摘要
本文提出一种自适应副本管理机制—AdpReplica。AdpReplica将期望可用性和一致性维护开销看成副本数的函数,并建立自适应模型。该模型动态管理副本,使文件副本数维持在一个合理的水平,既满足用户的期望可用性,提高访问效率和平衡负载,又减少带宽消耗,保证系统稳定,为用户提供满意的存储QoS。
In this paper, we present an Adaptive Replica Management Mechanism called AdpReplica. The AdpReplica constructs adaptive model regarding user anticipant availability and consistency maintenance overload as a function of a file's replica number. The AdpReplica model manages replica dynamically and maintains a rational replica number, not only satisfying the user anticipant availability, improving access efficiency and balancing overload, but also reducing bandwidth requirement, keeping the system stable and proving satisfied storage QOS.
出处
《计算机科学》
CSCD
北大核心
2004年第12期34-36,51,共4页
Computer Science
基金
国家95重点攻关项目支持
