Machine room temperature control method and device, storage medium and electronic equipment
By collecting data on the air intake and component temperatures of the equipment, local hotspots can be identified and addressed, solving the problem of difficulty in identifying heat sources in IT equipment in existing technologies and achieving effective control of the computer room temperature.
Patent Information
- Application Number
- CN202211383986.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-07
- Publication Date
- 2026-02-13
- Estimated Expiration
- 2042-11-07
AI Technical Summary
Existing computer room temperature control methods struggle to identify localized hotspots caused by IT equipment in a timely manner, resulting in poor temperature control performance.
By collecting the air intake temperature and component temperature of the equipment, it is determined whether the equipment and cabinet meet the conditions for local hot spots, and equipment anomaly inspection and cooling treatment are carried out. The cooling system is used to cool down the hot spot equipment and cabinet in a targeted manner.
Timely identification and handling of local hot spots improves the effectiveness of computer room temperature control, ensuring that equipment operates within a suitable temperature range.
Smart Images

Figure CN115666097B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of equipment operation and maintenance, in particular to a method and device for temperature control of a computer room, a storage medium and an electronic device. BACKGROUND
[0002] A computer room of a data center is a working place of enterprise data processing equipment and electronic communication equipment, and has a large heat load, so that the temperature of the computer room needs to be adjusted all the year round to be suitable. An air conditioning system is usually deployed in the computer room, and a common temperature control method is to detect the environment temperature of the computer room by the air conditioning system, and to adjust the refrigeration effect based on the environment temperature to realize temperature control.
[0003] However, the temperature distribution inside the computer room is actually uneven, and a local area with excessively high temperature is called a local hot spot. The local hot spot is likely to bring adverse effects to the operation of the data center, so the processing of the local hot spot has become one of the keys to the temperature control of the computer room. In the scenario considering the local hot spot, the existing computer room temperature control method usually identifies whether there is a local hot spot by the inlet air temperature of the cabinet, so as to adjust the refrigeration effect of the air conditioning system to eliminate the local hot spot and realize the temperature control of the computer room.
[0004] The inventors have found that the heat source of the local hot spot is usually the IT equipment. In the existing computer room temperature control method, the local hot spot is processed based on the inlet air temperature of the cabinet, and the inlet air temperature of the cabinet is usually lower than the temperature of the IT equipment. When the IT equipment has high temperature or high temperature trend, it is difficult to identify the local hot spot in time, and the temperature control effect is poor. SUMMARY
[0005] Therefore, the embodiments of the present application provide a computer room temperature control method to solve the problem that the existing computer room temperature control method is difficult to identify the local hot spot with the IT equipment as the heat source in time and the temperature control effect is poor.
[0006] The embodiments of the present application also provide a computer room temperature control device to ensure the implementation and application of the above method in practice.
[0007] To achieve the above object, the embodiments of the present application provide the following technical solutions:
[0008] A computer room temperature control method comprises the following steps:
[0009] In the case of needing to control the temperature of the computer room, a plurality of computer room modules corresponding to the computer room are determined, each computer room module comprises a plurality of cabinets, and a plurality of devices are arranged in each cabinet;
[0010] For each device deployed in each of the cabinets, determine a current device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set including a plurality of device component temperatures corresponding to the device;
[0011] For each device deployed in each of the cabinets, determine a current device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set including a plurality of device component temperatures corresponding to the device;
[0012] For each of the cabinets, determine whether the cabinet meets a preset cabinet local hotspot condition according to the device inlet air temperature corresponding to each device deployed in the cabinet, and if the cabinet meets the preset cabinet local hotspot condition, determine the cabinet as a hotspot cabinet;
[0013] According to a preset device detection strategy, perform device anomaly checking on each of the hotspot devices to obtain an anomaly checking result corresponding to each of the hotspot devices;
[0014] For each of the hotspot devices, perform anomaly processing on the hotspot device according to the anomaly checking result corresponding to the hotspot device, so that the hotspot device is in a normal operating state, to reduce the operating temperature of the hotspot device;
[0015] By a preset refrigeration system, perform cooling processing on each of the hotspot cabinets to reduce the ambient temperature of each of the hotspot cabinets, to complete the temperature control process.
[0016] The above method can optionally include the following steps:
[0017] Determine a device model corresponding to the device;
[0018] In a plurality of device temperature collection instructions, determine a target device temperature collection instruction corresponding to the device model; each device temperature collection instruction is a hardware management interface operation instruction based on an intelligent platform management interface;
[0019] According to the target device temperature collection instruction, create a device temperature collection task corresponding to the device;
[0020] Execute the device temperature collection task to obtain a device temperature collection result corresponding to the device;
[0021] In the device temperature collection result, obtain the device inlet air temperature corresponding to the device;
[0022] In the device temperature collection result, a plurality of device component temperatures corresponding to the device are obtained, and the plurality of device component temperatures corresponding to the device form a component temperature set corresponding to the device.
[0023] Optionally, the method further comprises:
[0024] For each device component temperature in the component temperature set corresponding to the device, a component temperature threshold corresponding to the device component temperature is determined, and it is determined whether the device component temperature is greater than the component temperature threshold corresponding thereto.
[0025] It is determined whether the target device component temperature exists in the component temperature set corresponding to the device.
[0026] Optionally, the method further comprises:
[0027] For each device deployed in the cabinet, a device inlet temperature threshold corresponding to the device is determined, and it is determined whether the device inlet temperature corresponding to the device is greater than the device inlet temperature threshold.
[0028] It is determined whether the local hotspot device exists in the cabinet.
[0029] Optionally, the method further comprises:
[0030] In the plurality of floor air outlets included in the preset refrigeration system, a floor air outlet corresponding to each hotspot cabinet is determined.
[0031] For each hotspot cabinet, a device position corresponding to a local hotspot device of the hotspot cabinet is determined, and based on the device position corresponding to the local hotspot device and the device inlet temperature, outlet information corresponding to the floor air outlet corresponding to the hotspot cabinet is determined, the outlet information including an outlet direction and an outlet amount.
[0032] Based on the outlet information corresponding to the floor air outlet corresponding to each hotspot cabinet, a refrigeration adjustment instruction is generated.
[0033] sending the refrigeration adjustment instruction to the preset refrigeration system, so that the preset refrigeration system controls air outlet of a floor air outlet corresponding to each hot spot cabinet to perform cooling processing on each hot spot cabinet.
[0034] Optionally, the method further comprises:
[0035] determining a cabinet inlet air temperature corresponding to each cabinet;
[0036] For each data center module, determining whether the data center module meets a preset module local hot spot condition according to the cabinet inlet air temperature corresponding to each cabinet included in the data center module, and if the data center module meets the preset module local hot spot condition, determining the data center module as a hot spot module.
[0037] performing cooling processing on each hot spot module by the preset refrigeration system to reduce the ambient temperature of each hot spot module.
[0038] Optionally, the method further comprises:
[0039] For each cabinet included in the data center module, determining whether the cabinet inlet air temperature corresponding to the cabinet is greater than a preset module temperature threshold, and if the cabinet inlet air temperature corresponding to the cabinet is greater than the preset module temperature threshold, determining the cabinet as a local hot spot cabinet.
[0040] determining whether there is the local hot spot cabinet in each cabinet included in the data center module, and if there is the local hot spot cabinet in each cabinet included in the data center module, determining that the data center module meets the preset module local hot spot condition.
