排序方式: 共有18条查询结果,搜索用时 171 毫秒
1.
Using web services to expose applications over the Internet is now a widely accepted practice. Currently, there are several ongoing efforts that provide ways to effectively compose web services distributed across different organizations. One of the problems underlying the deployment of such composite services on the web, however, is service co-allocation that arises when a composite service needs to ensure all the required component services to be available for execution at the same time. Motivated by this, this paper presents a new decentralized protocol, named web service co-allocation protocol (WSCP), which can facilitate fast execution of composite web services. The proposed framework is an enhancement of the famous two phase commit protocol through the incorporation of tentative hold phase as well as the employment of a new high performance backoff protocol developed to better address the dynamics of the service co-allocation problem. The simulation results show that the proposed approach yields significant improvements over existing protocols. 相似文献
2.
Characterization of Bandwidth-Aware Meta-Schedulers for Co-Allocating Jobs Across Multiple Clusters 总被引:6,自引:2,他引:4
William?M.?JonesEmail author Walter?B.?LigonIII Louis?W.?Pang Dan?Stanzione 《The Journal of supercomputing》2005,34(2):135-163
In this paper, we present a bandwidth-centric job communication model that captures the interaction and impact of simultaneously co-allocating jobs across multiple clusters. We compare our dynamic model with previous research that utilizes a fixed execution time penalty for co-allocated jobs. We explore the interaction of simultaneously co-allocated jobs and the contention they often create in the network infrastructure of a dedicated computational multi-cluster.We also present several bandwidth-aware co-allocating meta-schedulers. These schedulers take inter-cluster network utilization into account as a means by which to mitigate degraded job run-time performance. We make use of a bandwidth-centric parallel job communication model that captures the time-varying utilization of shared inter-cluster network resources. By doing so, we are able to evaluate the performance of multi-cluster scheduling algorithms that focus not only on node resource allocation, but also on shared inter-cluster network bandwidth. 相似文献
3.
提出一种支持时间和空间二维松弛的预留接纳策略,允许在一定条件下接纳与已有预留存在叠交的预留请求,从而降低预留服务对系统性能的负面影响。理论分析给出了松弛预留策略的系统收益与风险计算方法,并针对独立任务的协同预留问题设计了相应的请求接纳算法。实验结果表明,松弛预留策略能有效提高资源利用率并降低预留请求拒绝率,当系统面对较高的预留请求率时,松弛预留策略对动态负载变化具有良好的自适应性。 相似文献
4.
协同分配是在分布式计算环境中进行资源分配的一种重要技术,用于把一个应用程序分解为多个子作业,然后将其分配到多个资源上同时处理来满足特定的性能要求。本文提出了一个离散事件驱动的网格资源协同分配仿真系统,实现了对用户、调度器、协同分配器、协同预留器等协同分配相关实体的仿真,实现了FCFS、FPFS、Backfill等主要的协同分配调度算法和策略,可用于资源协同分配相关的分布式计算环境的资源管理和调度算法的仿真和研究。 相似文献
5.
P2P网络环境下的一种高效虚拟协同服务模型 总被引:1,自引:0,他引:1
在现实网络中,资源主要集中在少数的重要节点中,大量节点是服务请求者.由于P2P网络是建立在Internet之上的应用层虚拟网络,加上网络中搭便车现象日益严重,在广域环境下,不可避免地存在拥塞、单点失效、效率和服务质量不高的问题.针对这些问题,通过在系统中动态地构造由协同服务盟员组成的服务池来解决.提出了一种有盟主的虚拟协同服务组织模型,旨在现实环境下针对盟主的目标需求,解决盟主如何动态组织自主的协同伙伴和构建虚拟组织协同进行求解的问题.构造了基于D-S证据推理的服务盟员选择策略,运用节点交易历史信息和推荐证书的方法来表征备选服务盟员的全局信任特征属性,给出了构建虚拟协同服务池的数学模型、约束条件和构造规则,并进行了较为详细的分析.仿真实验表明,动态构造服务池的负载平衡策略能较好地解决P2P网络中存在拥塞、单点失效、效率和服务质量不高的问题,极大地改善了P2P网络的服务质量. 相似文献
6.
为异构分布式系统中提供良好的资源映射算法,可以有效、加速部署在分布式系统中的应用程序的执行,其中Alhusaini算法是该研究领域中成功和具有影响力的算法之一。本文针对该算法的不足提出了一个两阶段动态资源映射的改进算法:第一个阶段仅仅收集数据以提供给第二阶段使用;在第二个阶段选择一组独立的任务并根据这些任务的权值将它们映射到相关资源中去。改进的算法有效地解决了Alhusaini算法存在的算法复杂度过高和在通信密集型应用中算法效率低等问题。 相似文献
7.
8.
通过对网格计算中资源协同调度机制的研究,根据该机制的资源协同分配需求,提出一个以Globus Toolkit为平台的基于网格计算的分布协同计算模型。在基于经济模型的作业调度机制的竞价机制中,给出一个较为完善的价格函数模型以及相应的作业预测完成时间模型,利用设计的价格函数模型实现资源提供的主观能动性,使得资源的调配更加合理、快速。同时,在分布式计算模型中还给出一个基于备份的作业调度容错机制。 相似文献
9.
10.