会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Highly scalable system and method of regulating internet traffic to server farm to support (min,max) bandwidth usage-based service level agreements
    • 高度可扩展的系统和方法,将互联网流量调整到服务器场,以支持(最小,最大)带宽使用率的服务级别协议
    • US06857025B1
    • 2005-02-15
    • US09543207
    • 2000-04-05
    • Kiyoshi MaruyamaGerman GoldszmidtJean LorrainKaren Appleby-Hougham
    • Kiyoshi MaruyamaGerman GoldszmidtJean LorrainKaren Appleby-Hougham
    • G06F15/16H04L12/56H04L29/06H04L29/08
    • H04L69/329H04L47/10H04L47/11H04L47/125H04L47/15H04L47/193H04L47/70H04L47/781H04L47/808H04L47/822H04L47/823H04L67/1002H04L67/1012H04L67/1029H04L67/325
    • A highly scalable system and method for supporting (mim,max) based Service Level Agreements (SLA) on outbound bandwidth usage for a plurality of customers whose applications (e.g.,Web sites) are hosted by a server farm that consists of a very large number of servers. The system employs a feedback system that enforces the outbound link bandwidth SLAs by regulating the inbound traffic to a server or server farm. Inbound traffic is admitted to servers using a rate denoted as Rt(i,j), which is the amount of the ith customer's jth type of traffic that can be admitted within a service cycle time to servers which support the ith customer. A centralized device computes Rt(i,j) based on the history of admitted inbound traffic to servers, the history of generated outbound traffic from servers, and the SLAs of various customers. The Rt(i,j) value is then relayed to one or more inbound traffic limiters that regulate the inbound traffic using the rates Rt(i,j) in a given service cycle time. The process of computing and deploying Rt(i,j) values is repeated periodically. In this manner, the system provides a method by which differentiated services can be provided to various types of traffic, the generation of output from a server or a server farm is avoided if that output cannot be delivered to end users, and revenue can be maximized when allocating bandwidth beyond the minimums.
    • 一种用于支持(mim,max)的服务级别协议(SLA)的高度可扩展的系统和方法,用于多个客户的出站带宽使用,其应用程序(例如,网站)由服务器场托管,服务器场由非常大的数目 的服务器。 系统采用反馈系统,通过调节到服务器或服务器场的入站流量来强制执行出站链路带宽SLA。 入站流量被允许使用表示为Rt(i,j)的速率进入服务器,该速率是可以在服务周期内允许的服务器中支持的第i类客户的第j类流量的数量 我客户。 集中式设备根据入站到服务器的入站流量的历史记录,服务器生成的出站流量和不同客户的SLA的历史记录计算Rt(i,j)。 然后将Rt(i,j)值中继到一个或多个入站流量限制器,其在给定的服务周期时间内使用速率Rt(i,j)来调节入站流量。 计算和部署Rt(i,j)值的过程周期性地重复。 以这种方式,系统提供了一种可以将差分服务提供给各种类型的业务的方法,如果该输出不能传递给最终用户,则避免从服务器或服务器场的输出的产生,并且可以使收入最大化 当分配带宽超过最小值时。