Managed switch architectures for implementing logical datapath sets

• US 9,306,875 B2
• Filed: 08/26/2011
• Issued: 04/05/2016
• Est. Priority Date: 07/06/2010
• Status: Active Grant

• Current Assignee: Nicira Incorporated (Broadcom, Inc.)
• Original Assignee: Nicira Incorporated (Broadcom, Inc.)
• Inventors: Casado, Martin, Amidon, Keith E., Pfaff, Benjamin L.
• Primary Examiner(s): HSU, ALPUS
• Application Number:
  US13/218,477
• Publication Number:
  US 20130058255A1
• Time in Patent Office: 1,684 Days
• Field of Search: 370/235, 370/254, 370/256, 370/396, 370/397, 370/400, 370406-409, 370/428, 709/201, 709/230, 709/238, 709/252, 709/223
• US Class Current: 1/1
• CPC Class Codes: G06F 11/07 Responding to the occurrence of a fault, e.g. fault tolerance
• CPC Class Codes: G06F 15/17312 Routing techniques specific to parallel machines, e.g. wormhole, store and forward, shortest path problem congestion routing on a LAN H04L45/00
• CPC Class Codes: H04L 12/4633 Interconnection of networks using encapsulation techniques, e.g. tunneling
• CPC Class Codes: H04L 2101/622 Layer-2 addresses, e.g. medium access control [MAC] addresses
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• CPC Class Codes: H04L 41/0853 by actively collecting configuration information or by backing up configuration information
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/0895 Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/122 of virtualised topologies, e.g. software-defined networks [SDN] or network function virtualisation [NFV]
• CPC Class Codes: H04L 45/00 Routing or path finding of packets in data switching networks routing or path finding in wireless networks H04W40/00
• CPC Class Codes: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 45/036 Updating the topology between route computation elements, e.g. between OpenFlow controllers
• CPC Class Codes: H04L 45/586 of virtual routers
• CPC Class Codes: H04L 45/76 Routing in software-defined topologies, e.g. routing between virtual machines
• CPC Class Codes: H04L 47/783 Distributed allocation of resources, e.g. bandwidth brokers
• CPC Class Codes: H04L 49/00 Packet switching elements
• CPC Class Codes: H04L 49/1546 using pipelined operation
• CPC Class Codes: H04L 49/3063 Pipelined operation
• CPC Class Codes: H04L 49/70 : Virtual switches
• CPC Class Codes: H04L 61/5007 : Internet protocol [IP] addresses

Abstract

Some embodiments provide a system that includes a set of network controllers for receiving definitions of first and second logical switching elements. The system includes several managed switching elements. The set of network controllers configure the several managed switching elements to implement the defined first and second logical switching elements. The system includes several network hosts that are each (1) communicatively coupled to one of the several managed switching elements and (2) associated with one of the first and second logical switching elements. Network data communicated between network hosts associated with the first logical switching element are isolated from network data communicated between network hosts associated with the second logical switching element.

Claims

1. A system comprising:

a plurality of network controller instances for identifying definitions of a first logical datapath set (LDPS) and a second LDPS;

a plurality of managed edge (ME) switching elements comprising a set of hardware switching elements and a set of software switching elements;

a plurality of machines that are each (1) communicatively coupled to one of the plurality of ME switching elements and (2) associated with at least one of the first LDPS and the second LDPS; and

a set of managed non-edge (MNE) switching elements for facilitating communication between the ME switching elements,

wherein the plurality of network controller instances are further for managing the ME and MNE switching elements by providing the ME and MNE switching elements with configuration data for specifying flow entries for forwarding network data between machines of the plurality of machines based on the identified definitions of the first LDPS and the second LDPS.

2. The system of claim 1, wherein at least one ME switching element in the plurality of ME switching elements is provided with configuration data based on the identified definitions of both the first LDPS and the second LDPS.

