公开(公告)号：US07209977B2

公开(公告)日：2007-04-24

申请号：US09968127

申请日：2001-10-01

申请人： Arup Acharya ,  Anees A. Shaikh ,  Renu Tewari ,  Dinesh C. Verma

发明人： Arup Acharya ,  Anees A. Shaikh ,  Renu Tewari ,  Dinesh C. Verma

IPC分类号： G06F15/173 ,  H04L12/28 ,  H04L12/56

CPC分类号： H04L29/12783 ,  H04L29/12009 ,  H04L45/306 ,  H04L61/35 ,  H04L67/1002 ,  H04L67/1023 ,  H04L67/14 ,  H04L67/2804 ,  H04L67/2819 ,  H04L67/2876 ,  H04L67/327 ,  H04L69/16 ,  H04L69/161 ,  H04L69/162 ,  H04L69/163 ,  H04L69/329 ,  H04L2029/06054

摘要： This invention provides methods and apparatus for web switching without connection termination while providing content routing functionality. Content-aware web switches terminate incoming TCP connections and inspect the HTTP header to recognize the URL (content) being requested from a web server farm. This invention maps application layer information (URLs) to MPLS labels. This allows a standard MPLS switch to provide web switching functionality without terminating TCP connections. In addition to content routing, this method is applied for client session affinity, server load balancing and service differentiation. This invention also relates to using TCP port numbers instead of MPLS labels to achieve web-switching functionality through the use of a TCP router that translates IP address and port numbers.

摘要翻译： 本发明提供了用于在不提供内容路由功能的情况下连接终止的web切换的方法和装置。 内容感知Web交换机终止传入的TCP连接，并检查HTTP头以识别从Web服务器场请求的URL（内容）。 本发明将应用层信息（URL）映射到MPLS标签。 这允许标准的MPLS交换机提供Web切换功能而不终止TCP连接。 除了内容路由，该方法也适用于客户端会话亲和性，服务器负载均衡和服务差异化。 本发明还涉及使用TCP端口号而不是MPLS标签来通过使用转换IP地址和端口号的TCP路由器来实现web切换功能。

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：US20050071599A1

公开(公告)日：2005-03-31

申请号：US10676464

申请日：2003-09-30

申请人： Dharmendra Modha ,  Divyesh Jadav ,  Pawan Goyal ,  Renu Tewari

发明人： Dharmendra Modha ,  Divyesh Jadav ,  Pawan Goyal ,  Renu Tewari

IPC分类号： G06F9/50 ,  G06F12/12 ,  G06F12/00

CPC分类号： G06F9/5016 ,  G06F12/0871 ,  G06F12/12 ,  G06F2212/282 ,  G06F2212/6042

摘要： A method and system for dynamically allocating cache space in a storage system among multiple workload classes each having a unique set of quality-of-service (QoS) requirements. The invention dynamically adapts the space allocated to each class depending upon the observed response time for each class and the observed temporal locality in each class. The dynamic allocation is achieved by maintaining a history of recently evicted pages for each class, determining a future cache size for the class based on the history and the QoS requirements where the future cache size might be different than a current cache size for the class, determining whether the QoS requirements for the class are being met, and adjusting the future cache size to maximize the number of classes in which the QoS requirements are met. The future cache sizes are increased for the classes whose QoS requirements are not met while they are decreased for those whose QoS requirements are met.

