Liquid cooling fan control method, device, equipment and storage medium

Abstract

The present specification relates to the field of data center cooling and server cabinet heat dissipation, and in particular to a liquid cooling fan control method, device, equipment and storage medium. Among them, the liquid cooling fan control method includes: obtaining temperature data of multiple server groups in a server cluster, each server group corresponds to a fan for heat dissipation; calculating the temperature distribution data of the server cluster based on the temperature data of the multiple server groups; determining the temperature difference data between the multiple server groups based on the temperature distribution data; when the temperature difference data is greater than or equal to the temperature difference threshold, selecting a target server group with a fan speed greater than or equal to the speed threshold from the multiple server groups, and increasing the fan speed of the adjacent server groups of the target server group. The embodiments of this specification provide a refined fan speed control strategy based on temperature differences, which is of great significance for reducing the PUE value of the server cabinet under normal working conditions and extending the service life of the server and fan.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data center cooling and server cabinet heat dissipation, and specifically to a liquid cooling fan control method, device, equipment and storage medium. Background Art

[0002] At present, PUE (the ratio of all energy consumed by the data center to the energy consumed by the IT load) has become an important indicator for measuring the energy efficiency of existing data centers. The smaller the PUE value, the less energy the IT equipment consumes, that is, the better the energy efficiency level. During the operation of a cabinet equipped with multiple servers, due to the influence of factors such as different application scenarios and operating power of different servers, the temperature fields in different areas inside the cabinet are usually quite different, resulting in a large temperature drop, which affects the uniformity of heat dissipation.

[0003] Traditional server fan control methods usually adopt a unified fan speed strategy. When the local temperature is high, the fan will be uniformly adjusted to a higher speed. When a unified fan speed strategy is adopted, the PUE value is often very large, resulting in energy waste and shortening the service life of the server and fan. Therefore, how to reduce the PUE value and extend the service life of the server and fan when the server cabinet is working normally is a key issue that needs to be solved in the current server cabinet heat dissipation field. Summary of the invention

[0004] The purpose of the embodiments of this specification is to provide a liquid cooling fan control method, system, device and storage medium to improve the problem that the PUE value of a server cabinet is too large and the service life of the server and the fan is short.

[0005] On the one hand, an embodiment of the present specification proposes a liquid cooling fan control method, the method comprising: obtaining temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation; calculating temperature distribution data of the server cluster based on the temperature data of the multiple server groups; determining temperature difference data between the multiple server groups based on the temperature distribution data; when the temperature difference data is greater than or equal to a temperature difference threshold, selecting a target server group whose fan speed is greater than or equal to the speed threshold from the multiple server groups, and increasing the fan speed of adjacent server groups of the target server group, and the distance between the adjacent server groups and the target server group meets the adjacent condition.

[0006] On the other hand, a liquid cooling fan control device includes: an acquisition module, used to acquire temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation; a calculation module, used to calculate temperature distribution data of the server cluster based on the temperature data of the multiple server groups; a determination module, used to determine temperature difference data between the multiple server groups based on the temperature distribution data; an addition module, when the temperature difference data is greater than or equal to a temperature difference threshold, selects a target server group whose fan speed is greater than or equal to a speed threshold from the multiple server groups, and increases the fan speed of an adjacent server group of the target server group, and the distance between the adjacent server group and the target server group satisfies the adjacent condition.

[0007] On the other hand, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned liquid cooling fan control method.

[0008] Finally, an embodiment of the present invention further provides a computer storage medium on which computer instructions are stored. When the computer instructions are executed by a processor of a computer device, the above-mentioned liquid cooling fan control method is executed.

[0009] It can be seen from the technical solutions provided by the above embodiments of this specification that the embodiments of this specification obtain temperature data of multiple server groups in a server cluster, and each server group corresponds to a fan for heat dissipation; according to the temperature data of the multiple server groups, the temperature distribution data of the server cluster is calculated; according to the temperature distribution data, the temperature difference data between the multiple server groups is determined; when the temperature difference data is greater than or equal to the temperature difference threshold, a target server group whose fan speed is greater than or equal to the speed threshold is selected from the multiple server groups, and the fan speed of the adjacent server group of the target server group is increased, and the distance between the adjacent server group and the target server group meets the adjacent condition. The fan speed of the target server group is greater than or equal to the speed threshold, indicating that the target server group is a server group with a large load. For the target server group with a large load, the fan speed of its adjacent server group is increased. In this way, the fans of the adjacent server groups can be used to assist the heat dissipation of the target server group, so as to fully dissipate the heat of the target server group. In this way, not only energy saving and consumption reduction can be achieved, but also the service life of the server and the fan can be extended. The technical solution of the embodiment of this specification is of great significance for reducing the PUE value of the server cabinet under normal working conditions and extending the service life of the server and the fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art description are briefly introduced below.