3. The system of claim 1, wherein the set of hardware switching elements comprises a set of top-of-rack hardware switching elements, wherein each top-of-rack hardware switching element is part of a rack that includes a set of machines of the plurality of machines.

4. The system of claim 1 further comprising a plurality of unmanaged switching elements that are not managed by the network controller instances and that communicatively couple the ME and MNE switching elements, the plurality of unmanaged switching elements comprising at least one top-of-rack hardware switch.

5. The system of claim 1, wherein the set of software switching elements execute on a set of hosts, each host in the set of hosts for executing (i) a set of virtual machines of the plurality of machines, (ii) a hypervisor for managing the set of virtual machines, and (iii) a software switching element in the set of software switching elements.

6. The system of claim 1, wherein the set of MNE switching elements is for forwarding network data from a first ME switching element in the plurality of ME switching elements to a second ME switching element in the plurality of ME switching elements when the first ME switching element cannot forward the network data to the second ME switching element.

7. The system of claim 6, wherein the network controller instances are further for configuring the set of MNE switching elements to forward the network data from the first ME switching element to the second ME switching element when the network data comprises multi-recipient network data.

8. The system of claim 7, wherein the multi-recipient network data is broadcast network data.

9. The system of claim 7, wherein the multi-recipient network data is multicast network data.

10. The system of claim 6, wherein the plurality of network controller instances are further for configuring the set of MNE switching elements to forward the network data from the first ME switching element to the second ME switching element when the first ME switching element and the second ME switching element are not directly coupled to each other.

11. The system of claim 6, wherein the plurality of network controller instances are further for configuring the set of MNE switching elements to forward network data between the first ME switching element and the second ME switching element when a tunnel is not established between the first ME switching element and the second ME switching element.

12. The system of claim 1, wherein the plurality of network controller instances are further for configuring the plurality of ME switching elements through a set of communication protocols comprising a configuration protocol for communicating configuration information.

13. The system of claim 1, wherein the plurality of network controller instances are further for configuring the plurality of ME switching elements through a set of communication protocols comprising an OpenFlow protocol for communicating data regarding the specified flow entries.

14. The system of claim 1, wherein the plurality of network controller instances comprises a first network controller instance for configuring a first subset of the plurality of ME switching elements and a second network controller instance for configuring a second, different subset of the plurality of ME switching elements.

15. The system of claim 1,

wherein each network controller instance in the plurality of network controller instances comprises a control application layer and a virtualization application layer;

wherein a particular network controller instance identifies logical control plane data for the first LDPS and the second LDPS;

wherein the control application layer of the particular network controller instance is for converting the logical control plane data for the first LDPS and the second LDPS to logical forwarding plane data for the first LDPS and the second LDPS;

wherein the virtualization application layer of the particular network controller is for converting the logical forwarding plane data of the first LDPS and the second LDPS to physical control plane data for the ME switching elements; and

wherein the set of network controllers provide the plurality of ME switching elements with the configuration data by sending the physical control plane data to the plurality of ME switching elements for conversion to physical forwarding plane data.

16. For a network controller instance that manages switching elements based on definitions of logical datapath sets, a method comprising:

identifying definitions of a first logical datapath set (LDPS) and a second LDPS;

based on the definitions of the first LDPS and the second LDPS;

generating a first set of configuration data for specifying flow entries for a plurality of managed edge (ME) switching elements to forward network data between sets of machines coupled to the plurality of ME switching elements, the plurality of ME switching elements comprising a set of hardware switching elements and a set of software switching elements; and

generating a second set of configuration data for a set of managed non-edge (MNE) switching elements to facilitate communication between the plurality of ME switching elements; and

managing the ME and MNE switching elements by providing the generated first and second sets of configuration data to the ME and MNE switching elements using a communication protocol.

17. The method of claim 16, wherein the generated first set of configuration data comprises configuration data for specifying flow entries for a particular ME switching element in the plurality of ME switching elements based on the definitions of both the first LDPS and the second LDPS.

