WO2013097134A1 - 一种节能监控方法以及设备 - Google Patents

一种节能监控方法以及设备 Download PDF

Info

Publication number
WO2013097134A1
WO2013097134A1 PCT/CN2011/084888 CN2011084888W WO2013097134A1 WO 2013097134 A1 WO2013097134 A1 WO 2013097134A1 CN 2011084888 W CN2011084888 W CN 2011084888W WO 2013097134 A1 WO2013097134 A1 WO 2013097134A1
Authority
WO
WIPO (PCT)
Prior art keywords
virtual machine
occupation information
management system
layer management
resource occupation
Prior art date
Application number
PCT/CN2011/084888
Other languages
English (en)
French (fr)
Inventor
张南军
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN2011800033122A priority Critical patent/CN102893229B/zh
Priority to PCT/CN2011/084888 priority patent/WO2013097134A1/zh
Priority to EP11878330.7A priority patent/EP2712122B1/en
Publication of WO2013097134A1 publication Critical patent/WO2013097134A1/zh
Priority to US14/140,787 priority patent/US9411344B2/en
Priority to US15/205,008 priority patent/US9917704B2/en

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2823—Reporting information sensed by appliance or service execution status of appliance services in a home automation network
    • H04L12/2827—Reporting to a device within the home network; wherein the reception of the information reported automatically triggers the execution of a home appliance functionality
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B15/00—Systems controlled by a computer
    • G05B15/02—Systems controlled by a computer electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00—Control of temperature
    • G05D23/19—Control of temperature characterised by the use of electric means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • G06F1/3209—Monitoring remote activity, e.g. over telephone lines or network connections
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/3246—Power saving characterised by the action undertaken by software initiated power-off
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5094—Allocation of resources, e.g. of the central processing unit [CPU] where the allocation takes into account power or heat criteria
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/02—Details
    • H04L12/12—Arrangements for remote connection or disconnection of substations or of equipment thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2823—Reporting information sensed by appliance or service execution status of appliance services in a home automation network
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate

