INFRASTRUCTURE FOR ADAPTIVE ENVIRONMENTAL CONTROL FOR EQUIPMENT IN A BOUNDED AREA

• US 20100235003A1
• Filed: 03/12/2009
• Published: 09/16/2010
• Est. Priority Date: 03/12/2009
• Status: Active Grant

• Current Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Original Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Inventors: Maly, James Brian
• Granted Patent: US 8,321,057 B2
• Time in Patent Office: Days
• US Class Current: 700/276
• CPC Class Codes: G06F 1/206 comprising thermal management
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: H05K 7/20836 Thermal management, e.g. server temperature control

Abstract

Integrating information and performance controls for individual devices with environmental controls. Integrating the individual devices with general environmental control enables adaptive environmental control. For equipment housed in a bounded space such as a server room, information about the thermal environment within the bounded space can affect the performance of the equipment. Additionally, information about the performance conditions and/or thermal conditions about a piece of equipment can affect how the environmental control system for the bounded space operates. The equipment exchanges environmental event messages with a control node to affect the performance of the equipment and/or the environmental control system.

Claims

1. A computer-implemented method comprising:

detecting a change in a condition that affects a thermal environment of a bounded space having multiple hardware devices that provide data access services,

the bounded space having an environmental control system that manages the thermal environment of the bounded space,

the multiple hardware devices further being part of an environmental event network having a master node that manages network-wide event responses, where each of the multiple hardware devices is a slave node of the environmental event network that integrates local conditions into the environmental event network; and

exchanging an event message between the master node and a slave node to indicate the condition, to cause the event message recipient to perform an operation in response to the event message, the operation to adjust the thermal environment of the bounded space.

2. The method of claim 1, wherein the multiple hardware devices comprise servers.

3. The method of claim 1, wherein the multiple hardware devices comprise routers or data storage devices.

4. The method of claim 1, wherein the environment control system includes a system controller and multiple control points separated into zones to individually control a sub-portion of the bounded space.

5. The method of claim 1, wherein detecting the condition comprises:

the master node receiving information from the environmental control system related to the thermal environment of the bounded space; and

wherein exchanging the event message further comprises;

the master node sending an event message to cause the slave node to adjust its performance based on the thermal environment of the bounded space.

6. The method of claim 1, wherein detecting the condition comprises:

the master node receiving information related to performance requirements of the hardware devices from a business system; and

wherein exchanging the event message further comprises;

the master node sending an event message to cause the slave node to adjust its performance based on the thermal environment of the bounded space.

7. The method of claim 1, wherein detecting the condition comprises:

a slave node detecting a condition based on local information; and

wherein exchanging the event message further comprises;

the slave node generating an event; and

the slave node sending the event to the master node to cause the master node to perform an operation to adjust the environment of a section of the bounded space associated with the slave node.

8. The method of claim 7, wherein the slave node detecting the condition based on local information comprises:

the slave node detecting one or more of a performance condition that causes the slave node to generate a different amount of heat, or a temperature condition of the processing equipment of the slave node.

9. The method of claim 7, wherein the slave node sending the event to the master node to cause the master node to perform the operation to adjust the environment comprises:

the slave node sending the event to cause the master node to issue a command to one or more of the environmental control system to adjust the temperature of the bounded space, or issue a command to one or more slave nodes to cause the slave node(s) to adjust performance of the slave node(s).

10. A computer-readable storage medium having instructions stored thereon, which when executed, cause a processor to perform operations including:

detecting a change in a condition that affects a thermal environment of a bounded space having multiple hardware devices that provide data access services,

the bounded space having an environmental control system that manages the thermal environment of the bounded space,

the multiple hardware devices further being part of an environmental event network having a master node that manages network-wide event responses, where each of the multiple hardware devices is a slave node of the environmental event network that integrates local conditions into the environmental event network; and

exchanging an event message between the master node and a slave node to indicate the condition, to cause the event message recipient to perform an operation in response to the event message, the operation to adjust the thermal environment of the bounded space.

11. The computer readable medium of claim 10, wherein the processor is a processor of the master node, and wherein the instructions for detecting the condition comprise instructions for

receiving information from the environmental control system related to the thermal environment of the bounded space;

and

wherein the instructions for exchanging the event message further comprise instructions for

sending an event message to cause the slave node to adjust its performance based on the thermal environment of the bounded space.

12. The computer readable medium of claim 10, wherein the processor is a processor of the slave node, and wherein the instructions for detecting the condition comprise instructions for

detecting a condition based on local information;

and

wherein the instructions for exchanging the event message further comprise instructions for

generating an event; and

sending the event to the master node to cause the master node to perform an operation to adjust the environment of a section of the bounded space associated with the slave node.

13. The computer readable medium of claim 12, wherein the processor is a processor of the slave node, and wherein the instructions for detecting the condition based on local information comprise instructions for

detecting one or more of a performance condition that causes the slave node to generate a different amount of heat, or a temperature condition of the processing equipment of the slave node.

14. The computer readable medium of claim 12, wherein the processor is a processor of the slave node, and wherein the instructions for sending the event to the master node to cause the master node to perform the operation to adjust the environment comprise instructions for

sending the event to cause the master node to issue a command to one or more of the environmental control system to adjust the temperature of the bounded space, or issue a command to one or more slave nodes to cause the slave node(s) to adjust performance of the slave node(s).

15. A computing device comprising:

a data interface having a port with a socket to send and receive environmental condition information of an environmental condition that affects a thermal environment of a bounded space in which the computing device is physically located, where the bounded space has an environmental control system that manages the thermal environment of the bounded space, and the computing device is one of multiple hardware devices that are part of an environmental event network having a master node that manages network-wide event responses, where each of the multiple hardware devices is a slave node of the environmental event network that integrates local conditions into the environmental event network; and

an daemon process that detects a change in the environmental condition, and exchange an event message with another node of the environmental event network, the event message to cause the event message recipient to perform an operation in response to the event message, the operation to adjust the thermal environment of the bounded space.

16. The computing device of claim 15, wherein the computing device is the master node of the environmental event network, and wherein detecting the change in the environmental condition comprises receiving an indication of a condition from one of a batch process, a scheduler, a sensor of the environmental control system, or a slave node.

17. The computing device of claim 15, wherein the computing device is a slave node of the environmental event network, and wherein detecting the change in the environmental condition comprises one of reading an internal temperature, detecting a change in a workload, or detecting a change in a number of requests for processing.

18. An environmental event system, comprising:

a slave node of the environmental event system, the slave node including a server that processes data requests for client devices, the slave node to include a daemon process to monitor local environmental condition information related to a local thermal condition of the slave node, and an interface to communicate environmental condition information, wherein the slave node is one node of a bounded space that has multiple slave nodes in a environmental event network; and

a master node of the environmental event system that controls behavior of the environmental event system, the master node to include a daemon process to receive local the environmental condition information from the slave node and determine one or more actions to adjust the local thermal condition of the slave node based on the received environmental condition information.

19. The environmental event system of claim 18, wherein the daemon processes are kernel-level modules.

20. The environmental event system of claim 18, wherein the master node interfaces with an environmental control system to adjust cooling directed to the slave node in response to the received environmental condition information to adjust the local thermal condition of the slave node.

21. The environmental event system of claim 20, wherein the master node further receives information related to one or more of:

limits of cooling capacity and status of the environmental control system, capacity and status of a power system of the bounded space, or minimum and maximum power usage for a the slave node.