JP2004046356A5 - - Google Patents

Download PDF

Info

Publication number
JP2004046356A5
JP2004046356A5 JP2002200274A JP2002200274A JP2004046356A5 JP 2004046356 A5 JP2004046356 A5 JP 2004046356A5 JP 2002200274 A JP2002200274 A JP 2002200274A JP 2002200274 A JP2002200274 A JP 2002200274A JP 2004046356 A5 JP2004046356 A5 JP 2004046356A5
Authority
JP
Japan
Prior art keywords
clusters
cluster
majority
processing
application program
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP2002200274A
Other languages
Japanese (ja)
Other versions
JP2004046356A (en
Filing date
Publication date
Application filed filed Critical
Priority to JP2002200274A priority Critical patent/JP2004046356A/en
Priority claimed from JP2002200274A external-priority patent/JP2004046356A/en
Publication of JP2004046356A publication Critical patent/JP2004046356A/en
Publication of JP2004046356A5 publication Critical patent/JP2004046356A5/ja
Pending legal-status Critical Current

Links

Claims (5)

複数のクラスタであって、各クラスタは複数のノードからなり、各クラスタの複数のノードはアプリケーションプログラムの処理を分担して並列に実行するものと、
該複数のクラスタからの複数の実行結果の中から、最も多くのクラスタからの実行結果を前記アプリケーションプログラムの実行結果として採用する多数決手段とを具備し、
前記多数決手段は、すべてのクラスタにおいてチェックポイントの処理を行った後において前記多数決の判断を行なう高信頼性クラスタシステム。A plurality of clusters, each cluster comprising a plurality of nodes, and each node of each cluster shares the processing of the application program and executes in parallel;
A majority voting means that adopts the execution result from the largest number of clusters as the execution result of the application program among the plurality of execution results from the plurality of clusters ;
The high-reliability cluster system in which the majority voting means determines the majority after performing checkpoint processing in all clusters. 前記多数決手段は、隣り合うクラスタ間で比較を繰り返すことによって多数決の判断を行なう請求項１記載のシステム。The system according to claim 1, wherein the majority decision means makes a majority decision by repeating comparison between adjacent clusters. 多数決に敗れたクラスタを通知する手段をさらに具備する請求項１記載のシステム。The system of claim 1, further comprising means for notifying a cluster that has lost a majority vote. 複数のコンピュータに請求項１〜３のいずれか１項記載のシステムを実現させるプログラム。The program which makes a some computer implement | achieve the system of any one of Claims 1-3 . 複数のクラスタであって、各クラスタは複数のノードからなり、各クラスタの複数のノードはアプリケーションプログラムの処理を分担して並列に実行するものを設け、A plurality of clusters, each cluster is composed of a plurality of nodes, and a plurality of nodes in each cluster are provided to execute processing in parallel by sharing the processing of the application program,
すべてのクラスタにおいてチェックポイントの処理を行なった後において、該複数のクラスタからの複数の実行結果の中から、最も多くのクラスタからの実行結果を前記アプリケーションプログラムの実行結果として採用することを具備する方法。After performing checkpoint processing in all clusters, the execution result from the largest number of execution results from the plurality of execution results from the plurality of clusters is employed as the execution result of the application program. Method.
JP2002200274A 2002-07-09 2002-07-09 High reliability cluster system and program for implementing the same Pending JP2004046356A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2002200274A JP2004046356A (en) 2002-07-09 2002-07-09 High reliability cluster system and program for implementing the same

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2002200274A JP2004046356A (en) 2002-07-09 2002-07-09 High reliability cluster system and program for implementing the same

Publications (2)

Publication Number Publication Date
JP2004046356A JP2004046356A (en) 2004-02-12
JP2004046356A5 true JP2004046356A5 (en) 2005-10-27

Family

ID=31707189

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2002200274A Pending JP2004046356A (en) 2002-07-09 2002-07-09 High reliability cluster system and program for implementing the same

Country Status (1)

Country Link
JP (1) JP2004046356A (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4773715B2 (en) * 2004-12-01 2011-09-14 富士通株式会社 How to get checkpoint
JP4533251B2 (en) 2005-06-09 2010-09-01 キヤノン株式会社 Information processing system and job assignment method
JP2007265193A (en) * 2006-03-29 2007-10-11 Fujitsu Ltd Job assignment program, job assigning device, and job assigning method
CN103180832B (en) * 2011-03-23 2016-01-13 株式会社日立制作所 Department of computer science unifies data processing method
JP7157709B2 (en) * 2019-07-04 2022-10-20 株式会社日立製作所 Computer system and program execution method

Similar Documents

Publication Publication Date Title
Zhu et al. Gemini: A {Computation-Centric} distributed graph processing system
Attia et al. Cygraph: A reconfigurable architecture for parallel breadth-first search
Hong et al. Efficient parallel graph exploration on multi-core CPU and GPU
Luo et al. An effective GPU implementation of breadth-first search
CN208766643U (en) Hardware tracking system
Bosilca et al. Unified model for assessing checkpointing protocols at extreme‐scale
Bhatele et al. Overcoming scaling challenges in biomolecular simulations across multiple platforms
You et al. A load-aware scheduler for MapReduce framework in heterogeneous cloud environments
EP1690163A4 (en) Transparent checkpointing and process migration in a distributed system
WO2005081104A3 (en) Methods and apparatus for processor task migration in a multi-processor system
WO2011156746A3 (en) Systems and methods for rapid processing and storage of data
CN1279471C (en) Autonomic cluster-based optimization system and method
JP2013164704A5 (en)
Chen et al. CloudRS: An error correction algorithm of high-throughput sequencing data based on scalable framework
Meneses et al. Evaluation of simple causal message logging for large-scale fault tolerant HPC systems
Dsouza et al. Resilient dynamic data driven application systems (rDDDAS)
JP2010218307A (en) Distributed calculation controller and method
Zhang et al. FBSGraph: Accelerating asynchronous graph processing via forward and backward sweeping
JP2004046356A5 (en)
Yang et al. Improving Spark performance with MPTE in heterogeneous environments
WO2005008414A3 (en) Method and apparatus for parallel action processing
WO2006083043A3 (en) Processor task migration over a network in a multi-processor system
CN104281636A (en) Concurrent distributed processing method for mass report data
Deelman et al. Breadth-first rollback in spatially explicit simulations
CN103997524A (en) Distributed type modularized web crawler with high availability and extendibility