Method and apparatus for directing a flow of packets based on request and server attributes

• US 20050193114A1
• Filed: 02/11/2005
• Published: 09/01/2005
• Est. Priority Date: 08/01/1997
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Krawczyk, John J., Wasson, Scott, Stevens, Richard C., Nair, Raj Krishnan, Royce, Katherine, Colby, Steven, Siegel, Kenneth P.
• Granted Patent: US 7,257,634 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/724 at intermediate nodes, e.g. resource reservation protocol [RSVP]
• CPC Class Codes: H04L 47/745 Reaction in network
• CPC Class Codes: H04L 47/801 Real time traffic
• CPC Class Codes: H04L 47/805 QOS or priority aware
• CPC Class Codes: H04L 47/822 Collecting or measuring resource availability data
• CPC Class Codes: H04L 49/355 Application aware switches, e.g. for HTTP
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/10015 Access to distributed or replicated servers, e.g. using brokers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/1012 based on compliance of requirements or conditions with available server resources
• CPC Class Codes: H04L 67/1014 based on the content of a request
• CPC Class Codes: H04L 67/1021 based on client or server locations
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/1027 Persistence of sessions during load balancing
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/1031 Controlling of the operation of servers by a load balancer, e.g. adding or removing servers that serve requests
• CPC Class Codes: H04L 67/51 Discovery or management thereof, e.g. service location protocol [SLP] or web services
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 69/329 : in the application layer [OSI layer 7]
• CPC Class Codes: H04L 9/40 : Network security protocols

Abstract

A content-aware flow switch intercepts a client content request in an IP network, and transparently directs the content request to a best-fit server. The best-fit server is chosen based on the type of content requested, the quality of service requirements implied by the content request, the degree of load on available servers, network congestion information, and the proximity of the client to available servers. The flow switch detects client-server flows based on the arrival of TCP SYNs and/or HTTP GETs from the client. The flow switch implicitly deduces the quality of service requirements of a flow based on the content of the flow. The flow switch also provides the functionality of multiple physical web servers on a single web server in a way that is transparent to the client, through the use of virtual web hosts and flow pipes.

Claims

1-49. -49. (canceled)

50. A content aware flow switch interconnecting a plurality of web servers and at least one client side device, comprising:

a client side interface operable to connect a plurality of client computing devices for receiving client requests for content and delivering network services in the form of media content responsive to the client requests;

a content server database operable to store server metrics and content switching criteria, and further operable to derive content information from the client request, the content information indicative of criteria for processing the client request

a flow admission controller for identifying, from among a plurality of servers, a set of potential servers adapted to service the client request, the set of potential servers each having a plurality of server metrics indicative of server resources; and

a web flow redirector operable to compute, based on analyzing the derived content information and the content switching criteria, a best-fit server from the set of potential servers, the best fit server having a high correspondence between the plurality of server metrics and the criteria for processing the client request.

51. The method of claim 50 wherein the web flow redirector is further operable to assign packets responsive to the client request based on a high correspondence between the plurality of server metrics and the criteria for processing the client request.

52. The method of claim 51 wherein the web flow redirector is operable to assign packets corresponding to a particular criteria to at least on of a flow pipe and a virtual connection VC pipe.

53. The method of claim 52 wherein the assigned packets are forwarded on a forwarding path based on flow content information derived from source address, destination address, transport layer protocol, port number QOS designation

54. The method of claim 53 wherein the packets corresponding to a particular client request are packet flows, the packet flows assigned to VC pipes based on matching characteristics in the content information of respective flows through the VC pipe.

55. A web server responsive to a content aware flow switch for delivering network content responsive to client requests comprising:

an interface to a content aware flow switch for receiving a client request for network services, the client request for at least one of a particular type of content; and

a content resource, the content resource responsive to derived content information from the client request, the content information indicative of criteria for processing the client request, the interface invokable by the content aware flow switch based on identifying, from among a plurality of servers, a set of potential servers adapted to service the client request, the set of potential servers each having a plurality of server metrics indicative of server resources, the content aware flow switch further operable to compute, based on analyzing the derived content information and the content switching criteria, a best-fit server from the set of potential servers, the best fit server having a high correspondence between the plurality of server metrics and the criteria for processing the client request.

56. The method of claim 55 wherein the web server is operable to selectively apportion the data flow for response traffic emanating from the web server, the data traffic responsive to client requests and directed to an end user.

57. The method of claim 56 wherein the web server is responsive to the content aware flow switch for determining whether to admit a flow to the flow switch.

58. The method of claim 57 wherein the content aware flow switch is operable to compute the derived content information based on transport and session level routing information derived from data traffic packets.

59. The method of claim 58 wherein the content aware flow switch is operable to Identify a sticky server and reassign flow traffic accordingly, a sticky server being sensitive to a packet context such that subsequent packets expect the same server as previous packets.

60. In a computer network operable for providing network services, a client side router coupled to end station computing devices operable to serve a plurality of end user comprising:

an interface to a content aware flow switch operable as a front end to a plurality of web servers; and

an interface to at least one user operable to receive a client request for network services, the client request for at least one of a particular type of content, the client request having derivable content information indicative of content switching criteria for processing the client request, the client side router responsive to the content aware flow switch for identifying, from among a plurality of servers, a set of potential servers adapted to service the client request, the set of potential servers each having a plurality of server metrics indicative of server resources, the content aware flow switch further operable to compute, based on analyzing the derived content information and the content switching criteria, a best-fit server from the set of potential servers, the best fit server having a high correspondence between the plurality of server metrics and the criteria for processing the client request.

61. The method of claim 60 wherein the router is operable to route assigned packets to a packet flow based on a high correspondence between the plurality of server metrics and the content switching criteria for processing the client request, the packets assigned by the content aware flow switch.

62. The method of claim 61 wherein the content aware flow switch is operable to assign packets corresponding to a particular criteria to at least on of a flow pipe and a virtual connection VC pipe.

63. The method of claim 62 wherein the assigned packets are forwarded on a forwarding path based on flow content information derived from source address, destination address, transport layer protocol, port number QOS designation

64. The method of claim 63 wherein the packet flows are packets corresponding to a particular request, the packet flows being assigned to VC pipes based on matching characteristics in the content information of respective flows through the VC pipe.

65. In a network data communications device, a method for identifying a server to service a network request comprising:

receiving a client request for network services, the client request for at least one of a particular type of content;

deriving content information from the client request, the content information indicative of content switching criteria for processing the client request;

identifying, from among a plurality of servers, a set of potential servers adapted to service the client request, the set of potential servers each having a plurality of server metrics indicative of server resources;

computing, based on analyzing the derived content information and the content switching criteria, a best-fit server from the set of potential servers, the best fit server having a high correspondence between the plurality of server metrics and the criteria for processing the client request;

selecting at least one of one of a flow pipe and a virtual connection VC pipe for a particular packet; and

assigning packets corresponding to a particular criteria to a packet flow based on a high correspondence between the plurality of server metrics and the content switching criteria, the packets assigned by the content aware flow switch, the assigning to a packet flow further comprising;

selectively apportioning the data flow for response traffic, the response traffic emanating from a web server and directed to an end user responsive to a client request;

determining whether to admit a flow to a particular flow via the flow switch based on flow content information based on transport and session level routing information derived from data traffic packets; and

forwarding assigned packets on a forwarding path based on flow content information derived from source address, destination address, transport layer protocol, port number QOS designation, the packets corresponding to a particular request further comprising a packet flow, the packet flows being assigned to VC pipes based on matching characteristics in the content information of respective flows through the VC pipe.

66. The method of claim 65 further comprising identifying a sticky server and reassigning flow traffic accordingly to avoid context loss, a sticky server being sensitive to a packet context such that subsequent packets expect the same server as previous packets.

67. The method of claim 66 wherein assigning packets further comprises establishing a flow between the client originating the client request and the computed best-fit server, the flow established by a flow admission controller module by:

assigning, if an existing VC pipe shares similar characteristics with the established flow, the established flow to the existing VC pipe; and

creating, if an existing VC pipe has insufficient resources to handle the established flow, a new VC pipe for the established flow.

68. The method of claim 67 wherein identifying the set of potential servers and computing the best fit server is performed in a continuous non-blocking manner independent of external inputs.

69. The method of claim 68 wherein computing based on the content switching criteria further comprises querying content rules, content records, and server records, the content rules indicative of flow switch operation, the content records derived from the content rules, and the server records indicative of processing resources at a particular server.