摘要翻译： 一种用于在多个工作负载类别中动态地分配存储系统中的高速缓存空间的方法和系统，每个工作负载类别具有唯一的服务质量（QoS）要求。 本发明根据每个类的观察到的响应时间和每个类中观察到的时间局部性动态地适应分配给每个类的空间。 通过维护每个类别的最近被逐出的页面的历史来实现动态分配，基于历史和QoS要求确定将来的高速缓存大小，其中将来的高速缓存大小可能与该类的当前高速缓存大小不同， 确定是否满足该类的QoS要求，以及调整未来的高速缓存大小以最大化满足QoS要求的类的数量。 对于满足QoS要求的类，对于满足QoS要求的用户而言，对于不满足QoS要求的类，对于未来的高速缓存大小会有所增加。

公开(公告)号：US20050071421A1

公开(公告)日：2005-03-31

申请号：US10321908

申请日：2002-12-17

申请人： Seraphin Calo ,  Anees Shaikh ,  Renu Tewari ,  Dinesh Verma

发明人： Seraphin Calo ,  Anees Shaikh ,  Renu Tewari ,  Dinesh Verma

IPC分类号： G06F15/16

CPC分类号： H04L67/1021 ,  G06Q30/0273 ,  G06Q30/0275 ,  G06Q40/04 ,  H04L29/08846 ,  H04L67/1002 ,  H04L67/28

摘要： This invention provides methods and apparatus for executing applications in a distributed manner employing one or more proxy servers and one origin server. The invention allows the applications to be executed primarily at the proxy servers rather than at the origin servers, thereby gaining in scalability and improved user response time. A redirection mechanism is used to direct requests to one of the proxy servers. The proxy server uses caching techniques to bring information records needed for application execution to the proxy servers. The code required for application execution is also obtained from the origin server. The invention discusses applying this technique to three Web-based applications, namely Web-based auctions, generating personalized content for Web-users, and creating advertisements for users accessing a Web page.

摘要翻译： 本发明提供了使用一个或多个代理服务器和一个原始服务器以分布式方式执行应用的方法和装置。 本发明允许应用程序主要在代理服务器而不是原始服务器上执行，从而获得可扩展性和改进的用户响应时间。 重定向机制用于将请求引导到其中一个代理服务器。 代理服务器使用缓存技术将应用程序执行所需的信息记录带到代理服务器。 应用程序执行所需的代码也可以从源服务器获取。 本发明讨论了将这种技术应用于三个基于Web的应用程序，即基于Web的拍卖，为Web用户生成个性化内容，以及为访问网页的用户创建广告。

公开(公告)号：US09244933B2

公开(公告)日：2016-01-26

申请号：US13098317

申请日：2011-04-29

申请人： Dean Hildebrand ,  Renu Tewari ,  Vasily Tarasov

发明人： Dean Hildebrand ,  Renu Tewari ,  Vasily Tarasov

IPC分类号： G06F17/30

CPC分类号： G06F17/30233 ,  G06F9/45558 ,  G06F17/30132 ,  G06F2009/45579 ,  G06F2009/45583

摘要： A method for disk image access in a storage system comprises receiving an input/output (I/O) request to a disk image in a file system of a storage system, and in response to the I/O request to the disk image in the file system, reconstructing a file system request. Introspection is performed on the disk image to determine an original file system request based on the I/O request to the disk image. The method further includes laying out a disk image in the file system of the storage system, and performing type-specific introspection on the disk image. Based upon the results of the introspection, data ranges in the disk image are mapped to block or files within the file system. A mapping of disk image data ranges to block or files in the file system is maintained for responding to further I/O requests.

摘要翻译： 一种用于存储系统中的磁盘映像访问的方法包括：在存储系统的文件系统中接收对磁盘映像的输入/输出（I / O）请求，并且响应于对所述磁盘映像的I / O请求 文件系统，重建文件系统请求。 在磁盘映像上执行自省以根据对磁盘映像的I / O请求确定原始文件系统请求。 该方法还包括在存储系统的文件系统中布置磁盘映像，并对磁盘映像执行类型特定的内省。 基于内省的结果，磁盘映像中的数据范围映射到文件系统中的块或文件。 维护磁盘映像数据范围到文件系统中的块或文件的映射以响应进一步的I / O请求。

