The Effect of Networking Performance on High Energy Physics Computing

High Energy Physics (HEP) data analysis consists of simulating and analysing events in particle physics. In order to understand physics phenomena, one must collect and go through a very large quantity of data generated by particle accelerators and software simulations. This data analysis can be done using the cloud computing paradigm in distributed computing environment where data and computation can be located in different, geographically distant, data centres. This adds complexity and overhead to networking. In this paper, we study how the networking solution and its performance affects the efficiency and energy consumption of HEP computing. Our results indicate that higher latency both prolongs the processing time and increases the

[1]  Injong Rhee,et al.  CUBIC: a new TCP-friendly high-speed TCP variant , 2008, OPSR.

[2]  Carlos Reaño,et al.  Influence of InfiniBand FDR on the performance of remote GPU virtualization , 2013, 2013 IEEE International Conference on Cluster Computing (CLUSTER).

[3]  A Lahiff,et al.  Quantifying XRootD Scalability and Overheads , 2014 .

[4]  Tim Bell,et al.  Review of CERN Data Centre Infrastructure , 2012 .

[5]  Roger D. Hersch,et al.  Parallelization and scheduling of data intensive particle physics analysis jobs on clusters of PCs , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[6]  Gerd Behrmann,et al.  Xrootd in dCache - design and experiences , 2011 .

[7]  David Haussler,et al.  Navigating protected genomics data with UCSC Genome Browser in a Box , 2014, Bioinform..

[8]  Sabela Ramos,et al.  Performance analysis of HPC applications in the cloud , 2013, Future Gener. Comput. Syst..

[9]  Predrag Buncic,et al.  Recent Developments in the CernVM-File System Server Backend , 2015 .

[10]  Predrag Buncic,et al.  CernVM-FS: delivering scientific software to globally distributed computing resources , 2011, NDM '11.

[11]  Marco Cattaneo,et al.  Update of the Computing Models of the WLCG and the LHC Experiments , 2014 .

[12]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[13]  Hermann Härtig,et al.  Measuring energy consumption for short code paths using RAPL , 2012, PERV.

[14]  Ming-Jer Tsai,et al.  Optimal approximation algorithm of virtual machine placement for data latency minimization in cloud systems , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[15]  Marius Hillenbrand,et al.  High performance cloud computing , 2013, Future Gener. Comput. Syst..

[16]  Simon Lin,et al.  Managed Grids and Cloud Systems in the Asia-Pacific Research Community , 2010 .

[17]  Franco Davoli,et al.  Energy Efficiency in the Future Internet: A Survey of Existing Approaches and Trends in Energy-Aware Fixed Network Infrastructures , 2011, IEEE Communications Surveys & Tutorials.

[18]  Wei Yang,et al.  Data federation strategies for ATLAS using XRootD , 2014 .

[19]  Richard Hughes-Jones,et al.  Evaluation of Advanced TCP Stacks on Fast Long-Distance Production Networks , 2003, Journal of Grid Computing.

[20]  Feng Wang,et al.  A deep investigation into network performance in virtual machine based cloud environments , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[21]  Lorenzo Moneta,et al.  ROOT - A C++ framework for petabyte data storage, statistical analysis and visualization , 2009, Comput. Phys. Commun..

[22]  F. Fabozzi,et al.  Physics Analysis Tools for the CMS Experiment at LHC , 2008, IEEE Transactions on Nuclear Science.

[23]  Jun Yan,et al.  A Network-aware Virtual Machine Placement and Migration Approach in Cloud Computing , 2010, 2010 Ninth International Conference on Grid and Cloud Computing.

[24]  Dzmitry Kliazovich,et al.  GreenCloud: a packet-level simulator of energy-aware cloud computing data centers , 2010, The Journal of Supercomputing.

[25]  M Tadel,et al.  XRootd, disk-based, caching proxy for optimization of data access, data placement and data replication , 2014 .

[26]  P. Elmer,et al.  XROOTD-A highly scalable architecture for data access , 2005 .