Definitions

  • the embodiments of the present invention relate to the field of monitoring cloud network devices, and in particular, to an energy-saving monitoring method and a device.
  • Cloud computing refers to the delivery and usage patterns of services that provide the services they need, on an as-needed, and easily scalable basis. Such services may be related to information technology (IT, Information Technology), software related services or Internet related services, or other services.
  • IT information technology
  • software related services or Internet related services, or other services.
  • the core idea of cloud computing is to unify and manage a large number of computing resources connected by network to form a computing resource pool to provide users with on-demand services (that is, services provided according to user needs).
  • cloud The network that provides resources is called “cloud,”.
  • Cloud the resources in the user's view can be expanded indefinitely, and can be obtained at any time, use as needed, expand at any time, pay for usage.
  • cloud computing uses virtualization technology to turn solid-state server devices, network devices, and storage devices into virtual computing resources, virtual network resources, and virtual machine storage resources. These virtual resources can be collectively referred to as virtual machines (virtual resource computers).
  • the cloud computing data center can be divided into three layers: the infrastructure layer (Levell), the IT equipment layer (Level2), and the service and application layer (Level3); wherein, the infrastructure layer can include power equipment, machine rejection equipment, and refrigeration equipment. , heat dissipating equipment, fire fighting equipment, security equipment and maintenance equipment, etc., which are monitored by the infrastructure layer monitoring system; the IT equipment layer may include server equipment, network equipment, security equipment and storage equipment, and IT equipment layer
  • the management system manages these devices in a unified manner.
  • the business and application layers contain a wide range of services or applications, such as: e-mail, office software, and multimedia. User's application.
  • cloud computing data centers Due to the wide range of services and applications involved in cloud computing, cloud computing data centers have a large business load pressure; in order to handle these business loads, cloud computing data centers are equipped with many virtual machines at the IT equipment layer, and at the same time, to ensure these The virtual machine's normal operation and operating efficiency, the cloud computing data center at the infrastructure layer equipped these virtual machines with the corresponding cooling equipment, and these cooling equipment generates a large amount of power consumption.
  • electricity consumption brings to cloud computing data centers
  • the power used for the refrigeration equipment has equalized or exceeded the power consumption of the virtual machine; therefore, how to effectively ensure the normal operation of the cloud computing data center equipment Reducing power usage effectiveness (PUE, Power Usage Effectiveness) in an data center is an important issue.
  • PUE Power Usage Effectiveness
  • both the IT equipment layer and the infrastructure layer have independent control systems, and there is no message interaction mechanism between the IT equipment layer management system and the infrastructure layer monitoring system, that is, the infrastructure layer cannot know the business changes of the IT equipment layer.
  • the IT equipment layer service is shut down, the virtual machine of the IT equipment layer is powered off, and at this time, the cooling equipment of the infrastructure layer is still normally cooled, resulting in a relatively large waste of power consumption, increasing the operating cost of the cloud computing data center. .
  • Embodiments of the present invention provide an energy-saving monitoring method and device for performing cooling adjustment on a virtual machine at an IT equipment layer.
  • the energy-saving monitoring method provided by the present invention includes: acquiring system resource occupation information of an IT device layer management system; and sending a power-off instruction to the IT device layer management system according to the system resource occupation information, so that the IT device layer management system Turning off the virtual machine in the idle state; receiving the power-off feedback message sent by the IT device layer management system, and sending a cooling adjustment instruction to the infrastructure layer monitoring system according to the running state of the virtual machine corresponding to the cooling area where the virtual machine is powered off And causing the infrastructure layer monitoring system to adjust a cooling deployment of the cooling area in which the virtual machine is powered off.
  • the energy-saving monitoring method provided by the present invention includes: providing system resource occupation information of an IT equipment layer management system to an energy-saving monitoring device; receiving a power-off instruction sent by the energy-saving monitoring device according to the system resource occupation information; Instructing to shut down the virtual machine in the idle state, and sending a power-off feedback message to the energy-saving monitoring device, so that the energy-saving monitoring device moves to the infrastructure layer according to the running state of the virtual machine corresponding to the cooling region where the virtual machine is powered off.
  • the monitoring system sends a cooling adjustment command.
  • the energy-saving monitoring device includes: an acquiring unit, configured to acquire system resource occupation information of an IT device layer management system; and a power-off instruction unit, configured to: according to the system resource occupation information, to the IT device layer management system Sending a power-off command, so that the IT device layer management system shuts down the virtual machine in an idle state; a feedback receiving unit, configured to receive a power-off feedback message sent by the IT device layer management system; and a cooling adjustment unit, configured to The virtual area corresponding to the cooling area where the virtual machine is powered off The operating state of the aircraft is sent to the infrastructure layer monitoring system to send a cooling adjustment command, so that the infrastructure layer monitoring system adjusts the cooling deployment of the cooling area in which the virtual machine is powered off.
  • the information technology device layer management system includes: an information providing unit, configured to provide system resource occupation information of an IT device layer management system to the energy saving monitoring device; and a powering instruction receiving unit, configured to receive the energy saving monitoring device according to The power-off instruction sent by the system resource occupation information; the shutdown unit is configured to shut down the virtual machine in an idle state according to the power-off instruction; and the feedback unit is configured to send a power-off feedback message to the energy-saving monitoring device, And causing the energy-saving monitoring device to send a cooling adjustment instruction to the infrastructure layer monitoring system according to an operating state of the virtual machine corresponding to the cooling area where the virtual machine is powered off.
  • the embodiments of the present invention have the following advantages:
  • the energy-saving monitoring device can obtain the operating state of each virtual machine by querying the system resource occupation information of the IT device layer management system, thereby determining whether cooling adjustment is needed; when the cooling adjustment is needed, the IT equipment layer can be The management system sends a power-off command, so that the IT device layer management system shuts down the virtual machine in an idle state, so that the infrastructure layer monitoring system can perform cooling adjustment according to the running state of the virtual machine corresponding to the cooling area in which the virtual machine is powered off ( Reduce the cooling effect in light load areas, or turn off the cooling equipment in the empty area) to achieve optimal resource allocation.
  • FIG. 1 is a schematic diagram of an embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 2 is a schematic diagram of another embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 3 is a schematic diagram of another embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 4 is a schematic diagram of another embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 5 is a schematic diagram of another embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 6 is a schematic diagram of another embodiment of an energy saving monitoring method according to the present invention.
  • FIG. 7 is a schematic diagram of an embodiment of an energy saving monitoring device of the present invention.
  • FIG. 8 is a schematic diagram of an embodiment of an IT device layer management system according to the present invention.
  • the embodiment of the invention provides an energy-saving monitoring method and device for reasonably performing cooling adjustment on a virtual machine of an IT equipment layer.
  • An embodiment of the energy saving monitoring method in the embodiment of the present invention includes: Obtaining system resource occupation information of the IT device layer management system;
  • the refrigerating area is an area where the cooling device cools a plurality of virtual machines stored in one space.
  • one refrigerating area may be an area where one machine rejects (one machine refuses to store multiple virtual machines), one cooling
  • the area can be an area in a room, and the range of the cooling area can be determined according to actual conditions, which is not limited herein.
  • the energy-saving monitoring device may be a linkage function entity between an IT device layer management system and an infrastructure layer monitoring system.
  • SOAP single object access protocol
  • the management system and the infrastructure layer monitor the exchange of messages between the systems; and, by the linkage gate functional entity.
  • the energy-saving monitoring device can know the system resource occupation information of the IT device layer management system, that is, the running state of each virtual machine can be known, thereby determining to shut down the virtual machine in the idle state; and leading in the energy-saving monitoring device The virtual machine in the idle state is closed, so that the operating state of the cooling area where the virtual machine is shut down can be performed, and accordingly, the infrastructure layer monitoring system can perform cooling adjustment to realize optimal resource configuration.
  • an embodiment of an energy saving monitoring method in an embodiment of the present invention includes:
  • the energy saving monitoring device sends a system resource query message to the information technology device layer management system.
  • the energy saving monitoring device sends a system resource query message to the IT device layer management system to query system resource occupation information of the IT device layer management system.
  • the energy-saving monitoring device acquires system resource occupation information of the IT device layer management system; the energy-saving monitoring device receives the system resource occupation information returned by the information technology device layer management system; and the system resource query message in step 101 provided by the embodiment may be
  • the energy-saving monitoring device can actively obtain the system resource occupation information.
  • the step 101 is not performed, and the IT device layer management system can also actively send system resource occupation information to the energy-saving monitoring device, for example, timing push.
  • the energy-saving monitoring device can directly obtain the system resource occupation information actively pushed by the IT device layer management system.
  • the system resource occupation information may be: information about a current operating system, a process, a thread, and an application utilization rate of each virtual machine in the IT device layer management system, and the information is analyzed by the energy saving monitoring device. Obtaining CPU usage information and/or memory occupation information of each virtual machine in the IT device layer management system;
  • the system resource occupation information may be: CPU occupation information and/or memory occupation information of each virtual machine; after the IT equipment layer management system receives the system resource query message, it is managed by the IT equipment layer.
  • the system internally queries the current operating system, processes, threads, and application utilization information of each virtual machine in the local operation, thereby obtaining CPU occupation information and/or memory occupation information of each virtual machine, and passing the system.
  • the resource occupation information feeds back the CPU occupation information and/or the memory occupation information to the energy saving monitoring device.
  • the IT device layer management system can uniformly manage each virtual machine of the IT device layer, monitor the running status of each virtual machine in real time, and instruct the virtual machine to perform various operations (for example, Thermal migration operation and power-off operation).
  • the energy saving monitoring device determines, according to the system resource occupation information, whether the virtual machine deployment needs to be changed;
  • the energy-saving monitoring device determines whether the virtual machine deployment needs to be changed according to the system resource occupation information. If yes, the step 104 is triggered to instruct the IT device layer management system to centrally deploy the virtual machine in a load state; if not, maintain the IT The status of each virtual machine in the device layer management system is unchanged, and the process ends.
  • the energy-saving monitoring device receives the system resource occupation information, determining, according to the system resource occupation information, an operation state of each virtual machine in the IT device layer management system, when the virtual machine is in an idle state and a load state.
  • the load status may further include a light load state and a heavy load state, and may further consider the virtual machine between the no-load, light-load, and heavy-load states when considering whether hot migration is required.
  • the reference ratio of the deployment of the virtual machine may be determined according to actual needs, which is not limited herein.
  • the foregoing determining whether the virtual machine is in a light load state or a heavy load state may be determined by setting a preset load threshold. For example, if the load is greater than or equal to 50%, the virtual machine is in a heavy load state, and the load is less than one hundred. Fifty-four virtual machines are in light load.
  • the energy-saving monitoring device instructs the IT device layer management system to centrally deploy the virtual machine in a load state according to the system resource occupation information;
  • the energy-saving monitoring device may determine the virtual machine that needs to perform the migration according to the system resource occupation information, and further, determine the centralized deployment policy according to the virtual machine that needs to perform the migration.
  • the policy is used to implement the centralized deployment of the virtual machine in the load state.
  • the energy-saving monitoring device instructs the IT device layer management system to centrally deploy the virtual machine in a load state according to the centralized deployment policy.
  • the centralized deployment policy of the centralized deployment may be various, and is specifically described in the following embodiments, and is not limited herein.
  • the energy-saving monitoring device notifies the information technology device layer management system to send a power-off command, so that the information technology device layer management system closes the virtual machine in an idle state;
  • the energy-saving monitoring device After confirming that the virtual machine in the load state completes the centralized deployment, the energy-saving monitoring device sends a power-off instruction to the information technology device layer management system, so that the IT device layer management system shuts down the virtual machine in the idle state.
  • the energy-saving monitoring device can receive the power-off feedback message sent by the IT device layer management system, and confirm that the virtual machine in the idle state is powered off. Status, sends a cooling adjustment command to the infrastructure layer monitoring system.
  • the energy-saving monitoring device After confirming that the virtual machine in the no-load state is shut down, the energy-saving monitoring device sends a cooling adjustment instruction to the infrastructure layer monitoring system according to the running state of the virtual machine corresponding to the cooling region in which the virtual machine is powered off, so that the infrastructure layer monitoring system adjustment is turned off.
  • the cooling adjustment command may include a cooling adjustment strategy, where the cooling adjustment command may be a first cooling adjustment instruction of the cooling device that causes the infrastructure layer monitoring system to close the empty area, or may be
  • the second cooling adjustment instruction that causes the infrastructure layer monitoring system to reduce the cooling effect of the light load area may also include the deployment situation of the changed virtual machine, and the infrastructure layer monitoring system determines the cooling adjustment according to the deployment situation. Strategy.
  • the cooling adjustment strategy may include: closing a refrigeration device of the no-load region, the cooling effect of the region, wherein the light load region is a virtual machine in a load state in the cooling region is less than a preset number of refrigeration regions .
  • a refrigeration zone in the embodiment of the present invention is equipped with a refrigeration device, which can be independently operated or shut down. In actual operation, one refrigeration zone is rejected by one machine, and one virtual machine can be configured in one machine, and the configuration can be configured.
  • a refrigeration unit In actual operation, one refrigeration zone is rejected by one machine, and one virtual machine can be configured in one machine, and the configuration can be configured.
  • the infrastructure layer monitoring system can uniformly monitor and manage the cooling equipment in the infrastructure layer.
  • the running state of each virtual machine can be known, thereby determining whether cooling adjustment is needed; when the cooling adjustment is needed, the IT device layer management system can be instructed
  • the virtual machines in the load state are deployed in a centralized manner, so that the infrastructure layer monitoring system can perform cooling adjustment and optimize resource allocation.
  • FIG. 2 Another embodiment of the energy-saving monitoring method in the embodiment of the present invention includes:
  • the energy-saving monitoring device sends a system resource query message to the information technology device layer management system.
  • the content of the step 201 in the embodiment is the same as that of the step 101 in the embodiment shown in FIG. 1 , and details are not described herein again.
  • the energy saving monitoring device receives the system resource occupation letter returned by the information technology device layer management system Interest rate
  • the energy-saving monitoring device receives system resource occupation information returned by the IT device layer management system, where the system resource occupation information carries CPU occupation information and/or memory occupation information of the virtual machine in the IT device layer management system.
  • the IT device layer management system After the IT device layer management system receives the system resource query message, the IT device layer management system performs information about current operating systems, processes, threads, and application utilization of each virtual machine in the local operation.
  • the internal query is used to obtain the CPU occupation information and/or the memory occupation information of each virtual machine, and feed back the CPU occupation information and/or the memory occupation information to the energy saving monitoring device through the system resource occupation information.
  • the energy saving monitoring device determines, according to the system resource occupation information, whether the virtual machine deployment needs to be changed;
  • the energy-saving monitoring device determines, according to the CPU occupation information and/or the memory occupation information in the system resource occupation information, whether to perform the change virtual machine deployment, and if yes, triggers step 204 to determine a centralized deployment strategy of the virtual machine; Then keep the state of each virtual machine in the IT device layer management system unchanged, and end the process.
  • the energy saving monitoring device may determine the number of virtual machines in an idle state and in a load state according to the CPU occupation information and/or the memory occupation information.
  • the virtual machine that is initially determined to be in an idle state is again tested for CPU usage information and/or memory occupation information, if the current CPU and memory usage information of the virtual machine and the CPU and memory when idle. If the deviation of the occupancy information is less than 1%, it is determined that the virtual machine is in an idle state.
  • the CPU occupation information and/or the memory occupation information of the virtual machine reach a preset load condition, and if yes, determining that the virtual machine is in a load state; for example, if the virtual machine is When the deviation between the previous CPU and memory usage information and the CPU and memory usage information at idle is higher than 1% and lasts for 20 seconds, it is determined that the virtual machine is in a loaded state; similar to the judgment of no-load, for further ensuring The accuracy of the judgment can be determined twice for the virtual machine initially determined to be in the load state.
  • the energy-saving monitoring device After determining the operating states of the virtual machines in the IT equipment layer, the energy-saving monitoring device separately counts the number of virtual machines in the idle state and the number of virtual machines in the load state, and determines the virtual machines in the idle state and are in the load.
  • the proportion of the virtual machine in the state determining whether the ratio meets the preset condition, for example, whether the proportion of the virtual machine in the idle state reaches 30%, and if so, the deployment of the virtual machine needs to be changed;
  • the preset conditions may be set to other conditions, such as the reference to the temperature of the area in which the virtual machine is located and the time period in which the virtual machine is located, and may be determined according to the actual situation, which is not limited herein.
  • the energy-saving monitoring device determines the centralized deployment strategy of the virtual machine according to the system resource occupation information. After confirming that the deployment of the virtual machine needs to be changed, the energy-saving monitoring device may determine, according to the system resource occupation information, a virtual machine that needs to perform centralized deployment.
  • the deployment includes centralized deployment of the virtual machines in the load state.
  • the virtual machines in the load state include the light load state virtual machine and the overloaded state virtual machine. For example, the load virtual machine in a certain area is lower than the preset number or the virtual machine in the area is light. If the state is loaded, it is determined that the virtual machine in the area needs to be deployed in a centralized manner. Further, the centrally deployed virtual machine can be used to determine the centralized deployment policy.
  • the virtual machine hot migration mode can be adopted for the centralized deployment of the virtual machine.
