CDN LOAD BALANCING IN THE CLOUD

• US 20140122725A1
• Filed: 11/01/2012
• Published: 05/01/2014
• Est. Priority Date: 11/01/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Batrouni, Marwan, Zions, Jason Drew, Hornoiu, Octavian
• Granted Patent: US 9,537,973 B2
• Time in Patent Office: Days
• US Class Current: 709/226
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• 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 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
• CPC Class Codes: H04L 41/5096 wherein the managed service relates to distributed or central networked applications
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/289 Intermediate processing functionally located close to the data consumer application, e.g. in same machine, in same home or in same sub-network
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

CND load balancing in the cloud. Server resources are allocated at an edge data center of a content delivery network to properties that are being serviced by edge data center. Based on near real-time data, properties are sorted by trending traffic at the edge data center. Server resources are allocated for at least one property of the sorted properties at the edge data center. The server resources are allocated based on rules developed from long-term trends. The resource allocation includes calculating server needs for the property in a partition at the edge data center, and allocating the server needs for the property to available servers in the partition.

Claims

1. At a computer system including one or more processors and system memory, a method for allocating server resources at an edge data center of a content delivery network (CDN) to properties serviced by the edge data center, the method comprising:

an act of the computer system sorting, based on near real-time data, a plurality of properties by trending traffic at the edge data center; and

an act of the computer system allocating server resources for at least one property of the sorted plurality of properties at the edge data center based on one or more rules developed from long-term trends, including;

an act of the computer system calculating server needs for the at least one property in a partition at the edge data center; and

an act of the computer system allocating the server needs for the at least one property to one or more available servers in the partition.

2. The method as recited in claim 1, wherein allocating server resources for at least one property of the sorted plurality of properties at the edge data center comprises allocating server resources for a property having a larger trending traffic prior to allocating server resources for a property having a smaller trending traffic.

3. The method as recited in claim 1, wherein calculating server needs for the at least one property in the partition at the edge data center comprises determining that trending traffic will cause the at least one property to experience a load type increase.

4. The method as recited in claim 3, further comprising:

an act of the computer system assigning a new load type to the at least one property; and

an act of the computer system calculating server needs for the at least one property based on the new load type.

5. The method as recited in claim 1, wherein allocating the server needs for the at least one property comprises allocating the server needs for the at least one property to a plurality of partitions at the same edge data center.

6. The method as recited in claim 1, wherein allocating the server needs for the at least one property to one or more available servers in the partition comprises sorting a plurality of available servers in the partition according to a weighted average of one or more of a resources aggregates index, a stickiness of cached data index, or a compatibility index.

7. The method as recited in claim 6, wherein the compatibility index is computed based on applying a penalty coefficient to incompatible property types at a server.

8. The method as recited in claim 1, wherein the stickiness of cached data index is computed based on how long data has been cached at a server.

9. The method as recited in claim 1, further comprising:

an act of the computer system handling server deficit.

10. The method as recited in claim 9, wherein handling server deficit comprises requesting resources from one or more other edge data centers.

11. A computer program product comprising one or more physical storage devices storing computer-executable instructions that, when executed by one or more processors of a computer system, cause the computer system to implement method for allocating server resources at an edge data center of a content delivery network (CDN) to properties serviced by the edge data center, the method comprising:

an act of the computer system sorting, based on near real-time data, a plurality of properties by trending traffic at the edge data center; and

an act of the computer system allocating server resources for at least one property of the sorted plurality of properties at the edge data center based on one or more rules developed from long-term trends, including;

an act of the computer system calculating server needs for the at least one property in a partition at the edge data center; and

an act of the computer system allocating the server needs for the at least one property to one or more available servers in the partition.

12. The computer program product as recited in claim 11, wherein allocating server resources for at least one property of the sorted plurality of properties at the edge data center comprises allocating server resources for a property having a larger trending traffic prior to allocating server resources for a property having a smaller trending traffic.

13. The computer program product as recited in claim 11, wherein calculating server needs for the at least one property in the partition at the edge data center comprises determining that trending traffic will cause the at least one property to experience a load type increase.

14. The computer program product as recited in claim 13, further comprising:

an act of the computer system assigning a new load type to the at least one property; and

an act of the computer system calculating server needs for the at least one property based on the new load type.

15. The computer program product as recited in claim 11, wherein allocating the server needs for the at least one property comprises allocating the server needs for the at least one property to a plurality of partitions at the same edge data center.

16. The computer program product as recited in claim 11, wherein allocating the server needs for the at least one property to one or more available servers in the partition comprises sorting a plurality of available servers in the partition according to a weighted average of one or more of a resources aggregates index, a stickiness of cached data index, or a compatibility index.

17. The computer program product as recited in claim 16, wherein the compatibility index is computed based on applying a penalty coefficient to incompatible property types at a server.

18. The computer program product as recited in claim 11, further comprising:

an act of the computer system handling server deficit.

19. The computer program product as recited in claim 18, wherein handling server deficit comprises requesting resources from one or more other edge data centers.

20. A computer system, comprising:

one or more processors;

system memory; and

one or more computer-readable storage media having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computer system to perform a method for allocating server resources at an edge data center of a content delivery network (CDN) to properties serviced by the edge data center, including the following;

sorting, based on near real-time data, a plurality of properties by trending traffic at the edge data center; and

allocating server resources for at least one property of the sorted plurality of properties at the edge data center based on one or more rules developed from long-term trends, the long-term trends being developed based on both an explicit adjustment to the long-term trends made as a result of the performance impact of a configuration value change and an implicit adjustment to the long-term trends made as a result of aggregated trend data, including;

calculating server needs for the at least one property in a partition at the edge data center; and

allocating the server needs for the at least one property to one or more available servers in the partition.