Automatic discovery of physical connectivity between power outlets and IT equipment

• US 8,886,985 B2
• Filed: 07/07/2008
• Issued: 11/11/2014
• Est. Priority Date: 07/07/2008
• Status: Active Grant

• Current Assignee: Sunbird Software, Inc.
• Original Assignee: Raritan Americas Incorporated (Legrand SA)
• Inventors: Somasundaram, Siva, Yang, Allen
• Primary Examiner(s): Patel, Nimesh G
• Application Number:
  US12/168,504
• Publication Number:
  US 20100005331A1
• Time in Patent Office: 2,318 Days
• Field of Search: 713/340
• US Class Current: 713/340
• CPC Class Codes: G06F 1/26 Power supply means, e.g. regulation thereof for memories G11C
• CPC Class Codes: G06F 1/28 Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 11/3051 Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs verification or detection of system hardware configuration G06F11/2247
• CPC Class Codes: G06F 11/3062 where the monitored property is the power consumption power management in a computing system G06F1/3203
• CPC Class Codes: G06F 11/3093 Configuration details thereof, e.g. installation, enabling, spatial arrangement of the probes

Abstract

The invention relates generally to the field of power management in data centers and more specifically to the automatic discovery and association of connectivity relationships between power outlets and IT equipment, and to methods of operating data centers having automatic connectivity discovery capabilities.

Claims

1. A method for operating a discovery system in a data center having a plurality of servers powered via a plurality of power supply outlets, the method comprising of steps of:

selecting a feasible set of candidate power supply outlets for at least one of the servers connected to at least one of the plurality power supply outlets, the feasible set being a subset of the plurality of power supply outlets;

collecting power consumption data for the feasible power outlets over time and central processing unit utilization data for the at least one server during an overlapping time by a data collection module of the discovery system;

storing the information collected by a data collection module of the discovery system;

correlating the CPU utilization data to the power consumption data for candidate pairings of feasible power supply outlets with the at least one server by a correlation engine of the discovery system according to a first set of metrics;

determining whether correlations according to the first set of metrics indicate that the at least one server is associated with one or more of the set of feasible power supply outlets; and

correlating the CPU utilization data to the power consumption data by the correlation engine according to a second set of metrics when the correlation according to the first set of metrics is insufficient to determine an association.

2. The method of claim 1 wherein the step of selecting the feasible set of power supply outlets includes the substep of selecting power supply outlets that are located within a specified distance from the at least one server.

3. The method of claim 1 further comprising the step of correlating the power consumption data to theoretical power consumption data for the at least one server by the correlation engine of the discovery system.

4. The method of claim 1 wherein the collecting step includes the substep of specifying an IP address for the at least one server.

5. The method of claim 1 wherein at least one of the correlating steps includes the substep of quantizing the CPU utilization data.

6. The method of claim 1 wherein at least one of the correlating steps includes the substep of time-stamping the power consumption data and the CPU utilization data.

7. The method of claim 1 wherein at least one of the correlating steps includes the substep of correlating state changes between the CPU utilization data and the power consumption data.

8. The method of claim 1 further comprising the step of correlating the power consumption data to theoretical power consumption data for the at least one server in the correlation engine of the discovery system,

wherein the step of selecting the feasible set of power supply outlets step includes the substep of selecting power supply outlets that are located within a distance from the at least one server,

wherein the collecting step includes the substep of specifying an IP address for the at least one server and

wherein at least one of the correlating steps includes the substeps of

quantizing the CPU utilization data,

time-stamping the power consumption data and the CPU utilization data, and

correlating state changes between the quantized CPU utilization data and the power consumption data.

9. The method according to claim 1, wherein the second set of metrics includes metrics selected from the group consisting of CPU utilization level histograms, CPU utilization wavelets, and processor type.

10. The method according to claim 1 wherein the first set of metrics includes quantized CPU utilization data.

11. The method of claim 1 wherein the step of selecting the feasible, set of power supply outlets includes the substeps of:

determining a historical average power delivery by each of the plurality of power supply outlets,

determining a name plate power consumption by the at least one server, and

selecting power supply outlets having a historical average power delivery that is less than the name plate power consumption for the at least one server.

12. A system for automatically discovering the connectivity of servers to a plurality of power outlets in a data center comprising:

a data collection module interfaced with power supply outlets and IT equipment, the data collection module operable to collect actual power usage for power supply outlets and CPU usage from IT equipment;

a data store having the information collected by the data collection module; and

a correlation engine operable select a feasible set of candidate power supply outlets and correlate the CPU usage data with actual power usage data to identify a piece of IT equipment connected to one of the power supply outlets, the feasible set of power supply outlets being a subset of the plurality of power supply outlets,

wherein the correlation engine determines whether correlations according to a first set of metrics indicate that the at least one server is associated with one or more of the set of feasible power supply outlets, and in addition determines correlations according to a second set of metrics when the correlations according to the first set of metrics are insufficient to determine an association.

13. The system according to claim 12, wherein the second set of metrics includes metrics selected from the group consisting of CPU utilization level histograms, CPU utilization wavelets, and processor type.

14. The method according to claim 12 wherein the first set of metrics includes quantized CPU utilization data.

15. A method for monitoring racks of IT equipment by a discovery system, comprising the steps of:

aggregating CPU usage data for the IT equipment in a database of the discovery system;

selecting a feasible set of candidate power supply outlets for an IT server located in the rack of IT equipment, the feasible set being a subset of a plurality of power supply outlets;

correlating CPU usage for the IT server with actual power usage of a candidate power strip by a correlation engine of the discovery system according to a first set of metrics, wherein the correlating steps include the substep of identifying state changes for the IT equipment;

determining whether the correlations according to the first set of metrics indicate that the IT server is associated with one of the set of feasible power supply outlets, and

correlating the CPU utilization data to the power consumption data by the correlation engine according to a second set of metrics when the correlation according to the first set of metrics is insufficient to determine an association.

16. The method according to claim 15, wherein the second set of metrics includes metrics selected from the group consisting of CPU utilization level histograms, CPU utilization wavelets, and processor type.

17. The method according to claim 15 wherein the first set of metrics includes quantized CPU utilization data.

18. The method of claim 15 wherein the step of selecting the feasible, set of power supply outlets includes the substeps of:

determining a historical average power delivery by each of the plurality of power supply outlets,

determining a name plate power consumption by the IT server, and

selecting power supply outlets having a historical average power delivery that is less than the name plate power consumption for the at least one server.

19. The method of claim 15 wherein the step of selecting the feasible set of power supply outlets includes the substep of selecting power supply outlets that are located within a specified distance from the IT server.