  • the virtual machine hot migration refers to completely saving the running state of the entire virtual machine, and can quickly restore to another of the original hardware platforms. Virtual machines or virtual machines with different hardware platforms; and, in the process of recovery, virtual machines can achieve smooth and non-disruptive business migration, so that users will not notice any difference.
  • the centralized deployment policy may include the migrated object (that is, the virtual machine that needs to perform the hot migration) and the migrated rule, and the rule of the migration in the centralized deployment policy may be: preferentially migrating the server device to the proximity The area of the management device is second; secondly, the server device is thermally migrated to an area close to the storage device; again, the server device is thermally migrated to an area close to the network device.
  • the virtual machine includes a server device, a management device, a network device, and a storage device. Because the management device, the network device, and the storage device cannot be powered off, therefore, the hot migration is performed. Whenever possible, the virtual machine of the server device type is hot-migrated to the vicinity of the virtual machine that cannot be powered off, so that the cooling system of the infrastructure layer can centrally supply power and cool the area where the virtual machine that cannot be powered off is located.
  • the energy-saving monitoring device may determine the migration target according to the current running state of each virtual machine, and calculate a path of the migration object to perform hot migration according to the preset algorithm and the foregoing migration rule, thereby obtaining a specific concentration.
  • the deployment policy is optional. After the migration object is determined, the running status of each virtual machine and the preset migration scenarios (each centralized deployment policy has a corresponding centralized deployment policy) can be calculated. Select one of the preset centralized deployment strategies as the current strategy for performing hot migration. The method of obtaining a centralized deployment policy can be determined based on actual conditions, and is not limited here.
  • the energy saving monitoring device sends a hot migration command carrying the centralized deployment policy to the information technology device layer management system.
  • the energy-saving monitoring device sends a hot migration command carrying the centralized deployment policy to the information technology device layer management system, so that the IT device layer management system performs hot migration on the virtual machine according to the centralized deployment policy, thereby causing the virtual machine in a load state.
  • Centralized deployment
  • the energy saving monitoring device After performing the centralized deployment, the energy saving monitoring device needs to return to steps 201 and 202 to obtain system resource occupation information after centralized deployment of the IT device layer management system.
  • the energy-saving monitoring device notifies the information technology device layer management system to send a power-off instruction according to the system resource occupation information after the centralized deployment of the IT device layer management system, so that the information technology device layer management system closes the virtual machine in an idle state;
  • the content of the step 206 in this embodiment is the same as that of the step 106 in the foregoing embodiment shown in FIG. 1, and details are not described herein again.
  • Status sends a cooling adjustment command to the infrastructure layer monitoring system.
  • step 207 in this embodiment is the same as that of step 106 in the foregoing embodiment shown in FIG. 1, and details are not described herein again.
  • FIG. 3 another embodiment of the energy-saving monitoring method in the embodiment of the present invention includes: 301.
  • the energy-saving monitoring device sends a system resource query message to the information technology device layer management system.
  • the content of the step 301 in the embodiment is the same as the content of the step 101 in the embodiment shown in FIG. 1 , and details are not described herein again.
  • the energy saving monitoring device receives system resource occupation information returned by the information technology device layer management system
  • step 302 in this embodiment is the same as that of step 202 in the foregoing embodiment shown in FIG. 2, and details are not described herein again.
  • the energy saving monitoring device determines, according to the system resource occupation information, whether the virtual machine deployment needs to be changed;
  • the energy-saving monitoring device determines, according to the CPU occupation information and/or the memory occupation information in the system resource occupation information, whether to perform the change virtual machine deployment, and if yes, triggers step 304 to determine a centralized deployment strategy of the virtual machine; Then keep the state of each virtual machine in the IT device layer management system unchanged, and end the process.
  • the energy-saving monitoring device determines the centralized deployment strategy of the virtual machine according to the system resource occupation information. After confirming that the deployment of the virtual machine needs to be changed, the energy-saving monitoring device may determine the virtual machine that needs to perform the hot migration according to the system resource occupation information, and further You can also determine a centralized deployment strategy based on the virtual machines that need to perform hot migration.
  • the centralized deployment policy may include the migrated object and the migrated rule, and the rule for migrating in the centralized deployment policy may be: preferentially migrating the server device to an area close to the management device; secondly, The server device is hot migrated to an area close to the storage device; again, the server device is hot migrated to an area close to the network device.
  • the energy saving monitoring device sends, to the information technology device layer management system, a sending hot migration command that carries the centralized deployment policy.
  • the energy-saving monitoring device sends a transmission hot migration instruction carrying the centralized deployment policy to the information technology device layer management system, so that the IT device layer management system performs hot migration on the virtual machine according to the centralized deployment policy, thereby making the virtual state in a load state Centralized deployment of machines.
  • the energy-saving monitoring device receives the hot migration completion response returned by the information technology device layer management.
  • the IT device layer management system responds to the hot migration returned by the energy-saving monitoring device, and
  • the energy saving monitoring device receives the completion of the heat transfer After that, it can be confirmed that the hot migration of the virtual machine is completed, and then step 307 can be triggered to perform the shutdown operation of the virtual machine in the idle state.
  • the energy saving monitoring device After performing the centralized deployment, the energy saving monitoring device needs to return to steps 301 and 302 to obtain system resource occupation information after centralized deployment of the IT device layer management system.
  • the energy saving monitoring device sends a power-off instruction to the information technology device layer management system.
  • the energy saving monitoring device After confirming that the hot migration of the virtual machine is completed, the energy saving monitoring device sends a power-off instruction to the information technology device layer management system according to the system resource occupation information after the centralized deployment of the IT device layer management system, so that the IT device layer management system is closed. A virtual machine that is in an idle state.
  • the energy-saving monitoring device receives the power-off feedback message sent by the information technology device layer management system.
  • the IT device layer management system may send the power-off monitoring device to the energy-saving monitoring device after completing the power-off operation of the virtual machine in the idle state.
  • the power-saving monitoring device receives the power-off feedback message, and can learn the specific situation in which the virtual machine executes the power-off command according to the power-off feedback message (for example, the virtual machine in the idle state has been powered off) ).
  • the power-off feedback message carries an organic rejection number, and the machine rejection number is a number of the machine that the virtual machine that performs the power-off is rejected.
  • the energy saving monitoring device confirms that the virtual machine needs to perform cooling adjustment; if the identifier matches; if yes, trigger step 309 to send a cooling adjustment instruction to the infrastructure layer monitoring system; if not, send an inquiry message to the IT equipment layer management system, The IT device layer management system is caused to reconfirm the matching relationship between the machine rejection number and the machine rejection virtual machine.
  • the virtual machine is placed in the machine rejection device of the IT device layer, and multiple virtual machines can be placed in one machine rejection, and the IT device layer management system records that the identifier of the virtual machine matches the number of the machine rejection. Relationships (for example, which virtual machines are stored in a machine, these virtual machines can be uniquely identified by the identity of the virtual machine, and the matching relationship is the correspondence between the machine's rejection number and the identity of each virtual machine stored in the machine.
  • the energy-saving monitoring device needs to check the matching relationship between the machine rejection number and the identifier of the corresponding virtual machine (ie, Query whether there is an empty virtual machine ID that needs to be powered off in the ID of each virtual machine corresponding to the machine rejection number. If yes, the error is confirmed.) After confirming the error, you can go to the infrastructure.
  • the layer monitoring system sends a cooling adjustment command. 310.
  • the energy saving monitoring device sends a cooling adjustment instruction to the infrastructure layer monitoring system according to the deployment situation of the virtual machine.
  • the energy-saving monitoring device sends a cooling adjustment command to the infrastructure layer monitoring system according to the deployment situation of the virtual machine, specifically:
  • the area of the closed virtual machine is an empty area, sending a first cooling adjustment instruction to the infrastructure layer monitoring system, so that the infrastructure layer monitoring system closes the cooling device in the empty area, where the empty area is an area All virtual machines in the area where the virtual machine is powered off;
  • the area of the virtual machine that is shut down is a light load area
  • the virtual machine in the load state is less than the preset number (the preset number can be determined according to the actual situation, which is not limited here). Since the virtual machine is still running in the light load area, the refrigeration equipment in the area cannot be turned off; and because of the hot migration in the area, the number of virtual machines in the load state is small, so the cooling effect of the area can be reduced. .
  • Another embodiment of the energy-saving monitoring method in the embodiment of the present invention includes:
  • the information technology device layer management system receives a system resource query message sent by the energy saving monitoring device.
  • the IT device layer management system After receiving the system resource query message sent by the energy saving monitoring device, the IT device layer management system queries the system resource resource occupying information of the IT device layer management system according to the system resource query message.
  • the information technology device layer management system returns system resource occupation information to the energy saving monitoring device.
  • the IT device layer management system returns system resource occupancy information to the energy saving monitoring device.
  • the system resource occupation information may include: CPU occupation information and/or memory occupation information of each virtual machine in the IT device layer management system.
  • the IT device layer management system can internally query information about the current operating system, processes, threads, and application utilization of each virtual machine in the local operation, thereby obtaining CPU usage information and/or memory usage of each virtual machine. Information, the IT device layer management system may return the CPU occupation information and/or memory occupation information to the energy saving monitoring device.
  • the system resource occupation information may also be: information about current operating systems, processes, threads, and application utilization of each virtual machine; the IT device layer management system directly returns each virtual machine to the energy saving monitoring device. Current operating system, processes, threads, and application utilization, etc.
  • the information causes the energy saving monitoring device to obtain the CPU occupation information and/or memory occupation information through the information.
  • the IT device layer management system may actively send the system resource occupation information to the energy saving monitoring device every preset time; therefore, if the transmission is active, the foregoing steps are not required.
  • the information technology device layer management system receives a hot migration instruction sent by the energy saving monitoring device.
  • the IT device layer management system receives the hot migration command sent by the energy saving monitoring device.
  • the hot migration command may include an instruction that the IT device layer management system performs a centralized deployment strategy.
  • the information technology device layer management system performs hot migration on the virtual machine according to the hot migration instruction.
  • the IT device layer management system performs hot migration of the virtual machines in the IT device layer management system according to the hot migration instruction, so that the virtual machines in the load state are deployed in a centralized manner.
  • the virtual machine hot migration refers to the complete preservation of the running state of the entire virtual machine, and can be quickly restored to another virtual machine of the original hardware platform or a virtual machine of a different hardware platform; and, in the process of recovery In this case, the virtual machine can achieve smooth and non-disruptive business migration, so that users will not notice any difference.
  • the hot migration rules for implementing the centralized deployment of the virtual machine may be multiple.
  • the centralized deployment policy may include a migrated object (that is, a virtual device that needs to perform hot migration).
  • the rule of the migration, and the rule of the migration in the centralized deployment policy may be: preferentially migrating the server device to an area close to the management device; secondly, thermally migrating the server device to the storage device The area; again, the server device is hot migrated to an area close to the network device.
  • the virtual machine includes the server device, the management device, the network device, and the storage device. Because the management device, the network device, and the storage device cannot be powered off, when performing the hot migration, try to use the server device type. The virtual machine is hot-migrated to the vicinity of the virtual machine that cannot be powered off, so that the cooling system of the infrastructure layer can centrally supply and cool the area where the virtual machine that cannot be powered off is located.
  • the energy-saving monitoring device may determine the migration target according to the current running state of each virtual machine, and calculate a path of the migration object to perform hot migration according to the preset algorithm and the foregoing migration rule, thereby obtaining a specific concentration.
  • the deployment policy is optional. After the migration object is determined, the running status of each virtual machine and several preset migration scenarios can be calculated. The matching degree of the corresponding centralized deployment policy is set, so that one of the preset centralized deployment strategies is selected as the current hot migration strategy. The method of obtaining the centralized deployment policy can be determined according to the actual situation, which is not limited here.
  • the information technology device layer management system returns a hot migration completion response to the energy saving monitoring device.
  • the IT device layer management system returns a hot migration completion response to the energy saving monitoring device.
  • the energy-saving monitoring device can be further operated (for example, the virtual machine indicating the no-load state is powered off).
  • the information technology device layer management system receives a power-off command sent by the energy-saving monitoring device.
  • the IT device layer management system receives a power-off command sent by the energy-saving monitoring device, where the power-off command is used to indicate an IT device layer management system. Turn off the virtual machine in the idle state.
  • the energy saving monitoring device can confirm that the hot migration of the virtual machine is completed, and then obtain the system resource occupation information after the centralized deployment of the IT device layer management system, and accordingly, the IT device layer can be obtained.
  • the management system sends a power-off command.
  • the information technology device layer management system turns off the virtual machine in an idle state according to the power-off instruction.
  • the IT device layer management system shuts down the virtual machine in the idle state according to the power-off instruction, and sends a power-off feedback message to the energy-saving monitoring device, and feeds back to the energy-saving monitoring device the specific situation in which the virtual machine executes the power-off command (for example, The virtual machines in the idle state are powered off, so that the energy-saving monitoring device sends a cooling adjustment command to the infrastructure layer monitoring system according to the power-off feedback message, and adjusts the cooling deployment.
  • the cloud computing data center contains 1000 virtual machines, including server devices, network devices, security devices, and storage devices. Among them, there are 50 virtual machines that cannot be powered off, such as network devices, security devices, and storage devices. They are deployed in three machines, Al, A2, and A3. (English characters indicate lines, and numeric characters indicate columns. For example, A2 indicates A line 2 The machine ID of the column is A1S01 ⁇ A1S20, A2S01-A2S20, A3S01 ⁇ A3S10 (S01 ⁇ S20 indicates the identifier of the virtual machine, for example, S05 indicates the No. 5 virtual machine).
  • the time period for triggering the energy-saving monitoring process can be set, for example: 08:00-22:00 in one day is a period of heavy business, and the energy-saving monitoring process can be omitted; 24:00 in one day- 06:00 is a period of low traffic, and the energy saving monitoring process can be performed.
  • the linkage energy-saving monitoring device
  • the linkage starts to query and analyze the system resource occupation information from 22:30 in the evening, if the CPU occupancy rate is 30% ⁇ 100%, or the memory occupancy rate is 20% ⁇ 100%. If the percentage of the entire data center virtual machine is more than 30%, the state of each virtual machine in the IT device layer management system is kept unchanged, and the query and analysis of the system resource occupation information is continued.
  • the percentage of the virtual machine in the data center is less than 30%. Then, according to the CPU usage and/or memory usage statistics, one is obtained. Correspondence table between the utilization rate and the virtual machine ID, such as: A1S06, load 58%; E5S20, load 20%.
  • the linkage portal may determine the virtual machine hot migration policy according to the relationship correspondence table, for example, preferentially migrating the virtual machine with the CPU utilization and the memory utilization less than 30% to the idle resources in the A1 ⁇ A3 machine rejection.
  • Use the virtual machine ID to query the IP address of the virtual machine to be migrated before the migration, and perform point-to-point hot migration based on the IP address. Then according to the utilization rate of 40%, 60%, 80%.
  • Hot migration of all virtual machines is done in 100% increments.
  • the server resources of A3 ⁇ A5 are used; if the resources are still insufficient, the B1 ⁇ B5, and C1 ⁇ C5 are used.
  • Server device resources Since the load of the entire data center has been calculated to be less than 30%, the server resources of A1 ⁇ A5, B1-B5, and C1 ⁇ C5 can fully bear these loads, and there will be no more virtual machine migration requirements.
  • the virtual machine is powered off, and the sensor feedbacks ⁇ 1 ⁇ 5.
  • the temperature information inside and around the machine is rejected, and the information from the infrastructure layer monitoring system feeds back the information to the linkage Portal. According to the temperature, the linkage is determined by the linkage portal.
  • the machine rejection number of the power-off condition after the linkage Portal queries the corresponding relationship between the machine rejection number and the air conditioner in the database, the air conditioner number that can be powered off or cooled is sent to the monitoring system of the L1 layer, and is executed by the monitoring system of the L1 layer. Operation or cooling operation, and feedback execution log information (including message name, execution time, status of execution result) to the linkage Portal.
  • the energy saving monitoring method in the embodiment of the present invention is performed by the third-party device (energy-saving monitoring device).
  • the energy-saving monitoring method in the embodiment of the present invention may also be performed by the IT device layer management system.
  • FIG. 5, another embodiment of the energy saving monitoring method in the embodiment of the present invention includes:
  • the information technology device layer management system acquires system resource occupation information of the virtual machine.
  • the IT device layer management system obtains the system resource occupation information of the virtual machine.
  • the system resource occupation information may be: CPU occupation information and/or memory occupation information of each virtual machine; CPU occupation information of each virtual machine and
  • the memory usage information can be queried and analyzed by the IT device layer management system for information about the current operating system, processes, threads, and application utilization of each virtual machine in the local operation.
  • the information technology device layer management system determines, according to the system resource occupation information, whether the virtual machine deployment needs to be changed.
  • the IT device layer management system determines whether the virtual machine is to be changed according to the system resource occupation information. If yes, the step 503 is triggered to send a hot migration instruction to the virtual machine that needs to perform the hot migration, so that the virtual machine in the load state is deployed in a centralized manner. If not, keep the state of each virtual machine in the IT device layer management system unchanged, and end the process.
  • the IT device layer management system determines, according to the system resource occupation information, an operation state of each virtual machine in the IT device layer management system, when in a no-load, load state virtual state
  • the load status may further include a light load state and a heavy load state.
  • the method may further Considering the number ratio between the virtual machines in the no-load, light-load, and heavy-duty states, the reference conditions for determining whether the hot migration is required may be determined according to actual requirements, which is not limited herein.
