作者: Adriana Iamnitchi , Ian Foster , Daniel C. Nurmi
DOI:
关键词:
摘要: Computational grids provide mechanisms for sharing and accessing large heterogeneous collections of remote resources such as computers, online instruments, storage space, data, applications. Resources are requested (”discovered”) by specifying a set desired attributes. Resource attributes have various degrees dynamism, from mostly static attributes, operating system version, to highly dynamic ones, available network bandwidth or CPU load. Another dimension dynamism is introduced variable diverse policies: made the grid community based on locally defined potentially changing policies. In environment it often more efficient forward requests than disseminate resource information that soon becomes stale. We investigate request forwarding strategies in peer-to-peer like architecture: each peer acts independently, possibly partial outdated about rest forwards cannot solve another peer. these environments with different characteristics, distributions, networks up 32768 (215) peers. The results allow characterize correlation between discovery performance forwarding, user patterns.