[0041] A data center temperature control device comprises:
[0042] a first determination unit configured to determine a plurality of data center modules corresponding to a data center in a case where temperature control of the data center is needed, each data center module comprising a plurality of cabinets, and each cabinet comprising a plurality of devices;
[0043] a second determination unit configured to determine, for each device arranged in each cabinet, a device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set comprising a plurality of device component temperatures corresponding to the device;
[0044] The first judging unit is configured to judge, for each device deployed in each cabinet, whether the device meets a preset device local hotspot condition according to a component temperature set corresponding to the device, and determine the device as a hotspot device if the device meets the preset device local hotspot condition.
[0045] The second judging unit is configured to judge, for each cabinet, whether the cabinet meets a preset cabinet local hotspot condition according to an equipment inlet temperature corresponding to each device deployed in the cabinet, and determine the cabinet as a hotspot cabinet if the cabinet meets the preset cabinet local hotspot condition.
[0046] The abnormality checking unit is configured to perform device abnormality checking on each hotspot device according to a preset device detection strategy, and obtain an abnormality checking result corresponding to each hotspot device.
[0047] The abnormality processing unit is configured to perform abnormality processing on each hotspot device according to an abnormality checking result corresponding to the hotspot device, so that the hotspot device is in a normal operation state, and the operation temperature of the hotspot device is reduced.
[0048] The cooling processing unit is configured to perform cooling processing on each hotspot cabinet by a preset refrigeration system, so as to reduce the environment temperature of each hotspot cabinet, and complete the temperature control process.
[0049] A storage medium includes stored instructions, wherein the instructions, when executed, control a device in which the storage medium is located to perform the data center temperature control method.
[0050] An electronic device includes a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the data center temperature control method.
[0051] Based on the above-mentioned machine room temperature control method provided by the embodiment of the application, the method comprises the following steps: determining a plurality of machine room modules corresponding to the machine room, each machine room module comprising a plurality of cabinets, and a plurality of devices being arranged in each cabinet; determining a device inlet air temperature corresponding to each device and a component temperature set corresponding to each device, the component temperature set corresponding to each device comprising a plurality of device component temperatures corresponding to the device; judging whether each device meets a preset device local hotspot condition according to the component temperature set corresponding to each device, and determining a device meeting the device local hotspot condition as a hotspot device; judging whether each cabinet meets a preset cabinet local hotspot condition according to the device inlet air temperature corresponding to each device arranged in each cabinet, and determining a cabinet meeting the cabinet local hotspot condition as a hotspot cabinet; performing device anomaly checking on each hotspot device according to a preset device detection strategy to obtain an anomaly checking result corresponding to each hotspot device; for each hotspot device, performing anomaly processing according to the anomaly checking result corresponding to the hotspot device, so that the hotspot device is in a normal operating state, so as to reduce the device operating temperature; and performing cooling processing on each hotspot cabinet by a preset refrigeration system, so as to reduce the environment temperature of each hotspot cabinet. By applying the method provided by the embodiment of the application, whether there is a local hotspot can be identified based on the inlet air temperature and the component temperature of the device in the cabinet, and the device inlet air temperature associated local hotspot and the component temperature associated local hotspot can be processed respectively. The identification of the local hotspot is based on the related temperature of the device, and when the device has a high temperature or a high temperature trend, the local hotspot can be identified in time, temperature control can be performed in time, the local hotspot can be eliminated or reduced, the temperature of the machine room can be controlled in a suitable range, and the temperature control effect is good. BRIEF DESCRIPTION OF DRAWINGS
[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.
[0053] Figure 1 The method flowchart of the machine room temperature control method provided by the embodiment of the present application;
[0054] Figure 2 The schematic diagram of the IT device local hotspot provided by the embodiment of the present application;
[0055] Figure 3 The schematic diagram of the cabinet local hotspot provided by the embodiment of the present application;
[0056] Figure 4 The schematic diagram of the module local hotspot provided by the embodiment of the present application;
[0057] Figure 5 An example diagram of a machine room temperature control process provided for an embodiment of the present application;
[0058] Figure 6 Another example diagram of a machine room temperature control process provided for an embodiment of the present application;
[0059] Figure 7 A structural schematic diagram of a machine room temperature control device provided for an embodiment of the present application;
[0060] Figure 8 A structural schematic diagram of an electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION
[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.
[0062] In the present application, the terms “comprising”, “containing” or any other variants thereof are intended to cover non-exclusive containing, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement “including a…” does not exclude the presence of another identical element in the process, method, article or device including the element.
[0063] As known from the background, eliminating local hot spots is one of the goals of machine room temperature control. In actual scenarios, it is usually due to different heating powers of different devices and different business loads. Devices with high power and high load are usually at a high operating temperature. If these devices are placed in a local area, it is easy to cause overheating in the local area of the machine room, resulting in serious problems such as hardware damage or shutdown of some devices due to overheating. In the traditional data center operation process, when judging whether there is a local hot spot in the machine room, only the machine room environment temperature is generally considered, and the cabinet inlet temperature is focused on. However, the cabinet inlet temperature is usually lower than the relevant temperature of the device, so it is difficult to identify local hot spots in time. Secondly, the local hot spot is currently handled in the way of reducing the air conditioner temperature and optimizing the air flow organization. However, if the device itself or its surrounding heat generation is high due to device component failure or high load of the deployed business, the traditional way of handling local hot spots often treats the symptoms but not the root cause, and it is difficult to achieve good temperature control effect.
[0064] Therefore, the embodiment of the present application provides a method for controlling temperature of a machine room, which can identify local hot spots and perform targeted processing by collecting relevant temperatures of equipment, so that the local hot spots can be identified in time and the temperature control effect is improved.
[0065] The embodiment of the present application provides a method for controlling temperature of a machine room, which can be applied to a machine room temperature control system, and the execution subject of the method can be a server of the system. Figure 1
[0066] S101: In the case of needing to control temperature of a machine room, a plurality of machine room modules corresponding to the machine room are determined, each of the machine room modules comprising a plurality of cabinets, and each of the cabinets deploying a plurality of equipment;
[0067] In the method provided by the embodiment of the present application, the machine room of the data center is divided into a plurality of machine room modules, the machine room module refers to a physical space of the machine room for storing a specific group of cabinets, each of the machine room modules comprises a plurality of cabinets, and each of the cabinets deploys a plurality of equipment, and the equipment is an IT equipment such as a server, a switch, a router and the like.
[0068] S102: For each of the equipment deployed in each of the cabinets, a device inlet temperature corresponding to the equipment and a component temperature set corresponding to the equipment are determined, and the component temperature set comprises a plurality of equipment component temperatures corresponding to the equipment;
[0069] In the method provided by the embodiment of the present application, temperature collection is performed for each of the equipment in the machine room (i.e., each of the equipment on each of the cabinets in each of the machine room modules), and the device inlet temperature and the component temperature set corresponding to each of the equipment are obtained. The equipment deploys an air inlet and an air outlet, and the device inlet temperature corresponding to the equipment is the air temperature of the air inlet of the equipment. The component temperature set corresponding to the equipment comprises the temperature of each equipment component of the equipment, i.e., the equipment component temperature refers to the temperature of the equipment component, and the equipment component comprises a CPU, a hard disk, a memory and the like.
