Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Interaction between MPI and TCP in grids.

Ludovic Hablot 1, 2 Olivier Glück 1, 2 Jean-Christophe Mignot 1, 2 Romaric Guillier 1, 2 Sébastien Soudan 1, 2 Pascale Vicat-Blanc Primet 1, 2 
2 RESO - Protocols and softwares for very high-performance network
Inria Grenoble - Rhône-Alpes, ENS Lyon - École normale supérieure - Lyon, CNRS - Centre National de la Recherche Scientifique : UMR5668
Abstract : As MPI applications are more and more resource consuming, they need to be executed on grids. The communications on the WAN interconnecting clusters mostly use TCP which suffers from WAN features: high latency, sharing between users, bandwidth smaller than the aggregate bandwidth of the nodes. In this report, we first study the interaction between MPI and TCP on grids. We show why the nature of MPI traffic raises problems while using TCP on WAN links. TCP's loss detection and congestion control mechanism can both slow down the application. Then, we propose MPI5000, a transparent applicative layer between MPI and TCP, using proxies to improve the execution of MPI applications on a grid. Proxies aim at splitting TCP connections in order to detect losses faster and avoid to return in a slowstart phase after an idle time. Finally, we test our layer on Grid'5000, the French research grid, using MPICH2. The results on the NPB (NAS Parallel Benchmarks) validate our architecture that reduces the number of idle timeout and the number of long-distance retransmissions for certain benchmarks, namely BT, SP and LU benchmarks. Using MPI5000, these applications can decrease their execution time by 35%, 28%, and, 15% respectively.
Keywords : MPI TCP TCP Split proxies
Complete list of metadata

Cited literature [23 references]  Display  Hide  Download
Contributor : Ludovic Hablot Connect in order to contact the contributor
Submitted on : Tuesday, June 2, 2009 - 10:54:47 AM
Last modification on : Friday, February 4, 2022 - 3:18:18 AM
Long-term archiving on: : Monday, October 15, 2012 - 11:27:11 AM


Files produced by the author(s)


  • HAL Id : ensl-00389842, version 1



Ludovic Hablot, Olivier Glück, Jean-Christophe Mignot, Romaric Guillier, Sébastien Soudan, et al.. Interaction between MPI and TCP in grids.. 2009. ⟨ensl-00389842⟩



Record views


Files downloads