公开(公告)号：US06519636B2

公开(公告)日：2003-02-11

申请号：US09181376

申请日：1998-10-28

申请人： Robert Engel ,  Tsipora P. Barzilai ,  Dilip Dinkar Kandlur ,  Ashish Mehra

发明人： Robert Engel ,  Tsipora P. Barzilai ,  Dilip Dinkar Kandlur ,  Ashish Mehra

IPC分类号： G06F15173

CPC分类号： H04L47/10 ,  H04L47/20 ,  H04L47/21 ,  H04L47/22 ,  H04L47/2416 ,  H04L47/2441 ,  H04L63/02 ,  H04L63/0227 ,  H04L63/0263 ,  H04L69/22

摘要： A computer connected to one or more networks through appropriate network interfaces is used to classify, manipulate, and/or control communications, e.g., packets sent and/or received over the network by one or more applications executing in the computer. Each application is connected to the network through one or more sockets to enable this communication. The computer also comprises one or more rule sets of one or more rules. A socket set of one or more of the sockets is associated with only one of the rule sets. The rules in the rule set are used to control one or more of the packets communicated by the applications communicating over the socket(s) associated with the respective rule set. Rules can be added to the rule set, deleted from the rule set, or modified in order to classify, manipulate, and/or control the communication of the packets, e.g. to control the rate at which the packets are sent or to provide certain security functions.

摘要翻译： 通过适当的网络接口连接到一个或多个网络的计算机被用于通过在计算机中执行的一个或多个应用来分类，操纵和/或控制通信，例如通过网络发送和/或接收的分组。 每个应用程序通过一个或多个套接字连接到网络，以实现此通信。 计算机还包括一个或多个规则集合的一个或多个规则。 一个或多个套接字的套接字集仅与规则集中的一个相关联。 规则集中的规则用于控制通过与相应规则集相关联的套接字通信的应用传送的一个或多个分组。 可以将规则添加到规则集中，从规则集中删除或修改，以便分类，操纵和/或控制分组的通信，例如。 以控制分组发送的速率或提供某些安全功能。

公开(公告)号：US08024424B2

公开(公告)日：2011-09-20

申请号：US12544026

申请日：2009-08-19

申请人： Douglas M. Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

发明人： Douglas M. Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

IPC分类号： G06F15/16

CPC分类号： H04L67/16 ,  H04L29/06 ,  H04L67/28 ,  H04L67/2819 ,  H04L67/325 ,  H04L67/42 ,  H04L69/22 ,  H04L69/329

摘要： The increasing number of Internet users and innovative new services such as e-commerce are placing new demands on Web servers. It is becoming essential for Web servers to provide performance isolation, have fast recovery times, and provide continuous service during overload at least to preferred customers. The invention describes a kernel-based architecture for content-aware service differentiation that protects Web servers against overload by controlling the amount and rate of work entering the system. We have invented a mechanism that provides admission control and service differentiation based on connection and application level information. The application header-based connection control uses application-level information (such as URIs and cookies for HTTP) to define different service differentiation actions. The present invention provides the kernel mechanisms that are more efficient and scalable than application level controls implemented in current Web servers.

摘要翻译： 越来越多的互联网用户和创新的新服务，如电子商务正在为Web服务器提出新的要求。 Web服务器至关重要的是提供性能隔离，快速恢复时间，并在至少向优先客户过载时提供持续服务。 本发明描述了用于内容感知服务差异化的基于内核的架构，其通过控制进入系统的工作量和速率来保护Web服务器免受过载。 我们发明了一种基于连接和应用级信息提供入网控制和服务差异化的机制。 基于应用程序标头的连接控制使用应用程序级信息（例如HTTP的URI和Cookie）来定义不同的服务区分操作。 本发明提供了比当前Web服务器中实现的应用程序级别控制更有效和可扩展的内核机制。

公开(公告)号：US07127492B1

公开(公告)日：2006-10-24

申请号：US09702927

申请日：2000-10-31

申请人： Seraphin Bernard Calo ,  Richard Orville LaMaire ,  Ashish Mehra ,  Anees Abdul Shaikh ,  Renu Tewari ,  Dinesh Chandra Verma

发明人： Seraphin Bernard Calo ,  Richard Orville LaMaire ,  Ashish Mehra ,  Anees Abdul Shaikh ,  Renu Tewari ,  Dinesh Chandra Verma

IPC分类号： G06F15/167

CPC分类号： H04L67/1008 ,  H04L67/1002 ,  H04L67/1014 ,  H04L67/1027 ,  H04L67/28 ,  H04L67/2809 ,  H04L67/2814

摘要： The present invention presents methods and apparatus supporting acceleration of networked applications by means of dynamic distributed execution and maintenance. It also enables management and administration of the distributed components of the networked applications from a responsible point of origination. The method and apparatus deploys a plurality of proxy servers within the network. Clients are directed to one of the proxy servers using wide area load balancing techniques. The proxy servers download programs from backend servers and cache them in a local store. These programs, in conjunction with data stored at cached servers, are used to execute applications at the proxy server, eliminating the need for a client to communicate to a backend server to execute a networked application.

