• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Reconfigurable Parallel Processing Plug&Play Clustering

Research Project

Project/Area Number 12558025
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section展開研究
Research Field 計算機科学
Research InstitutionTokyo Institute of Technology

Principal Investigator

MATSUOKA Satoshi  Global Scientific information and Computing Center, Professor, 学術国際情報センター, 教授 (20221583)

Co-Investigator(Kenkyū-buntansha) ISHIKAWA Yutaka  National Institute of Advanced Industrial Science and Technology, Researcher, 情報アーキテクチャ部, 主任研究官
OGAWA Hirotaka  Graduate School of Science, Dept. of Mathematical and Computer Sciences, Tokyo Institute of Technology, Assistant, 大学院・情報理工学研究科, 助手 (90302968)
AIDA Kento  Inter Disciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Lecturer, 大学院・総合理工学研究科, 講師 (80247212)
TAKAGI Hiromitsu  National Institute of Advanced Industrial Science and Technology, Researcher, 情報アーキテクチャ部, 主任研究官
Project Period (FY) 2000 – 2001
Project Status Completed (Fiscal Year 2001)
Budget Amount *help
¥8,100,000 (Direct Cost: ¥8,100,000)
Fiscal Year 2001: ¥1,000,000 (Direct Cost: ¥1,000,000)
Fiscal Year 2000: ¥7,100,000 (Direct Cost: ¥7,100,000)
KeywordsPlug & Play / Lucie / Dependable computing / Fault-tolerant MPI / Automated Cluster Installation and Configuration / Node hot swap / Large-scale cluster management / チェックポイント / マイグレーション / 並列処理 / クラスタ評価環境
Research Abstract

The objective of the project is to push the technological envelop of fault tolerance and reconfigurability in large-scale clustering such that the clusters become almost self-sustaining, and reconfiguring is a matter of "Plug&Play". Some of the salient results are as follows :
1) Construction of the "Plug&Play" clustering testbed (20 nodes of DELL Inspiron , Mobile Celeron 600 MHz, 128 MB Memory, 20 GB HDD, 3COM Plug&Play PCMCIA 100Base-T Network Card). This served as a flexible testbed for middleware development. It was also very compact (a small rack) and low power (less than 400 watts/20 nodes)
2) Development of the Parakeet Fault Tolerant, High-Performance Cluster MPI which allows various checkpointing algorithms to be selected from a set of available algorithm by the user according to his application characteristics. Parakeet is an entirely user-level implementation, is portable and efficient, and frees the users from checkpointing concerns within his code. We have implemented vario … More us checkpointing strategies to achieve the best efficiency, and conducted detailed performance analysis comparing with full restart.
3) Self-organizing cluster middleware, the Lucie prototype. As a basic technology, plug&play clustering requires hot swapping of nodes, reconfiguration of software organization within a node, and dynamic partition management. Lucie builds on existing Linux tools to implement full cluster configuration capabilities in an automated fashion. Lucie allows fully automated (re)installation and configuration of every node in a cluster in a very rapid fashion.
4) Prototyping scalable, secure and self-organizing cluster communication. We have identified that scalable, reliable, secure, and self-organizing communication within the cluster node is the essential foundation for reliable, plug&play clustering. We have prototyped some of the ideas in the Gfarm (cluster middleware for Petascale Datagrid processing) job manager : there, the self-organizing process ring structure governs all the nodes, and jobs can be started up rapidly in parallel, in a safe secure manner. Less

Report

(3 results)
  • 2001 Annual Research Report   Final Research Report Summary
  • 2000 Annual Research Report
  • Research Products

    (28 results)

All Other

All Publications (28 results)

