（1，上海海洋大學  海洋科學學院，上海 201306）
摘要：Linux 有不同的集群系統，可以滿足不同的用途和需要。但確定應該使用哪一個集群系統卻不是那么容易。問題的部分原因在于集群系統可以用于不同場合。公司IT經理可能關心如何使服務器運行時間更長，或使應用程序運行得更快，而科學家可能更關心在集群系統上進行大規模數值模擬計算。兩者都需要集群，但是各自需要不同特性的群集，而且有舊集群利用和管理的需求，這就需要整合集群來滿足不同特性業務需求。本文以前期調查及實際參與了不同形式的集群系統建設為基礎，以科學計算集群為例，來詳細闡述了基于Linux不同系統架構的集群整合關鍵技術。
關鍵詞：集群；Linux集群；整合
中圖分類號：TP 393              文獻標識碼：A
Key Technology Research and Implementation of Linux-based cluster integration
WANG Xiao1
（1.College of marine sciences,Shanghai Ocean University,Shanghai 201306,China.wangxiao）
【Abstract】 Linux has different cluster system, which can meet different uses and demand.
But,which cluster system you should choose is not so easy. Part of the problem is that the cluster system can be used for different occasions.IT managers in the corporate ,may be concerned about how to make the server run longer, or to make applications run faster, while scientists may be more concerned about the large-scale numerical simulation on a cluster system. The two both need cluster system, but each needs cluster of different characteristics, and needs old cluster utilization and management , which needs to integrate cluster to meet the different business demand. In this paper, based on the preliminary investigation and the actual participation of building the different cluster system,for example,scientific computing clusters,to elaborate on the key technologies of cluster integration based on Linux different cluster system architecture.
【Key words】cluster;Linux cluster; integration

參考文獻:
[1] "Rock-Hard Lustre: Trends in Scalability and Quality". Nathan Rutman, Xyratex. Retrieved 2012-02-02
[2]http://blog.163.com/security_help/blog/static/245109032007263134518. 2007-03-06.
[3] Mark Baker, et al., Cluster Computing White Paper [7], 11 Jan 2001.
[4] Evan Marcus, Hal Stern: Blueprints for High Availability: Designing Resilient Distributed Systems, John Wiley & Sons, ISBN 0-471-35601-8
[5] Greg Pfister: In Search of Clusters, Prentice Hall, ISBN 0-13-899709-8
[6] Rajkumar Buyya (editor): High Performance Cluster Computing: Architectures and Systems, Volume 1, ISBN 0-13-013784-7, and Volume 2, ISBN 0-13-013785-5, Prentice Hall, NJ, USA, 1999.
[7] William W. Hargrove and Forrest M. Hoffman (1999). "Cluster Computing: Linux Taken to the Extreme". Linux magazine. Retrieved October 18, 2011.
[8] M. Yokokawa et al The K Computer, in "International Symposium on Low Power Electronics and Design" (ISLPED) 1-3 Aug. 2011, pages 371-372

基金項目：上海高校青年教師培養資助計劃（項目編號：B-5409-12-0009）