[0070] S103: For each of the equipment deployed in each of the cabinets, whether the equipment meets a preset equipment local hot spot condition is judged according to the component temperature set corresponding to the equipment, and if the equipment meets the preset equipment local hot spot condition, the equipment is determined as a hot spot equipment;
[0071] In the method provided by this invention, local hotspot conditions are pre-set according to actual needs. These conditions define what conditions must be met for a set of component temperatures corresponding to a device to be considered a local hotspot at the device level. For example, a component average threshold is set; when the average temperature of all device components in the component temperature set exceeds this threshold, the condition is considered met. Alternatively, a maximum temperature value is set; when the temperature of the device component with the highest temperature value in the component temperature set exceeds a preset maximum temperature value, the condition is considered met. It should be noted that in specific implementations, local hotspot conditions can be set according to actual needs without affecting the functionality of the method provided by this invention.
[0072] In the method provided by this invention, for each device in the computer room, the set of component temperatures is determined to match the conditions for a local hotspot. If they match, the corresponding device is determined to meet the local hotspot condition. When a device meets the local hotspot condition, it is considered a hotspot device, meaning that the device is considered to have a local hotspot.
[0073] S104: For each of the cabinets, based on the air intake temperature of each device deployed in the cabinet, determine whether the cabinet meets the preset cabinet local hot spot conditions. If the cabinet meets the preset cabinet local hot spot conditions, then the cabinet is identified as a hot spot cabinet.
[0074] In the method provided by this embodiment of the invention, rack local hotspot conditions are pre-set according to actual needs. These conditions define the conditions under which the inlet air temperature of devices within the rack is considered to constitute a rack-level local hotspot. For example, a device average threshold is set; when the average inlet air temperature of all devices in the rack exceeds this threshold, the condition is considered met. It should be noted that in specific implementations, rack local hotspot conditions can be set according to actual needs without affecting the functionality of the method provided by this embodiment of the invention.
[0075] In the method provided by this embodiment of the invention, for each rack in the data center (i.e., each rack in each data center module), it is determined whether the air intake temperature of each device in the rack matches the conditions of the local hot spot condition of the rack. If they match, the rack is determined to meet the local hot spot condition. When a rack meets the local hot spot condition, it is considered a hot spot rack, that is, it is believed that the rack has a local hot spot.
[0076] S105: Based on the preset device detection strategy, perform device anomaly checks on each of the hotspot devices to obtain the anomaly check results corresponding to each of the hotspot devices;
[0077] The method provided by the embodiment of the application has the device detection strategy preset according to actual needs, including scripts for multiple detections of the device, and the detection items in the device detection strategy can include hardware health state checking, power consumption querying, CPU load checking, memory load checking, hard disk bandwidth checking, network card flow checking, etc. For each hotspot device, abnormal checking can be performed on the hotspot device according to the preset device detection strategy, and the corresponding abnormal checking result of the hotspot device is obtained, which can include the checking results of the detection items.
[0078] S106: For each hotspot device, abnormal processing is performed on the hotspot device according to the corresponding abnormal checking result of the hotspot device, so that the hotspot device is in a normal operation state, thereby reducing the operation temperature of the hotspot device.
[0079] In the method provided by the embodiment of the application, the abnormal processing scripts of various checking items are preset. According to the abnormal checking result of each hotspot device, the corresponding abnormal checking item of each hotspot device is determined, and the abnormal checking item refers to the checking item with an abnormal checking result. For each hotspot device, the abnormal processing script corresponding to the corresponding abnormal checking item of the hotspot device is called to perform abnormal processing on the hotspot device. The abnormal processing script can be a script directly performing processing operation, which can directly eliminate the abnormal state and restore the hotspot device to normal operation. For the checking item that cannot be automatically disposed, the corresponding abnormal processing script can further check the abnormal result, and send a disposal prompt to an operation and maintenance personnel according to the checking result, so that the operation and maintenance personnel process the abnormality and restore the device to a normal state. When the hotspot device is in a normal operation state, the heat generation of each device component of the hotspot device should be in a normal range, so the operation temperature of the hotspot device can be reduced.
[0080] In the method provided by the embodiment of the application, the content of abnormal processing can specifically include:
[0081] The script is called to generate a maintenance suggestion (whether to stop maintenance, how long to stop, how to maintain, etc. according to the hardware redundancy) when a hardware fault is found in the checking;
[0082] The script is called to query the power consumption data of the device in the past month, and it is detected whether there is an abnormal value, and a prompt is issued when the power consumption of the device is found to be too high in the checking;
[0083] The script is called to check and close abnormal processes, and the script is called to start overclocking to improve performance when the CPU load is found to be high in the checking;
[0084] The script is called to find a program process occupying a large amount of memory when the memory load is found to be high in the checking, and according to the finding result, the script automatically sets the recycling time, the maximum memory usage value and the common process pool, so as to reduce the occupation of the memory;
[0085] The check finds that the hard disk bandwidth is too high, a script is called to obtain the hard disk SMART log, whether the hard disk is a hidden bad disk is checked, and whether the hard disk is a hidden bad disk result is sent;
[0086] The check finds that the network card flow is too high, a script is called to check whether there is abnormal flow, and whether there is abnormal flow result is sent;
[0087] The past period of time is recalled, whether the device has always existed local hot spot is determined, if yes, disposal suggestions are sent, including: optimizing application deployment mode, installing a cooling unit, etc.
[0088] It should be noted that the specific check items and abnormal processing content mentioned in the embodiments of the present application are only specific embodiments provided by the method provided by the embodiments of the present application for better illustrating the method, and in the specific implementation process, the specific check items and abnormal processing mode can be set according to the actual demand, which does not affect the function of the method provided by the embodiments of the present application.
[0089] S107: through the preset refrigeration system, the temperature of each hot spot cabinet is reduced to reduce the environment temperature of each hot spot cabinet, and the temperature control process is completed.
[0090] In the method provided by the embodiments of the present application, the refrigeration system, that is, the air conditioning system, is pre-deployed in the machine room, the machine room temperature control system can communicate with the refrigeration system, the machine room temperature control system can trigger the refrigeration system to adjust the running state of the corresponding refrigeration equipment (such as fan, air outlet, etc.) based on the relevant information (such as position) of each hot spot cabinet, change the refrigeration effect, and reduce the temperature of the environment where each hot spot cabinet is located, thereby reducing the environment temperature of each hot spot cabinet.
[0091] Based on the method provided in the embodiment of the application, a plurality of machine room modules corresponding to the machine room are determined, each machine room module includes a plurality of cabinets; a set of device inlet air temperature and component temperature corresponding to each device deployed in each cabinet is determined; whether each device meets a preset device local hotspot condition is judged according to the set of component temperature corresponding to the device, and the device meeting the condition is regarded as a hotspot device; whether each cabinet meets a preset cabinet local hotspot condition is judged according to the device inlet air temperature of each device in the cabinet, and the cabinet meeting the condition is regarded as a hotspot cabinet; device abnormality checking is performed on each hotspot device according to a preset device detection strategy, and an abnormality checking result is obtained; the hotspot device is processed abnormally according to the abnormality checking result of the hotspot device, so that the hotspot device is in a normal operation state, so as to reduce the device operation temperature; and the hotspot cabinet is cooled by a preset refrigeration system, so as to reduce the cabinet environment temperature. By using the method provided in the embodiment of the application, whether there is a local hotspot can be identified based on the inlet air temperature and the component temperature of the device in the cabinet, and the local hotspot associated with the inlet air temperature of the device and the local hotspot associated with the component temperature of the device can be processed respectively. The identification of the local hotspot is based on the related temperature of the device, and when the device has a high temperature or a high temperature trend, the local hotspot can be identified in time, temperature control can be performed in time, the local hotspot can be eliminated or reduced, the temperature of the machine room can be controlled in a suitable range, and the temperature control effect is good.
