...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International journal of information technology, communications and convergence >CoreLB: towards providing multi-metric score-based load balancing using OpenFlow and SNMP
【24h】

CoreLB: towards providing multi-metric score-based load balancing using OpenFlow and SNMP

机译：CoreLB：使用OpenFlow和SNMP提供基于多度量分数的负载平衡

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Load balancing is still one of the most crucial services offered by service providers. In spite of having several load balancing solutions in the market, this area has gained attraction with SDN and OpenFlow. In this article, we present CoreLB, a new load balancing model that takes into account a broader range of metrics from both networking devices and servers to achieve a better balancing of the servers' workload. CoreLB combines statistics of servers, using the SNMP protocol, and forwarding devices, through the OpenFlow protocol. Its scientific contribution is twofold: 1) a novel score-based load balancing metric; 2) a service agnostic metric, i.e., a metric capable of handling the requests of CPU-bound, network-bound and IO-bound services. We evaluated CoreLB through a prototype implementation, which uses web services and handles different types of requests and load balancing scenarios. Our results show that CoreLB provides a better response time from the user's viewpoint. In average, the request processing time has been reduced by 19%, when compared to non-balancing, and 9% when compared other load balancing strategies. In addition, we also achieve an evener resource utilisation when using CoreLB.
机译：负载平衡仍然是服务提供商提供的最重要的服务之一。尽管市场上有几种负载平衡解决方案，但该地区已经获得了SDN和OpenFlow的吸引力。在本文中，我们展示了Corelb，这是一个新的负载平衡模型，它考虑了来自网络设备和服务器的更广泛的指标，以实现服务器工作负载的更好平衡。 Corelb通过OpenFlow协议使用SNMP协议和转发设备将服务器的统计信息组合。其科学贡献是双重的：1）基于新的得分载荷平衡度量; 2）服务不可知性能标准，即，能够处理CPU绑定，网络绑定和IO绑定服务请求的指标。我们通过原型实现评估了CoreLB，它使用Web服务并处理不同类型的请求和负​​载平衡方案。我们的结果表明，Corelb提供了来自用户的观点的更好的响应时间。平均而言，与非平衡相比，请求处理时间已减少19％，而在比较其他负载平衡策略时9％。此外，我们还在使用Corelb时实现了均匀的资源利用率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号