公开(公告)号：US08949182B2

公开(公告)日：2015-02-03

申请号：US13162615

申请日：2011-06-17

申请人： Dean Hildebrand ,  Aameek Singh ,  Renu Tewari

发明人： Dean Hildebrand ,  Aameek Singh ,  Renu Tewari

IPC分类号： G06F17/30

CPC分类号： G06F17/30578

摘要： Embodiments of the invention relate to creating and maintaining consistent data sets in a shared pool of configurable computer resources to support disaster recovery support. Data from an application is stored in local data storage and replicated to another data storage. A consistency point of the data is created in both of the data storage, with the consistency point representing an identical data set at a point-in-time. Based upon the created consistency points, a consistent set of application data may be requested to support a read operation for a migrated application.

公开(公告)号：US08701113B2

公开(公告)日：2014-04-15

申请号：US12788937

申请日：2010-05-27

申请人： Dean Hildebrand ,  Renu Tewari

发明人： Dean Hildebrand ,  Renu Tewari

IPC分类号： G06F9/46

CPC分类号： G06F17/30197

摘要： Embodiments of the invention related to a switch-aware parallel file system. A computing cluster is partitioned into a plurality of computing cluster building blocks comprising a parallel file system. Each computing cluster building block comprises a file system client, a storage module, a building block metadata module, and a building block network switch. The building block metadata module tracks a storage location of data allocated by the storage module within the computing cluster building block. The computing cluster further comprises a file system metadata module that tracks which of the plurality of computing cluster building blocks data is allocated among within the parallel file system. The computing cluster further comprises a file system network switch to provide the parallel file system with access to each of the plurality of computing cluster building blocks and the file system metadata module. At least one additional computing cluster building block is added to the computing cluster, if resource utilization of the computing cluster exceeds a pre-determined threshold.

摘要翻译： 本发明的实施例涉及一种开关感知并行文件系统。 计算集群被划分成包括并行文件系统的多个计算集群构建块。 每个计算集群构建块包括文件系统客户端，存储模块，构建块元数据模块和构建块网络交换机。 构建块元数据模块跟踪由计算集群构建块内的存储模块分配的数据的存储位置。 计算集群还包括文件系统元数据模块，其跟踪在并行文件系统内的多个计算集群构建块中的哪一个被分配的文件系统元数据模块。 计算集群还包括文件系统网络交换机，以向并行文件系统提供对多个计算集群构建块和文件系统元数据模块中的每一个的访问。 如果计算集群的资源利用超过预定阈值，则至少一个计算集群构建块被添加到计算集群。

公开(公告)号：US20120278295A1

公开(公告)日：2012-11-01

申请号：US13098317

申请日：2011-04-29

申请人： Dean Hildebrand ,  Renu Tewari ,  Vasily Tarasov

发明人： Dean Hildebrand ,  Renu Tewari ,  Vasily Tarasov

IPC分类号： G06F17/30

CPC分类号： G06F17/30233 ,  G06F9/45558 ,  G06F17/30132 ,  G06F2009/45579 ,  G06F2009/45583

摘要： A method for disk image access in a storage system comprises receiving an input/output (I/O) request to a disk image in a file system of a storage system, and in response to the I/O request to the disk image in the file system, reconstructing a file system request. Introspection is performed on the disk image to determine an original file system request based on the I/O request to the disk image. The method further includes laying out a disk image in the file system of the storage system, and performing type-specific introspection on the disk image. Based upon the results of the introspection, data ranges in the disk image are mapped to block or files within the file system. A mapping of disk image data ranges to block or files in the file system is maintained for responding to further I/O requests.

