Unified replication mechanism for fault-tolerance of state

    公开(公告)号:US11012292B2

    公开(公告)日:2021-05-18

    申请号:US16270588

    申请日:2019-02-07

    申请人: Nicira, Inc.

    摘要: A network control system that achieves high availability for forwarding state computation within a controller cluster by replicating different levels of table state between controllers of the controller cluster. To build a highly available controller cluster, the tables for storing the forwarding state are replicated across the controllers. In order to reduce network traffic between the controllers, fewer tables are replicated to slave controllers, which then recompute the forwarding state of the master controller in order to have a replicate copy of the master controller's forwarding state for possible failover. In other embodiments, more tables are replicated to minimize the recomputations and processor load on the slave controller. The network control system of some embodiments performs continuous snapshotting to minimize downtime associated with reaching a fixed point and replicating the state.

    PHYSICAL CONTROLLERS FOR CONVERTING UNIVERSAL FLOWS
    2.
    发明申请
    PHYSICAL CONTROLLERS FOR CONVERTING UNIVERSAL FLOWS 有权
    用于转换通用流量的物理控制器

    公开(公告)号:US20130117428A1

    公开(公告)日:2013-05-09

    申请号:US13660999

    申请日:2012-10-25

    申请人: Nicira, Inc.

    IPC分类号: H04L12/24

    摘要: Some embodiments provide a network control system for generating physical control plane data for managing first and second managed forwarding elements that implement forwarding operations associated with a first logical datapath set. The system includes a first controller instance for converting logical control plane data for the first logical datapath set to universal physical control plane (UPCP) data. The system includes a second controller instance for converting UPCP data to customized physical control plane (CPCP) data for the first managed forwarding element but not the second managed forwarding element. Each controller instance includes a network information base (NIB) storage for storing data and exchanging data with the other controller instance.

    摘要翻译: 一些实施例提供用于生成物理控制平面数据的网络控制系统,用于管理实现与第一逻辑数据路径集相关联的转发操作的第一和第二被管理转发元素。 该系统包括用于将第一逻辑数据路径集合的逻辑控制平面数据转换成通用物理控制平面(UPCP)数据的第一控制器实例。 该系统包括用于将UPCP数据转换成用于第一被管理转发元件而不是第二管理转发元件的定制物理控制平面(CPCP)数据的第二控制器实例。 每个控制器实例包括用于存储数据并与其他控制器实例交换数据的网络信息库(NIB)存储。

    Chassis controllers for converting universal flows
    3.
    发明授权
    Chassis controllers for converting universal flows 有权
    用于转换通用流量的机箱控制器

    公开(公告)号:US09288104B2

    公开(公告)日:2016-03-15

    申请号:US13661002

    申请日:2012-10-25

    申请人: Nicira, Inc.

    IPC分类号: H04L12/24 H04L12/773

    摘要: A network control system for generating physical control plane data for managing first and second managed forwarding elements that implement forwarding operations associated with a first logical datapath set is described. The system includes (1) a first controller for converting logical control plane data for the first logical datapath set to universal physical control plane (UPCP) data, (2) a second controller for converting UPCP data to customized physical control plane (CPCP) data for the first managed forwarding element but not the second managed forwarding element, and (3) a third controller for receiving UPCP data generated by the first controller instance, identifying the second controller as the controller instance responsible for generating the CPCP data for the first managed forward element, and supplying the received UPCP data to the second controller. Each controller includes a network information base (NIB) storage for exchanging data with another controller instance.

