Method, apparatus, and system for implementing a content switch

• US 10,609,091 B2
• Filed: 07/30/2015
• Issued: 03/31/2020
• Est. Priority Date: 04/03/2015
• Status: Active Grant

• Current Assignee: Nicira Incorporated (Broadcom, Inc.)
• Original Assignee: Nicira Incorporated (Broadcom, Inc.)
• Inventors: Hong, Xinhua, Jain, Jayant, Sengupta, Anirban
• Primary Examiner(s): Bates, Kevin T
• Assistant Examiner(s): McCray, Clarence D
• Application Number:
  US14/813,659
• Publication Number:
  US 20160294933A1
• Time in Patent Office: 1,706 Days
• Field of Search: 709206
• CPC Class Codes: G06F 9/00 Arrangements for program control, e.g. control units program control for peripheral devices G06F13/10
• CPC Class Codes: G06F 9/46 Multiprogramming arrangements
• CPC Class Codes: H04L 41/08 Configuration management of networks or network elements address allocation H04L61/50
• CPC Class Codes: H04L 41/0895 Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 67/1004 Server selection for load balancing
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 67/141 Setup of application sessions admission control or resource allocation in data switching networks H04L47/70
• CPC Class Codes: H04L 67/288 Distributed intermediate devices, i.e. intermediate devices for interaction with other intermediate devices on the same level
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]

Abstract

Some embodiments provide a novel content switching method that distributes requests for different types of content to different sets of content servers. In some embodiments, the method deploys a content switch in the ingress data path of a first content server that is part of a first set of servers that processes requests for a first type of content. This content switch receives each content request that is directed to the first content server, and determines whether the received request is for the first content type that is processed by the first content server. If so, the content switch directs the request to the first content server. On the other hand, if the request is for a second type of content that is processed by a second set of servers, the content switch identifies a second content server in the second set and forwards the request to the second content server. When the second set of servers includes two or more servers, the content switch in some embodiments performs a load balancing operation to distribute the load amongst the servers in the second set. For each request, the load balancing operation in some embodiments selects one server from the second server set based on a set of load balancing criteria that specifies one manner for distributing the requests among the servers of the second set, and then forwards the request to the selected server.

Claims

1. A method of implementing a distributed content switch that is implemented by a plurality of content switches executing on a plurality of physical host computers along with a plurality of content servers, the distributed content switch forwarding different content requests to different groups of content servers that process different types of content, the method comprising:

defining data that identifies first and second groups of content servers and first and second types of content processed by the first and second groups of content servers respectively, the first and second groups of content servers associated with a shared network address; and

distributing the defined data to the plurality of content switches, the plurality of content switches (1) executing on the plurality of host computers, (2) associated with the first and second groups of content servers, and (3) deployed in the ingress datapaths of the plurality of content servers,

said distributed data configuring a first content switch executing on a first host computer to make a determination (i) to forward a first request that is associated with the shared network address and that is for a first-type content to a first-group content server when the first-group content server executes on the first host computer, and (ii) to forward a second request that is associated with the shared network address and that is for a second-type content to a second host computer when a second-group content server executes on the second host computer by modifying a destination network address of the second request from a first address associated with a content server executing on the first host computer to a second address associated with the second-group content server executing on the second host computer, wherein a network element forwards the first and second requests to the first host computer based on the shared network address.

2. The method of claim 1, wherein the first address associated with a content server executing on the first host computer is the address of the content server executing on the first host computer.

3. The method of claim 1,

wherein the defined data distributed to the plurality of content switches comprises load-balancing criteria that are defined to distribute requests for each type of content among content servers that process each different type of content,

wherein prior to modifying the destination network address of the second request, the first content switch selects the second-group content server from the second group of content servers based on the load-balancing criteria.

4. The method of claim 3, wherein the distributed data comprises content request data message load on each content server in the second group of content servers.

5. The method of claim 3, wherein the load balancing criteria comprise load balancing parameters that specify a percentage of content requests that should be forwarded to each content server in the second group of content servers.

