Nicira, Inc.

Vmware, Inc.

Jeremy Stribling

Teemu Koponen

Martin Casado

Natasha Gude

W Andrew Lambeth

Bruce Davie

Amar Padmanabhan

Pankaj Thakkar

Alexander Yip

Ronghua Zhang

Alan Shieh

A network control system that includes several controllers for managing several switching elements. Each controller includes a network information base (NIB) storage that stores data regarding the switching elements and a secondary storage for facilitating replication of at least a portion of data across the NIB storages of the different controllers. In some embodiments, the primary purpose for one or more of the secondary storage structures is to back up the data in the NIB. In these or other embodiments, one or more of the secondary storage structures serve a purpose other than backing up the data in the NIB. In some embodiments, the NIB is stored in system memory while the system operates for fast access of the NIB records. In some embodiments, one or more of the secondary storage structures are stored on disks which can be slower to access.

Method and apparatus for using a network information base to control a plurality of shared network infrastructure switching elements

A control system including several controllers for managing several switching elements. A first controller registers a second controller for receiving a notification when a data tuple changes in a network information base (NIB) storage of the first controller that stores data for managing a set of switching elements. The first controller changes the data tuple in the NIB. The first controller sends the notification to the second controller of the change to the data tuple in the NIB. The first and second controllers operate on two different computing devices. Each controller receives logical control plane data for specifying logical datapath sets and converts the logical control plane data to physical control plane data for enabling the switching elements to implement the logical datapath sets.

Method and apparatus for interacting with a network information base in a distributed network control system with multiple controller instances

A network control system that includes several controllers for managing several switching elements. In some embodiments, each switching element implements at least one logical switching element and has a master controller. In some embodiments, at least one controller is a master of at least two switching elements. The network control system accepts definitions of the logical switching elements and, in some embodiments, each logical switching element has a master controller. In some embodiments, at least one controller is a master for at least two logical switching elements.

Method and apparatus for replicating network information base in a distributed network control system with multiple controller instances

Some embodiments provide a method for a first network controller located at a first physical domain that manages a logical network spanning several physical domains including the first domain. The method stores a set of context identifiers for assignment to logical entities. The context identifiers are for use in packets sent between managed forwarding elements in order to store logical network information in the packets. While connected to a master controller for the logical network at a second physical domain of the several physical domains, the method forwards state input requiring assignment of context identifiers to the master controller. While connectivity is lost with the master controller, the method assigns context identifiers from the stored set of context identifiers to logical entities.

Managing forwarding of logical network traffic between physical domains

A method for upgrading a set of controller nodes in a controller cluster that manages a plurality of forwarding elements in a way that minimizes dataplane outages. The method of some embodiments upgrades the control applications of a subset of the controller nodes before upgrading a decisive controller node. Once the decisive controller node is upgraded, the method switches the controller cluster to use a new version of the control applications.

Hitless upgrade for network control applications

Techniques for facilitating data upgrades in a distributed system are provided. In one embodiment, a first instance of a distributed application executing on a first node of a distributed system can receive a message from a second instance of the distributed application executing on a second node of the distributed system. The first instance of the distributed application can then determine, via logic included in application code generated by an interface definition language (IDL) compiler, whether the message can be natively understood. If the message cannot be natively understood, the first instance of the distributed application can invoke a translation service for translating the message.

Data upgrade framework for distributed systems

Storing network state at a network controller

Managing context identifier assignment across multiple physical domains

Some embodiments provide a network controller for managing a logical network that spans several physical domains. The network controller is located at a particular one of the several physical domains. The network controller includes a first storage for storing network state information that is local to the particular physical domain. The network controller includes a second storage for storing a first type of global network state information for the logical network. The network controller includes a third storage for storing a second type of global network state information for the logical network. The network controller includes an interface for communicating with other network controllers located at the other physical domains in the several physical domains spanned by the logical network. The interface is for sharing the first and second types of global network state information.

Some embodiments provide a method for a first network controller located at a first domain that manages a logical network spanning several physical domains including the first domain. Upon reconnection to a second network controller located at a second physical domain of the several physical domains after a period of disconnect, the method receives a first set of updates indicating modifications to logical network state from the second network controller. The method reconciles any conflicts between (i) the logical network state stored at the first controller, (ii) the first set of updates received from the second network controller, and (iii) updates received from other network controllers located at different physical domains of the several physical domains. The method transmits a second set of updates to the second controller indicating modifications to the logical network state based on the reconciliation of conflicts.

Reconciliation of network state across physical domains

Some embodiments provide a method for a first network controller located at a first physical domain that manages a logical network spanning several physical domains including the first domain. The method detects that connectivity is lost between the first network controller and a second network controller located in a second one of the physical domains. The method identifies a set of forwarding elements managed by the first network controller that implement the logical network. The method instructs the set of forwarding elements to drop packets for the logical network received from forwarding elements in the second physical domain.

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.

Growing community of inventors

San Francisco, CA, United States of America

Jeremy Stribling