18. The method of claim 16, wherein the set of hardware switching elements comprises a set of top-of-rack hardware switching elements for corresponding racks of machines, wherein the generated first set of configuration data comprises configuration data for configuring each top-of-rack hardware switching element in the set of top-of-rack hardware switching elements to forward network data for the corresponding rack of machines.

19. The method of claim 16, wherein the set of software switching elements execute on a set of hosts, each host in the set of hosts for executing (i) a set of virtual machines, (ii) a hypervisor for managing the set of virtual machines, and (iii) a software switching element in the set of software switching elements.

20. The method of claim 16, wherein the generated second set of configuration data comprises configuration data for configuring the set of MNE switching elements to forward network data from a first ME switching element to a second ME switching element when the first ME switching element cannot forward the network data to the second ME switching element.

21. The method of claim 20, wherein the generated second set of configuration data further comprises configuration data for configuring the set of MNE switching elements to forward the network data from the first ME switching element to the second ME switching element when the network data comprises multi-recipient network data.

22. The method of claim 21, wherein the multi-recipient network data is broadcast network data.

23. The method of claim 21, wherein the multi-recipient network data is multicast network data.

24. The method of claim 20, wherein the generated second set of configuration data further comprises configuration data for configuring the set of MNE switching elements to forward the network data from the first ME switching element to the second ME switching element when the first ME switching element and the second ME switching element are not directly coupled to each other.

25. The method of claim 20, wherein the generated second set of configuration data further comprises configuration data for configuring the set of MNE switching elements to forward the network data from the first ME switching element to the second ME switching element when a tunnel is not established between the first ME switching element and the second ME switching element.

26. The method of claim 16,

wherein identifying the definition of the first LDPS comprises identifying logical control plane data for the first LDPS and identifying the definition of the second LDPS comprises identifying logical control plane data for the second LDPS, the method further comprising:

converting the logical control plane data for the first and second LDPSs to logical forwarding plane data for the first and second LDPSs;

converting the logical forwarding plane data of the first and second LDPSs to physical control plane data for the ME switching elements; and

using a common communication protocol to send the physical control plane data to the plurality of ME switching elements and to the set of MNE switching elements.

27. A network system comprising:

a set of network controller instances for identifying a definition of a logical datapath set (LDPS);

a plurality of managed edge (ME) switching elements that are each for (1) coupling to a set of machines and (2) forwarding network data of the set of machines, the plurality of ME switching elements comprising a set of hardware ME switching elements and a set of software ME switching elements; and

a managed non-edge (MNE) switching element for facilitating communication between the plurality of ME switching elements based on the identified definition of the LDPS,

the set of network controller instances further for managing the plurality of ME switching elements and the MNE switching element by supplying configuration data to the sets of hardware and software ME switching elements, the configuration data for specifying flow entries for forwarding network data between the sets of machines based on the identified definition of the LDPS.

28. The network system of claim 27, wherein each hardware ME switching element of the set of hardware ME switching elements is a top-of-rack switching element for a corresponding rack of machines comprising the corresponding set of machines to which the top-of-rack switching element is coupled.

29. The network system of claim 27, wherein the MNE switching element is a hardware switching element.

30. The network system of claim 27, wherein the MNE switching element is a software switching element executing on a standalone computing device.

31. The network system of claim 30, wherein the MNE switching element is a first MNE switching element, the network system further comprising:

a second MNE switching element for facilitating communication between the plurality of ME switching elements and the first MNE switching element based on the identified definition of the LDPS.

32. The network system of claim 31, wherein the second MNE switching element is a software switching element executing on the standalone computing device along with the first MNE switching element.

33. The network system of claim 31, wherein the standalone computing device is a first standalone computing device, wherein the second MNE switching element is a software switching element executing on a second computing device different from the first standalone computing device.

34. The network system of claim 31, wherein the set of network controller instances is further for supplying the configuration data to the second MNE switching element, the configuration data for specifying flow entries for allowing the second MNE switching element to forward network data that the first MNE switching element cannot forward.