[0011] Figure 1 is a flow chart of a liquid cooling fan control method provided in an embodiment of this specification;

[0012] Figure 2 It is a schematic diagram of a server cabinet and its components provided in an embodiment of this specification;

[0013] Figure 3 It is a schematic diagram of the structure of a liquid cooling fan control device provided in an embodiment of this specification;

[0014] Figure 4 It is a schematic diagram of the structural composition of a computer device provided in an embodiment of this specification.

[0015] Reference numerals in the above drawings:

[0016] 201, rack; 202, back door (cooling source part of radiator); 203, back door (fan part); 204, cooling source of radiator; 205, server; 206, fan. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0018] It should be noted that any "fan" mentioned in this specification and the drawings means a "liquid cooling fan". In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0019] Figure 1 The figure is a flow chart of the liquid cooling fan control method. When implemented, the method includes the following steps:

[0020] S101: Acquire temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation.

[0021] In some embodiments, a server cluster includes multiple independent computers. The multiple independent computers use a high-speed communication network to form a larger computer service system, so that they can provide services to the outside as a whole. Each computer in the cluster can be an independent server running its own service. Multiple servers in the server cluster can communicate with each other, cooperate to provide applications, system resources and data to users, and manage them in a single system mode. The server cluster is set in a cabinet.

[0022] In some embodiments, the server cluster can be divided into multiple server groups according to the cabinet layout. Each server group can include one or more servers. The multiple server groups are arranged in different partitions of the cabinet. Each partition of the cabinet can include a server group, a fan for heat dissipation, and a sensor for collecting temperature data. Among them, the cabinet can include at least a rack and a cover plate (such as a back door), has a rectangular shape, has a closed structure, and is placed on the ground. The cabinet has good rigidity and strength, as well as good electromagnetic isolation, grounding, noise isolation, ventilation and heat dissipation, etc., to provide an appropriate environment and safety protection for the normal operation of computer equipment. Dividing the server cluster into multiple server groups according to the cabinet layout can be divided into multiple different partitions in advance according to the locations of different servers, or divided into multiple different partitions in advance according to the location of the heat source obtained from historical data, or divided into multiple different partitions in advance according to other methods. Each partition includes at least one server, and the partitions do not overlap with each other. For example, each server in the cabinet can be divided into a partition. For another example, the servers near some heat sources are frequently used and have high loads, and each of these frequently used and high-loaded servers can be divided into a partition separately. Some servers near heat sources are seldom used and have low loads. You can group these servers into one partition.

[0023] In some embodiments, each partition of the cabinet further includes a group of fans for heat dissipation and a group of sensors for collecting temperature data. The group of fans may include one or more fans, and the group of sensors may include one or more sensors. The acquisition of temperature data of multiple server groups in the server cluster includes acquiring temperature data collected by multiple sensors of each server group. The fan is used to introduce air into the cabinet or discharge hot air in the cabinet to the outside of the cabinet to dissipate heat. Different numbers of fans can be configured for different partitions according to the area and / or load conditions of different partitions. For example, for a cabinet partition with a lower load, two or even one fan can be configured; for a cabinet partition with a higher load, three or more fans can be configured. The sensor is used to obtain the real-time temperature of the partition. Different numbers of sensors can be configured for different partitions according to the area and / or load conditions of different partitions. For example, for a partition with a small area, one or two sensors can be configured; for a partition with a large area, more sensors can be configured. The sensor can use a contact sensor such as a thermal resistor and a thermocouple, or a non-contact sensor such as a radiation optical fiber temperature sensor and an infrared radiator.

[0024] Figure 2 It is a schematic diagram of a server cabinet and its components. Figure 2 Part (a) is a schematic diagram of the cabinet and its components when the back door (heat sink cold source part) 202 and the back door (fan part) 203 are closed; Figure 2 Part (b) is a schematic diagram of the cabinet and its components when the back door (heat sink cold source part) 202 and the back door (fan part) 203 are opened. Figure 2 As shown, the cabinet includes a rack 201, a back door (heat sink cold source part) 202 and a back door (fan part) 203. A plurality of servers 205 are arranged inside the rack 201, a radiator cold source 204 is arranged on the back door (heat sink cold source part) 202, and a plurality of fans 206 are arranged on the back door (fan part) 203.