  • the foregoing determining whether the virtual machine is in a light load state or a heavy load state may be determined by setting a preset load threshold. For example, if the load is greater than or equal to 50%, the virtual machine is in a heavy load state, and the load is less than one hundred. Fifty-four virtual machines are in light load.
  • the information technology device layer management system sends a hot migration message to the virtual machine that needs to perform the hot migration.
  • the IT device layer management system After determining that the hot migration of the virtual machine needs to be performed, the IT device layer management system determines a centralized deployment policy according to the CPU usage information and/or the memory occupation information of each virtual machine, and the IT device layer management system further performs the centralized deployment policy according to the centralized deployment policy.
  • a hot migration message is sent to a virtual machine that needs to perform a hot migration, so that the virtual machines in a load state are deployed in a centralized manner.
  • the information technology device layer management system sends a power-off command to the virtual machine in the idle state. After confirming that the hot migration of the virtual machine is completed, the IT device layer management system is in accordance with the system resource occupation information after centralized deployment. The virtual machine in the idle state sends a power-off command to shut down the virtual machine in the idle state.
  • the information technology equipment layer management system sends a cooling adjustment instruction to the infrastructure layer monitoring system. After confirming that the virtual machine in the no-load state has been powered off, the IT device layer management system sends a cooling adjustment command to the infrastructure layer monitoring system according to the distribution of the virtual machine executing the power-off command.
  • the infrastructure layer monitoring system adjusts the cooling equipment in the infrastructure layer according to the deployment of the virtual machine after the hot migration to optimize the cooling output.
  • the cooling adjustment command may include a cooling adjustment strategy
  • the cooling adjustment command may also include a deployment situation of the virtual machine after the hot migration, and the infrastructure layer monitoring system determines the deployment according to the deployment situation. Cooling adjustment strategy.
  • the cooling adjustment strategy may include: turning off a refrigeration device in an empty area,
  • the cooling effect is that the light load area is less than a preset number of virtual machines in a load state.
  • the following is a detailed description of the energy-saving monitoring method performed by the IT device layer management system. Referring to FIG. 6, another embodiment of the energy-saving monitoring method in the embodiment of the present invention includes:
  • the information technology device layer management system obtains the system resource occupation information of the virtual machine.
  • the content of the step 501 in the embodiment is the same as the content of the step 401 in the foregoing embodiment shown in FIG. 4, and details are not described herein again.
  • the information technology device layer management system determines, according to the system resource occupation information, whether to perform virtual storage (mechanical heat migration;
  • the IT device layer management system determines whether the hot migration of the virtual machine needs to be performed according to the CPU usage information and/or the memory occupation information in the system resource occupation information. If yes, the step 603 is triggered to send the heat to the virtual machine that needs to perform the hot migration. Migrate the message; if not, keep the state of each virtual machine in the IT device layer management system unchanged, and end the process.
  • the energy saving monitoring device may determine the number of virtual machines in an idle state and in a load state according to the CPU occupation information and/or the memory occupation information.
  • the virtual machine that is initially determined to be in an idle state is again tested for CPU usage information and/or memory occupation information, if the current CPU and memory usage information of the virtual machine and the CPU and memory when idle. If the deviation of the occupancy information is less than 1%, it is determined that the virtual machine is in an idle state.
  • the CPU occupation information and/or the memory occupation information of the virtual machine reach a preset load condition, and if yes, determine that the virtual machine is in a load state; for example, if the virtual machine current CPU and memory When the deviation between the occupancy information and the CPU and memory occupation information at the time of idle is higher than 1% and lasts for 20 seconds, it is determined that the virtual machine is in a loaded state; similar to the determination of no-load, in order to further ensure the accuracy of the judgment, For a virtual machine that is initially determined to be in a load state, it can also be performed. Determined.
  • the energy-saving monitoring device After determining the operating states of the virtual machines in the IT equipment layer, the energy-saving monitoring device separately counts the number of virtual machines in the idle state and the number of virtual machines in the load state, and determines the virtual machines in the idle state and are in the load.
  • the proportion of the virtual machine in the state determining whether the ratio meets the preset condition, for example, whether the proportion of the virtual machine in the idle state reaches 30%, and if so, the deployment of the virtual machine needs to be changed;
  • the preset conditions may be set to other conditions, such as the reference to the temperature of the area in which the virtual machine is located and the time period in which the virtual machine is located, and may be determined according to the actual situation, which is not limited herein.
  • the information technology device layer management system determines a centralized deployment strategy of the virtual machine according to the system resource occupation information.
  • the IT device layer management system may determine the virtual machine that needs to perform the hot migration according to the system resource occupation information, and further, determine the centralized deployment strategy according to the virtual machine that performs the hot migration according to the requirement. .
  • the centralized deployment policy may include the migrated object (that is, the virtual machine that needs to perform the hot migration) and the migrated rule, and the rule of the migration in the centralized deployment policy may be: preferentially migrating the server device to the proximity The area of the management device is second; secondly, the server device is thermally migrated to an area close to the storage device; again, the server device is thermally migrated to an area close to the network device.
  • the virtual machine includes the server device, the management device, the network device, and the storage device. Because the management device, the network device, and the storage device cannot be powered off, when performing the hot migration, try to use the server device type. The virtual machine is hot-migrated to the vicinity of the virtual machine that cannot be powered off, so that the cooling system of the infrastructure layer can centrally supply and cool the area where the virtual machine that cannot be powered off is located.
  • the IT device layer management system may determine the migration object according to the current running state of each virtual machine, and calculate a path of the migration object to perform hot migration according to the preset algorithm and the foregoing migration rule, thereby obtaining a specific
  • the centralized deployment strategy optionally, after the migration object is determined, the matching degree between the current running state of each virtual machine and the preset several migration scenarios (the corresponding centralized deployment strategy is configured for each migration scenario) may also be calculated. Therefore, one of the preset centralized deployment strategies is selected as the current hot migration strategy.
  • the method of obtaining the centralized deployment policy can be determined according to the actual situation, which is not limited here. 604.
  • the information technology device layer management system sends a hot migration message to the virtual machine that needs to perform the hot migration.
  • the information technology device layer management system sends a hot migration message to the virtual machine that needs to perform the hot migration, so that the virtual machine in the load state is deployed in a centralized manner.
  • the information technology device layer management system sends a power-off command to the virtual machine in an idle state. After confirming that the hot migration of the virtual machine is completed, the IT device layer management system is in accordance with the system resource occupation information after centralized deployment. The virtual machine in the idle state sends a power-off command to shut down the virtual machine in the idle state.
  • the information technology device layer management system sends a cooling adjustment instruction to the infrastructure layer monitoring system. After confirming that the virtual machine in the idle state has been powered off, the IT equipment layer management system sends a cooling adjustment instruction to the infrastructure layer monitoring system according to the deployment situation of the virtual machine, specifically:
  • the area of the closed virtual machine is an empty area, sending a first cooling adjustment instruction to the infrastructure layer monitoring system, so that the infrastructure layer monitoring system closes the cooling device in the empty area, where the empty area is an area All virtual machines in the area where the virtual machine is powered off;
  • the area of the virtual machine that is shut down is a light load area
  • the virtual machine in the load state is less than the preset number (the preset number can be determined according to the actual situation, which is not limited here). Since the virtual machine is still running in the light load area, the refrigeration equipment in the area cannot be turned off; and because of the hot migration in the area, the number of virtual machines in the load state is small, so the cooling effect of the area can be reduced. .
  • An embodiment of the energy-saving monitoring device of the present invention for performing the above-described energy-saving monitoring method is described.
  • the structure of the energy-saving monitoring device is as follows.
  • An embodiment of the energy-saving monitoring device in the embodiment of the present invention includes: an acquiring unit 701, configured to acquire The system resource occupation information of the IT device layer management system; the power-off indication unit 702 is configured to send a power-off instruction to the IT device layer management system according to the system resource occupation information, so that the IT device layer management system is shut down in an idle state.
  • the cooling adjustment unit 704 of the energy saving monitoring device in the example of the present invention may include: a shutdown indication module 7041, configured to monitor the infrastructure layer if the closed virtual machine is in an empty area The system sends a first cooling adjustment instruction, so that the infrastructure layer monitoring system closes the cooling device in the empty area, and the empty area is an area in which all virtual machines in the area are in a power-off state;
  • the adjustment indication module 7042 is configured to send a second cooling adjustment instruction to the infrastructure layer monitoring system if the cooling area where the closed virtual machine is located is a light load area, so that the infrastructure layer monitoring system reduces light load The cooling effect of the area, where the light load area is less than a preset number of virtual machines in a loaded state.
  • the energy-saving monitoring apparatus in the example of the present invention may further include:
  • the deployment determining unit 705 is configured to determine, according to the system resource occupation information, whether the deployment of the virtual machine needs to be changed, and if yes, trigger the centralized deployment unit;
  • the centralized deployment unit 706 is configured to: according to the system resource occupation information, instruct the IT device layer management system to centrally deploy the virtual machine in a load state, and after the centralized deployment of the virtual machine in the load state, trigger the The power indication unit 702 is powered off.
  • the obtaining unit 701 is further configured to acquire system resource occupation information after the centralized deployment of the IT device layer management system;
  • the power-off indication unit 702 is further configured to send a power-off instruction to the IT device layer management system according to the system resource occupation information after the centralized deployment of the IT device layer management system.
  • the obtaining unit 701 acquires system resource occupation information of the IT device layer management system.
  • the energy-saving monitoring device may send a system resource query message to the IT device layer management system to query system resource occupancy information of the IT device layer management system; the energy-saving monitoring device may also receive system resource occupancy information that is periodically pushed by the IT device layer management system. .
  • the system resource occupation information may be: information about a current operating system, a process, a thread, and an application utilization rate of each virtual machine in the IT device layer management system, and the information is analyzed by the energy saving monitoring device. Obtaining CPU usage information and/or memory occupation information of each virtual machine in the IT device layer management system;
  • the system resource occupation information may also be: CPU usage information of each virtual machine and/or Or memory occupancy information; after the IT device layer management system receives the system resource query message, the IT device layer manages the current operating system, processes, threads, and applications of each virtual machine in the local operation by the IT device layer. The information such as the utilization rate is internally queried, thereby obtaining the CPU occupation information and/or the memory occupation information of each virtual machine, and feeding back the CPU occupation information and/or the memory occupation information to the energy saving monitoring device through the system resource occupation information.
  • the power-off indication unit 702 After obtaining the system resource occupation information, the power-off indication unit 702 sends a power-off instruction to the IT device layer management system according to the system resource occupation information, so that the IT device layer management system shuts down the virtual machine in an idle state. .
  • the deployment determining unit 705 may further determine, according to the system resource occupation information, whether the deployment of the virtual machine needs to be changed, and if yes, trigger the centralized deployment unit 706; if not, maintain The state of each virtual machine in the IT device layer management system is unchanged, and the process ends.
  • the load status may further include a light load state and a heavy load state.
  • the number of the virtual machine in the state of the overloaded state may be determined according to actual requirements, which is not limited herein.
  • the foregoing determining whether the virtual machine is in a light load state or a heavy load state may be determined by setting a preset load threshold. For example, if the load is greater than or equal to 50%, the virtual machine is in a heavy load state, and the load is less than one hundred. Fifty-four virtual machines are in light load.
  • the centralized deployment unit 706 instructs the IT device layer management system to centrally deploy the virtual machine in the load state according to the system resource occupation information, and trigger the power-off indication after the centralized deployment of the virtual machine in the load state is completed.
  • Unit 702. the centralized deployment unit 706 may send the sending hot migration instruction carrying the centralized deployment policy to the IT device layer management system to instruct the IT device layer management system to perform centralized deployment; after confirming that the virtual machine needs to be changed,
  • the centralized deployment unit 706 can determine the virtual machine that needs to be deployed in a centralized manner according to the system resource occupation information. Further, the centralized deployment strategy can be determined by performing the centrally deployed virtual machine as needed.
  • virtual machine hot migration can be adopted for centralized deployment of virtual machines
  • virtual machine hot migration Refers to the complete preservation of the operating state of the entire virtual machine, and can be quickly restored to another virtual machine of the original hardware platform or a virtual machine of a different hardware platform; and, in the process of recovery, the virtual machine A smooth, non-disruptive business migration is enabled so that users are not aware of any differences.
  • the centralized deployment policy may include the migrated object and the migrated rule, and the rule for migrating in the centralized deployment policy may be: preferentially migrating the server device to an area close to the management device; The server device is hot migrated to an area close to the storage device; again, the server device is hot migrated to an area close to the network device.
  • the feedback receiving unit 703 receives the power-off feedback message sent by the IT device layer management system; subsequently, the infrastructure layer monitoring system can be triggered to send the cooling adjustment.
  • the instructions cause the infrastructure layer monitoring system to adjust a cooling deployment of the cooling zone in which the powered off virtual machine is located.
  • the shutdown indication module 7041 sends a first cooling adjustment instruction to the infrastructure layer monitoring system, so that the infrastructure layer monitoring system is closed.
  • a cooling device in the area where the empty area is an area in which all the virtual machines in the area are in a power-off state; if the closed virtual machine is located in the cooling area, the light-load area adjustment indication module 7042 is in the infrastructure layer
  • the monitoring system sends a second cooling adjustment command, so that the infrastructure layer monitoring system reduces the cooling effect of the light load area, wherein the light load area is less than a preset number of virtual machines in a load state.
  • an embodiment of the IT device layer management system of the present invention for performing the above-described energy saving monitoring method will be described.
  • an embodiment of the IT device layer management system in the embodiment of the present invention includes:
  • the information providing unit 801 is configured to provide system resource occupation information of the IT equipment layer management system to the energy saving monitoring device;
  • the power-off instruction receiving unit 802 is configured to receive a power-off instruction sent by the energy-saving monitoring device according to the system resource occupation information;
  • the closing unit 803 is configured to close the virtual machine in the idle state according to the power-off command
  • the feedback unit 804 is configured to send a power-off feedback message to the energy-saving monitoring device, so that the The infrastructure monitoring system sends a cooling adjustment command.
  • the IT device layer management system in the embodiment of the present invention may further include:
  • the deployment indication receiving unit 805 is configured to receive an indication that the energy saving monitoring device sends the virtual machine in a load state to be centrally deployed;
  • the deployment unit 806 is configured to centrally deploy the virtual machines in a load state according to the indication.
  • the information providing unit 801 is further configured to provide system resource occupation information after centralized deployment of the IT device layer management system to the energy saving monitoring device;
  • the power-off indication receiving unit 802 is further configured to receive a power-off instruction sent by the energy-saving monitoring apparatus according to the system resource occupation information after the centralized deployment.
  • the information providing unit 801 provides the system resource occupation information of the IT device layer management system to the energy saving monitoring device.
  • the information providing unit 801 can actively push the system resource occupation information of the IT device layer management system to the energy saving monitoring device.
  • the system resource occupancy information is carried in the response.
  • the power-off indication receiving unit 802 can receive the power-off instruction sent by the energy-saving monitoring device according to the system resource occupancy information, and the shut-off unit 803 can The virtual machine in the idle state is turned off according to the power-off command.
  • the deployment indication receiving unit 805 may receive the virtual state that is sent by the energy-saving monitoring device and is in a load state before receiving the power-off command.
  • the deployment indication receiving unit 805 may receive a hot migration instruction, where the hot migration instruction may include indicating that the IT equipment layer management system performs a centralized deployment policy, and the deployment unit 806 is configured according to the hot The migration instruction performs hot migration of the virtual machines in the IT device layer management system, so that the virtual machines in the load state are deployed in a centralized manner.
  • the manner in which the virtual machine is deployed in a centralized manner depends on the centralized deployment policy.
  • the hot migration rules for implementing the centralized deployment of the virtual machine may be multiple.
  • the centralized deployment policy may include a migrated object (that is, a virtual device that needs to perform hot migration).
  • the rule of the migration, and the rule of the migration in the centralized deployment policy may be: preferentially migrating the server device to an area close to the management device; secondly, thermally migrating the server device to the storage device Area; again, the server will be set up
  • the hot standby migrates to an area close to the network device.
  • a thermal migration completion response can be returned to the energy saving monitoring device so that the energy saving monitoring device can perform further operations.
  • the shutdown unit 803 After receiving the shutdown command, the shutdown unit 803 turns off the virtual machine in the idle state according to the power-off instruction; after completing the shutdown of the virtual machine in the idle state, the feedback unit 804 sends the power-off feedback to the energy-saving monitoring device. a message, so that the energy-saving monitoring device sends a cooling adjustment instruction to the infrastructure layer monitoring system according to the running state of the virtual machine corresponding to the cooling area where the virtual machine is powered off, so that the energy-saving monitoring device monitors the infrastructure layer according to the power-off feedback message.
  • the system sends a cooling adjustment command to adjust the cooling deployment.
  • the disclosed apparatus and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not executed.
  • the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical, mechanical or otherwise.
  • the units described as separate components may or may not be physically separate, and the components displayed as the units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention may contribute to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. , including a number of instructions to make a computer device (which can be a personal computer, a server, Or a network device or the like) performing all or part of the steps of the method of the various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Power Sources (AREA)
  • Selective Calling Equipment (AREA)
  • Devices That Are Associated With Refrigeration Equipment (AREA)

