Bi-directional affinity within a load-balancing multi-node network interface
    1.
    发明授权
    Bi-directional affinity within a load-balancing multi-node network interface 有权
    负载平衡多节点网络接口内的双向关联

    公开(公告)号:US07380002B2

    公开(公告)日:2008-05-27

    申请号:US10186899

    申请日:2002-06-28

    IPC分类号: G06F15/173

    摘要: A new network load balancing/firewall node for use in a system including multiple network load balancing/firewall nodes is disclosed. The network load balancing/firewall applies bi-directional load balancing affinity with regard to requests from external clients and corresponding responses from internal network servers. An external network load balancing adapter executes a load-balancing algorithm to determine whether a received client request is accepted by the network load balancing/firewall node. A firewall utility processes the received client request and maintains state information associated with the received client request. An internal network load balancing adapter ensures that the same network load balancing/firewall node accepts a response from an internal network server corresponding to the received client request.

    摘要翻译: 公开了一种用于包括多个网络负载平衡/防火墙节点的系统的新的网络负载平衡/防火墙节点。 网络负载平衡/防火墙对来自外部客户端的请求和内部网络服务器的相应响应应用双向负载均衡。 外部网络负载平衡适配器执行负载平衡算法来确定接收到的客户端请求是否被网络负载平衡/防火墙节点接受。 防火墙实用程序处理接收到的客户端请求并维护与接收的客户端请求相关联的状态信息。 内部网络负载平衡适配器确保相同的网络负载平衡/防火墙节点接受来自对应于接收的客户端请求的内部网络服务器的响应。

    Stateless, affinity-preserving load balancing
    4.
    发明授权
    Stateless, affinity-preserving load balancing 有权
    无状态,亲和力保持负载平衡

    公开(公告)号:US07693050B2

    公开(公告)日:2010-04-06

    申请号:US11106080

    申请日:2005-04-14

    IPC分类号: H04L12/26

    摘要: The invention relates to an architecture that facilitates load balancing among a plurality of hosts and preserve session affinity to a given host. An incoming stream of data packets that include packet sessions is input to one or more forwarding mechanisms for forwarding to one or more hosts. The forwarders generate a routing function that takes into consideration host availability, and distributes session packets according to the routing function. A session is distributed to the same host to preserve session affinity. When host availability changes, a new routing function is generated, such that any new session is routed according to the new routing function and existing sessions are routed according to the old routing function. When the old routing function becomes irrelevant, it is phased out. An optimization utilizes a maximally backward compatible hash function to minimize the differences between the old and new routing functions.

    摘要翻译: 本发明涉及一种便于多个主机之间的负载平衡并保持对给定主机的会话亲和性的架构。 包括数据包会话的数据包的输入流被输入到一个或多个转发机制以转发到一个或多个主机。 转发器产生考虑主机可用性的路由功能,并根据路由功能分配会话数据包。 会话分发给同一主机以保持会话亲和性。 当主机可用性发生变化时,会生成新的路由功能,以便根据新路由功能路由所有新会话,并根据旧路由功能路由现有会话。 当旧的路由功能变得无关时,它被淘汰。 优化利用最大向后兼容的散列函数来最小化旧路由功能和新路由功能之间的差异。

    Supporting point-to-point intracluster communications between replicated cluster nodes
    5.
    发明授权
    Supporting point-to-point intracluster communications between replicated cluster nodes 有权
    支持复制集群节点之间的点对点集群间通信

    公开(公告)号:US07631100B2

    公开(公告)日:2009-12-08

    申请号:US10680590

    申请日:2003-10-07

    IPC分类号: G06F15/16 G06F15/173

    摘要: A system and methods for carrying out point-to-point intracluster communications between hosts is provided. The disclosed system enables communication protocol layer components of hosts within a cluster to continue to operate in a cluster mode while facilitating such point-to-point communications. Initially, address discovery provides the non-cluster mode address for a target host. Thereafter, an initiating/source host issues a message including the non-cluster mode address of the target host. A network load balancing layer, or any other suitable component within the target host, intercepts the message and substitutes a cluster address for the non-cluster mode address within the message destination field before the message is presented to the communication protocol layer of the target host.