[0092] In Figure 1 Based on the method shown in the figure, in the method provided in the embodiment of the application, the process of determining the device inlet air temperature corresponding to the current device and the set of component temperatures corresponding to the device in step S102 includes:
[0093] Determining the device model corresponding to the device;
[0094] In the method provided in the embodiment of the application, the device characteristic information of all devices in the machine room is configured in the database in advance, and the device characteristic information can include the device type, the device model, the device physical position, the device cabinet, the device module and the like. The device characteristic information corresponding to the device currently processed can be obtained from the database, and the device model is read therefrom, so as to obtain the device model corresponding to the device.
[0095] In the plurality of device temperature collection instructions, the target device temperature collection instruction corresponding to the device model is determined; and each device temperature collection instruction is a hardware management interface operation instruction set based on an intelligent platform management interface;
[0096] The method provided by the embodiment of the present application is based on an intelligent platform management interface (IPMI) which is preset with a plurality of device temperature collection instructions, and the device temperature collection instructions are used to query the air inlet temperature of the device and the temperature of each component. The IPMI is an industry standard adopted by peripheral devices used in enterprise systems based on Intel structure, and users can monitor the physical health characteristics of IT devices such as servers, such as temperature, voltage, fan working state, power state and the like. Therefore, various hardware management interface operation instructions can be executed through the IPMI, and the device temperature collection instructions are one of the instructions. The device temperature collection instructions are configured according to the device model, that is, each device temperature collection instruction corresponds to each device model.
[0097] In the method provided by the embodiment of the present application, the device model corresponding to each device temperature collection instruction is matched with the device model of the current device respectively, so as to find the device temperature collection instruction matched with the device model of the current device in each device temperature collection instruction, and the device temperature collection instruction is taken as a target device temperature collection instruction.
[0098] According to the target device temperature collection instruction, a device temperature collection task corresponding to the device is created.
[0099] In the method provided by the embodiment of the present application, the device temperature collection task is initiated based on the target device temperature collection instruction.
[0100] The device temperature collection task is executed, and a device temperature collection result corresponding to the device is obtained.
[0101] In the method provided by the embodiment of the present application, a thread module can be called, a multi-thread queue is established, the device temperature collection task is executed through the queue, and a device temperature collection result of the device is obtained. The device temperature collection result includes the air inlet temperature, the air outlet temperature, the temperature of each component of the device and the like of the device.
[0102] In the device temperature collection result, the air inlet temperature corresponding to the device is obtained.
[0103] In the method provided by the embodiment of the present application, the air inlet temperature of the device can be read from the obtained device temperature collection result as the air inlet temperature corresponding to the device.
[0104] In the device temperature collection result, a plurality of component temperatures corresponding to the device are obtained, and the plurality of component temperatures corresponding to the device are combined to form a component temperature set corresponding to the device.
[0105] The method provided by the embodiment of the present application can read the temperature of each device component from the collected device temperature collection result as the temperature of each device component corresponding to the device, thereby obtaining a component temperature set.
[0106] In Figure 1 Based on the method shown, the method provided by the embodiment of the present application includes the following steps.
[0107] For each device component temperature in the component temperature set corresponding to the device, a component temperature threshold corresponding to the device component temperature is determined, and it is determined whether the device component temperature is greater than the corresponding component temperature threshold. If the device component temperature is greater than the corresponding component temperature threshold, the device component temperature is determined as a target device component temperature.
[0108] In the method provided by the embodiment of the present application, the component temperature threshold of each device component is pre-configured according to actual temperature control requirements. When the temperature of a device component of a certain type exceeds the corresponding component temperature threshold, it is considered that the device component of this type has a high temperature or a high temperature trend.
[0109] In the method provided by the embodiment of the present application, for each device component temperature, the component temperature threshold of the device component of this type can be found in the pre-configured component temperature threshold information according to the type of the device component corresponding to the device component temperature, and the component temperature threshold is taken as the component temperature threshold corresponding to the device component temperature. Each device component temperature is compared with the corresponding component temperature threshold. If the device component temperature currently being compared is greater than the corresponding component temperature threshold, the current device component temperature is marked, and the current device component temperature is taken as the target device component temperature. It can be considered that the device component corresponding to the target device component temperature has a high temperature or a high temperature trend. If the device component temperature currently being compared is not greater than the corresponding component temperature threshold, the device component temperature is not marked.
[0110] It is determined whether the target device component temperature exists in the component temperature set corresponding to the device. If the target device component temperature exists in the component temperature set corresponding to the device, it is determined that the device meets the preset device local hotspot condition.
[0111] In the method provided by the embodiment of the application, all equipment component temperatures in the component temperature set are marked and identified to identify whether the equipment component temperature is marked as the target equipment component temperature. If at least one equipment component temperature in the component temperature set is marked as the target equipment component temperature, it is considered that the corresponding equipment meets the preset equipment local hotspot condition. If none of the equipment component temperatures in the component temperature set is marked as the target equipment component temperature, it is considered that the corresponding equipment does not meet the preset equipment local hotspot condition.
[0112] In Figure 1 Based on the method shown, in the method provided by the embodiment of the application, the process of judging whether the cabinet meets the preset cabinet local hotspot condition according to the equipment inlet temperature corresponding to each equipment deployed in the cabinet in step S104 includes the following steps.
[0113] For each equipment deployed in the cabinet, the equipment inlet temperature threshold corresponding to the equipment is determined, and it is judged whether the equipment inlet temperature corresponding to the equipment is greater than the equipment inlet temperature threshold. If the equipment inlet temperature corresponding to the equipment is greater than the equipment inlet temperature threshold, the equipment is determined as the local hotspot equipment corresponding to the cabinet.
[0114] In the method provided by the embodiment of the application, according to actual temperature control requirements, the equipment inlet temperature thresholds of various equipment are preset. For each equipment in the current cabinet, the equipment inlet temperature threshold matched with the equipment can be found in the preset equipment inlet temperature threshold information according to the equipment type of the equipment, and the equipment inlet temperature threshold is used as the equipment inlet temperature threshold corresponding to the equipment. The equipment inlet temperature corresponding to each equipment is compared with the equipment inlet temperature threshold corresponding to the equipment. If the equipment inlet temperature is greater than the equipment inlet temperature threshold corresponding to the equipment, the equipment is marked as a local hotspot equipment. If the equipment inlet temperature is not greater than the equipment inlet temperature threshold corresponding to the equipment, the equipment is not marked.
[0115] It is judged whether the local hotspot equipment exists in the cabinet. If the local hotspot equipment exists in the cabinet, it is determined that the cabinet meets the preset cabinet local hotspot condition.
[0116] In the method provided by the embodiment of the application, each equipment deployed in the current cabinet is marked and identified to identify whether the equipment is marked as a local hotspot equipment. If at least one equipment deployed in the current cabinet is marked as a local hotspot equipment, it is considered that the current cabinet meets the preset cabinet local hotspot condition. If none of the equipment deployed in the current cabinet is marked as a local hotspot equipment, it is considered that the current cabinet does not meet the preset cabinet local hotspot condition.