  • [Publications] Yoshiaki Sakae, Sattoshi Matsuoka: "MPC++ Performance for Commodity Clustering"Proceedings of High Performance Network Computing. LNCS No.2110. 503-512 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 栄 純明, 松岡 聡, 佐藤 三久, 長谷川 篤史, 原田 浩: "ソフトウェア分散共有メモリ上のOpenMP Omni/SCASHのSPLASH2による性能評価"情報処理学会研究報告. HPC-85. 187-192 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 高宮 安仁, 松岡 聡: "ユーザ透過な耐故障性を実現するMPIへ向けて"情報処理学会研究報告. HPC-87. 129-134 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 笹生 健, 松岡 聡, 建部 修見: "ヘテロなクラスタ環境における並列LINPACKの最適化"情報処理学会研究報告. HPC-86. 49-54 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Y.Sohda, H.Nakada, S.Matsuoka, H.Ogawa: "Implementation of a Portable Software DSM in Java"Proceedings of ACM JavaGrande/ISCOPE 2001. 163-172 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 岩崎 聖, 松岡 聡, 曽田 哲之, 平野 基孝, 建部 修見, 関口 智嗣: "Grid環境における大規模クラスタ向けジョブマネジメントアーキテクチャの実装および性能評価"情報処理学会研究報告. Vol.2002,No.22. 77-42 (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 白砂 哲, 中田 秀基, 松岡 聡: "Ninfシステムにおけるフォールトトレランス"情報処理学会ハイパフォーマンスコンピューティング研究会. Vol.2001,No.77. 153-158 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] 白砂 哲, 中田 秀基, 松岡 聡, 関口 智嗣: "XMLベースGridRPCシステムの構築と評価"日本ソフトウェア科学会 第5回プログラミングおよび応用のシステムに関するワークショップ. (2002)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Satoshi Matsuoka, Shigeo Itou: "Towards performance evaluation of high-performance computing on multiple Java platforms"Future Generation Computer System. 18. 281-291 (2001)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Yoshiaki Sakae, Satoshi Matsuoka: "MPC++ Performance for Commodity Clustering"Proc. High Performance Network Computing. 503-512 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Yukishiko Sohda, Hidemoto Nakada, Satoshi Matsuoka: "Implementation of a Portable Software DSM in Java"Proc. ACM Java Grande/ISCOPE 2001. 163-172 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Satoshi Matsuoka, Shigeo Itou: "Towards performance evaluation of high-performance computing on multiple Java platforms"Future Generation Computer System. 281-291 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Satoshi Matsuoka: "AjaPack : A Performance Portable Parallel Java Numerical Library"Prod. AGM 2000 Java Grande Conference. 140-149 (2001)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2001 Final Research Report Summary
  • [Publications] Yoshiaki Sakae, Satoshi Matsuoka: "MPC++Performance for Commodity Clustering"Proceedings of High Performance Network Computing. LNCS No.2110. 503-512 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 栄 純明, 松岡 聡, 佐藤 三久, 長谷川 篤史, 原田 浩: "ソフトウェア分散共有メモリ上のOpenMP Omni/SCASHのSPLASH2による性能評価"情報処理学会研究報告. HPC・85. 187-192 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 高宮 安仁, 松岡 聡: "ユーザ透過な耐故障性を実現するMPIへ向けて"情報処理学会研究報告. HPC・87. 129-134 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 笹生 健, 松岡 聡, 建部 修見: "ヘテロなクラスタ環境における並列LINPACKの最適化"情報処理学会研究報告. HPC・86. 49-54 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] Y.Sohda, H.Nakada, S.Matsuoka, H.Ogawa: "Implementation of a Portable Software DSM in Java"Proceedings of ACM Java Grande/ISCOPE2001. 163-172 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 岩崎 聖, 松岡 聡, 曽田 哲之, 平野 基孝, 建部 修見, 関口 智嗣: "Grid環境における大規模クラスタ向けジョブマネジメントアーキテクチャの実装および性能評価"情報処理学会研究報告. Vol.2002, No.22. 37-42 (2002)

    • Related Report
      2001 Annual Research Report
  • [Publications] 白砂 哲, 中田 秀基, 松岡 聡: "Ninfシステムにおけるフォールトトレランス"情報処理学会ハイパフォーマンスコンピューティング研究会. Vol.2001, No.77. 153-158 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 白砂 哲, 中田 秀基, 松岡 聡, 関口 智嗣: "XMLベースGridRPCシステムの構築と評価"日本ソフトウェア科学会 第5回プログラミングおよび応用のシステムに関するワークショップ. (2002)

    • Related Report
      2001 Annual Research Report
  • [Publications] Satoshi Matsuoka, Shigeo Itou: "Towards performance evaluation of high-performance computing on multiple Java platforms"Future Generation Computer System. 18. 281-291 (2001)

    • Related Report
      2001 Annual Research Report
  • [Publications] 松岡聡: "MPC++-on-MPIのコモディティクラスタ環境における評価"情報処理学会論文誌:ハイパフォーマンスコンピューティングシステム. 41-8(HPS2). 60-72 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] Satoshi Matsuoka: "A Ja.Pack;A Performance Portable Parallel Java Numerical Library"Proceedings of the ACM 2000 Java Grande Conference. 140-149 (2000)

    • Related Report
      2000 Annual Research Report
  • [Publications] 松岡聡: "PCクラスタにおけるEthernetによる高速ユーザレベルバリアの性能評価"2000-HPC-82. 2000. 131-136

    • Related Report
      2000 Annual Research Report
  • [Publications] 松岡聡: "MPC++Multi-Thread Template Libraryの様々な通信レイヤ上での実装と性能評価"2000-HPC-82. 2000. 137-142

    • Related Report
      2000 Annual Research Report
  • [Publications] Satoshi Matsuoka: "Implementation of a Portable Software DSM in Java"Proceedings of ACM Java Grande/ISCOPE 2001. (掲載予定). (2001)

    • Related Report
      2000 Annual Research Report
  • [Publications] 小川宏高: "Java向けソフトウェア分散共有メモリの実現"情報処理学会論文誌:プログラミング. 2000(掲載予定).

    • Related Report
      2000 Annual Research Report

URL: 

Published: 2000-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi