Clustering-Based Resource Aggregation within a Data Center

• US 20120303618A1
• Filed: 05/23/2011
• Published: 11/29/2012
• Est. Priority Date: 05/23/2011
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Dutta, Debojyoti, Banerjee, Subrata, Spiegel, Ethan M., Ghosh, Arpan K.
• Granted Patent: US 8,924,392 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

Data representing capabilities of devices in a data is aggregated on a cluster-basis. Information representing capability attributes of devices in the data center is received. The information representing the capability attributes is analyzed to generate data that groups devices based on similarity of at least one capability attribute. Aggregation data is stored that represents the grouping of the devices based on similarity of the at least one capability attribute and identifies the devices in corresponding groups.

Claims

1. A method comprising:

receiving information representing capability attributes of devices in a data center;

analyzing the information representing the capability attributes to generate data that groups devices based on similarity of at least one capability attribute; and

storing aggregation data that represents the grouping of the devices based on similarity of the at least one capability attribute and identifies the devices in corresponding groups.

2. The method of claim 1, wherein receiving, analyzing and storing are performed in an aggregation switch device in the data center, and further comprising sending the aggregation data to another device at a higher hierarchical level in the data center.

3. The method of claim 1, and further comprising receiving user input that specifies which one or more capability attributes are to be used for grouping devices into groups based on similarity of the one or more capability attributes.

4. The method of claim 1, and further comprising evaluating stored policy information to select one or more of:

the capability attributes to be used for grouping devices, similarity/distance metrics to be used for grouping, a clustering algorithm to be used for grouping and relative weights to be placed on attributes used for grouping.

5. The method of claim 1, wherein analyzing comprises analyzing the information representing the capability attributes to group devices based on two or more capability attributes.

6. The method of claim 1, wherein analyzing and storing are performed when a service request in the data center is provisioned or when operational properties of a device in the data center change.

7. The method of claim 1, wherein receiving comprises receiving data representing each of a plurality of capability attributes associated with each of a plurality of devices in the data center, and wherein analyzing comprises analyzing the data to group devices that have a common set of capability attributes.

8. The method of claim 7, wherein analyzing comprises using clustering techniques to group the plurality of devices into groups based on distances between vectors representing the plurality of capability attributes for respective devices.

9. The method of claim 1, wherein analyzing comprises analyzing the information that includes one or more of:

uplink bandwidth, number of processing cores, available memory, processing unit utilization, hypervisor type, power consumption and local storage availability.

10. An apparatus comprising:

a network interface unit configured to enable communications over a network; and

a processor coupled to the network interface unit and configured to;

analyze information representing capability attributes of devices in a data center to generate data that groups devices based on similarity of at least one capability attribute; and

store aggregation data that represents the grouping of the devices based on similarity of the at least one capability attribute and identifies the devices in corresponding groups.

11. The apparatus of claim 10, wherein the processor is further configured to send the aggregation data via the network interface unit to another device at a higher hierarchical level in the data center.

12. The apparatus of claim 10, wherein the processor is further configured to analyze the information based on user input that specifies which one or more capability attributes are to be used for grouping devices into groups based on similarity of the one or more capability attributes.

13. The apparatus of claim 10, wherein the processor is configured to analyze information representing the capability attributes to group devices based on two or more capability attributes.

14. The apparatus of claim 10, wherein the processor is configured to analyze data representing each of a plurality of capability attributes associated with each of a plurality of devices in the data center to group devices that have a common set of capability attributes.

15. The apparatus of claim 14, wherein the processor is configured to analyze the information representing the capability attributes using clustering techniques to group the plurality of devices into groups based on distances between vectors representing the plurality of capability attributes for respective devices.

16. The apparatus of claim 10, wherein the processor is configured to analyze the information that includes one or more of:

uplink bandwidth, number of processing cores, available memory, processing unit utilization, hypervisor type, power consumption and local storage availability.

17. The apparatus of claim 10, wherein the processor is configured to evaluate stored policy information to select one or more of:

the capability attributes to be used for grouping devices, similarity/distance metrics to be used for grouping of devices, the clustering algorithm to be used for grouping and relative weights to be placed on attributes for grouping.

18. One or more computer readable storage media encoded with software comprising computer executable instructions and when the software is executed operable to:

analyze information representing capability attributes of devices in a data center to generate data that groups devices based on similarity of at least one capability attribute; and

store aggregation data that represents the grouping of the devices based on similarity of the at least one capability attribute and identifies the devices in corresponding groups.

19. The computer readable storage media of claim 18, and further comprising instructions that are operable to receive user input that specifies which one or more capability attributes are to be used for grouping devices into groups based on similarity of the one or more capability attributes.

20. The computer readable storage media of claim 18, and further comprising instructions that are operable to analyze information representing the capability attributes to group devices based on two or more capability attributes.

21. The computer readable storage media of claim 18, and further comprising instructions that are operable to analyze the information representing the capability attributes using clustering techniques to group the plurality of devices into groups based on distances between vectors representing the plurality of capability attributes for respective devices.

22. The computer readable storage media of claim 18, and further comprising instructions that are operable to analyze the information that includes one or more:

of uplink bandwidth, number of processing cores, available memory, processing unit utilization, hypervisor type, power consumption and local storage availability.

23. The computer readable storage media of claim 18, and further comprising instructions that are operable to evaluate stored policy information to select one or more of:

the attributes to be used for grouping devices, similarity/distance metrics to be used for grouping of devices, the clustering algorithm to be used for grouping and relative weights to be placed on attributes for grouping.