Abstract

一种节能监控方法以及设备。方法包括：获取IT设备层管理系统的系统资源占用信息；根据所述系统资源占用信息向所述IT设备层管理系统发送下电指令，使得所述IT设备层管理系统关闭处于空载状态的虚拟机；接收所述IT设备层管理系统发送的下电反馈消息，根据被关闭虚拟机所在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷调整指令，使得所述基础设施层监控系统调整所述被关闭虚拟机所在制冷区域的制冷部署。

Description

一种节能监控方法以及设备 技术领域
本发明实施例涉及云网络设备的监控领域，尤其涉及一种节能监控方法以 及设备。
背景技术
云计算指服务的交付和使用模式，通过网络以按需、 易扩展的方式获得所 需的服务。 这种服务可以是信息技术（IT, Information Technology ) 的相关服 务、 软件的相关服务或互联网的相关服务， 也可是其他服务。 云计算的核心思 想是将大量用网络连接的计算资源统一得进行管理和调度，构成一个计算资源 池为用户提供按需服务（即根据用户的需求提供的服务）。
提供资源的网络被称为"云，，。 "云，，中的资源在使用者看来是可以无限扩展 的， 并且可以随时获取， 按需使用， 随时扩展， 按使用付费。 目前云计算使用 虚拟化技术将固态的服务器设备， 网络设备， 存储设备变成虚拟计算资源， 虚 拟网络资源， 虚拟机存储资源， 将这些虚拟的资源可以统称为虚拟机（虚拟资 源计算机）。
云计算的数据中心可以分为 3 层： 基础设施层 （Levell ), IT设备层 ( Level2 ), 业务与应用层（ Level3 ); 其中， 基础设施层可以包含有电源设备， 机拒设备， 制冷设备， 散热设备， 消防设备， 安防设备和维护设备等， 由基础 设施层监控系统对这些设备进行统一的监控； IT设备层可以包含有服务器设 备， 网络设备， 安全设备和存储设备， 由 IT设备层管理系统对这些设备进行 统一的管理； 业务与应用层所包含的业务或应用的范围非常广泛， 如： 电子邮 件 （E-mail ), 办公室 （Office )软件和多媒体（Media )等多种直接面向用户 的应用。
由于云计算所涉及的业务和应用广泛， 因此， 云计算数据中心有着艮大的 业务负载压力； 为了处理这些业务负载， 云计算数据中心在 IT设备层配置有 许多虚拟机， 同时， 为了保证这些虚拟机的正常运作和运行效率， 云计算数据 中心在基础设施层为这些虚拟机配备了相应的制冷设备，而这些制冷设备则产 生了很大的电力能耗。 随着能源价格的增长， 电力能耗给云计算数据中心带来 了 4艮大的成本压力， 就制冷设备而言， 用于制冷设备的电力已经等于或超过了 虚拟机的运作用电； 因此， 在确保云计算数据中心的设备正常工作的前提下， 如何有效的降低数据中心的电源使用效率（ PUE, Power Usage Effectiveness ) 是一个重要的问题。
在现有技术中， IT设备层和基础设施层都具有独立的控制系统， IT设备 层管理系统和基础设施层监控系统间没有消息的交互机制，即基础设施层无法 获知 IT设备层的业务变化， 当 IT设备层的业务关闭时， IT设备层的虚拟机下 电，而此时基础设施层的制冷设备仍旧正常制冷，造成比较大的制冷功耗浪费， 增加了云计算数据中心的运营成本。
发明内容
本发明实施例提供了一种节能监控方法以及设备， 用于对 IT设备层的虚 拟机进行制冷调整。
本发明提供的节能监控方法， 包括： 获取 IT设备层管理系统的系统资源 占用信息； 根据所述系统资源占用信息向所述 IT设备层管理系统发送下电指 令， 使得所述 IT设备层管理系统关闭处于空载状态的虚拟机； 接收所述 IT设 备层管理系统发送的下电反馈消息，根据被关闭虚拟机所在制冷区域对应的虚 拟机的运行状态， 向基础设施层监控系统发送制冷调整指令，使得所述基础设 施层监控系统调整所述被关闭虚拟机所在制冷区域的制冷部署。
本发明提供的节能监控方法， 包括： 向节能监控装置提供 IT设备层管理 系统的系统资源占用信息；接收所述节能监控装置根据所述系统资源占用信息 发送的下电指令； 根据所述下电指令关闭处于空载状态的虚拟机， 并向所述节 能监控装置发送下电反馈消息，以使得所述节能监控装置根据被关闭虚拟机所 在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷调整指 令。
本发明提供的节能监控装置， 包括： 获取单元， 用于获取 IT设备层管理 系统的系统资源占用信息； 下电指示单元， 用于 ^据所述系统资源占用信息向 所述 IT设备层管理系统发送下电指令，使得所述 IT设备层管理系统关闭处于 空载状态的虚拟机； 反馈接收单元， 用于接收所述 IT设备层管理系统发送的 下电反馈消息； 制冷调整单元， 用于根据被关闭虚拟机所在制冷区域对应的虚 拟机的运行状态， 向基础设施层监控系统发送制冷调整指令，使得所述基础设 施层监控系统调整所述被关闭虚拟机所在制冷区域的制冷部署。
本发明提供的信息技术设备层管理系统， 包括： 信息提供单元， 用于向节 能监控装置提供 IT设备层管理系统的系统资源占用信息；下电指示接收单元， 用于接收所述节能监控装置根据所述系统资源占用信息发送的下电指令；关闭 单元， 用于根据所述下电指令关闭处于空载状态的虚拟机； 反馈单元， 用于向 所述节能监控装置发送下电反馈消息，以使得所述节能监控装置根据被关闭虚 拟机所在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷 调整指令。
从以上技术方案可以看出， 本发明实施例具有以下优点：
本发明实施例中， 节能监控装置通过查询 IT设备层管理系统的系统资源 占用信息，可以获知各个虚拟机的运行状态，从而确定是否需要进行制冷调整； 当需要制冷调整时， 可以向 IT设备层管理系统发送下电指令， 使得 IT设备层 管理系统关闭处于空载状态的虚拟机，从而根据被关闭虚拟机所在制冷区域对 应的虚拟机的运行状态，使得基础设施层监控系统可以进行制冷调整（降低轻 载区域的制冷效果， 或关闭空载区域的制冷设备）， 实现资源的优化配置。
附图说明
图 1为本发明节能监控方法一个实施例示意图；
图 2为本发明节能监控方法的另一个实施例示意图；
图 3为本发明节能监控方法的另一个实施例示意图；
图 4为本发明节能监控方法的另一个实施例示意图；
图 5为本发明节能监控方法的另一个实施例示意图；
图 6为本发明节能监控方法的另一个实施例示意图；
图 7为本发明节能监控装置的一个实施例示意图；
图 8为本发明 IT设备层管理系统的一个实施例示意图。
具体实施方式
本发明实施例提供了一种节能监控方法以及设备， 用于合理的对 IT设备 层的虚拟机进行制冷调整。
本发明实施例中节能监控方法的一个实施例包括： 获取 IT设备层管理系统的系统资源占用信息；
根据所述系统资源占用信息， 向所述 IT设备层管理系统发送下电指令， 使得所述 IT设备层管理系统关闭处于空载状态的虚拟机；
接收所述 IT设备层管理系统发送的下电反馈消息， 根据被关闭虚拟机所 在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷调整指 令，使得所述基础设施层监控系统调整所述被关闭虚拟机所在制冷区域的制冷 部署。
上述制冷区域为制冷设备对一个空间内存放的若干台虚拟机进行制冷的 区域， 具体的， 一个制冷区域可以为一个机拒（一个机拒可存放多台虚拟机） 中所在的区域， 一个制冷区域可以为一个房间内的区域， 制冷区域的范围划分 可以根据实际情况而定， 此处不作限定。
上述本发明实施例的方法可以由节能监控装置实施，在实际应用中， 所述 节能监控装置装置可以为 IT设备层管理系统和基础设施层监控系统之间的联 动门 （Portal )功能实体， 也可以为云计算数据中心的三层结构（基础设施层， IT设备层， 业务与应用层） 的统一监控系统； 其中， 所述联动门功能实体或 统一监控系统可以通过筒单对象访问协议 （SOAP, Simple Object Access Protocol )分别与 IT设备层管理系统和基础设施层监控系统建立连接，通过问 题（Request ), 响应 （Response ), 结果（Result ) 的通信机制分别实现联动门 功能实体、 IT设备层管理系统和基础设施层监控系统之间的消息交换； 并且， 由联动门功能实体。
本发明实施例中， 节能监控装置可以获知 IT设备层管理系统的系统资源 占用信息， 即可以获知各个虚拟机的运行状态，从而确定将空载状态的虚拟机 进行关闭； 并在节能监控装置主导下关闭了空载状态的虚拟机，从而可以根据 被关闭的虚拟机所在制冷区域的运行状态，并据此使得基础设施层监控系统可 以进行制冷调整， 实现资源的优化配置。
请参阅图 1 , 本发明实施例中节能监控方法的一个实施例包括：
101、 节能监控装置向信息技术设备层管理系统发送系统资源查询消息； 节能监控装置向 IT设备层管理系统发送系统资源查询消息，查询 IT设备 层管理系统的系统资源占用信息。 102、 节能监控装置获取 IT设备层管理系统的系统资源占用信息； 节能监控装置接收信息技术设备层管理系统返回的系统资源占用信息； 本实施例提供的通过步骤 101中的系统资源查询消息， 可选的， 节能监控 装置可以主动获取到系统资源占用信息，在其它的实施例中，也可以不执行步 骤 101 , IT设备层管理系统也可以主动向节能监控装置发送系统资源占用信 息， 例如定时推送， 节能监控装置可以直接获取 IT设备层管理系统主动推送 的系统资源占用信息。
可选的， 所述系统资源占用信息可以为： IT设备层管理系统中各台虚拟 机的当前操作系统， 进程， 线程以及应用程序的利用率等信息， 由节能监控装 置对这些信息进行分析，得到 IT设备层管理系统中各个虚拟机的 CPU占用信 息和 /或内存占用信息；
或者， 所述系统资源占用信息也可以为： 各台虚拟机的 CPU占用信息和 / 或内存占用信息； 所述在 IT设备层管理系统接收到所述系统资源查询消息之 后， 由 IT设备层管理系统对本地运营中的各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等信息进行内部查询，从而得到各台虚拟机的 CPU 占用信息和 /或内存占用信息， 并通过系统资源占用信息向节能监控装置反馈 所述 CPU占用信息和 /或内存占用信息。
在现有技术中， IT设备层管理系统可以对 IT设备层的各台虚拟机进行统 一的管理， 实时监控各台虚拟机的运行状态， 并可以指示所述虚拟机进行各种 操作 （如， 热迁移操作和下电操作）。
103、 节能监控装置根据系统资源占用信息判断是否需要改变虚拟机的部 署；
节能监控装置根据所述系统资源占用信息判断是否需要改变虚拟机的部 署， 若是， 则触发步骤 104, 指示所述 IT设备层管理系统将处于负载状态的 虚拟机集中部署； 若否， 则保持 IT设备层管理系统中各个虚拟机的状态不变， 结束流程。
具体的，在节能监控装置接收到所述系统资源占用信息之后，会根据所述 系统资源占用信息确定 IT设备层管理系统中各个虚拟机的运行状态， 当处于 空载和负载状态的虚拟机之间的数量比满足预置条件时，就可以确定需要改变 虚拟机的部署； 其中， 负载状态还可以进一步包括轻载状态和重载状态， 在考 虑是否需要进行热迁移时，也可以进一步的考虑处于空载、轻载和重载状态的 虚拟机之间的数量比，具体判断是否需要改变虚拟机的部署的参考条件可以根 据实际需求而定， 此处不作限定。
其中， 上述判断虚拟机处于轻载状态还是重载状态， 可以通过设定预设负 载阈值的方式进行判定，如，负载大于或等百分之五十的虚拟机处于重载状态， 负载小于百分之五十的虚拟机处于轻载状态。
在实际应用中， 由于 IT设备层在各个时段的业务量不恒定， 若在某段时 间内， 因业务量少而造成部分的虚拟机处于空载状态， 此时， 如果空载虚拟机 的分布散乱， 就算获知了各个虚拟机的运行状态，也没办法调整制冷设备的制 冷部署， 因为只要某一个制冷区域还有一台设备仍在运行， 为了保证设备的正 常运行， 该制冷区域就不能够关闭制冷设备， 因此， 就产生了改变虚拟机部署 的需求， 所述改变虚拟机的部署包括将负载状态的虚拟机集中部署。
104、节能监控装置根据所述系统资源占用信息指示所述 IT设备层管理系 统将处于负载状态的虚拟机集中部署；
可选的， 节能监控装置在确认了需要改变虚拟机的部署之后， 可以根据所 述系统资源占用信息确定需要执行迁移的虚拟机， 进一步的，还可以根据需要 执行迁移的虚拟机确定集中部署策略（该策略用于实现上述处于负载状态的虚 拟机集中部署 ),使得节能监控装置根据该集中部署策略指示所述 IT设备层管 理系统将处于负载状态的虚拟机集中部署； 其中， 实现上述虚拟机集中部署的 集中部署策略可以有多种， 具体在后续的实施例中描述， 此处暂时不作限定。
105、 节能监控装置通知信息技术设备层管理系统发送下电指令， 以使得 信息技术设备层管理系统关闭处于空载状态的虚拟机；
在确认处于负载状态的虚拟机完成集中部署之后，节能监控装置向信息技 术设备层管理系统发送下电指令， 使得所述 IT设备层管理系统关闭处于空载 状态的虚拟机。
节能监控装置可以通过接收 IT设备层管理系统发送的下电反馈消息， 确 认处于空载状态的虚拟机完成下电。 状态， 向基础设施层监控系统发送制冷调整指令。
在确认处于空载状态的虚拟机关闭之后，节能监控装置根据被关闭虚拟机 所在制冷区域对应的虚拟机的运行状态向基础设施层监控系统发送制冷调整 指令，使得基础设施层监控系统调整被关闭的虚拟机所在区域的制冷部署， 以 达到制冷输出的优化。
可选的， 所述制冷调整指令中可以包含有制冷调整的策略， 所述制冷调整 指令可以是使得所述基础设施层监控系统关闭空载区域的制冷设备的第一制 冷调整指令，也可以是使得所述基础设施层监控系统降低轻载区域的制冷效果 的第二制冷调整指令，也可以包含有改变后虚拟机的部署情况， 由基础设施层 监控系统根据所述部署情况自行决定制冷调整的策略。
具体的， 上述制冷调整的策略可以包括： 关闭空载区域的制冷设备， 所述 区域的制冷效果，所述轻载区域为该制冷区域内处于负载状态的虚拟机少于预 置数量的制冷区域。
本发明实施例中的一个制冷区域配备了一台制冷设备，该制冷设备可以独 立运作或者关闭， 实际操作中， 一个制冷区域即一个机拒， 一个机拒内可以配 置多台虚拟机， 以及配置一台制冷设备。
在现有技术中，基础设施层监控系统可以对基础设施层中的制冷设备进行 统一的监控和管理。
本发明实施例中， 通过查询 IT设备层管理系统的系统资源占用信息， 可 以获知各个虚拟机的运行状态，从而确定是否需要进行制冷调整； 当需要制冷 调整时， 可以指示 IT设备层管理系统将处于负载状态的虚拟机集中部署， 从 而使得基础设施层监控系统可以进行制冷调整， 实现资源的优化配置。
下面对具体如何实现处于负载状态的虚拟机的集中部署进行详细地描述， 请参考图 2, 本发明实施例中节能监控方法的另一个实施例包括：
201、 节能监控装置向信息技术设备层管理系统发送系统资源查询消息； 本实施例中的步骤 201的内容与前述图 1所示的实施例中步骤 101的内容 相同， 此处不再赘述。
202、 节能监控装置接收信息技术设备层管理系统返回的系统资源占用信 息；
节能监控装置接收 IT设备层管理系统返回的系统资源占用信息， 所述系 统资源占用信息中携带有 IT设备层管理系统中虚拟机的 CPU 占用信息和 /或 内存占用信息。
具体的， 在 IT设备层管理系统接收到所述系统资源查询消息之后， IT设 备层管理系统对本地运营中的各台虚拟机的当前操作系统， 进程， 线程以及应 用程序的利用率等信息进行内部查询， 从而得到各台虚拟机的 CPU占用信息 和 /或内存占用信息， 并通过系统资源占用信息向节能监控装置反馈所述 CPU 占用信息和 /或内存占用信息。
203、 节能监控装置根据系统资源占用信息判断是否需要改变虚拟机的部 署；
节能监控装置根据所述系统资源占用信息中的 CPU占用信息和 /或内存占 用信息判断是否需要执行改变虚拟机的部署， 若是， 则触发步骤 204, 向确定 虚拟机的集中部署策略； 若否， 则保持 IT设备层管理系统中各个虚拟机的状 态不变， 结束流程。
具体的， 节能监控装置可以根据所述 CPU占用信息和 /或内存占用信息分 别确定处于空载状态和处于负载状态的虚拟机的数目。
可选的， 可以判断所述虚拟机的 CPU占用信息和 /或内存占用信息是否到 达预置的空载条件， 若满足， 则确定所述虚拟机处于空载状态； 如， 若虚拟机 当前的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差低于 1% 且持续 60秒时， 则确定所述虚拟机处于空载的状态； 或者， 为了进一步的确 保判断的准确性， 可以进行二次确定， 如： 若虚拟机当前的 CPU和内存占用 信息与空闲时的 CPU和内存占用信息的偏差低于 1%且持续 60秒时， 则初步 确定所述虚拟机处于空载的状态，在 5分钟之后，对所述初步确定为空载状态 的虚拟机再次进行 CPU占用信息和 /或内存占用信息的检测， 若该虚拟机当前 的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差低于 1%, 则 确定所述虚拟机处于空载的状态。
同理， 可以判断所述虚拟机的 CPU占用信息和 /或内存占用信息是否到达 预置的负载条件， 若满足， 则确定所述虚拟机处于负载状态； 如， 若虚拟机当 前的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差高于 1%且 持续 20秒时， 则确定所述虚拟机处于负载的状态； 与判断空载时类似， 为了 进一步的确保判断的准确性，对于初步确定为负载状态的虚拟机也可以进行二 次确定。
在分别确定了 IT设备层中各台虚拟机的运行状态之后， 节能监控装置分 别统计处于空载状态的虚拟机和处于负载状态的虚拟机的数量，确定处于空载 状态的虚拟机和处于负载状态的虚拟机的比例，判断所述比例是否满足预置的 条件， 如， 空载状态的虚拟机的比例是否达到百分之三十， 若是， 则需要改变 虚拟机的部署； 可选的， 在实际应用中， 上述预置的条件还可以设置为其它条 件，如加入虚拟机所处区域的温度和所处的时段等参考因素， 具体可以根据实 际情况而定， 此处不作限定。
204、 节能监控装置根据系统资源占用信息确定虚拟机的集中部署策略； 在确认了需要改变虚拟机的部署之后，节能监控装置可以根据所述系统资 源占用信息确定需要执行集中部署的虚拟机（集中部署包括将负载状态的虚拟 机集中部署， 负载状态的虚拟机包括轻载状态虚拟机何重载状态虚拟机，如某 个区域内的负载虚拟机低于预置数量或该区域内的虚拟机处于轻载状态，则确 定需要对该区域内的虚拟机执行集中部署）， 进一步的， 还可以根据需要执行 集中部署的虚拟机确定集中部署策略。