[0117] On the basis of the method provided in the above embodiment, the method provided in the embodiment of the present application comprises the following steps:
[0118] In the plurality of floor air outlets comprised in the preset refrigeration system, a floor air outlet corresponding to each of the hot-spot cabinets is determined;
[0119] In the method provided in the embodiment of the present application, the floor type air supply design is adopted in the refrigeration system of the machine room, and the air outlet floor is installed in the machine room. The refrigeration system comprises a plurality of floor air outlets, and the air supply of the floor air outlet is realized through the air outlet floor. Each floor air outlet has an adjusting capacity, and can change the air outlet direction and air outlet volume.
[0120] In the method provided in the embodiment of the present application, the positions of the cabinets and the positions of the floor air outlets are pre-configured. For each hot-spot cabinet, the position of the hot-spot cabinet can be used to find the floor air outlet matched with the position, and the matched floor air outlet is taken as the floor air outlet corresponding to the hot-spot cabinet.
[0121] For each of the hot-spot cabinets, the device position corresponding to the local hot-spot device corresponding to the hot-spot cabinet is determined, and the air outlet information corresponding to the floor air outlet corresponding to the hot-spot cabinet is determined according to the device position corresponding to the local hot-spot device and the device inlet air temperature, the air outlet information comprising the air outlet direction and the air outlet volume;
[0122] In the method provided in the embodiment of the present application, the local hot-spot device is deployed in the hot-spot cabinet, the device position corresponding to the local hot-spot device is obtained from the pre-stored device characteristic information, and according to the preset control strategy, the corresponding air outlet direction and air outlet volume can be determined based on the device position corresponding to the local hot-spot device and the device inlet air temperature corresponding to the local hot-spot device, the air outlet direction corresponding to the device position of the local hot-spot device, and the air outlet volume determined by the device inlet air temperature, for example, the higher the device inlet air temperature, the greater the air outlet volume. Thus, the air outlet information corresponding to the floor air outlet corresponding to each hot-spot cabinet is obtained.
[0123] It should be noted that in the specific implementation process, there can be only one local hot-spot device in the hot-spot cabinet, or there can be multiple local hot-spot devices. In the case of multiple local hot-spot devices, each local hot-spot device can be processed based on the above process to obtain multiple sets of air outlet information, and the air outlet information of each set is integrated to obtain the air outlet information corresponding to the corresponding floor air outlet. In subsequent control, the floor air outlet can be controlled to perform air outlet control alternately according to the air outlet information of each set.
[0124] According to the air outlet information corresponding to the floor air outlet corresponding to each of the hot-spot cabinets, a refrigeration adjustment instruction is generated;
[0125] Send the refrigeration adjustment instruction to the preset refrigeration system, so that the preset refrigeration system controls the air outlet of the floor air outlet corresponding to each hot spot cabinet to cool each hot spot cabinet.
[0126] In the method provided by the embodiment of the application, the refrigeration system can receive the refrigeration adjustment instruction sent by the machine room temperature control system, and control the air outlet of the corresponding floor air outlet according to the refrigeration adjustment instruction, that is, control the corresponding floor air outlet to blow air according to the corresponding air outlet amount and air outlet direction.
[0127] In Figure 1 Based on the method shown, the method provided by the embodiment of the application further includes:
[0128] Determine the cabinet inlet air temperature corresponding to each cabinet;
[0129] In the method provided by the embodiment of the application, the inlet air temperature of each cabinet in the machine room can be collected by the preset machine room micro-environment monitoring system, and the collected inlet air temperature is used as the cabinet inlet air temperature of the corresponding cabinet. The machine room micro-environment monitoring system refers to a system for monitoring the environment on which IT equipment depends, including current, voltage, power, temperature, humidity and other indicators.
[0130] For each machine room module, it is determined whether the machine room module meets the preset module local hot spot condition according to the cabinet inlet air temperature corresponding to each cabinet included in the machine room module, and if the machine room module meets the preset module local hot spot condition, the machine room module is determined as a hot spot module.
[0131] In the method provided by the embodiment of the application, the module local hot spot condition is set in advance according to actual needs, and the module local hot spot condition defines that when the inlet air temperature of the cabinet in the machine room module meets a certain condition, the local hot spot in the module dimension is considered to exist. For example, a cabinet mean threshold is set, and when the mean value of the inlet air temperature of all cabinets in the machine room module exceeds the cabinet mean threshold, it is considered to meet the condition. It should be noted that in the specific implementation process, the module local hot spot condition can be set according to actual needs, without affecting the implementation function of the method provided by the embodiment of the application.
[0132] In the method provided by the embodiment of the application, for each machine room module, it is determined whether the cabinet inlet air temperature corresponding to each cabinet in the machine room module matches the condition content of the module local hot spot condition, and if it matches, it is determined that the machine room module meets the module local hot spot condition. When the machine room module meets the module local hot spot condition, the machine room module is marked as a hot spot module, that is, it is considered that the machine room module has a local hot spot.
[0133] Cooling each of the hotspot modules by the preset refrigeration system to reduce the ambient temperature of each of the hotspot modules.
[0134] In the method provided by the embodiment of the present application, the operation state of the corresponding refrigeration equipment is adjusted by the refrigeration system based on the relevant information of each hotspot module, such as the module position, and cooling treatment is performed on the environment in which each hotspot module is located.
[0135] Based on the method provided in the above embodiment, in the method provided by the embodiment of the present application, the process of determining whether the machine room module meets the preset module local hotspot condition according to the cabinet inlet air temperature corresponding to each cabinet included in the machine room module comprises:
[0136] For each cabinet included in the machine room module, it is determined whether the cabinet inlet air temperature corresponding to the cabinet is greater than the preset module temperature threshold value, and if the cabinet inlet air temperature corresponding to the cabinet is greater than the preset module temperature threshold value, the cabinet is determined as a local hotspot cabinet.
[0137] In the method provided by the embodiment of the present application, the module temperature threshold value, that is, the threshold value of the cabinet inlet air temperature, is set in advance according to the actual temperature control requirement. The cabinet inlet air temperature of each cabinet in the current machine room module is compared with the module temperature threshold value, and if the cabinet inlet air temperature corresponding to the cabinet being compared is greater than the module temperature threshold value, the cabinet is marked as a local hotspot cabinet. If the cabinet inlet air temperature is not greater than the module temperature threshold value, the cabinet is not marked.
[0138] It is determined whether there is the local hotspot cabinet in each cabinet included in the machine room module, and if there is the local hotspot cabinet in each cabinet included in the machine room module, it is determined that the machine room module meets the preset module local hotspot condition.
[0139] In the method provided by the embodiment of the present application, all cabinets in the current machine room module are marked and identified to identify whether the cabinet is marked as a local hotspot cabinet. If at least one cabinet in the current machine room module is marked as a local hotspot cabinet, it is considered that the current machine room module meets the module local hotspot condition, and if each cabinet in the current machine room module is not marked as a local hotspot cabinet, it is considered that the current machine room module does not meet the preset module local hotspot condition.
[0140] In order to better illustrate the method provided by the embodiment of the present application, in combination with the actual application scenario, the embodiment of the present application provides another machine room temperature control method. The machine room in the embodiment of the present application is also deployed based on the machine room module, the cabinet, the equipment in the cabinet and the like mentioned in the above embodiment.