    摘要翻译: 描述用于生成用于管理实现与第一逻辑数据路径集相关联的转发操作的第一和第二被管理转发元素的物理控制平面数据的网络控制系统。 该系统包括:(1)用于将第一逻辑数据路径集合的逻辑控制平面数据转换为通用物理控制平面(UPCP)数据的第一控制器,(2)用于将UPCP数据转换为定制物理控制平面(CPCP)数据的第二控制器 对于第一管理转发元件而不是第二管理转发元件,以及(3)第三控制器,用于接收由第一控制器实例生成的UPCP数据,将第二控制器标识为负责生成第一管理的CPCP数据的控制器实例 正向元件,并将接收到的UPCP数据提供给第二控制器。 每个控制器包括用于与另一控制器实例交换数据的网络信息库(NIB)存储器。

    UNIFIED REPLICATION MECHANISM FOR FAULT-TOLERANCE OF STATE
    4.
    发明申请
    UNIFIED REPLICATION MECHANISM FOR FAULT-TOLERANCE OF STATE 有权
    统一的国家承诺的复制机制

    公开(公告)号:US20150009800A1

    公开(公告)日:2015-01-08

    申请号:US14231543

    申请日:2014-03-31

    申请人: Nicira, Inc.

    IPC分类号: H04L12/24

    摘要: A network control system that achieves high availability for forwarding state computation within a controller cluster by replicating different levels of table state between controllers of the controller cluster. To build a highly available controller cluster, the tables for storing the forwarding state are replicated across the controllers. In order to take responsibility for a slice, the slave controller of some embodiments performs merging of replicated state on a slice-by-slice basis. The merging is performed in a manner to prevent disruptions to the network state while the slave controller is updated.

    摘要翻译: 一种网络控制系统,通过在控制器集群的控制器之间复制不同级别的表状态,实现高可用性,用于在控制器集群内转发状态计算。 要构建高可用性控制器集群,用于存储转发状态的表在控制器之间进行复制。 为了对切片负责,一些实施例的从属控制器在逐个片段的基础上执行复制状态的合并。 在从属控制器更新时,以防止中断网络状态的方式执行合并。

    Unified replication mechanism for fault-tolerance of state

    公开(公告)号:US10218564B2

    公开(公告)日:2019-02-26

    申请号:US14231527

    申请日:2014-03-31

    申请人: Nicira, Inc.

    摘要: A network control system that achieves high availability for forwarding state computation within a controller cluster by replicating different levels of table state between controllers of the controller cluster. To build a highly available controller cluster, the tables for storing the forwarding state are replicated across the controllers. In order to reduce network traffic between the controllers, fewer tables are replicated to slave controllers, which then recompute the forwarding state of the master controller in order to have a replicate copy of the master controller's forwarding state for possible failover. In other embodiments, more tables are replicated to minimize the recomputations and processor load on the slave controller. The network control system of some embodiments performs continuous snapshotting to minimize downtime associated with reaching a fixed point and replicating the state.

    Unified replication mechanism for fault-tolerance of state
    6.
    发明授权
    Unified replication mechanism for fault-tolerance of state 有权
    国家容错的统一复制机制

    公开(公告)号:US09432252B2

    公开(公告)日:2016-08-30

    申请号:US14231543

    申请日:2014-03-31

    申请人: Nicira, Inc.

    摘要: A network control system that achieves high availability for forwarding state computation within a controller cluster by replicating different levels of table state between controllers of the controller cluster. To build a highly available controller cluster, the tables for storing the forwarding state are replicated across the controllers. In order to take responsibility for a slice, the slave controller of some embodiments performs merging of replicated state on a slice-by-slice basis. The merging is performed in a manner to prevent disruptions to the network state while the slave controller is updated.

    摘要翻译: 一种网络控制系统,通过在控制器集群的控制器之间复制不同级别的表状态,实现高可用性,用于在控制器集群内转发状态计算。 要构建高可用性控制器集群,用于存储转发状态的表在控制器之间进行复制。 为了对切片负责,一些实施例的从属控制器在逐个片段的基础上执行复制状态的合并。 在从属控制器更新时,以防止中断网络状态的方式执行合并。

    UNIFIED REPLICATION MECHANISM FOR FAULT-TOLERANCE OF STATE

    公开(公告)号:US20190173744A1

    公开(公告)日:2019-06-06

    申请号:US16270588

    申请日:2019-02-07

    申请人: Nicira, Inc.