本实施例中，对虚拟机集中部署可以采用虚拟机热迁移的方式，虚拟机热 迁移指的是将整个虚拟机的运行状态完整保存下来，同时可以快速的恢复到原 有硬件平台的另一台虚拟机或是不同硬件平台的虚拟机上； 并且，在恢复的过 程中，虚拟机能够实现平滑的无中断的业务迁移，使得用户不会察觉到任何差 异。 具体的， 所述集中部署策略可以包括迁移的对象（即需要执行热迁移的虚 拟机）和迁移的规则， 而集中部署策略中迁移的规则可以为： 优先将所述服务 器设备热迁移至靠近所述管理设备的区域； 其次，将所述服务器设备热迁移至 靠近所述存储设备的区域； 再次，将所述服务器设备热迁移至靠近所述网络设 备的区域。
在实际应用中， 虚拟机包括有服务器设备， 管理设备， 网络设备和存储设 备； 由于管理设备， 网络设备和存储设备是不能下电的， 因此， 在进行热迁移 时，尽量将服务器设备类型的虚拟机热迁移至不能下电的虚拟机附近，使得基 础设施层的制冷系统可以对在不能下电的虚拟机所在的区域集中供电和制冷。
其中， 可选的， 节能监控装置可以根据当前各个虚拟机的运行状态， 确定 迁移对象，并根据预置的算法和上述迁移规则计算得到所述迁移对象进行热迁 移的路径， 从而得到具体的集中部署策略； 可选的， 在确定迁移对象之后， 也 可以计算当前各个虚拟机的运行状态与预置的几个迁移场景（每个迁移场景配 置有相应的集中部署策略）的匹配度，从而在预置的几个集中部署策略中选择 一个作为当前执行热迁移的策略。集中部署策略的获取方式可以根据实际情况 而定， 此处不作限定。
205、 节能监控装置向信息技术设备层管理系统发送携带有所述集中部署 策略的热迁移指令；
节能监控装置向信息技术设备层管理系统发送携带有所述集中部署策略 的热迁移指令， 使得 IT设备层管理系统根据所述集中部署策略对虚拟机执行 热迁移， 从而使得处于负载状态的虚拟机集中部署。
在执行完所述集中部署之后， 所述节能监控装置需要返回步骤 201及 202 以获取 IT设备层管理系统的集中部署后的系统资源占用信息。 206、 节能监控 装置根据 IT设备层管理系统的集中部署后的系统资源占用信息， 通知信息技 术设备层管理系统发送下电指令，以使得信息技术设备层管理系统关闭处于空 载状态的虚拟机；
本实施例中的步骤 206的内容与前述图 1所示的实施例中步骤 106的内容 相同， 此处不再赘述。 状态， 向基础设施层监控系统发送制冷调整指令。
本实施例中的步骤 207的内容与前述图 1所示的实施例中步骤 106的内容 相同， 此处不再赘述。
在实际应用中，在完成了虚拟机的集中部署后， 由于有一些区域的还存在 为数不多的处于负载状态的虚拟机，节能监控装置需要根据实际的部署情况指 示基础设施层监控系统进行制冷调整， 请参阅图 3, 本发明实施例中节能监控 方法的另一个实施例包括： 301、 节能监控装置向信息技术设备层管理系统发送系统资源查询消息； 本实施例中的步骤 301的内容与前述图 1所示的实施例中步骤 101的内容 相同， 此处不再赘述。
302、 节能监控装置接收信息技术设备层管理系统返回的系统资源占用信 息；
本实施例中的步骤 302的内容与前述图 2所示的实施例中步骤 202的内容 相同， 此处不再赘述。
303、 节能监控装置根据系统资源占用信息判断是否需要改变虚拟机的部 署；
节能监控装置根据所述系统资源占用信息中的 CPU占用信息和 /或内存占 用信息判断是否需要执行改变虚拟机的部署， 若是， 则触发步骤 304, 向确定 虚拟机的集中部署策略； 若否， 则保持 IT设备层管理系统中各个虚拟机的状 态不变， 结束流程。
304、 节能监控装置根据系统资源占用信息确定虚拟机的集中部署策略； 在确认了需要改变虚拟机的部署之后，节能监控装置可以根据所述系统资 源占用信息确定需要执行热迁移的虚拟机， 进一步的，还可以根据需要执行热 迁移的虚拟机确定集中部署策略。
具体的， 所述集中部署策略可以包括迁移的对象和迁移的规则， 而集中部 署策略中迁移的规则可以为：优先将所述服务器设备热迁移至靠近所述管理设 备的区域；其次，将所述服务器设备热迁移至靠近所述存储设备的区域；再次， 将所述服务器设备热迁移至靠近所述网络设备的区域。
305、 节能监控装置向信息技术设备层管理系统发送携带有所述集中部署 策略的发送热迁移指令；
节能监控装置向信息技术设备层管理系统发送携带有所述集中部署策略 的发送热迁移指令， 使得 IT设备层管理系统根据所述集中部署策略对虚拟机 执行热迁移， 从而使得处于负载状态的虚拟机集中部署。
306、 节能监控装置接收信息技术设备层管理返回的热迁移完成响应； 在实际应用中， IT设备层管理系统在完成虚拟机的热迁移之后， 会向节 能监控装置返回的热迁移完成响应，而节能监控装置接收到所述热迁移完成响 应之后， 即可确认虚拟机的热迁移完成， 随即可以触发步骤 307, 进行处于空 载状态的虚拟机的关闭操作。
在执行完所述集中部署之后， 所述节能监控装置需要返回步骤 301及 302 以获取 IT设备层管理系统的集中部署后的系统资源占用信息。
307、 节能监控装置向信息技术设备层管理系统发送下电指令；
在确认虚拟机的热迁移完成之后， 节能监控装置根据 IT设备层管理系统 的集中部署后的系统资源占用信息， 向信息技术设备层管理系统发送下电指 令， 使得所述 IT设备层管理系统关闭处于空载状态的虚拟机。
308、 节能监控装置接收信息技术设备层管理系统发送的下电反馈消息； 在实际应用中， IT设备层管理系统在完成处于空载状态的虚拟机的下电 操作后， 可以向节能监控装置发送下电反馈消息； 节能监控装置在接收到所述 下电反馈消息，可以根据所述下电反馈消息获知虚拟机执行下电指令的具体情 况（如， 处于空载状态的虚拟机皆已下电）。
其中， 所述下电反馈消息中携带有机拒编号， 所述机拒编号为执行下电的 虚拟机所在机拒的编号。
309、 节能监控装置确认需要执行制冷调整的虚拟机； 标识是否匹配； 若是， 则触发步骤 309, 向基础设施层监控系统发送制冷调整 指令； 若否， 则向 IT设备层管理系统发送查询消息， 使得所述 IT设备层管理 系统再次确认所述机拒编号与机拒内虚拟机的匹配关系。
在实际应用中， 虚拟机放置在 IT设备层的机拒设备中， 一个机拒中可以 放置有多个虚拟机， 并且 IT设备层管理系统记录有虚拟机的标识与该机拒的 编号的匹配关系（如， 一个机拒内存储了哪些虚拟机， 这些虚拟机都可以用虚 拟机的标识唯一的识别，匹配关系为该机拒编号与该机拒内存储的各台虚拟机 的标识的对应关系）； 由于发生了虚拟机的热迁移， 为了保证机拒与其拒内所 述放置的虚拟机的关系没有混乱，节能监控装置需要检查机拒编号与其对应的 虚拟机的标识的匹配关系 （即查询所述机拒编号对应的各个虚拟机的标识中， 是否有所需要进行下电的空载的虚拟机的标识， 若有， 则确认无误。）， 当确认 无误后， 即可向基础设施层监控系统发送制冷调整指令。 310、 节能监控装置根据虚拟机的部署情况向基础设施层监控系统发送制 冷调整指令。
节能监控装置根据虚拟机的部署情况向基础设施层监控系统发送制冷调 整指令， 具体的：
若被关闭的虚拟机所在区域为空载区域，则向基础设施层监控系统发送第 一制冷调整指令，使得所述基础设施层监控系统关闭空载区域的制冷设备， 所 述空载区域为区域内所有虚拟机皆处于下电状态的区域；
若被关闭的虚拟机所在区域为轻载区域，则向基础设施层监控系统发送第 二制冷调整指令，使得所述基础设施层监控系统降低轻载区域的制冷效果， 所 述轻载区域为处于负载状态的虚拟机少于预置数量（预置数量可以根据实际情 况而定， 此处不作限定）的区域。 由于轻载区域仍有虚拟机在运行， 因此， 不 能关闭该区域的制冷设备； 而又由于该区域发生了热迁移， 负载状态的虚拟机 的数量较少， 因此， 可以降低该区域的制冷效果。
下面从 IT设备层管理系统的角度对本发明实施例中的节能监控方法进行 描述， 请参阅图 4, 本发明实施例中节能监控方法的另一个实施例包括：
401、 信息技术设备层管理系统接收节能监控装置发送的系统资源查询消 息；
IT设备层管理系统在收到节能监控装置发送的系统资源查询消息之后， 根据所述系统资源查询消息查询 IT设备层管理系统的系统资源占用信息。
402、 信息技术设备层管理系统向节能监控装置返回系统资源占用信息；
IT设备层管理系统向节能监控装置返回系统资源占用信息。
具体的， 所述系统资源占用信息可以包括： IT设备层管理系统中各虚拟 机的 CPU占用信息和 /或内存占用信息。 IT设备层管理系统可以对本地运营中 的各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等信息进行 内部查询， 从而得到各台虚拟机的 CPU占用信息和 /或内存占用信息， IT设备 层管理系统可以向节能监控装置返回所述 CPU占用信息和 /或内存占用信息。
可选的， 所述系统资源占用信息也可以为： 各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等信息； IT设备层管理系统直接向节能监 控装置返回各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等 信息， 使得节能监控装置通过这些信息得到所述 CPU占用信息和 /或内存占用 信息。
可选的， IT设备层管理系统可以每隔预置时长主动向节能监控装置发送 系统资源占用信息； 因此， 若为主动发送， 则无需执行上述步骤 401.
403、 信息技术设备层管理系统接收节能监控装置发送的热迁移指令；
IT设备层管理系统接收节能监控装置发送的热迁移指令； 具体的， 所述 热迁移指令中可以包含有指示 IT设备层管理系统执行集中部署策略。
404、 信息技术设备层管理系统根据所述热迁移指令对所述虚拟机执行热 迁移；
IT设备层管理系统根据所述热迁移指令对所述 IT设备层管理系统中的虚 拟机进行热迁移， 使得处于负载状态的虚拟机集中部署。
虚拟机热迁移指的是将整个虚拟机的运行状态完整保存下来，同时可以快 速的恢复到原有硬件平台的另一台虚拟机或是不同硬件平台的虚拟机上； 并 且， 在恢复的过程中， 虚拟机能够实现平滑的无中断的业务迁移， 使得用户不 会察觉到任何差异。
具体的， 虚拟机集中部署的方式取决于集中部署策略， 其中， 实现上述虚 拟机集中部署的热迁移规则可以有多种，所述集中部署策略可以包括迁移的对 象（即需要执行热迁移的虚拟机）和迁移的规则， 而集中部署策略中迁移的规 则可以为： 优先将所述服务器设备热迁移至靠近所述管理设备的区域； 其次， 将所述服务器设备热迁移至靠近所述存储设备的区域； 再次，将所述服务器设 备热迁移至靠近所述网络设备的区域。
在实际应用中， 虚拟机包括有服务器设备， 管理设备， 网络设备和存储设 备； 由于管理设备， 网络设备和存储设备是不能下电的， 因此， 在进行热迁移 时，尽量将服务器设备类型的虚拟机热迁移至不能下电的虚拟机附近，使得基 础设施层的制冷系统可以对在不能下电的虚拟机所在的区域集中供电和制冷。
其中， 可选的， 节能监控装置可以根据当前各个虚拟机的运行状态， 确定 迁移对象，并根据预置的算法和上述迁移规则计算得到所述迁移对象进行热迁 移的路径， 从而得到具体的集中部署策略； 可选的， 在确定迁移对象之后， 也 可以计算当前各个虚拟机的运行状态与预置的几个迁移场景（每个迁移场景配 置有相应的集中部署策略）的匹配度，从而在预置的几个集中部署策略中选择 一个作为当前执行热迁移的策略。集中部署策略的获取方式可以根据实际情况 而定， 此处不作限定。
405、信息技术设备层管理系统向所述节能监控装置返回热迁移完成响应； 可选的， 在确认所述热迁移完成之后， IT设备层管理系统向所述节能监 控装置返回热迁移完成响应,使得节能监控装置可以进行进一步的操作 (如， 指示空载状态的虚拟机下电）。
406、 信息技术设备层管理系统接收所述节能监控装置发送的下电指令； IT设备层管理系统接收所述节能监控装置发送的下电指令， 所述下电指 令用于指示 IT设备层管理系统关闭处于空载状态的虚拟机。
具体的， 所述节能监控装置接收到热迁移完成响应之后， 即可确认虚拟机 的热迁移完成， 随即获取 IT设备层管理系统的集中部署后的系统资源占用信 息， 并据此可以 IT设备层管理系统发送下电指令。
407、 信息技术设备层管理系统根据所述下电指令关闭处于空载状态的虚 拟机。
IT设备层管理系统根据所述下电指令关闭处于空载状态的虚拟机， 并向 所述节能监控装置发送下电反馈消息，向节能监控装置反馈虚拟机执行下电指 令的具体情况（如， 处于空载状态的虚拟机皆已下电）， 使得节能监控装置根 据下电反馈消息向基础设施层监控系统发送制冷调整指令， 调整制冷部署。
为了便于理解，下面以一具体应用场景对上述的实施例中描述的节能监控 方法再进行详细描述， 具体为：
假设云计算的数据中心包含有 1000台虚拟机， 包括有服务器设备， 网络 设备， 安全设备和存储设备。 其中网络设备， 安全设备和存储设备等不能下电 的虚拟机有 50台， 分别部署在 Al , A2, A3三个机拒中 （英文字符表示行， 数字字符表示列，如 A2表示 A行 2列的机拒 ),虚拟机标识为 A1S01~A1S20, A2S01-A2S20, A3S01~A3S10 ( S01~S20表示虚拟机的标识， 如 S05表示第 5 号虚拟机）。 另外 950台虚拟机分别部署中 A3~A5, B1-B5, C1-C5, D1-D5, E1~E5等机拒中； 其他基础层设备均部署在 F1~F5, G1~G5机拒中。 其中， 每个机拒可以部署 20台虚拟机。 在实际应用中， 可以设定触发节能监控流程的时间段， 如： 一天内的 08:00-22:00 是业务量大的时段， 可以不执行节能监控流程； 而一天内的 24:00-06:00是业务量低的时段， 可以执行节能监控流程。
假设， 联动 Portal (节能监控装置 )从晚上 22:30开始执行系统资源占用 信息的查询和分析， 若 CPU 占用率为 30%~100% , 或者内存占用率为 20%~100%的虚拟机占整个数据中心虚拟机的百分比为 30%以上， 则保持 IT 设备层管理系统中各个虚拟机的状态不变，并继续执行系统资源占用信息的查 询和分析。
当 CPU占用率为 30%~100%或内存占用率为 20%~100%的虚拟机占整个 数据中心虚拟机的百分比小于 30%时， 则根据 CPU占用率和 /或内存占用率统 计得到一个利用率和虚拟机标识的关系对应表，如： A1S06,负荷 58%; E5S20, 负荷 20%。
那么，联动 Portal则可以根据所述关系对应表确定虚拟机热迁移策略，如： 优先将 CPU利用率和内存利用率均小于 30%的虚拟机迁移到 A1~A3机拒内的 空闲资源中， 在进行迁移前使用虚拟机标识查询到需要迁移至的虚拟机的 IP 地址，并基于该 IP地址进行点对点热迁移。之后按照利用率 40%, 60%, 80%。
100%的递增方式完成所有虚拟机的热迁移。
当虚拟机热迁移过程中发现 A1~A3内的服务器资源负荷不足以承担虚拟 机的热迁移时，则使用 A3~A5的服务器资源；若资源仍然不足则使用 B1~B5, 以及 C1~C5的服务器设备资源。 由于之前已经计算出整个数据中心的负荷是 低于 30%, 因此 A1~A5, B1-B5, C1~C5的服务器资源是完全可以承担这些 负荷的， 后续不会再有虚拟机迁移的诉求。
当虚拟机热迁移完成之后，进行虚拟机的下电操作，由传感器反馈 Α1~Α5 ,
B1-B5, C1-C5, D1-D5 , E1~E5等机拒内及其周边的温度信息， 并由基础设 施层监控系统将这些信息反馈给联动 Portal, 依据温度情况由联动 Portal判断 出符合下电条件的机拒编号，在联动 Portal查询到数据库中机拒编号与空调的 对应关系之后， 下发可以下电或者降温的空调编号给 L1层的监控系统， 由 L1 层的监控系统执行下电或者降温的操作，并反馈执行日志信息（包括消息名称， 执行时间， 执行结果的状态）给联动 Portal。 经过长期的运行后， 总结出此数据中心中的负荷分布情况， 则可以将长期 稳定的， 承担业务负荷大于 30%的虚拟机的均集中部署在 A1~A5, B1~B5和 C1-C5 的机拒中集中供冷， 对于长期弹性要求比较多的虚拟机则部署在其它 机拒中， 并有规律的在局部执行节能减排工作， 不需要在全局执行。
上面仅以一些例子对本发明实施例中的应用场景进行了说明，可以理解的 是， 在实际应用中， 还可以有更多的应用场景， 具体此处不作限定。
上述是以第三方设备 (节能监控装置 )执行本发明实施例中的节能监控方 法， 除了上述方法之外， 本发明实施例中的节能监控方法还可以由 IT设备层 管理系统执行， 具体请参阅图 5, 本发明实施例中节能监控方法的另一个实施 例包括：
501、 信息技术设备层管理系统获取虚拟机的系统资源占用信息；
IT设备层管理系统获取虚拟机的系统资源占用信息； 具体的， 所述系统 资源占用信息可以为： 各台虚拟机的 CPU占用信息和 /或内存占用信息； 各台 虚拟机的 CPU 占用信息和 /或内存占用信息可以由 IT设备层管理系统对本地 运营中的各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等信 息进行查询和分析得到。
502、 信息技术设备层管理系统根据系统资源占用信息判断是否需要改变 虚拟机的部署；
IT设备层管理系统根据所述系统资源占用信息判断是否需要改变虚拟机 的部署，若是， 则触发步骤 503, 向需要执行热迁移的虚拟机发送热迁移指令， 使得处于负载状态的虚拟机集中部署； 若否， 则保持 IT设备层管理系统中各 个虚拟机的状态不变， 结束流程。
具体的， 在获取到所述系统资源占用信息之后， IT设备层管理系统会根 据所述系统资源占用信息确定 IT设备层管理系统中各个虚拟机的运行状态， 当处于空载、 负载状态的虚拟机之间的数量比满足预置条件时， 就可以确定需 要改变虚拟机的部署；其中，负载状态还可以进一步包括轻载状态和重载状态， 在考虑是否需要进行热迁移时，也可以进一步的考虑处于空载、轻载和重载状 态的虚拟机之间的数量比，具体判断是否需要进行热迁移的参考条件可以根据 实际需求而定， 此处不作限定。 其中， 上述判断虚拟机处于轻载状态还是重载状态， 可以通过设定预设负 载阈值的方式进行判定，如，负载大于或等百分之五十的虚拟机处于重载状态， 负载小于百分之五十的虚拟机处于轻载状态。
在实际应用中， 由于 IT设备层在各个时段的业务量不恒定， 若在某段时 间内， 因业务量少而造成部分的虚拟机处于空载状态， 此时， 如果空载虚拟机 的分布散乱， 就算获知了各个虚拟机的运行状态，也没办法调整制冷设备的制 冷部署， 因为只要某一个制冷区域还有一台设备仍在运行， 为了保证设备的正 常运行， 该制冷区域就不能够关闭制冷设备， 因此， 就产生了改变虚拟机部署 的需求。
503、 信息技术设备层管理系统向需要执行热迁移的虚拟机发送热迁移消 息；
在确定需要执行虚拟机的热迁移后， IT设备层管理系统根据所述各台虚 拟机的 CPU占用信息和 /或内存占用信息确定集中部署策略， IT设备层管理系 统再根据所述集中部署策略向需要执行热迁移的虚拟机发送热迁移消息，从而 使得处于负载状态的虚拟机集中部署。