[0141] First, in combination with Figure 2-4The local hot spot in the embodiment of the present application is described. In the method provided by the embodiment of the present application, the local hot spot of the machine room is divided into IT equipment local hot spot, cabinet local hot spot, and module local hot spot. Figure 2 , Figure 3 and Figure 4 In the above, the oblique line mark indicates the area with higher temperature.
[0142] The IT equipment local hot spot refers to the local hot spot caused by the device component with higher temperature in the IT equipment. As shown in the schematic diagram in Figure 2 , a brief structure of an IT equipment is shown, which includes five components, component 1 to component 5, and component 3 is a device component with higher temperature, and component 3 is an IT equipment local hot spot.
[0143] The cabinet local hot spot refers to the local hot spot caused by the IT equipment with higher temperature in the cabinet. As shown in the schematic diagram in Figure 3 , a brief structure of a cabinet is shown, which deploys multiple IT equipments, IT equipment 1, IT equipment 2, IT equipment 3, …, IT equipment m, and IT equipment 2 is a device with higher temperature, and IT equipment 2 is a cabinet local hot spot.
[0144] The module local hot spot refers to the local hot spot caused by the cabinet with higher temperature in the machine room module. As shown in the schematic diagram in Figure 4 , a brief structure of a machine room module is shown, which deploys multiple cabinets, cabinet 1, cabinet 2, cabinet 3, and cabinet 4. Cabinet 4 is a cabinet with higher temperature, and cabinet 4 is a module local hot spot.
[0145] Referring to the flow chart in Figure 5 , the machine room temperature control process provided by the embodiment of the present application includes:
[0146] S201: Collecting IT equipment temperature;
[0147] In the method provided by the embodiment of the present application, the temperature of each IT equipment is collected by script, and the temperature of the IT equipment includes two types of temperature: IT equipment inlet and outlet temperature, and IT equipment component temperature.
[0148] As shown in Figure 6 , in the method provided by the embodiment of the present application, the process of collecting the temperature of the IT equipment in step S201 specifically includes:
[0149] S301: Configuring collection task, inputting the to-be-collected IT equipment features, and saving to the backend task configuration table of the database;
[0150] In the method provided by the embodiment of the present application, the IT equipment features can be as follows:
[0151] Table 1
[0152] IT equipment features Meaning Room Module in which it is located Cabinet Cabinet in which it is located Location Physical location Class IT equipment type Type IT equipment model SN Serial number ILO IP of the management port User Username Password Password
[0153] S302: Obtain various script information of IT equipment hardware management interface IPMI tools from a script library to form to-be-distributed script tool information.
[0154] In the method provided by the embodiment of the application, various script information of IT equipment hardware management interface IPMI tools is obtained from a script library to form to-be-distributed script tool information. For example, in a Linux environment, the operation method of using an IPMI interface to query the temperature of each component of a server of a Huawei RH5288H type is as follows: GET_TEMP_CMD='ipmitool -I lanplus -H {} -U {} -P {} sdrtype Temperature'.
[0155] S303: Perform script automatic matching of IT equipment models and hardware management interface operation instructions to perform an IT equipment temperature collection task.
[0156] In the method provided by the embodiment of the application, script automatic matching of IT equipment models and hardware management interface operation instructions is used to perform an IT equipment temperature collection task. An IT equipment temperature collection task is asynchronously initiated, a task ID is transmitted to a backend process, and to-be-collected IT equipment information and a collection script type are obtained from a backend task configuration table according to the task ID. A multi-thread queue is established on the to-be-collected IT equipment through a thread module to perform a collection task in an uninterrupted manner, and IT equipment temperatures of the following categories are collected:
[0157] Table 2
[0158]
[0159] S202: Collect cabinet air inlet temperature.
[0160] In the method provided by the embodiment of the application, cabinet air inlet temperature in a module is collected from a computer room micro-environment monitoring system.
[0161] S203: Temperature data processing, comparison with a preset temperature threshold, and judgment of whether there is a local hot spot.
[0162] In the method provided by the embodiment of the application, collected temperature is processed, each type of temperature is compared with a corresponding preset temperature threshold, and whether there is a local hot spot is judged. The threshold range of each type of temperature can be as follows:
[0163] Table 3
[0164]
[0165] It should be noted that the specific indexes and data contents shown in Table 1, Table 2 and Table 3 are only specific examples provided by the method for better illustrating the embodiments of the present application, wherein only part of the indexes and data in the actual application process are shown, and meanwhile, other indexes and data can also be used in the actual application process, and are not limited to the contents mentioned in the embodiments of the present application.
[0166] S204: analyzing the local hotspot type;
[0167] In the method provided by the embodiments of the present application, if the temperature of the IT equipment component exceeds the component temperature threshold value, it is judged that there is a local hotspot of the IT equipment; if the air inlet temperature of a single IT equipment in the same cabinet exceeds the preset IT equipment air inlet temperature threshold value, it is judged that there is a local hotspot of the cabinet; and if the cabinet air inlet temperature exceeds the module temperature threshold value, it is judged that there is a local hotspot of the module.
[0168] S205: giving different early warnings and processing according to the local hotspot type.
[0169] In the method provided by the embodiments of the present application, when there is a local hotspot of the IT equipment, the IT equipment inspection is initiated, and the processing is performed according to the inspection result.
[0170] Optionally, the IT equipment inspection includes hardware health state inspection, power consumption query, CPU load inspection, memory load inspection, hard disk bandwidth inspection, network card flow inspection, etc. The processing according to the inspection result can be performed by calling the processing script of the abnormal inspection item, and the specific processing process can be referred to the description of step S106 of the method shown in the above embodiments. Figure 1
[0171] In the method provided by the embodiments of the present application, when there is a local hotspot of the cabinet, the IT equipment air inlet temperature is optimized.
[0172] Optionally, the optimization of the IT equipment air inlet temperature includes prompting the operation and maintenance personnel to optimize the deployment position of the IT equipment, plugging the gap of the cabinet where the IT equipment is located, etc. The system can also be used for control, and according to the local hotspot position of the cabinet, the air outlet floor is automatically controlled to adjust the air outlet amount and the air outlet direction, so as to accurately cool the hotspot in the cabinet.
[0173] In the method provided by the embodiments of the present application, when there is a local hotspot of the module, the refrigeration adjustment is performed on the module.
[0174] Optionally, the refrigeration adjustment of the module includes adjusting the air outlet amount of the air outlet floor at the local hot spot of the module, plugging the gap between adjacent cabinets, adjusting the fan speed corresponding to the local hot spot position of the module, etc. Specifically, the position of the cabinet (i.e. the local hot spot position of the module) can be analyzed through the cabinet number, and the air fan speed of the nearest air conditioner at the local hot spot position of the module is controlled, so that the air inlet temperature of all cabinets in the module is maintained below the threshold value.
[0175] The method provided by the embodiment of the present application can collect the IT equipment component temperature, the IT equipment air inlet temperature and the cabinet air inlet temperature of the data center machine room, analyze whether there is a local hot spot and the local hot spot type according to the preset temperature threshold value, and perform targeted treatment on different types of local hot spots. Specifically, the method comprises the following steps: configuring a collection task and executing a script to collect the IT equipment temperature and the cabinet air inlet temperature in the module from the machine room micro-environment monitoring system; processing the collection result and comparing it with the preset threshold value; judging whether there is a local hot spot; and giving a warning and performing processing according to the local hot spot type.