摘要翻译： 一种用于存储系统中的磁盘映像访问的方法包括：在存储系统的文件系统中接收对磁盘映像的输入/输出（I / O）请求，并且响应于对所述磁盘映像的I / O请求 文件系统，重建文件系统请求。 在磁盘映像上执行自省以根据对磁盘映像的I / O请求确定原始文件系统请求。 该方法还包括在存储系统的文件系统中布置磁盘映像，并对磁盘映像执行类型特定的内省。 基于内省的结果，磁盘映像中的数据范围映射到文件系统中的块或文件。 维护磁盘映像数据范围到文件系统中的块或文件的映射以响应进一步的I / O请求。

公开(公告)号：US07472159B2

公开(公告)日：2008-12-30

申请号：US10439791

申请日：2003-05-15

申请人： Douglas Morgan Freimuth ,  Prashant Pradhan ,  Sambit Sahu ,  Renu Tewari ,  Donna N. Dillenberger

发明人： Douglas Morgan Freimuth ,  Prashant Pradhan ,  Sambit Sahu ,  Renu Tewari ,  Donna N. Dillenberger

IPC分类号： G06F15/16

CPC分类号： H04L69/163 ,  H04L29/06 ,  H04L47/11 ,  H04L47/15 ,  H04L47/2433 ,  H04L47/70 ,  H04L47/745 ,  H04L47/748 ,  H04L47/805 ,  H04L47/821 ,  H04L47/822 ,  H04L47/826 ,  H04L67/322 ,  H04L67/325 ,  H04L69/16 ,  H04L69/329

摘要： A method and system architecture to manage system resources in such a way as to provide service time guarantees to various classes of work using the system. In the case that the system resources are not sufficient to provide the specified service time guarantees, a method and system architecture is provided to limit work into the system such that the guarantees are satisfied and the revenue derived from the system is maximized.

摘要翻译： 一种管理系统资源的方法和系统架构，以便使用该系统为各类工作提供服务时间保证。 在系统资源不足以提供指定的服务时间保证的情况下，提供了一种方法和系统架构，以将工作限制到系统中，从而满足保证并且从系统获得的收入最大化。

公开(公告)号：US07406540B2

公开(公告)日：2008-07-29

申请号：US11737662

申请日：2007-04-19

申请人： Arup Acharya ,  Anees A. Shaikh ,  Renu Tewari ,  Dinesh C. Verma

发明人： Arup Acharya ,  Anees A. Shaikh ,  Renu Tewari ,  Dinesh C. Verma

IPC分类号： G06F15/173 ,  H04L12/28 ,  H04L12/56 ,  G06F15/16

CPC分类号： H04L29/12783 ,  H04L29/12009 ,  H04L45/306 ,  H04L61/35 ,  H04L67/1002 ,  H04L67/1023 ,  H04L67/14 ,  H04L67/2804 ,  H04L67/2819 ,  H04L67/2876 ,  H04L67/327 ,  H04L69/16 ,  H04L69/161 ,  H04L69/162 ,  H04L69/163 ,  H04L69/329 ,  H04L2029/06054

摘要： This invention provides methods and apparatus for web switching without connection termination while providing content routing functionality. Content-aware web switches terminate incoming TCP connections and inspect the HTTP header to recognize the URL (content) being requested from a web server farm. This invention maps application layer information (URLs) to MPLS labels. This allows a standard MPLS switch to provide web switching functionality without terminating TCP connections. In addition to content routing, this method is applied for client session affinity, server load balancing and service differentiation. This invention also relates to using TCP port numbers instead of MPLS labels to achieve web-switching functionality through the use of a TCP router that translates IP address and port numbers.

摘要翻译： 本发明提供了用于在不提供内容路由功能的情况下连接终止的web切换的方法和装置。 内容感知Web交换机终止传入的TCP连接，并检查HTTP头以识别从Web服务器场请求的URL（内容）。 本发明将应用层信息（URL）映射到MPLS标签。 这允许标准的MPLS交换机提供Web切换功能而不终止TCP连接。 除了内容路由，该方法也适用于客户端会话亲和性，服务器负载均衡和服务差异化。 本发明还涉及使用TCP端口号而不是MPLS标签来通过使用转换IP地址和端口号的TCP路由器来实现web切换功能。