504、 信息技术设备层管理系统向处于空载状态的虚拟机发送下电指令； 在确认所述虚拟机的热迁移完成之后， IT设备层管理系统根据集中部署 后的系统资源占用信息， 向处于空载状态的虚拟机发送下电指令， 关闭处于空 载状态的虚拟机。
505、信息技术设备层管理系统向基础设施层监控系统发送制冷调整指令。 在确认处于空载状态的虚拟机已经下电之后， IT设备层管理系统根据执 行所述下电指令的虚拟机的分布向基础设施层监控系统发送制冷调整指令。
使得基础设施层监控系统根据热迁移后虚拟机的部署，对基础设施层中的 制冷设备进行调整， 以达到制冷输出的优化。
可选的， 所述制冷调整指令中可以包含有制冷调整的策略， 所述制冷调整 指令中也可以包含有热迁移后虚拟机的部署情况，由基础设施层监控系统根据 所述部署情况自行决定制冷调整的策略。
具体的， 上述制冷调整的策略可以包括： 关闭空载区域的制冷设备， 所述 的制冷效果， 所述轻载区域为处于负载状态的虚拟机少于预置数量的区域。 下面对 IT设备层管理系统执行的节能监控方法进行详细描述， 请参阅图 6, 本发明实施例中节能监控方法的另一个实施例包括：
601、 信息技术设备层管理系统获取虚拟机的系统资源占用信息； 本实施例中的步骤 501的内容与前述图 4所示的实施例中步骤 401的内容 相同， 此处不再赘述。
602、 信息技术设备层管理系统根据系统资源占用信息判断是否需要执行 虚^ (机的热迁移；
IT设备层管理系统根据所述系统资源占用信息中的 CPU占用信息和 /或内 存占用信息判断是否需要执行虚拟机的热迁移， 若是， 则触发步骤 603, 向需 要执行热迁移的虚拟机发送热迁移消息； 若否， 则保持 IT设备层管理系统中 各个虚拟机的状态不变， 结束流程。
具体的， 节能监控装置可以根据所述 CPU占用信息和 /或内存占用信息分 别确定处于空载状态和处于负载状态的虚拟机的数目。
可选的， 可以判断所述虚拟机的 CPU占用信息和 /或内存占用信息是否到 达预置的空载条件， 若满足， 则确定所述虚拟机处于空载状态； 如， 若虚拟机 当前的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差低于 1% 且持续 60秒时， 则确定所述虚拟机处于空载的状态； 或者， 为了进一步的确 保判断的准确性， 可以进行二次确定， 如： 若虚拟机当前的 CPU和内存占用 信息与空闲时的 CPU和内存占用信息的偏差低于 1%且持续 60秒时， 则初步 确定所述虚拟机处于空载的状态，在 5分钟之后，对所述初步确定为空载状态 的虚拟机再次进行 CPU占用信息和 /或内存占用信息的检测， 若该虚拟机当前 的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差低于 1%, 则 确定所述虚拟机处于空载的状态。
同理， 可以判断所述虚拟机的 CPU占用信息和 /或内存占用信息是否到达 预置的负载条件， 若满足， 则确定所述虚拟机处于负载状态； 如， 若虚拟机当 前的 CPU和内存占用信息与空闲时的 CPU和内存占用信息的偏差高于 1%且 持续 20秒时， 则确定所述虚拟机处于负载的状态； 与判断空载时类似， 为了 进一步的确保判断的准确性，对于初步确定为负载状态的虚拟机也可以进行二 次确定。
在分别确定了 IT设备层中各台虚拟机的运行状态之后， 节能监控装置分 别统计处于空载状态的虚拟机和处于负载状态的虚拟机的数量，确定处于空载 状态的虚拟机和处于负载状态的虚拟机的比例，判断所述比例是否满足预置的 条件， 如， 空载状态的虚拟机的比例是否达到百分之三十， 若是， 则需要改变 虚拟机的部署； 可选的， 在实际应用中， 上述预置的条件还可以设置为其它条 件，如加入虚拟机所处区域的温度和所处的时段等参考因素， 具体可以根据实 际情况而定， 此处不作限定。
603、 信息技术设备层管理系统根据系统资源占用信息确定虚拟机的集中 部署策略；
在确定需要执行虚拟机的热迁移后， IT设备层管理系统可以根据所述系 统资源占用信息确定需要执行热迁移的虚拟机， 进一步的，还可以根据需要执 行热迁移的虚拟机确定集中部署策略。
具体的， 所述集中部署策略可以包括迁移的对象（即需要执行热迁移的虚 拟机）和迁移的规则， 而集中部署策略中迁移的规则可以为： 优先将所述服务 器设备热迁移至靠近所述管理设备的区域； 其次，将所述服务器设备热迁移至 靠近所述存储设备的区域； 再次，将所述服务器设备热迁移至靠近所述网络设 备的区域。
在实际应用中， 虚拟机包括有服务器设备， 管理设备， 网络设备和存储设 备； 由于管理设备， 网络设备和存储设备是不能下电的， 因此， 在进行热迁移 时，尽量将服务器设备类型的虚拟机热迁移至不能下电的虚拟机附近，使得基 础设施层的制冷系统可以对在不能下电的虚拟机所在的区域集中供电和制冷。
其中， 可选的， IT设备层管理系统可以根据当前各个虚拟机的运行状态， 确定迁移对象，并根据预置的算法和上述迁移规则计算得到所述迁移对象进行 热迁移的路径，从而得到具体的集中部署策略；可选的，在确定迁移对象之后， 也可以计算当前各个虚拟机的运行状态与预置的几个迁移场景（每个迁移场景 配置有相应的集中部署策略）的匹配度，从而在预置的几个集中部署策略中选 择一个作为当前执行热迁移的策略。集中部署策略的获取方式可以根据实际情 况而定， 此处不作限定。 604、 信息技术设备层管理系统向需要执行热迁移的虚拟机发送热迁移消 息；
信息技术设备层管理系统向需要执行热迁移的虚拟机发送热迁移消息，使 得处于负载状态的虚拟机集中部署。
605、 信息技术设备层管理系统向处于空载状态的虚拟机发送下电指令； 在确认所述虚拟机的热迁移完成之后， IT设备层管理系统根据集中部署 后的系统资源占用信息， 向处于空载状态的虚拟机发送下电指令， 关闭处于空 载状态的虚拟机。
606、信息技术设备层管理系统向基础设施层监控系统发送制冷调整指令。 在确认处于空载状态的虚拟机已经下电之后， IT设备层管理系统根据虚 拟机的部署情况向基础设施层监控系统发送制冷调整指令， 具体的：
若被关闭的虚拟机所在区域为空载区域，则向基础设施层监控系统发送第 一制冷调整指令，使得所述基础设施层监控系统关闭空载区域的制冷设备， 所 述空载区域为区域内所有虚拟机皆处于下电状态的区域；
若被关闭的虚拟机所在区域为轻载区域，则向基础设施层监控系统发送第 二制冷调整指令，使得所述基础设施层监控系统降低轻载区域的制冷效果， 所 述轻载区域为处于负载状态的虚拟机少于预置数量（预置数量可以根据实际情 况而定， 此处不作限定）的区域。 由于轻载区域仍有虚拟机在运行， 因此， 不 能关闭该区域的制冷设备； 而又由于该区域发生了热迁移， 负载状态的虚拟机 的数量较少， 因此， 可以降低该区域的制冷效果。
下面对用于执行上述节能监控方法的本发明节能监控装置的实施例进行 说明， 其结构请参考图 7, 本发明实施例中节能监控装置的一个实施例包括： 获取单元 701 , 用于获取 IT设备层管理系统的系统资源占用信息； 下电指示单元 702, 用于根据所述系统资源占用信息向所述 IT设备层管 理系统发送下电指令， 使得 IT设备层管理系统关闭处于空载状态的虚拟机； 反馈接收单元 703 , 用于接收 IT设备层管理系统发送的下电反馈消息； 运行状态， 向基础设施层监控系统发送制冷调整指令，使得所述基础设施层监 控系统调整所述被关闭虚拟机所在制冷区域的制冷部署。 可选的， 本发明实例中节能监控装置的制冷调整单元 704可以包括： 关闭指示模块 7041 , 用于若所述被关闭的虚拟机所在制冷区域为空载区 域， 则向所述基础设施层监控系统发送第一制冷调整指令，使得所述基础设施 层监控系统关闭空载区域的制冷设备，所述空载区域为区域内所有虚拟机皆处 于下电状态的区域；
调整指示模块 7042, 用于若所述被关闭的虚拟机所在制冷区域为轻载区 域， 则向所述基础设施层监控系统发送第二制冷调整指令，使得所述基础设施 层监控系统降低轻载区域的制冷效果，所述轻载区域为处于负载状态的虚拟机 少于预置数量的区域。
可选的， 本发明实例中节能监控装置还可以包括：
部署判断单元 705 , 用于根据所述系统资源占用信息判断是否需要改变虚 拟机的部署， 若是， 则触发集中部署单元；
集中部署单元 706, 用于根据所述系统资源占用信息指示所述 IT设备层 管理系统将处于负载状态的虚拟机集中部署，并在所述处于负载状态的虚拟机 完成集中部署之后， 触发所述下电指示单元 702。
那么， 此场景下， 所述获取单元 701还用于获取所述 IT设备层管理系统 集中部署之后的系统资源占用信息；
所述下电指示单元 702还用于根据所述 IT设备层管理系统集中部署之后 的系统资源占用信息， 向所述 IT设备层管理系统发送下电指令。
本发明实施例节能监控装置中各个单元具体的交互过程如下：
获取单元 701获取 IT设备层管理系统的系统资源占用信息。 可选的， 节 能监控装置可以向 IT设备层管理系统发送系统资源查询消息，查询 IT设备层 管理系统的系统资源占用信息； 节能监控装置也可以接收 IT设备层管理系统 定时推送的系统资源占用信息。
可选的， 所述系统资源占用信息可以为： IT设备层管理系统中各台虚拟 机的当前操作系统， 进程， 线程以及应用程序的利用率等信息， 由节能监控装 置对这些信息进行分析，得到 IT设备层管理系统中各个虚拟机的 CPU占用信 息和 /或内存占用信息；
或者， 所述系统资源占用信息也可以为： 各台虚拟机的 CPU占用信息和 / 或内存占用信息； 所述在 IT设备层管理系统接收到所述系统资源查询消息之 后， 由 IT设备层管理系统对本地运营中的各台虚拟机的当前操作系统， 进程， 线程以及应用程序的利用率等信息进行内部查询，从而得到各台虚拟机的 CPU 占用信息和 /或内存占用信息， 并通过系统资源占用信息向节能监控装置反馈 所述 CPU占用信息和 /或内存占用信息。
在获取到所述系统资源占用信息之后，下电指示单元 702根据所述系统资 源占用信息向所述 IT设备层管理系统发送下电指令，使得 IT设备层管理系统 关闭处于空载状态的虚拟机。
可选的， 在下电指示单元 702执行操作之前， 还可以由部署判断单元 705 根据所述系统资源占用信息判断是否需要改变虚拟机的部署， 若是， 则触发集 中部署单元 706; 若否， 则保持 IT设备层管理系统中各个虚拟机的状态不变， 结束流程。
在接收到所述系统资源占用信息之后，会根据所述系统资源占用信息确定 IT设备层管理系统中各个虚拟机的运行状态， 当处于空载和负载状态的虚拟 机之间的数量比满足预置条件时， 就可以确定需要改变虚拟机的部署； 其中， 负载状态还可以进一步包括轻载状态和重载状态，在考虑是否需要进行热迁移 时， 也可以进一步的考虑处于空载、 轻载和重载状态的虚拟机之间的数量比， 具体判断是否需要改变虚拟机的部署的参考条件可以根据实际需求而定，此处 不作限定。 其中， 上述判断虚拟机处于轻载状态还是重载状态， 可以通过设定 预设负载阈值的方式进行判定，如， 负载大于或等百分之五十的虚拟机处于重 载状态， 负载小于百分之五十的虚拟机处于轻载状态。
集中部署单元 706根据所述系统资源占用信息指示所述 IT设备层管理系 统将处于负载状态的虚拟机集中部署，并在所述处于负载状态的虚拟机完成集 中部署之后， 触发所述下电指示单元 702。 具体的， 集中部署单元 706可以通 过向 IT设备层管理系统发送携带有所述集中部署策略的发送热迁移指令， 指 示 IT设备层管理系统进行集中部署； 在确认了需要改变虚拟机的部署之后， 集中部署单元 706 可以根据所述系统资源占用信息确定需要执行集中部署的 虚拟机，进一步的，还可以根据需要执行集中部署的虚拟机确定集中部署策略。 本实施例中，对虚拟机集中部署可以采用虚拟机热迁移的方式，虚拟机热迁移 指的是将整个虚拟机的运行状态完整保存下来，同时可以快速的恢复到原有硬 件平台的另一台虚拟机或是不同硬件平台的虚拟机上；并且，在恢复的过程中， 虚拟机能够实现平滑的无中断的业务迁移，使得用户不会察觉到任何差异。 具 体的， 所述集中部署策略可以包括迁移的对象和迁移的规则， 而集中部署策略 中迁移的规则可以为：优先将所述服务器设备热迁移至靠近所述管理设备的区 域； 其次， 将所述服务器设备热迁移至靠近所述存储设备的区域； 再次， 将所 述服务器设备热迁移至靠近所述网络设备的区域。
在 IT设备层管理系统关闭了处于空载状态的虚拟机之后， 反馈接收单元 703会接收到 IT设备层管理系统发送的下电反馈消息； 随后， 则可以触发制 基础设施层监控系统发送制冷调整指令，使得所述基础设施层监控系统调整所 述被关闭虚拟机所在制冷区域的制冷部署。
可选的， 若所述被关闭的虚拟机所在制冷区域为空载区域， 则关闭指示模 块 7041向所述基础设施层监控系统发送第一制冷调整指令， 使得所述基础设 施层监控系统关闭空载区域的制冷设备，所述空载区域为区域内所有虚拟机皆 处于下电状态的区域；若所述被关闭的虚拟机所在制冷区域为轻载区域调整指 示模块 7042向所述基础设施层监控系统发送第二制冷调整指令， 使得所述基 础设施层监控系统降低轻载区域的制冷效果，所述轻载区域为处于负载状态的 虚拟机少于预置数量的区域。
下面对用于执行上述节能监控方法的本发明 IT设备层管理系统的实施例 进行说明， 其结构请参考图 8, 本发明实施例中 IT设备层管理系统的一个实 施例包括：
信息提供单元 801 , 用于向节能监控装置提供 IT设备层管理系统的系统 资源占用信息；
下电指示接收单元 802, 用于接收所述节能监控装置根据所述系统资源占 用信息发送的下电指令；
关闭单元 803, 用于根据所述下电指令关闭处于空载状态的虚拟机； 反馈单元 804, 用于向所述节能监控装置发送下电反馈消息， 以使得所述 础设施层监控系统发送制冷调整指令。
可选的， 本发明实施例中的 IT设备层管理系统还可以包括：
部署指示接收单元 805, 用于接收节能监控装置发送的将处于负载状态的 虚拟机集中部署的指示；
部署单元 806, 用于根据所述指示将处于负载状态的虚拟机集中部署。 此场景下， 所述信息提供单元 801 , 还用于向节能监控装置提供 IT设备 层管理系统的集中部署之后的系统资源占用信息；
下电指示接收单元 802, 还用于接收所述节能监控装置根据所述集中部署 之后的系统资源占用信息发送的下电指令。
本发明实施例节能监控装置中各个单元具体的操作过程如下：
信息提供单元 801向节能监控装置提供 IT设备层管理系统的系统资源占 用信息； 可选的， 信息提供单元 801可以定时主动向节能监控装置推送 IT设 备层管理系统的系统资源占用信息， 也可以在接收到系统资源查询消息之后， 在响应中携带该系统资源占用信息。
在向节能监控装置提供 IT设备层管理系统的系统资源占用信息之后， 下 电指示接收单元 802 可以接收到所述节能监控装置根据所述系统资源占用信 息发送的下电指令，则关闭单元 803可以根据所述下电指令关闭处于空载状态 的虚拟机。
可选的， 若实际应用中， 节能监控装置需要进行负载状态虚拟机的集中部 署， 则在接收到下电指令之前，部署指示接收单元 805可以接收到节能监控装 置发送的将处于负载状态的虚拟机集中部署的指示； 具体的，部署指示接收单 元 805接收到的可以为热迁移指令， 所述热迁移指令中可以包含有指示 IT设 备层管理系统执行集中部署策略,部署单元 806根据所述热迁移指令对所述 IT 设备层管理系统中的虚拟机进行热迁移， 使得处于负载状态的虚拟机集中部 署。 具体的， 虚拟机集中部署的方式取决于集中部署策略， 其中， 实现上述虚 拟机集中部署的热迁移规则可以有多种，所述集中部署策略可以包括迁移的对 象（即需要执行热迁移的虚拟机）和迁移的规则， 而集中部署策略中迁移的规 则可以为： 优先将所述服务器设备热迁移至靠近所述管理设备的区域； 其次， 将所述服务器设备热迁移至靠近所述存储设备的区域； 再次，将所述服务器设 备热迁移至靠近所述网络设备的区域。
在确认所述热迁移完成之后，可以向所述节能监控装置返回热迁移完成响 应，使得节能监控装置可以进行进一步的操作。
在接收到关闭指令之后，关闭单元 803根据所述下电指令关闭处于空载状 态的虚拟机； 在完成空载状态的虚拟机的关闭之后，反馈单元 804向所述节能 监控装置发送下电反馈消息，以使得所述节能监控装置根据被关闭虚拟机所在 制冷区域对应的虚拟机的运行状态， 向基础设施层监控系统发送制冷调整指 令，使得节能监控装置根据下电反馈消息向基础设施层监控系统发送制冷调整 指令， 调整制冷部署。
在本申请所提供的几个实施例中，应该理解到， 所揭露的装置和方法可以 通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如， 所述单元的划分，仅仅为一种逻辑功能划分， 实际实现时可以有另外的划分方 式， 例如多个单元或组件可以结合或者可以集成到另一个系统， 或一些特征可 以忽略， 或不执行。 另一点， 所显示或讨论的相互之间的耦合或直接耦合或通 信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性， 机才戒或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为 单元显示的部件可以是或者也可以不是物理单元， 即可以位于一个地方， 或者 也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部 单元来实现本实施例方案的目的。
另外， 在本发明各个实施例中的各功能单元可以集成在一个处理单元中， 也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元 中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的 形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售 或使用时， 可以存储在一个计算机可读取存储介质中。基于这样的理解， 本发 明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全 部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储 介质中， 包括若干指令用以使得一台计算机设备（可以是个人计算机，服务器， 或者网络设备等）执行本发明各个实施例所述方法的全部或部分步骤。 而前述 的存储介质包括： U盘、 移动硬盘、 只读存储器（ROM, Read-Only Memory ), 随机存取存储器（RAM, Random Access Memory ), 磁碟或者光盘等各种可以 存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于 此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内， 可轻易想到 变化或替换， 都应涵盖在本发明的保护范围之内。 因此， 本发明的保护范围应 所述以权利要求的保护范围为准。

