Modular architecture for computer network operations

Patent metadata

Field	Value
Publication number	US-10135724-B2
Application number	US-201615390309-A
Country	US
Kind code	B2
Filing date	Dec 23, 2016
Priority date	May 9, 2016
Publication date	Nov 20, 2018
Grant date	Nov 20, 2018

Abstract

Disclosed embodiments include a method of operation of a distributed network system. The method includes nodes of the network system that send messages over a protocol-independent message bus, and other nodes that receive the messages. Content from the received messages can be stored in a database distributed among nodes of the network system. At least some of the content stored in the database is published. The published content can be accessed by one or more applications to perform one or more functions.

First claim

We claim:

1. A method of operation of a distributed network system including a plurality of nodes, the method comprising:
sending, by a first subset of the plurality of nodes, a plurality of messages over a protocol-independent message bus;
receiving, by a second subset of the plurality of nodes, the plurality of messages sent over the protocol-independent message bus;
storing content from the plurality of messages in a database distributed among at least the second subset of the plurality of nodes that received the plurality of messages;
publishing the content stored in the database to provide published content, the published content being accessible by a plurality of applications; and
accessing the published content by one or more of the plurality of applications to perform one or more functions.

2. The method of claim 1 , further comprising, prior to receiving the plurality of messages by the second subset of the plurality of nodes:
propagating, by a third subset of the plurality of nodes, at least some of the plurality of messages sent by the first subset of the plurality of nodes over the protocol-independent message bus in accordance with a flooding exchange.

3. The method of claim 1 , further comprising, prior to receiving the plurality of messages by the second subset of the plurality of nodes:
segmenting the plurality of nodes into a plurality of clusters, each cluster including one or more nodes of the plurality of nodes;
propagating, among the plurality of clusters, the plurality of messages over the protocol-independent message bus in accordance with a flooding exchange.

4. The method of claim 3 , wherein segmenting the plurality of nodes into the plurality of clusters comprises:
determining one or more spanning trees configured to send messages over nodes in a loop-free manner over the protocol-independent message bus, wherein each of the one or more spanning trees forms a cluster of the plurality of clusters.

5. The method of claim 4 , further comprising:
performing path tracing to determine a plurality of paths taken by the plurality of messages traversing nodes of the plurality of nodes; and
preventing a subset of the plurality of messages from traversing a subset of the plurality of clusters when the subset of the plurality of messages has previously traversed the subset of the plurality of clusters.

6. The method of claim 1 , wherein the plurality of applications comprises at least one of a routing application, a bandwidth allocation application, or a traffic engineering application.

7. The method of claim 1 , wherein the plurality of applications are distributed among at least some of the plurality of nodes.

8. The method of claim 1 , wherein the plurality of applications are resident on one or more nodes separate and distinct from the network system.

9. The method of claim 1 , wherein content stored in the database is periodically synchronized between nodes of the plurality of nodes that have a common link.

10. The method of claim 1 , wherein the database is a key-value database that does not limit keys or values to a maximum size.

11. The method of claim 1 , wherein the database includes existing content associated with one or more timestamps and the content from the plurality of messages is new content, and storing the new content in the database comprises:
designating the existing content as expired content upon exceeding a period of time stored in the database relative to the one or more timestamps; and
replacing the expired content included in the database with the new content from the plurality of messages.

12. The method of claim 1 , wherein the database includes existing content and the content from the plurality of messages is new content, and storing the new content in the database comprises:
designating a subset of the existing content to be replaced with the new content; and
replacing the subset of the existing content with the new content.

13. The method of claim 1 , further comprising:
sending a hello message over a common connecting link from a first node of the plurality of nodes to a second node of the plurality of nodes;
receiving an acknowledgement message by the first node from the second node, the acknowledgement message acknowledging the reception of the hello message by the second node;
sending the hello message over a common connecting link from the second node to a third node of the plurality of nodes; and
receiving an acknowledgement message by the first node from the third node, the acknowledgement message acknowledging the reception of the hello message by the third node.

14. The method of claim 1 , wherein the network system comprises a hello protocol module for sending messages between any two nodes of the plurality of nodes being directly connected to a common link, the hello protocol module being used to perform any of computing spanning tree metrics, automating clustering of the plurality of nodes, or providing bidirectional discovery of neighboring nodes.

15. The method of claim 1 , wherein the method further comprises:
operating the plurality of nodes in a learning mode during which the plurality of nodes learn of public keys of the plurality of nodes, wherein the plurality of nodes having public keys learned during the learning mode are trusted nodes; and
operating the plurality of nodes in a protected mode during which the plurality of nodes accept messages over the message bus only from the trusted nodes.

16. The method of claim 1 , wherein the database is a key-value database comprising Thrift-encoded keys and values.

17. The method of claim 1 , wherein the message bus utilizes a software framework that provides scalable cross-language services for communicating messages among the plurality of nodes.

18. The method of claim 1 , wherein messages sent over the protocol-independent message bus are Thrift encoded.

19. The method of claim 1 , wherein the plurality of messages comprise a plurality of messages that include content that is encoded in accordance with different coding languages and have different formats.

20. The method of claim 1 , wherein the network system is comprised in a backhaul, datacenter, or backbone network.

21. The method of claim 1 , wherein the one or more functions comprises at least one of an address assignment function, an auditing function, a monitoring function, an adaptive control function, an optimization function, or a machine learning function.

22. A distributed network application framework architecture, comprising:
a protocol-agnostic message bus connected to a plurality of nodes of the network, the plurality of nodes being configured to facilitate at least one of sending, receiving, or propagating a plurality of messages over the protocol-agnostic message bus;
a payload-agnostic database distributed across the plurality of nodes and storing content included in at least some of the plurality of messages communicated over the protocol-agnostic message bus; and
one or more applications utilizing the content stored in the database to perform one or more functions.

23. A node of a distributed network system, the node comprising:
an interface to a protocol-agnostic message bus connected to a plurality of nodes of the network system, the interface being configured to facilitate sending, receiving, and propagating a plurality of messages over the protocol-agnostic message bus;
a database component of a payload-agnostic database distributed a

Assignees

• Facebook Inc

Inventors

• Lapukhov Petr V
• Saab Paul M
• Baldonado Omar Castillo
• Williams James
• Somasundaram Manikandan

Classifications

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L43/10

  Active monitoring, e.g. heartbeat, ping or trace-route · CPC title

• H04L12/44 Primary

  Star or tree networks · CPC title

• H04L67/1097

  for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title

• H04L45/48 Primary

  Routing tree calculation · CPC title