two NDN forwarding strategies for retrieving the data; NDN Best-Path strategy (NDN-BP) and NDN Multi-path strategy (NDN-MP). SDTMA-NDN shows a better performance than the existing HTTP protocol in transferring the data. Further, it shows more resiliency and outperforms CVMFS-CDN under different network conditions.

KW - CERN virtual machine file system (CVMFS)

KW - Named data networking

KW - Scientific data

UR - http://www.scopus.com/inward/record.url?scp=85074974780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074974780&partnerID=8YFLogxK

U2 - 10.1016/j.comnet.2019.106954

DO - 10.1016/j.comnet.2019.106954

M3 - Article

AN - SCOPUS:85074974780

VL - 166

JO - Computer Networks

JF - Computer Networks

SN - 1389-1286

M1 - 106954

ER -