摘要翻译： 本发明提出了通过动态分布式执行和维护支持联网应用加速的方法和装置。 它还可以从负责任的角度管理和管理联网应用程序的分布式组件。 该方法和装置在网络内部署多个代理服务器。 使用广域负载平衡技术将客户端定向到其中一个代理服务器。 代理服务器从后端服务器下载程序并将其缓存在本地存储中。 这些程序与存储在缓存服务器上的数据一起用于在代理服务器上执行应用程序，从而无需客户端与后端服务器通信以执行联网应用程序。

公开(公告)号：US20090307350A1

公开(公告)日：2009-12-10

申请号：US12544026

申请日：2009-08-19

申请人： Douglas Morgan Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

发明人： Douglas Morgan Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

IPC分类号： G06F15/173

CPC分类号： H04L67/16 ,  H04L29/06 ,  H04L67/28 ,  H04L67/2819 ,  H04L67/325 ,  H04L67/42 ,  H04L69/22 ,  H04L69/329

摘要： The increasing number of Internet users and innovative new services such as e-commerce are placing new demands on Web servers. It is becoming essential for Web servers to provide performance isolation, have fast recovery times, and provide continuous service during overload at least to preferred customers. The invention describes a kernel-based architecture for content-aware service differentiation that protects Web servers against overload by controlling the amount and rate of work entering the system. We have invented a mechanism that provides admission control and service differentiation based on connection and application level information. The application header-based connection control uses application-level information (such as URIs and cookies for HTTP) to define different service differentiation actions. The present invention provides the kernel mechanisms that are more efficient and scalable than application level controls implemented in current Web servers.

摘要翻译： 越来越多的互联网用户和创新的新服务，如电子商务正在为Web服务器提出新的要求。 Web服务器至关重要的是提供性能隔离，快速恢复时间，并在至少向优先客户过载时提供持续服务。 本发明描述了用于内容感知服务差异化的基于内核的架构，其通过控制进入系统的工作量和速率来保护Web服务器免受过载。 我们发明了一种基于连接和应用级信息提供入网控制和服务差异化的机制。 基于应用程序标头的连接控制使用应用程序级信息（例如HTTP的URI和Cookie）来定义不同的服务区分操作。 本发明提供了比当前Web服务器中实现的应用程序级别控制更有效和可扩展的内核机制。

公开(公告)号：US20080059636A1

公开(公告)日：2008-03-06

申请号：US11933200

申请日：2007-10-31

申请人： Douglas Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

发明人： Douglas Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

IPC分类号： G06F15/16

CPC分类号： H04L67/16 ,  H04L29/06 ,  H04L67/28 ,  H04L67/2819 ,  H04L67/325 ,  H04L67/42 ,  H04L69/22 ,  H04L69/329

摘要： The increasing number of Internet users and innovative new services such as e-commerce are placing new demands on Web servers. It is becoming essential for Web servers to provide performance isolation, have fast recovery times, and provide continuous service during overload at least to preferred customers. The invention describes a kernel-based architecture for content-aware service differentiation that protects Web servers against overload by controlling the amount and rate of work entering the system. We have invented a mechanism that provides admission control and service differentiation based on connection and application level information. The application header-based connection control uses application-level information (such as URIs and cookies for HTTP) to define different service differentiation actions. The present invention provides the kernel mechanisms that are more efficient and scalable than application level controls implemented in current Web servers.

摘要翻译： 越来越多的互联网用户和创新的新服务，如电子商务正在为Web服务器提出新的要求。 Web服务器至关重要的是提供性能隔离，快速恢复时间，并在至少向优先客户过载时提供持续服务。 本发明描述了用于内容感知服务差异化的基于内核的架构，其通过控制进入系统的工作量和速率来保护Web服务器免受过载。 我们发明了一种基于连接和应用级信息提供入网控制和服务差异化的机制。 基于应用程序标头的连接控制使用应用程序级信息（例如HTTP的URI和Cookie）来定义不同的服务区分操作。 本发明提供了比当前Web服务器中实现的应用程序级别控制更有效和可扩展的内核机制。

公开(公告)号：US07315892B2

公开(公告)日：2008-01-01

申请号：US10053012

申请日：2002-01-18

申请人： Douglas Morgan Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

发明人： Douglas Morgan Freimuth ,  Ashish Mehra ,  Renu Tewari ,  Thiemo Voigt

IPC分类号： G06F15/16 ,  G06F7/04

CPC分类号： H04L67/16 ,  H04L29/06 ,  H04L67/28 ,  H04L67/2819 ,  H04L67/325 ,  H04L67/42 ,  H04L69/22 ,  H04L69/329

摘要： The increasing number of Internet users and innovative new services such as e-commerce are placing new demands on Web servers. It is becoming essential for Web servers to provide performance isolation, have fast recovery times, and provide continuous service during overload at least to preferred customers. The invention describes a kernel-based architecture for content-aware service differentiation that protects Web servers against overload by controlling the amount and rate of work entering the system. We have invented a mechanism that provides admission control and service differentiation based on connection and application level information. The application header-based connection control uses application-level information (such as URIs and cookies for HTTP) to define different service differentiation actions. The present invention provides the kernel mechanisms that are more efficient and scalable than application level controls implemented in current Web servers.

摘要翻译： 越来越多的互联网用户和创新的新服务，如电子商务正在为Web服务器提出新的要求。 Web服务器至关重要的是提供性能隔离，快速恢复时间，并在至少向优先客户过载时提供持续服务。 本发明描述了用于内容感知服务差异化的基于内核的架构，其通过控制进入系统的工作量和速率来保护Web服务器免受过载。 我们发明了一种基于连接和应用级信息提供入网控制和服务差异化的机制。 基于应用程序标头的连接控制使用应用程序级信息（例如HTTP的URI和Cookie）来定义不同的服务区分操作。 本发明提供了比当前Web服务器中实现的应用程序级别控制更有效和可扩展的内核机制。