Claims

权 利 要 求
1、 一种节能监控方法， 其特征在于， 包括：
获取 IT设备层管理系统的系统资源占用信息；
根据所述系统资源占用信息向所述 IT设备层管理系统发送下电指令， 使 得所述 IT设备层管理系统关闭处于空载状态的虚拟机；
接收所述 IT设备层管理系统发送的下电反馈消息， 根据被关闭虚拟机所 在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷调整指 令，使得所述基础设施层监控系统调整所述被关闭虚拟机所在制冷区域的制冷 部署。
2、 根据权利要求 1所述的方法， 其特征在于， 所述根据被关闭虚拟机所 在制冷区域对应的虚拟机的运行状态，向基础设施层监控系统发送制冷调整指 令， 使得所述基础设施层监控系统调整被关闭的虚拟机所在区域的制冷部署， 包括：
若所述被关闭的虚拟机所在制冷区域为空载区域，则向所述基础设施层监 控系统发送第一制冷调整指令，使得所述基础设施层监控系统关闭空载区域的 制冷设备， 所述空载区域为所有虚拟机皆处于下电状态的区域；
若所述被关闭的虚拟机所在制冷区域为轻载区域，则向所述基础设施层监 控系统发送第二制冷调整指令，使得所述基础设施层监控系统降低轻载区域的 制冷效果， 所述轻载区域为处于负载状态的虚拟机少于预置数量的区域。
3、 根据权利要求 1或 2所述的方法， 其特征在于， 所述根据系统资源占 用信息向所述 IT设备层管理系统发送下电指令之前， 包括：
根据所述系统资源占用信息判断是否需要改变虚拟机的部署， 若是， 则根 据所述系统资源占用信息指示所述 IT设备层管理系统将处于负载状态的虚拟 机集中部署， 在所述处于负载状态的虚拟机完成集中部署之后， 获取所述 IT 设备层管理系统集中部署之后的系统资源占用信息；
则所述根据所述系统资源占用信息向所述 IT设备层管理系统发送下电指 令包括：
根据所述 IT设备层管理系统集中部署之后的系统资源占用信息， 向所述 IT设备层管理系统发送下电指令。
4、 根据权利要求 3所述的方法， 其特征在于， 所述根据系统资源占用信 息指示所述 IT设备层管理系统将处于负载状态的虚拟机集中部署， 包括： 根据所述系统资源占用信息确定虚拟机的集中部署策略；
向所述 IT设备层管理系统发送携带所述集中部署策略的热迁移指令， 使 得处于负载状态的虚拟机执行热迁移以实现所述集中部署。
5、 根据权利要求 4所述的方法， 其特征在于，
所述虚拟机包括： 服务器设备， 管理设备， 网络设备和存储设备； 根据所述系统资源占用信息确定虚拟机的集中部署策略包括：
根据所述系统资源占用信息确定待迁移的服务器设备，
所述集中部署策略包括：优先将所述待迁移的服务器设备热迁移至靠近所 述管理设备的区域；次优先将所述待迁移的服务器设备热迁移至靠近所述存储 设备的区域； 再次，将所述待迁移的服务器设备热迁移至靠近所述网络设备的 区域。
6、 根据权利要求 3所述的方法， 其特征在于，
所述系统资源占用信息包括： 所述 IT设备层管理系统中虚拟机的中央处 理器 CPU占用信息和 /或内存占用信息；
所述根据系统资源占用信息判断是否需要执行虚拟机的热迁移， 包括： 才艮据所述 CPU占用信息和 /或内存占用信息分别确定处于空载状态和处于 负载状态的虚拟机的数目；
当处于空载状态的虚拟机和处于负载状态的虚拟机的比例满足预置的条 件时， 则确认需要改变虚拟机的部署。
7、 根据权利要求 6所述的方法， 其特征在于， 所述根据 CPU占用信息和 /或内存占用信息分别确定处于空载状态和处于负载状态的虚拟机的数量， 包 括：
若所述虚拟机的 CPU占用信息和 /或内存占用信息到达预置的空载条件， 则初步确定所述虚拟机处于空载状态， 间隔预置时长后，再次获取所述虚拟机 的 CPU占用信息和 /或内存占用信息， 若再次获取到的 CPU占用信息和 /或内 存占用信息仍满足预置的空载条件， 则确定所述虚拟机处于空载状态；
若所述虚拟机的 CPU占用信息和 /或内存占用信息到达预置的负载条件， 则初步确定所述虚拟机处于负载状态， 间隔预置时长后，再次获取所述虚拟机 的 CPU占用信息和 /或内存占用信息， 若再次获取到的 CPU占用信息和 /或内 存占用信息仍满足预置的负载条件， 则确定所述虚拟机处于负载状态；
分别统计处于空载状态的虚拟机和处于负载状态的虚拟机的数量。
8、 根据权利要求 1至 7任意一项所述的方法， 其特征在于， 所述下电反 馈消息携带有执行下电的虚拟机所在机拒的机拒编号，所述虚拟机所在机拒对 应于所述虚拟机所在的制冷区域；
检测所述机拒编号与空载状态的虚拟机的标识是否匹配， 若是， 则触发所 控系统发送制冷调整指令的步骤。
9、 一种节能监控方法， 其特征在于， 包括：
向节能监控装置提供 IT设备层管理系统的系统资源占用信息；
接收所述节能监控装置根据所述系统资源占用信息发送的下电指令； 根据所述下电指令关闭处于空载状态的虚拟机，并向所述节能监控装置发 送下电反馈消息，以使得所述节能监控装置根据被关闭虚拟机所在制冷区域对 应的虚拟机的运行状态， 向基础设施层监控系统发送制冷调整指令。
10、 根据权利要求 9所述的方法， 其特征在于， 所述系统资源占用信息中 携带有所述 IT设备层管理系统中各虚拟机的 CPU 占用信息和 /或内存占用信 息。
11、 根据权利要求 9或 10所述的方法， 其特征在于， 所述接收所述节能 监控装置根据所述系统资源占用信息发送的下电指令之前， 还包括：
接收节能监控装置发送的将处于负载状态的虚拟机集中部署的指示，并根 据所述指示将处于负载状态的虚拟机集中部署。
12、 根据权利要求 11所述的方法， 其特征在于， 所述接收节能监控装置 发送的将处于负载状态的虚拟机集中部署的指示，并根据所述指示将处于负载 状态的虚拟机集中部署， 包括：
接收节能监控装置发送的热迁移指令，所述热迁移指令中携带有虚拟机的 集中部署策略；
根据所述集中部署策略向需要执行热迁移的虚拟机发送热迁移消息，使得 处于负载状态的虚拟机集中部署。
13、 根据权利要求 12所述的方法， 其特征在于，
所述虚拟机包括： 服务器设备， 管理设备， 网络设备和存储设备； 所述集中部署策略包括：优先将待迁移的服务器设备热迁移至靠近所述管 理设备的区域； 其次，将所述待迁移的服务器设备热迁移至靠近所述存储设备 的区域；再次，将所述待迁移的服务器设备热迁移至靠近所述网络设备的区域。
14、 根据权利要求 11所述的方法， 其特征在于， 还包括：
向所述节能监控装置提供所述 IT设备层管理系统的集中部署之后的系统 资源占用信息， 以使得所述节能监控装置根据所述 IT设备层管理系统集中部 署之后的系统资源占用信息， 向所述 IT设备层管理系统发送下电指令。
15、 一种节能监控装置， 其特征在于， 包括：
获取单元， 用于获取 IT设备层管理系统的系统资源占用信息；
下电指示单元， 用于根据所述系统资源占用信息向所述 IT设备层管理系 统发送下电指令， 使得所述 IT设备层管理系统关闭处于空载状态的虚拟机； 反馈接收单元， 用于接收所述 IT设备层管理系统发送的下电反馈消息； 状态， 向基础设施层监控系统发送制冷调整指令，使得所述基础设施层监控系 统调整所述被关闭虚拟机所在制冷区域的制冷部署。
16、 根据权利要求 15所述的装置， 其特征在于， 所述制冷调整单元包括： 关闭指示模块， 用于若所述被关闭的虚拟机所在制冷区域为空载区域， 则 向所述基础设施层监控系统发送第一制冷调整指令，使得所述基础设施层监控 系统关闭空载区域的制冷设备，所述空载区域为所有虚拟机皆处于下电状态的 区域；
调整指示模块， 用于若所述被关闭的虚拟机所在制冷区域为轻载区域， 则 向所述基础设施层监控系统发送第二制冷调整指令，使得所述基础设施层监控 系统降低轻载区域的制冷效果，所述轻载区域为处于负载状态的虚拟机少于预 置数量的区域。
17、 根据权利要求 15或 16所述的装置， 其特征在于， 所述装置还包括： 部署判断单元，用于根据所述系统资源占用信息判断是否需要改变虚拟机 的部署， 若是， 则触发集中部署单元；
集中部署单元， 用于根据所述系统资源占用信息指示所述 IT设备层管理 系统将处于负载状态的虚拟机集中部署；
则， 所述获取单元还用于获取所述 IT设备层管理系统集中部署之后的系 统资源占用信息；
所述下电指示单元还用于根据所述 IT设备层管理系统集中部署之后的系 统资源占用信息， 向所述 IT设备层管理系统发送下电指令。
18、 一种信息技术设备层管理系统， 其特征在于， 包括：
信息提供单元， 用于向节能监控装置提供 IT设备层管理系统的系统资源 占用信息；
下电指示接收单元，用于接收所述节能监控装置根据所述系统资源占用信 息发送的下电指令；
关闭单元， 用于根据所述下电指令关闭处于空载状态的虚拟机； 反馈单元， 用于向所述节能监控装置发送下电反馈消息， 以使得所述节能 施层监控系统发送制冷调整指令。
19、 根据权利要求 18所述的系统， 其特征在于， 所述系统还包括： 部署指示接收单元，用于接收节能监控装置发送的将处于负载状态的虚拟 机集中部署的指示，
部署单元， 用于根据所述指示将处于负载状态的虚拟机集中部署； 贝' J , 所述信息提供单元， 还用于向节能监控装置提供 IT设备层管理系统 的集中部署之后的系统资源占用信息；
下电指示接收单元，还用于接收所述节能监控装置根据所述集中部署之后 的系统资源占用信息发送的下电指令。
PCT/CN2011/084888 2011-12-29 2011-12-29 一种节能监控方法以及设备 WO2013097134A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
CN2011800033122A CN102893229B (zh) 2011-12-29 2011-12-29 一种节能监控方法以及设备
PCT/CN2011/084888 WO2013097134A1 (zh) 2011-12-29 2011-12-29 一种节能监控方法以及设备
EP11878330.7A EP2712122B1 (en) 2011-12-29 2011-12-29 Energy saving monitoring method and device
US14/140,787 US9411344B2 (en) 2011-12-29 2013-12-26 Energy saving monitoring method and device
US15/205,008 US9917704B2 (en) 2011-12-29 2016-07-08 Energy saving monitoring method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2011/084888 WO2013097134A1 (zh) 2011-12-29 2011-12-29 一种节能监控方法以及设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14/140,787 Continuation US9411344B2 (en) 2011-12-29 2013-12-26 Energy saving monitoring method and device

Publications (1)

Publication Number Publication Date
WO2013097134A1 true WO2013097134A1 (zh) 2013-07-04

Family

ID=47535595

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2011/084888 WO2013097134A1 (zh) 2011-12-29 2011-12-29 一种节能监控方法以及设备

Country Status (4)

Country Link
US (2) US9411344B2 (zh)
EP (1) EP2712122B1 (zh)
CN (1) CN102893229B (zh)
WO (1) WO2013097134A1 (zh)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015112614A1 (en) 2014-01-21 2015-07-30 Oracle International Corporation System and method for supporting multi-tenancy in an application server, cloud, or other environment
US11057272B2 (en) * 2014-09-26 2021-07-06 Oracle International Corporation System and method for transactions in a multitenant application server environment
CN105528054B (zh) * 2015-12-25 2018-09-11 珠海国芯云科技有限公司 集群系统综合调度节能方法及装置
CN106850322B (zh) * 2017-04-06 2020-05-12 上海烟草集团有限责任公司 基于六层模型的资源设备管理系统
CN110119301A (zh) * 2018-02-07 2019-08-13 卓望数码技术（深圳）有限公司 一种虚拟机迁移方法及系统
JP7104327B2 (ja) * 2018-10-19 2022-07-21 富士通株式会社 情報処理装置、仮想マシン管理プログラムおよび仮想マシン管理方法
CN110187726B (zh) * 2019-05-17 2020-08-18 安徽京仪自动化装备技术有限公司 一种用于半导体温控装置的温度控制算法
US11461210B2 (en) 2019-06-26 2022-10-04 Kyndryl, Inc. Real-time calculation of data center power usage effectiveness

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011043317A1 (ja) * 2009-10-07 2011-04-14 日本電気株式会社 省電力化システム、及び省電力化方法
CN102096461A (zh) * 2011-01-13 2011-06-15 浙江大学 基于虚拟机迁移和负载感知整合的云数据中心节能方法
CN102193525A (zh) * 2010-03-05 2011-09-21 朗德华信（北京）自控技术有限公司 基于云计算的设备监控系统及方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7203944B1 (en) * 2003-07-09 2007-04-10 Veritas Operating Corporation Migrating virtual machines among computer systems to balance load caused by virtual machines
US7437730B2 (en) * 2003-11-14 2008-10-14 International Business Machines Corporation System and method for providing a scalable on demand hosting system
JP4895266B2 (ja) * 2005-12-28 2012-03-14 富士通株式会社 管理システム、管理プログラムおよび管理方法
US8296760B2 (en) * 2006-10-27 2012-10-23 Hewlett-Packard Development Company, L.P. Migrating a virtual machine from a first physical machine in response to receiving a command to lower a power mode of the first physical machine
CN102057367A (zh) * 2008-04-10 2011-05-11 惠普开发有限公司 依照环境数据的虚拟机迁移
JP2010097533A (ja) * 2008-10-20 2010-04-30 Hitachi Ltd パーティションで区切られた計算機システムにおけるアプリケーション移動及び消費電力の最適化
US9778718B2 (en) * 2009-02-13 2017-10-03 Schneider Electric It Corporation Power supply and data center control
US8850426B2 (en) * 2009-12-13 2014-09-30 International Business Machines Corporation Managing remote deployment of a virtual machine and service request to be processed by the virtual machines based on network bandwith and storage connectivity
CN102096416A (zh) * 2011-01-31 2011-06-15 中国恩菲工程技术有限公司 太阳能电池组件的控制方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011043317A1 (ja) * 2009-10-07 2011-04-14 日本電気株式会社 省電力化システム、及び省電力化方法
CN102193525A (zh) * 2010-03-05 2011-09-21 朗德华信（北京）自控技术有限公司 基于云计算的设备监控系统及方法
CN102096461A (zh) * 2011-01-13 2011-06-15 浙江大学 基于虚拟机迁移和负载感知整合的云数据中心节能方法

Also Published As

Publication number Publication date
US20140107855A1 (en) 2014-04-17
US9917704B2 (en) 2018-03-13
EP2712122A4 (en) 2014-07-23
EP2712122B1 (en) 2016-08-31
EP2712122A1 (en) 2014-03-26
US9411344B2 (en) 2016-08-09
US20160323119A1 (en) 2016-11-03
CN102893229A (zh) 2013-01-23
CN102893229B (zh) 2013-12-04

Similar Documents

Publication Publication Date Title
WO2013097134A1 (zh) 一种节能监控方法以及设备
JP5496518B2 (ja) 集中電力管理方法、装置側エージェント、集中電力管理コントローラ及び集中電源管理システム
Boru et al. Energy-efficient data replication in cloud computing datacenters
US8527793B2 (en) Method for saving power in a system by placing inactive computing devices in optimized configuration corresponding to a specific constraint
CA2522467C (en) Automated power control policies based on application-specific redundancy characteristics
JP4922255B2 (ja) 情報処理システムおよびそのシステムにおける省電力制御方法
US8250382B2 (en) Power control of servers using advanced configuration and power interface (ACPI) states
US9274585B2 (en) Combined dynamic and static power and performance optimization on data centers
Mukherjee et al. Model-driven coordinated management of data centers
US10148531B1 (en) Partitioned performance: adaptive predicted impact
Jin et al. Energy-efficient task scheduling for CPU-intensive streaming jobs on Hadoop
Lin et al. Eafr: An energy-efficient adaptive file replication system in data-intensive clusters
Abdullah et al. An energy efficient message scheduling algorithm considering node failure in IoT environment
CN111400036A (zh) 基于服务器集群的云应用管理系统、方法、装置及介质
US10033620B1 (en) Partitioned performance adaptive policies and leases
Yu et al. An energy-aware algorithm for optimizing resource allocation in software defined network
WO2011076589A1 (en) Advanced disk drive power management based on maximum system throughput
US11567553B2 (en) Power supply unit power level protection limits
Chaudhry et al. Considering thermal-aware proactive and reactive scheduling and cooling for green data-centers
He et al. Joint optimization of energy saving and load balancing for data center networks based on software defined networks
Villebonnet et al. Thermal-aware cloud middleware to reduce cooling needs
Leite et al. Power‐aware server consolidation for federated clouds
US11586274B2 (en) Managing server performance and reliability during reductions in a number of power supply units
Nzanywayingoma et al. A literature survey on resource management techniques, issues and challenges in cloud computing
Islam et al. Distributed resource management in data center with temperature constraint

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 201180003312.2

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 11878330

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2011878330

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2011878330

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE