Automatic configuration of external services based upon network activity

Patent metadata

Field	Value
Publication number	US-9392050-B2
Application number	US-201313842394-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Mar 15, 2013
Publication date	Jul 12, 2016
Grant date	Jul 12, 2016

Abstract

System, computer program product, and method to configure an external network based on internal network conditions, by monitoring a load attribute of one or more network flows traversing an ingress port of at least one network element in a software-defined networking (SDN) enabled network, upon determining that the load attribute of a first network element in the SDN enabled network exceeds a predefined threshold, provisioning, by the application, an additional service on the external network, by the application, an additional service on the external network, and extending, by the application, the SDN enabled network to include the additional service on the external network.

First claim

We claim:

1. A computer-implemented method, comprising:
applying, by an application, an input filter to an ingress port of a first network element to monitor one or more network flows traversing the ingress port of the first network element using an application programming interface (API), the API abstracting a control plane of the first network element to permit the application to monitor and control data traffic traversing the first network element, wherein the first network element is in a software defined networking (SDN) enabled network, wherein the SDN enabled network comprises a private cloud network;
monitoring, by the input filter, a load attribute of the one or more network flows;
upon determining that the load attribute exceeds a predefined threshold, issuing, by the input filter applied to the first network element, a high load notification to the application;
provisioning, by the application, an additional service on an external network, wherein the external network comprises a public cloud network, wherein the external network is external to and not a part of the SDN enabled network; and
extending, by the application, the SDN enabled network to include the additional service on the external network, wherein extending the SDN enabled network creates a hybrid network comprising the private cloud network and the public cloud network.

2. The method of claim 1 , wherein the load attribute comprises each of: (i) a number of connections of the ingress port of the first network element, (ii) a load of a processor of the first network element, (iii) a number of dropped connections of the ingress port of the first network element, and (iv) an observed response latency of the one or more data flows traversing the ingress port of the first network element.

3. The method of claim 2 , wherein provisioning the additional service on the external network comprises:
instantiating at least one virtual machine sourced from a public cloud computing provider; and
calling external configuration tools to instantiate services on the at least one virtual machine.

4. The method of claim 3 , wherein extending the SDN enabled network to include the additional service on the external network comprises:
altering, by the application, a routing information base of the first network element to distribute traffic across the hybrid network.

5. The method of claim 4 , further comprising:
upon determining that the load attribute of the first network element falls below the threshold, decommissioning the additional service to remove the additional service from the SDN enabled network, wherein removing the additional service from the SDN enabled network removes the public cloud network from the SDN enabled network and converts the hybrid cloud network to the private cloud network.

6. The method of claim 5 , wherein the application is executed on the first network element.

7. The method of claim ≡ON, wherein the application is a distributed application comprising a plurality of instances of the application executing on a respective one of a plurality of network elements in the SDN enabled network, wherein each of the plurality of instances are communicably coupled to determine an optimal load of the plurality of network elements based on each of: (i) a temperature of a data center housing at least a subset of the plurality of network elements, (ii) an electric grid load, (iii) a response time of a second application, a (iv) a client identifier.

8. The method of claim 7 , wherein a plurality of network elements in the SDN enabled network each comprise a respective input filter and a respective API for monitoring load attributes of data traffic traversing the plurality of network devices.

9. A system, comprising:
one or more computer processors; and
a memory containing a program, which when executed by the one or more computer processors, performs an operation comprising:
applying, by an application, an input filter to an ingress port of a first network element in a software defined networking (SDN) enabled network to monitor one or more network flows traversing the ingress port of the first network element using an application programming interface (API), the API abstracting a control plane of the first network element to permit the application to monitor and control data traffic traversing the first network element:
monitoring, by the input filter, a load attribute of the one or more network flows;
upon determining that the load attribute exceeds a predefined threshold, issuing, by the input filter applied to the first network element, a high load notification to the application;
provisioning, by the application, an additional service on an external network, wherein the external network comprises a public cloud network and is external to and not a part of the SDN enabled network, wherein the SDN enabled network comprises a private cloud network; and
extending, by the application, the SDN enabled network to include the additional service on the external network, wherein extending the SDN enabled network creates a hybrid network comprising the SDN enabled network and the external network.

10. The system of claim 9 , wherein the load attribute comprises each of: (i) a number of connections of the ingress port of the first network element, (ii) a load of a processor of the first network element, (iii) a number of dropped connections of the ingress port of the first network element, and (iv) an observed response latency of the one or more data flows traversing the ingress port of the first network element.

11. The system of claim 10 , wherein provisioning the additional service on the external network comprises:
instantiating at least one virtual machine sourced from a public cloud computing provider; and
calling external configuration tools to instantiate services on the at least one virtual machine.

12. The system of claim 11 , wherein extending the SDN enabled network to include the additional service on the external network comprises:
altering, by the application, a routing information base of the first network element to distribute traffic across the hybrid network.

13. The system of claim 12 , the operation further comprising:
upon determining that the load attribute of the first network element falls below the threshold, decommissioning the additional service to remove the additional service from the SDN enabled network, wherein removing the additional service from the SDN enabled network removes the public cloud network from the SDN enabled network and converts the hybrid cloud network to the private cloud network.

14. The system of claim 13 , wherein the application is executed on the first network element.

15. The system of claim 13 , wherein the application is a distributed application comprising a plurality of instances of the application executing on a respective one of a plurality of network elements in the SDN enabled network, wherein each of the plurality of instances are communicably coupled to determine an optimal load of the plurality of network elements based on each of: (i) a temperature of a data center housing at least a subset of the plurality of network elements, (ii) an electric grid load, (iii) a response time of a second application, a (iv) a client identifier.

16. The system of claim 15 , wherein a plurality of network elements in the SDN enabled network each comprise a respective input filter and a respective API for monitoring load attributes of data traffic traversing the plurality of network devices.

17. A computer program product to configure external network

Assignees

• Cisco Tech Inc

Inventors

• Voit Eric A
• Pruss Richard M
• Mcdowall John E

Classifications

• H04L41/5096

  wherein the managed service relates to distributed or central networked applications · CPC title

• G06F9/5083

  Techniques for rebalancing the load in a distributed system · CPC title

• G06F2209/5022

  Workload threshold · CPC title

• H04L41/0816

  the condition being an adaptation, e.g. in response to network events · CPC title

• H04L67/10 Primary

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title