[0176] The method provided by the embodiment of the present application adopts an IT equipment temperature collection method based on an IT equipment hardware management interface protocol, can efficiently and timely collect the temperature values of each component of the IT equipment through an automatic script, establishes a machine room local hot spot analysis method, classifies different local hot spots in combination with each temperature threshold value in the machine room environment, and establishes a local hot spot processing method of different types, so as to timely process different local hot spots.
[0177] The method provided by the embodiment of the present application takes the IT equipment component temperature as a reference index of the health status of the IT equipment, establishes a connection between the machine room refrigeration field and the IT equipment hardware operation and maintenance field, provides help for the fault discovery and load analysis of the IT equipment, and does not need manual intervention in the whole process, thereby saving a large amount of manpower and time resources and greatly improving the operation and maintenance efficiency. In the complex refrigeration system of the large data center, the IT equipment component temperature, the IT equipment air inlet temperature and the cabinet temperature and other multi-level temperatures are combined, the local hot spot type of the machine room is analyzed from multiple angles, the operation and maintenance personnel are helped to judge the machine room refrigeration from multiple dimensions, the machine room refrigeration is optimized from multiple starting points, and the fine degree of operation and maintenance of the machine room is improved.
[0178] With Figure 1 Corresponding to the machine room temperature control method shown in Figure 1 The structure diagram is shown in Figure 7 The machine room temperature control device comprises:
[0179] The first determination unit 401 is configured to determine a plurality of machine room modules corresponding to the machine room in a case that temperature control of the machine room is required, each of the machine room modules comprising a plurality of cabinets, and each of the cabinets comprising a plurality of devices.
[0180] The second determination unit 402 is configured to determine, for each of the devices arranged in each of the cabinets, a device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set comprising a plurality of device component temperatures corresponding to the device.
[0181] The first judgment unit 403 is configured to judge, for each of the devices arranged in each of the cabinets, whether the device meets a preset device local hotspot condition according to the component temperature set corresponding to the device, and determine the device as a hotspot device if the device meets the preset device local hotspot condition.
[0182] The second judgment unit 404 is configured to judge, for each of the cabinets, whether the cabinet meets a preset cabinet local hotspot condition according to the device inlet air temperature corresponding to each of the devices arranged in the cabinet, and determine the cabinet as a hotspot cabinet if the cabinet meets the preset cabinet local hotspot condition.
[0183] The anomaly checking unit 405 is configured to perform device anomaly checking on each of the hotspot devices according to a preset device detection strategy, and obtain an anomaly checking result corresponding to each of the hotspot devices.
[0184] The anomaly processing unit 406 is configured to perform anomaly processing on each of the hotspot devices according to the anomaly checking result corresponding to the hotspot device, so that the hotspot device is in a normal operation state, and the operation temperature of the hotspot device is reduced.
[0185] The cooling processing unit 407 is configured to perform cooling processing on each of the hotspot cabinets by a preset refrigeration system, so as to reduce the environment temperature of each of the hotspot cabinets, and complete the temperature control process.
[0186] Based on the apparatus provided in this embodiment of the invention, multiple data center modules corresponding to a data center are determined, each data center module including multiple server racks; the set of equipment inlet air temperature and component temperature corresponding to each device deployed in each server rack is determined; based on the set of component temperature corresponding to each device, it is determined whether it meets the preset local hot spot conditions, and the devices that meet the conditions are regarded as hot spot devices; based on the equipment inlet air temperature of each device in each server rack, it is determined whether each server rack meets the preset local hot spot conditions, and the server racks that meet the conditions are regarded as hot spot server racks; based on the preset equipment detection strategy, each hot spot device is checked for equipment anomalies, and the anomaly check results are obtained; based on the anomaly check results of the hot spot devices, anomaly processing is performed on them to bring them into normal operation, thereby reducing the equipment operating temperature; through a preset cooling system, the hot spot server racks are cooled down to reduce the server rack ambient temperature. Using the apparatus provided in this embodiment of the invention, the existence of local hot spots can be identified based on the inlet air temperature and component temperature of the devices in the server rack, and targeted processing can be performed on local hot spots associated with equipment inlet air temperature and local hot spots associated with component temperature. Local hotspot identification is based on the relevant temperature of the equipment. When the equipment is at a high temperature or has a high temperature trend, local hotspots can be identified in time, and temperature control can be carried out in a timely manner to eliminate or reduce local hotspots, thereby keeping the computer room temperature within a suitable range and achieving good temperature control results.
[0187] exist Figure 7 Based on the device shown, the device provided in this embodiment of the invention can be further extended to include multiple units. The functions of each unit can be found in the descriptions of the various embodiments of the computer room temperature control method provided above, and will not be further illustrated here.
[0188] This invention also provides a storage medium that includes stored instructions, wherein when the instructions are executed, the device containing the storage medium is controlled to perform the computer room temperature control method described above.
[0189] This invention also provides an electronic device, the structural schematic of which is shown below. Figure 8 As shown, it specifically includes a memory 501 and one or more instructions 502, wherein one or more instructions 502 are stored in the memory 501 and configured to be executed by one or more processors 503 to perform the following operations:
[0190] When temperature control of the computer room is required, multiple computer room modules corresponding to the computer room are identified, each computer room module includes multiple cabinets, and each cabinet is equipped with multiple devices;
[0191] For each device deployed in each of the cabinets, determine a device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set including a plurality of device component temperatures corresponding to the device;
[0192] For each device deployed in each of the cabinets, determine a device inlet air temperature corresponding to the device and a component temperature set corresponding to the device, the component temperature set including a plurality of device component temperatures corresponding to the device;
[0193] For each cabinet, determine whether the cabinet meets a preset cabinet local hotspot condition according to the device inlet air temperature corresponding to each device deployed in the cabinet, and if the cabinet meets the preset cabinet local hotspot condition, determine the cabinet as a hotspot cabinet;
[0194] According to a preset device detection strategy, perform device anomaly checking on each of the hotspot devices to obtain an anomaly checking result corresponding to each of the hotspot devices;
[0195] For each of the hotspot devices, perform anomaly processing on the hotspot device according to the anomaly checking result corresponding to the hotspot device, so that the hotspot device is in a normal operating state, to reduce the operating temperature of the hotspot device;
[0196] Perform cooling processing on each of the hotspot cabinets by a preset refrigeration system to reduce the ambient temperature of each of the hotspot cabinets, to complete the temperature control process.
[0197] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each of the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the relevant part can be referred to the part of the method embodiment. The system and system embodiment described above are only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place or distributed on multiple network units. According to the actual needs, some or all of the modules can be selected to achieve the purpose of the embodiment scheme. Those skilled in the art can understand and implement without creative labor.
[0198] Those skilled in the art will further realize that the mechanisms of the various examples described herein are capable of being implemented using any number of combinations of the described features. Accordingly, these examples are not limited to the mechanisms described herein, but rather, the intent is to cover all modifications and alternatives equivalent thereto. The preceding description of the examples is illustrative, and not restrictive. Many other examples will be apparent to those of skill in the art upon reviewing the above description. The scope of the examples should, therefore, be determined not with reference to the above description, but instead should be given to the appended claims, along with their full scope of equivalents.
[0199] The above description of disclosed examples is intended to be illustrative, and not restrictive. Many other examples will be apparent to those of skill in the art upon reviewing the above description. The scope of the examples should, therefore, be determined not with reference to the above description, but instead should be given to the appended claims, along with their full scope of equivalents.