6. The method of claim 1 further comprising:

from the plurality of content switches, collecting data to quantify the content request load processed by each content server; and

changing membership of one of the server groups based on the collected data.

7. The method of claim 1, wherein at least one content switch is associated with more than one content server.

8. The method of claim 1, wherein at least one content server is a virtual machine or a container that executes on a host computer.

9. The method of claim 1, wherein at least one content switch is associated with just one content server executing on the same host computer, and is implemented as a filter module that intercepts data messages forwarded to the associated content server from the ingress datapath of the associated content server.

10. The method of claim 1, wherein said distributed data further configures a second content switch executing on the second host computer to make a determination (i) to forward a third request that is associated with the shared network address and that is for the second-type content to the second-group content server executing on the second host computer, and (ii) to forward a fourth request that is associated with the shared network address and that is for the first-type content to the first host computer by modifying a destination network address of the fourth request from a third address associated with a content server executing on the second host computer to a fourth address associated with a first-group content server executing on the first host computer, wherein a network element forwards the third and fourth requests to the second host computer based on the shared network address.

11. The method of claim 1, wherein the first address associated with a content server executing on the first host computer is the address of the first host computer, the network element replacing the shared network address with the first address in both the first and second requests.

12. The method of claim 1, wherein the second address associated with the second-group content server executing on the second host computer is the address of the second-group content server executing on the second host computer.

13. The method of claim 1, wherein the second address associated with the second-group content server executing on the second host computer is the address of the second host computer on which the second-group content server executes.

14. A non-transitory machine readable medium storing a program for defining a distributed content switch that is implemented by a plurality of content switches executing on a plurality of physical host computers along with a plurality of content servers, the distributed content switch forwarding different content requests to different groups of servers that process different types of content, the program comprising sets of instructions for:

defining data that identifies first and second groups of content servers and first and second types of content processed by the first and second groups of content servers respectively, the first and second groups of content servers associated with a shared network address; and

distributing the defined data to the plurality of content switches, the plurality of content switches (1) executing on the plurality of host computers, (2) associated with the first and second groups of content servers, and (3) deployed in the ingress datapaths of the plurality of content servers,

said distributed data configuring a first content switch executing on a first host computer to make a determination (i) to forward a first request that is associated with the shared network address and that is for a first-type content to a first-group content server when the first-group content server executes on the first host computer, and (ii) to forward a second request that is associated with the shared network address and that is for a second-type content to a second host computer when a second-group content server executes on the second host computer by modifying a destination network address of the second request from a first address associated with a content server executing on the first host computer to a second address associated with the second-group content server executing on the second host computer, wherein a network element forwards the first and second requests to the first host computer based on the shared network address.

15. The non-transitory machine readable medium of claim 14, wherein the data distributed to each content switch of each server group includes identities of servers in the other server group.

16. The non-transitory machine readable medium of claim 14,

wherein the defined data distributed to the plurality of content switches comprises load balancing criteria that are defined to distribute requests for each type of content among content servers that process each type of content,

wherein prior to modifying the destination network address of the second request, the first content switch selects the second-group content server from the second group of content servers based on the load balancing criteria.

17. The non-transitory machine readable medium of claim 16, wherein the load balancing criteria comprises content request data message load on each server in the second group.

18. The non-transitory machine readable medium of claim 17, wherein the program further comprises sets of instructions for:

from the plurality of content switches, collecting data to quantify the content request load processed by each content server; and

modifying the load balancing criteria for at least one content server group based on the collected data.

19. The non-transitory machine readable medium of claim 16, wherein the load balancing criteria comprise load balancing parameters that specify a portion of content requests that should be redirected to each second-group content server in the second group of content servers.

20. The non-transitory machine readable medium of claim 14, wherein each content switch establishes a layer 4 session with the source of each content request to receive a set of payload packets for analysis to determine the type of content being requested.

21. The non-transitory machine readable medium of claim 14, wherein the distributed data identifies more than two groups of content servers for processing more than two types of content.

22. The non-transitory machine readable medium of claim 14, wherein at least one group of content servers processes content requests for more than one type of content.