SELF-MANAGED OVERLAY NETWORKS

• US 20170063679A1
• Filed: 08/27/2015
• Published: 03/02/2017
• Est. Priority Date: 08/27/2015
• Status: Active Grant

• Current Assignee: Nicira Incorporated (Broadcom, Inc.)
• Original Assignee: Nicira Incorporated (Broadcom, Inc.)
• Inventors: Olmsted-Thompson, Jeremy
• Granted Patent: US 10,122,626 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 12/4633 Interconnection of networks using encapsulation techniques, e.g. tunneling
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/306 Route determination based on the nature of the carried application
• CPC Class Codes: H04L 45/586 of virtual routers
• CPC Class Codes: H04L 45/64 using an overlay routing layer

Abstract

Some embodiments provide a method for processing data messages through an overlay network for a cluster of application instances operating on machines located across several datacenters. The method receives a data message, from a first application instance of the cluster operating on a first machine in a first datacenter, destined to a second application instance. When the second application instance operates on a machine in a different, second datacenter, the method (i) encapsulates the data message according to an overlay network defined for the cluster and (ii) forwards the encapsulated data message to a publicly accessible machine of the second datacenter. Only a subset of the application instances operating in the second datacenter operate on publicly accessible machines. When the second application instance operates on a machine in the first datacenter, the method forwards the data message directly to the machine on which the second application instance operates.

Claims

1. A method for processing data messages through an overlay network for a cluster of application instances operating on machines located across a plurality of datacenters, the method comprising:

receiving a data message, from a first application instance of the cluster operating on a first machine in a first datacenter, destined to a second application instance of the cluster;

when the second application instance operates on a machine in a different, second datacenter;

encapsulating the data message according to an overlay network defined for the cluster of application instances; and

forwarding the encapsulated data message to a publicly accessible machine of the second datacenter, wherein only a subset of the application instances operating in the second datacenter operate on publicly accessible machines; and

when the second application instance operates on a machine in the first datacenter, forwarding the data message directly to the machine on which the second application instance operates.

2. The method of claim 1 further comprising:

maintaining a cluster topology of the cluster of application instances that identifies, for each application instance of the cluster, the datacenter in which the application instance operates; and

updating a set of forwarding tables based on the cluster topology, wherein the set of forwarding tables are used to forward data messages.

3. The method of claim 1, wherein encapsulating the data message comprises using a tunneling protocol.

4. The method of claim 1, wherein the encapsulated data message comprises an address associated with the second application instance, wherein when the encapsulated data message is forwarded to a publicly accessible machine of the second datacenter a cluster manager operating on the publicly accessible machine captures the encapsulated data message and forwards the encapsulated data message to the address associated with the second application instance.

5. The method of claim 4, wherein the address associated with the second application instance is an overlay address assigned to the application instance in the overlay network.

6. The method of claim 1, wherein the publicly accessible machine of the second datacenter is a first publicly accessible machine, the method further comprising, when the second application instance operates in the second datacenter, receiving a response data message, sent by the second application instance to the first application instance, from a second publicly accessible machine of the first datacenter.

7. The method of claim 1, wherein the application instances of the cluster form a complete graph in the overlay network, wherein each application instance is connected to every other application instance in the cluster.

8. The method of claim 1 further comprising:

maintaining a cluster topology that identifies the datacenter in which each application instance of the cluster operates.

receiving a request for at least a portion of the cluster topology from the first application instance; and

providing the requested portion of the cluster topology to the first application instance, wherein the first application instance generates data messages based on the cluster topology.

9. The method of claim 1, wherein the cluster of application instances is a first cluster and the overlay network is a first overlay network, the method further comprising:

receiving a data message from a third application instance of a second cluster of application instances destined for a fourth application instance in a third datacenter, the third application instance operating on the first machine;

encapsulating the data message according to a second overlay network defined for the second cluster of application instances; and

forwarding the data message to a publicly accessible machine of the third datacenter.

10. The method of claim 1, wherein forwarding the encapsulated data message to a publicly accessible machine comprises identifying a particular publicly accessible machine from a plurality of publicly accessible machines in the second datacenter.

11. The method of claim 10, wherein the encapsulated data message is a part of a group of data messages, wherein forwarding the encapsulated data message further comprises sending each data message of the group of data messages to the particular publicly accessible machine.

12. The method of claim 10 further comprising forwarding a second data message destined for the second application instance to a different publicly accessible machine of the plurality of publicly accessible machines.

21. The non-transitory machine readable medium of claim 10, wherein the program further comprises a set of instructions for forwarding a second data message destined for the second application instance to a different publicly accessible machine of the plurality of publicly accessible machines.

13. A non-transitory machine readable medium storing a program which when executed by at least one processing unit processes data messages through an overlay network for a cluster of application instances operating on machines located across a plurality of datacenters, the program comprising sets of instructions for:

receiving a data message, from a first application instance of the cluster operating on a first machine in a first datacenter, destined to a second application instance of the cluster;

when the second application instance operates on a machine in a different, second datacenter;

encapsulating the data message according to an overlay network defined for the cluster of application instances; and

forwarding the encapsulated data message to a publicly accessible machine of the second datacenter, wherein only a subset of the application instances operating in the second datacenter operate on publicly accessible machines; and

when the second application instance operates on a machine in the first datacenter, forwarding the data message directly to the machine on which the second application instance operates.

14. The non-transitory machine readable medium of claim 13, wherein the program further comprises sets of instructions for:

maintaining a cluster topology of the cluster of application instances that identifies, for each application instance of the cluster, the datacenter in which the application instance operates; and

updating a set of forwarding tables based on the cluster topology, wherein the set of forwarding tables are used to forward data messages.

15. The non-transitory machine readable medium of claim 13, wherein the set of instructions for encapsulating the data message comprises a set of instructions for using a tunneling protocol.

16. The non-transitory machine readable medium of claim 13, wherein the encapsulated data message comprises an address associated with the second application instance, wherein when the encapsulated data message is forwarded to a publicly accessible machine of the second datacenter a cluster manager operating on the publicly accessible machine captures the encapsulated data message and forwards the encapsulated data message to the address associated with the second application instance.

17. The non-transitory machine readable medium of claim 16, wherein the address associated with the second application instance is an overlay address assigned to the application instance in the overlay network.

18. The non-transitory machine readable medium of claim 13, wherein the publicly accessible machine of the second datacenter is a first publicly accessible machine, the program further comprising a set of instructions for, when the second application instance operates in the second datacenter, receiving a response data message, sent by the second application instance to the first application instance, from a second publicly accessible machine of the first datacenter.

19. The non-transitory machine readable medium of claim 13, wherein the cluster of application instances is a first cluster and the overlay network is a first overlay network, the program further comprising sets of instructions for:

receiving a data message from a third application instance of a second cluster of application instances destined for a fourth application instance in a third datacenter, the third application instance operating on the first machine;

encapsulating the data message according to a second overlay network defined for the second cluster of application instances; and

forwarding the data message to a publicly accessible machine of the third datacenter.

20. The non-transitory machine readable medium of claim 13, wherein the set of instructions for forwarding the encapsulated data message to a publicly accessible machine comprises a set of instructions for identifying a particular publicly accessible machine from a plurality of publicly accessible machines in the second datacenter.