    摘要翻译: 提供了一种用于在主机之间进行点对点集群间通信的系统和方法。 所公开的系统使得集群内的主机的通信协议层组件能够继续在群集模式下操作,同时促进这种点对点通信。 最初,地址发现为目标主机提供非群集模式地址。 此后,启动/源主机发出包括目标主机的非集群模式地址的消息。 网络负载平衡层或目标主机内的任何其他合适的组件在消息呈现给目标主机的通信协议层之前拦截该消息并将消息目的地字段内的非集群模式地址替换为集群地址 。

    Network load balancing with connection manipulation
    6.
    发明授权
    Network load balancing with connection manipulation 有权
    网络负载平衡与连接操纵

    公开(公告)号:US07606929B2

    公开(公告)日:2009-10-20

    申请号:US10657568

    申请日:2003-09-08

    IPC分类号: G06F15/16

    摘要: In an exemplary device implementation, a device includes: a connection migrator that is configured to migrate connections away from the device; the connection migrator capable of precipitating a compilation of protocol state for a connection across a protocol stack; the connection migrator adapted to aggregate the compiled protocol state with data for the connection into an aggregated connection state; the connection migrator further capable of causing the aggregated connection state to be sent toward a target device. In an exemplary media implementation, processor-executable instructions direct a device to perform actions including: obtaining at least a portion of a source/destination pair from a packet; accessing an encapsulation mapping table using the at least a portion of the source/destination pair to locate an encapsulation mapping entry; extracting a flow identifier from the encapsulation mapping entry; and replacing part of the packet with the flow identifier to produce an encapsulated packet.

    摘要翻译: 在示例性设备实现中,设备包括:被配置为将连接迁移离开设备的连接迁移器; 所述连接迁移器能够通过协议栈来引起对于连接的协议状态的编译; 所述连接迁移器适于将所述编译协议状态与所述连接的数据聚合成聚合连接状态; 连接迁移器还能够使聚合的连接状态被发送到目标设备。 在示例性媒体实现中,处理器可执行指令指示设备执行动作,包括:从分组获得源/目的地对的至少一部分; 使用所述源/目的地对的所述至少一部分来访问封装映射表以定位封装映射条目; 从封装映射条目提取流标识符; 并用流标识符替换分组的一部分以产生封装的分组。

    Network load balancing with traffic routing
    9.
    发明授权
    Network load balancing with traffic routing 有权
    网络负载均衡与流量路由

    公开(公告)号:US07567504B2

    公开(公告)日:2009-07-28

    申请号:US10657412

    申请日:2003-09-08

    摘要: In an exemplary method implementation, a method includes: receiving a packet requesting a new connection at a forwarding component; sending the packet from the forwarding component to a classifying component; selecting, by the classifying component, a route for the new connection; and plumbing, by the classifying component, the route for the new connection by causing a new entry to be added in a local routing table of the forwarding component. In an exemplary media implementation, one or more processor-accessible media include processor-executable instructions that, when executed, enable a system to perform actions including: receiving a first packet for a connection at first forwarding functionality; plumbing a route for the connection at the first forwarding functionality; receiving a second packet for the connection at second forwarding functionality; and plumbing the route for the connection at the second forwarding functionality using a distributed session tracking table.

    摘要翻译: 在示例性方法实现中,一种方法包括:在转发组件处接收请求新连接的分组; 将分组从转发组件发送到分类组件; 由分类组件选择新连接的路由; 并且通过在转发组件的本地路由表中添加新条目来由分类组件管理新连接的路由。 在示例性媒体实现中,一个或多个处理器可访问媒体包括处理器可执行指令,其在执行时使得系统能够执行动作,包括:以第一转发功能接收用于连接的第一分组; 在第一转发功能下管理连接的路由; 在第二转发功能处接收用于所述连接的第二分组; 并使用分布式会话跟踪表在第二转发功能处管理用于连接的路由。