    摘要: A network control system that achieves high availability for forwarding state computation within a controller cluster by replicating different levels of table state between controllers of the controller cluster. To build a highly available controller cluster, the tables for storing the forwarding state are replicated across the controllers. In order to reduce network traffic between the controllers, fewer tables are replicated to slave controllers, which then recompute the forwarding state of the master controller in order to have a replicate copy of the master controller's forwarding state for possible failover. In other embodiments, more tables are replicated to minimize the recomputations and processor load on the slave controller. The network control system of some embodiments performs continuous snapshotting to minimize downtime associated with reaching a fixed point and replicating the state.

    CHASSIS CONTROLLERS FOR CONVERTING UNIVERSAL FLOWS
    8.
    发明申请
    CHASSIS CONTROLLERS FOR CONVERTING UNIVERSAL FLOWS 有权
    用于转换通用流量的底盘控制器

    公开(公告)号:US20130117429A1

    公开(公告)日:2013-05-09

    申请号:US13661002

    申请日:2012-10-25

    申请人: Nicira, Inc.

    IPC分类号: H04L12/24

    摘要: A network control system for generating physical control plane data for managing first and second managed forwarding elements that implement forwarding operations associated with a first logical datapath set is described. The system includes (1) a first controller for converting logical control plane data for the first logical datapath set to universal physical control plane (UPCP) data, (2) a second controller for converting UPCP data to customized physical control plane (CPCP) data for the first managed forwarding element but not the second managed forwarding element, and (3) a third controller for receiving UPCP data generated by the first controller instance, identifying the second controller as the controller instance responsible for generating the CPCP data for the first managed forward element, and supplying the received UPCP data to the second controller. Each controller includes a network information base (NIB) storage for exchanging data with another controller instance.

    摘要翻译: 描述用于生成用于管理实现与第一逻辑数据路径集相关联的转发操作的第一和第二被管理转发元素的物理控制平面数据的网络控制系统。 该系统包括:(1)用于将第一逻辑数据路径集合的逻辑控制平面数据转换成通用物理控制平面(UPCP)数据的第一控制器,(2)用于将UPCP数据转换为定制物理控制平面(CPCP)数据的第二控制器 对于第一管理转发元件而不是第二管理转发元件,以及(3)第三控制器,用于接收由第一控制器实例生成的UPCP数据,将第二控制器标识为负责生成第一管理的CPCP数据的控制器实例 正向元件,并将接收到的UPCP数据提供给第二控制器。 每个控制器包括用于与另一控制器实例交换数据的网络信息库(NIB)存储器。

    Physical controllers for converting universal flows
    10.
    发明授权
    Physical controllers for converting universal flows 有权
    用于转换通用流量的物理控制器

    公开(公告)号:US09137107B2

    公开(公告)日:2015-09-15

    申请号:US13660999

    申请日:2012-10-25

    申请人: Nicira, Inc.

    IPC分类号: G06F15/173 H04L12/24

    摘要: Some embodiments provide a network control system for generating physical control plane data for managing first and second managed forwarding elements that implement forwarding operations associated with a first logical datapath set. The system includes a first controller instance for converting logical control plane data for the first logical datapath set to universal physical control plane (UPCP) data. The system includes a second controller instance for converting UPCP data to customized physical control plane (CPCP) data for the first managed forwarding element but not the second managed forwarding element. Each controller instance includes a network information base (NIB) storage for storing data and exchanging data with the other controller instance.

    摘要翻译: 一些实施例提供用于生成物理控制平面数据的网络控制系统,用于管理实现与第一逻辑数据路径集相关联的转发操作的第一和第二被管理转发元素。 该系统包括用于将第一逻辑数据路径集合的逻辑控制平面数据转换成通用物理控制平面(UPCP)数据的第一控制器实例。 该系统包括用于将UPCP数据转换成用于第一被管理转发元件而不是第二管理转发元件的定制物理控制平面(CPCP)数据的第二控制器实例。 每个控制器实例包括用于存储数据并与其他控制器实例交换数据的网络信息库(NIB)存储。