Claims
1. A method for controlling the temperature of a computer room, characterized in that, include: When temperature control of the computer room is required, multiple computer room modules corresponding to the computer room are identified, each computer room module includes multiple cabinets, and each cabinet is equipped with multiple devices; For each device deployed in each of the cabinets, determine the current inlet air temperature of the device and the set of component temperatures corresponding to the device. The set of component temperatures corresponding to the device includes the temperatures of each device component, and the device component temperature refers to the temperature of the device parts. For each device deployed in each of the aforementioned cabinets, based on the component temperature set corresponding to that device, it is determined whether the device meets the preset local hot spot conditions. If the device meets the preset local hot spot conditions, then the device is identified as a hot spot device. For each of the cabinets, based on the air intake temperature of each device deployed in the cabinet, it is determined whether the cabinet meets the preset local hot spot conditions. If the cabinet meets the preset local hot spot conditions, the cabinet is identified as a hot spot cabinet. Based on the preset device detection strategy, each hotspot device is checked for device anomalies, and the anomaly check result corresponding to each hotspot device is obtained. The detection items in the device detection strategy include hardware health status check, power consumption query, CPU load check, memory load check, hard disk bandwidth check, and network card traffic check. For each hotspot device, based on the corresponding anomaly check result, the hotspot device is handled to bring it into normal operation and reduce its operating temperature. The pre-set cooling system is used to cool down each of the hotspot cabinets, thereby reducing the ambient temperature of each hotspot cabinet and completing the temperature control process.
2. The method according to claim 1, characterized in that, Determining the current equipment inlet air temperature and the set of component temperatures corresponding to the equipment includes: Determine the corresponding equipment model; Among a plurality of preset device temperature acquisition commands, the target device temperature acquisition command corresponding to the device model is determined; each device temperature acquisition command is a hardware management interface operation command set based on the intelligent platform management interface. Based on the target device temperature acquisition instruction, create a device temperature acquisition task corresponding to the device; Execute the device temperature acquisition task to obtain the device temperature acquisition result corresponding to the device; From the equipment temperature acquisition results, obtain the equipment inlet air temperature corresponding to the equipment; In the equipment temperature acquisition results, the temperatures of multiple equipment components corresponding to the equipment are obtained, and the temperatures of these multiple equipment components are combined into a set of component temperatures corresponding to the equipment.
3. The method according to claim 1, characterized in that, The step of determining whether the device meets the preset local hot spot conditions based on the temperature set of the corresponding components includes: For each device component temperature in the set of component temperatures corresponding to the device, determine the component temperature threshold corresponding to the device component temperature, and determine whether the device component temperature is greater than its corresponding component temperature threshold. If the device component temperature is greater than its corresponding component temperature threshold, then the device component temperature is determined as the target device component temperature. Determine whether the target device component temperature exists in the component temperature set corresponding to the device. If the target device component temperature exists in the component temperature set corresponding to the device, then the device is determined to meet the preset device local hot spot condition.
4. The method according to claim 1, characterized in that, The step of determining whether the rack meets the preset rack local hotspot conditions based on the air intake temperature of each device deployed in the rack includes: For each device deployed in the cabinet, determine the inlet air temperature threshold corresponding to the device, and determine whether the inlet air temperature corresponding to the device is greater than the inlet air temperature threshold. If the inlet air temperature corresponding to the device is greater than the inlet air temperature threshold, then the device is determined as a local hotspot device corresponding to the cabinet. Determine whether the local hotspot device exists in the cabinet. If the local hotspot device exists in the cabinet, then the cabinet is determined to meet the preset cabinet local hotspot conditions.
5. The method according to claim 4, characterized in that, The cooling process for each of the hotspot cabinets using a pre-set cooling system includes: Among the multiple floor vents included in the preset cooling system, determine the floor vent corresponding to each hotspot cabinet; For each hotspot cabinet, determine the location of the local hotspot device corresponding to the hotspot cabinet, and based on the location of the local hotspot device and the inlet air temperature of the device, determine the outlet air information of the floor vent corresponding to the hotspot cabinet, which includes the outlet air direction and outlet air volume. Based on the airflow information corresponding to the floor vents of each hotspot cabinet, a cooling adjustment command is generated; The cooling adjustment command is sent to the preset cooling system, which then controls the airflow from the floor vents corresponding to each hotspot cabinet to cool down each hotspot cabinet.
6. The method according to claim 1, characterized in that, Also includes: Determine the cabinet intake air temperature for each of the aforementioned cabinets; For each of the data center modules, based on the air intake temperature of each cabinet in the data center module, it is determined whether the data center module meets the preset local hot spot conditions. If the data center module meets the preset local hot spot conditions, then the data center module is identified as a hot spot module. The preset cooling system is used to cool down each of the hotspot modules, thereby reducing the ambient temperature of each hotspot module.
7. The method according to claim 6, characterized in that, The step of determining whether the data center module meets the preset local hotspot conditions based on the intake air temperature of each rack in the data center module includes: For each rack included in the data center module, determine whether the rack intake air temperature is greater than the preset module temperature threshold. If the rack intake air temperature is greater than the preset module temperature threshold, then the rack is identified as a local hotspot rack. Determine whether the local hotspot cabinet exists in any of the cabinets included in the data center module. If the local hotspot cabinet exists in any of the cabinets included in the data center module, then the data center module is determined to meet the preset module local hotspot condition.
8. A computer room temperature control device, characterized in that, include: The first determining unit is used to determine multiple computer room modules corresponding to the computer room when temperature control of the computer room is required. Each computer room module includes multiple cabinets, and multiple devices are deployed in each cabinet. The second determining unit is used to determine, for each device deployed in each of the cabinets, the current inlet air temperature of the device and the set of component temperatures corresponding to the device, wherein the set of component temperatures corresponding to the device includes the temperatures of each device component of the device, and the device component temperature refers to the temperature of the device parts. The first judgment unit is used to determine whether each device deployed in each of the cabinets meets the preset local hot spot conditions based on the component temperature set corresponding to the device. If the device meets the preset local hot spot conditions, the device is identified as a hot spot device. The second judgment unit is used to determine whether each cabinet meets the preset cabinet local hot spot conditions based on the air intake temperature of each device deployed in the cabinet. If the cabinet meets the preset cabinet local hot spot conditions, the cabinet is determined as a hot spot cabinet. An anomaly detection unit is used to perform anomaly detection on each of the hotspot devices according to a preset device detection strategy, and obtain the anomaly detection result corresponding to each hotspot device. The detection items in the device detection strategy include hardware health status check, power consumption query, CPU load check, memory load check, hard disk bandwidth check, and network card traffic check. An anomaly handling unit is used to perform anomaly handling on each hotspot device according to the anomaly check result corresponding to the hotspot device, so as to put the hotspot device into normal operation and reduce the operating temperature of the hotspot device. The cooling unit is used to cool each of the hotspot cabinets through a preset cooling system, thereby reducing the ambient temperature of each hotspot cabinet and completing the temperature control process.
9. A storage medium, characterized in that, The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the computer room temperature control method as described in any one of claims 1 to 7.
10. An electronic device, characterized in that, It includes a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Method and device for reducing complete equipment cabinet disk failure rate
CN105353993A
Hardware equipment exception monitoring method, server and computer readable storage medium
CN110851322A
Cabinet temperature acquisition method, system and device and storage medium
CN114485993A