公开(公告)号：US07707289B1

公开(公告)日：2010-04-27

申请号：US11379557

申请日：2006-04-20

申请人： Bryan D. Skene ,  Peter M. Thornewell

发明人： Bryan D. Skene ,  Peter M. Thornewell

IPC分类号： G06F15/16

CPC分类号： H04L67/1008 ,  H04L29/06 ,  H04L67/1002 ,  H04L67/101 ,  H04L67/1027 ,  H04L67/14 ,  H04L69/329 ,  H04L2029/06054

摘要： Disclosed are methods and systems for providing persistence across multiple requests in a WAN load-balanced environment. More than one load balancing system may be used to provide persistence while load balancing. One method and system disclosed provides persistence by using modulus arithmetic to load balance requests. Another method and system disclosed provides persistence using topology information contained in the request. Another method and system disclosed provides persistence by storing connection information to refer a timely continuation request of a prior request to the same server the prior request was referred to. When more than one load balancing system is used with this method, the load balancing systems periodically exchange the stored connection information so that each load balancing system may provide persistence to repeat requests.

摘要翻译： 公开了用于在WAN负载平衡环境中跨多个请求提供持久性的方法和系统。 可以使用多个负载平衡系统来提供持久性，同时负载平衡。 所公开的一种方法和系统通过使用模数运算来负载平衡请求来提供持久性。 所公开的另一方法和系统使用包含在请求中的拓扑信息来提供持久性。 所公开的另一种方法和系统通过存储连接信息来提供持续性，以将先前请求的及时请求引用到同一服务器。 当使用多个负载平衡系统时，负载平衡系统周期性地交换存储的连接信息，以便每个负载均衡系统可以提供持久性来重复请求。

公开(公告)号：US07047301B2

公开(公告)日：2006-05-16

申请号：US09773427

申请日：2001-01-31

申请人： Bryan D. Skene ,  Peter M. Thornewell

发明人： Bryan D. Skene ,  Peter M. Thornewell

IPC分类号： G06F15/16

CPC分类号： H04L67/1008 ,  H04L29/06 ,  H04L67/1002 ,  H04L67/101 ,  H04L67/1027 ,  H04L67/14 ,  H04L69/329 ,  H04L2029/06054

摘要： Disclosed are methods and systems for providing persistence across multiple requests in a WAN load-balanced environment. More than one load balancing system may be used to provide persistence while load balancing. One method and system disclosed provides persistence by using modulus arithmetic to load balance requests. Another method and system disclosed provides persistence using topology information contained in the request. Another method and system disclosed provides persistence by storing connection information to refer a timely continuation request of a prior request to the same server the prior request was referred to. When more than one load balancing system is used with this method, the load balancing systems periodically exchange the stored connection information so that each load balancing system may provide persistence to repeat requests.

摘要翻译： 公开了用于在WAN负载平衡环境中跨多个请求提供持久性的方法和系统。 可以使用多个负载平衡系统来提供持久性，同时负载平衡。 所公开的一种方法和系统通过使用模数运算来负载平衡请求来提供持久性。 所公开的另一方法和系统使用包含在请求中的拓扑信息来提供持久性。 所公开的另一种方法和系统通过存储连接信息来提供持续性，以将先前请求的及时请求引用到同一服务器。 当使用多个负载平衡系统时，负载平衡系统周期性地交换存储的连接信息，以便每个负载均衡系统可以提供持久性来重复请求。

公开(公告)号：US07590625B1

公开(公告)日：2009-09-15

申请号：US11532876

申请日：2006-09-18

申请人： Scott P. Tennican ,  Bryan D. Skene

发明人： Scott P. Tennican ,  Bryan D. Skene

IPC分类号： G06F17/30

CPC分类号： H04L29/1233 ,  H04L45/742 ,  H04L61/25 ,  Y10S707/99933

摘要： The invention provides for employing a complex data structure to optimize the retrieval of data over a network. The complex data structure includes two separate sub-data structures (Trie and List) that separately reference the same data objects in a data store. The Trie sub-data structure is used to fulfill a single data object request. The List sub-data structure is employed with function requests related to several data objects. Each data object is associated with a parent object that includes a list of every reference to the data object in both the Trie and List sub-data structures. A collector object is a type of data object that is associated with a member object and which includes a list of other related data/collector objects. When data associated with the collector object is requested, other data associated with the other data/collector objects on the member object list are automatically retrieved.

摘要翻译： 本发明提供了采用复杂数据结构来优化网络上的数据检索。 复杂数据结构包括分别引用数据存储中的相同数据对象的两个单独的子数据结构（Trie和List）。 Trie子数据结构用于实现单个数据对象请求。 列表子数据结构用于与几个数据对象相关的功能请求。 每个数据对象与父对象相关联，父对象包括在Trie和List子数据结构中对数据对象的每个引用的列表。 收集器对象是与成员对象相关联的一种数据对象，其中包含其他相关数据/收集器对象的列表。 当请求与收集器对象相关联的数据时，会自动检索与成员对象列表上的其他数据/收集器对象关联的其他数据。

公开(公告)号：US08438253B2

公开(公告)日：2013-05-07

申请号：US13480943

申请日：2012-05-25

申请人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

发明人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

IPC分类号： G06F11/20 ,  G06F9/44 ,  G06F15/16

CPC分类号： H04L41/0668 ,  G06F8/656 ,  G06F11/203 ,  G06F11/2033

摘要： A method, system, machine-readable storage medium, and apparatus are directed towards upgrading a cluster by bifurcating the cluster into two virtual clusters, an “old” virtual cluster (old active cluster) and a “new” virtual cluster (new standby cluster), and iteratively upgrading members of the old cluster while moving them into the new cluster. While members are added to the new cluster, existing connections and new connections are seamlessly processed by the old cluster. Optionally, state mirroring occurs between the old cluster and the new cluster once the number of members of the old and new clusters are approximately equal. Once a threshold number of members have been transferred to the new cluster, control and processing may be taken over by the new cluster. Transfer of control from the old cluster to the new cluster may be performed by failing over connectivity from the old cluster to the new cluster.

摘要翻译： 方法，系统，机器可读存储介质和装置旨在通过将集群分为两个虚拟集群，“旧”虚拟集群（旧主动集群）和“新”虚拟集群（新的备用集群） ），并在将旧群集的成员移动到新群集中时迭代升级。 当成员添加到新集群时，旧集群将无缝地处理现有连接和新连接。 可选地，一旦旧集群和新集群的成员数量大致相等，就会在旧集群和新集群之间发生状态镜像。 一旦将阈值数量的成员转移到新群集，则可以由新群集接管控制和处理。 控制从旧集群传输到新集群可能会通过从旧集群到新集群的连接失败来执行。

公开(公告)号：US20130047026A1

公开(公告)日：2013-02-21

申请号：US13480943

申请日：2012-05-25

申请人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

发明人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

IPC分类号： G06F11/20 ,  G06F15/177

CPC分类号： H04L41/0668 ,  G06F8/656 ,  G06F11/203 ,  G06F11/2033

摘要： A method, system, machine-readable storage medium, and apparatus are directed towards upgrading a cluster by bifurcating the cluster into two virtual clusters, an “old” virtual cluster (old active cluster) and a “new” virtual cluster (new standby cluster), and iteratively upgrading members of the old cluster while moving them into the new cluster. While members are added to the new cluster, existing connections and new connections are seamlessly processed by the old cluster. Optionally, state mirroring occurs between the old cluster and the new cluster once the number of members of the old and new clusters are approximately equal. Once a threshold number of members have been transferred to the new cluster, control and processing may be taken over by the new cluster. Transfer of control from the old cluster to the new cluster may be performed by failing over connectivity from the old cluster to the new cluster.

摘要翻译： 一种方法，系统，机器可读存储介质和装置旨在通过将集群分成两个虚拟集群，旧虚拟集群（旧主动集群）和新的虚拟集群（新的备用集群））来迭代地升级集群，并且迭代地 升级旧集群的成员，同时将其移动到新集群中。 当成员添加到新集群时，旧集群将无缝地处理现有连接和新连接。 可选地，一旦旧集群和新集群的成员数量大致相等，就会在旧集群和新集群之间发生状态镜像。 一旦将阈值数量的成员转移到新群集，则可以由新群集接管控制和处理。 控制从旧集群传输到新集群可能会通过从旧集群到新集群的连接失败来执行。

公开(公告)号：US20100042869A1

公开(公告)日：2010-02-18

申请号：US12543448

申请日：2009-08-18

申请人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

发明人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

IPC分类号： G06F11/20 ,  G06F9/44 ,  G06F15/16

CPC分类号： H04L41/0668 ,  G06F8/656 ,  G06F11/203 ,  G06F11/2033

摘要： A method, system, machine-readable storage medium, and apparatus are directed towards upgrading a cluster by bifurcating the cluster into two virtual clusters, an “old” virtual cluster (old active cluster) and a “new” virtual cluster (new standby cluster), and iteratively upgrading members of the old cluster while moving them into the new cluster. While members are added to the new cluster, existing connections and new connections are seamlessly processed by the old cluster. Optionally, state mirroring occurs between the old cluster and the new cluster once the number of members of the old and new clusters are approximately equal. Once a threshold number of members have been transferred to the new cluster, control and processing may be taken over by the new cluster. Transfer of control from the old cluster to the new cluster may be performed by failing over connectivity from the old cluster to the new cluster.

摘要翻译： 方法，系统，机器可读存储介质和装置旨在通过将集群分为两个虚拟集群，“旧”虚拟集群（旧主动集群）和“新”虚拟集群（新的备用集群） ），并在将旧群集的成员移动到新群集中时迭代升级。 当成员添加到新集群时，旧集群将无缝地处理现有连接和新连接。 可选地，一旦旧集群和新集群的成员数量大致相等，就会在旧集群和新集群之间发生状态镜像。 一旦将阈值数量的成员转移到新群集，则可以通过新群集来接管控制和处理。 控制从旧集群传输到新集群可能会通过从旧集群到新集群的连接失败来执行。

公开(公告)号：US08516129B1

公开(公告)日：2013-08-20

申请号：US13084536

申请日：2011-04-11

申请人： Bryan D. Skene

发明人： Bryan D. Skene

IPC分类号： G06F15/173

CPC分类号： H04L67/1002 ,  H04L45/12 ,  H04L45/22

摘要： A system, apparatus, and method are directed to managing network communications between a client and a server by enabling the client to make decisions involving the selection of alternate network paths. The client and/or the server may be multi-homed to a network. In one embodiment, a link load balancer provides the client with a message and/or path data that enables the client to improve its connections with the server by redirecting network packets using an alternate network path. The message may be based on a static policy at the server, changes in availability of the network connections between the client and server, changes in a quality of the network connections, paths, or the like. Redirecting the network packet by the client may include closing one network connection and establishing another network connection, and/or employing an available alternate network path to re-route network packets towards the server.

摘要翻译： 系统，装置和方法旨在通过使客户端能够做出涉及选择备用网络路径的决策来管理客户端和服务器之间的网络通信。 客户机和/或服务器可以被多归属于网络。 在一个实施例中，链路负载平衡器向客户端提供消息和/或路径数据，其使客户端能够通过使用备用网络路径重新定向网络分组来改善其与服务器的连接。 消息可以基于服务器上的静态策略，客户端和服务器之间的网络连接的可用性的改变，网络连接的质量，路径等的改变。 客户端重定向网络数据包可能包括关闭一个网络连接并建立另一个网络连接，和/或使用可用的备用网络路径将网络数据包重新路由到服务器。

公开(公告)号：US07958222B1

公开(公告)日：2011-06-07

申请号：US12880659

申请日：2010-09-13

申请人： Joseph A. Pruitt ,  Bryan D. Skene ,  Patrick D. Jenny ,  Gary N. Mager

发明人： Joseph A. Pruitt ,  Bryan D. Skene ,  Patrick D. Jenny ,  Gary N. Mager

IPC分类号： G06F15/173

CPC分类号： H04L67/16 ,  H04L29/12066 ,  H04L29/12113 ,  H04L61/1511 ,  H04L61/1541

摘要： A system for accessing network services includes a plurality of resolvers including a root resolver and a secondary resolver, each resolver arranged to perform actions comprising determining a set of service locations based at least in part on the service and an address associated with a client. the system includes an intermediate device that manipulates scores returned by a set of resolvers of the plurality of resolvers, wherein the root resolver is further arranged to combine sets of the determined service locations and return a combined set of service locations to the client, and wherein at least one resolver of the plurality of resolvers employs an algorithm that is different from an algorithm employed by another resolver of the plurality of resolvers, wherein each algorithm is employed to determine scores of service locations, wherein the combined set of services locations comprises the scores of service locations.

摘要翻译： 用于访问网络服务的系统包括多个解析器，包括根解算器和辅助解析器，每个解析器被布置成执行动作，包括至少部分地基于服务和与客户端相关联的地址来确定一组服务位置。 所述系统包括操纵由所述多个解析器的一组解析器返回的分数的中间设备，其中所述根解算器还被布置为组合所确定的服务位置的集合并将一组组合的服务位置返回给所述客户端，并且其中 所述多个解析器中的至少一个解析器采用不同于所述多个解析器的另一解析器所使用的算法的算法，其中使用每个算法来确定服务位置的分数，其中所述组合的服务位置包括得分 的服务地点。

公开(公告)号：US07146354B1

公开(公告)日：2006-12-05

申请号：US09596796

申请日：2000-06-19

申请人： Scott P. Tennican ,  Bryan D. Skene

发明人： Scott P. Tennican ,  Bryan D. Skene

IPC分类号： G06F17/30

CPC分类号： H04L29/1233 ,  H04L45/742 ,  H04L61/25 ,  Y10S707/99933

摘要： The invention provides for employing a complex data structure to optimize the retrieval of data from a data store over a network. The complex data structure includes two separate sub-data structures (Trie and List) that separately reference the same data objects in a data store. The complex data structure employs a functional interface to determine which data structure matches a particular function request for data. A Trie sub-data structure is used to fulfill a single data object request. The List sub-data structure is employed with function requests related to several data objects. Each data object is associated with a parent object that includes a list of every reference to the data object in both the Trie and List sub-data structures. When a data object is subsequently deleted, the parent object list is employed to automatically delete every reference to the deleted data object in both the Trie and List sub-data structures. A collector object is a type of data object that is associated with a member object and which includes a list of other related data/collector objects. When data associated with the collector object is requested, other data associated with the other data/collector objects on the member object list are automatically retrieved. The complex data structure can also use a Hash sub-data structure to retrieve single data objects.

摘要翻译： 本发明提供了采用复杂数据结构来优化通过网络从数据存储器检索数据。 复杂数据结构包括分别引用数据存储中的相同数据对象的两个单独的子数据结构（Trie和List）。 复杂数据结构采用功能接口来确定哪个数据结构与数据的特定功能请求相匹配。 Trie子数据结构用于实现单个数据对象请求。 列表子数据结构用于与几个数据对象相关的功能请求。 每个数据对象与父对象相关联，父对象包括在Trie和List子数据结构中对数据对象的每个引用的列表。 当数据对象随后被删除时，使用父对象列表来自动删除Trie和List子数据结构中对被删除的数据对象的每个引用。 收集器对象是与成员对象相关联的一种数据对象，其中包含其他相关数据/收集器对象的列表。 当请求与收集器对象相关联的数据时，会自动检索与成员对象列表上的其他数据/收集器对象关联的其他数据。 复杂数据结构也可以使用哈希子数据结构来检索单个数据对象。

公开(公告)号：US08209403B2

公开(公告)日：2012-06-26

申请号：US12543448

申请日：2009-08-18

申请人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

发明人： Paul I. Szabo ,  Bryan D. Skene ,  Saxon Amdahl

IPC分类号： G06F11/20 ,  G06F9/44 ,  G06F15/16

CPC分类号： H04L41/0668 ,  G06F8/656 ,  G06F11/203 ,  G06F11/2033

摘要： A method, system, machine-readable storage medium, and apparatus are directed towards upgrading a cluster by bifurcating the cluster into two virtual clusters, an “old” virtual cluster (old active cluster) and a “new” virtual cluster (new standby cluster), and iteratively upgrading members of the old cluster while moving them into the new cluster. While members are added to the new cluster, existing connections and new connections are seamlessly processed by the old cluster. Optionally, state mirroring occurs between the old cluster and the new cluster once the number of members of the old and new clusters are approximately equal. Once a threshold number of members have been transferred to the new cluster, control and processing may be taken over by the new cluster. Transfer of control from the old cluster to the new cluster may be performed by failing over connectivity from the old cluster to the new cluster.

摘要翻译： 方法，系统，机器可读存储介质和装置旨在通过将集群分为两个虚拟集群，“旧”虚拟集群（旧主动集群）和“新”虚拟集群（新的备用集群） ），并在将旧群集的成员移动到新群集中时迭代升级。 当成员添加到新集群时，旧集群将无缝地处理现有连接和新连接。 可选地，一旦旧集群和新集群的成员数量大致相等，就会在旧集群和新集群之间发生状态镜像。 一旦将阈值数量的成员转移到新群集，则可以由新群集接管控制和处理。 控制从旧集群传输到新集群可能会通过从旧集群到新集群的连接失败来执行。