[0025] In some embodiments, the temperature data collected by some or all sensors of each server group may be obtained. The temperature data collected by the sensor represents the real-time temperature of the server group in which the sensor is located. For each server group, the first representative temperature data of the temperature data collected by some or all sensors of the server group may be obtained as the temperature data of the server group. Among them, the average value, median or weighted average value may be calculated based on the temperature data of some or all sensors of the server group as the first representative temperature data. Alternatively, one temperature data may be selected from the temperature data of some or all sensors of the server group as the first representative temperature data.

[0026] S102: Determine temperature distribution data of the server cluster according to the temperature data of the multiple server groups.

[0027] In some embodiments, the temperature data of each server group can represent the heat generated by the server group in real time, and thus can reflect the load size of the server group. The temperature distribution data of the server cluster can be determined using the temperature data of each server group in the server cluster. The temperature distribution data of the server cluster can characterize the difference in the temperature data of the server cluster and the size of the overall heat dissipation. In one possible implementation, the temperature data of the multiple server groups can constitute the temperature distribution data. Thus, the temperature distribution data may include the temperature data of the multiple server groups. In another possible implementation, the temperature distribution data of the server cluster can also be determined based on the temperature data of the multiple server groups. For example, a temperature distribution curve, a temperature histogram, or a temperature thermodynamic map can be generated based on the temperature data of each server group in the server cluster. The temperature distribution data of the server cluster may include the generated temperature distribution curve, temperature histogram, or temperature thermodynamic map.

[0028] S103: Determine temperature difference data among the plurality of server groups according to the temperature distribution data.

[0029] In some instances, the temperature difference data between the multiple server groups can be calculated based on the temperature distribution data of the server cluster. The temperature difference data is used to characterize the degree of difference in temperature data between the server groups in the server cluster. Depending on the temperature distribution data, the method of calculating the temperature difference data may be different. Several possible implementations are introduced below. For example, the temperature distribution data may include temperature data of multiple server groups, and the temperature difference data may be the variance between the temperature data of multiple server groups. For example, the temperature distribution data may include a temperature distribution curve, and the temperature difference data may include the difference between the maximum value and the minimum value of the temperature distribution curve. For another example, the temperature distribution data may include a temperature histogram, and the temperature interval corresponding to the most server groups may be selected, and the median of the temperature interval may be obtained as the temperature difference data.

[0030] By calculating the temperature difference data between multiple server groups, we can comprehensively obtain the load balance of each server group in the server cluster, which is of great significance for the selection of fan speed control strategy under different subsequent load conditions.

[0031] Depending on the temperature distribution data, the method of calculating the temperature difference data may be different. For example, when the temperature distribution data directly includes the temperature data of multiple server groups, the variance or standard deviation of the temperature distribution data (i.e., the temperature data of all server groups) may be calculated as the temperature difference data between the multiple server groups, or the absolute deviation value between the maximum value and the minimum value in the temperature data of all server groups may be calculated as the temperature difference data between the multiple server groups. For example, when the temperature distribution data includes a temperature distribution curve, the absolute deviation value between the maximum value and the minimum value of the temperature distribution curve may be calculated to obtain the temperature difference data between the multiple server groups. For another example, when the temperature distribution data includes a temperature histogram, the temperature interval corresponding to the most server groups may be selected, and the median of the temperature interval may be obtained to obtain the temperature difference data between the multiple server groups. The temperature difference data may represent the degree of fluctuation of the temperature distribution curve formed by the temperature data of multiple server groups, i.e., the fluctuation size and frequency of the temperature data of multiple server groups. The smaller the temperature difference data, the more stable the temperature distribution curve formed by the temperature data of multiple server groups, and the more balanced the load of the server cluster; the larger the temperature difference data, the more tortuous the temperature distribution curve formed by the temperature data of multiple server groups, and the more unbalanced the load of the server cluster.

[0032] S104: When the temperature difference data is greater than or equal to the temperature difference threshold, a target server group whose fan speed is greater than or equal to the speed threshold is selected from the multiple server groups, and the fan speed of the adjacent server group of the target server group is increased, and the distance between the adjacent server group and the target server group meets the adjacent condition.

[0033] In some embodiments, when the temperature difference data is greater than or equal to the temperature difference threshold, it indicates that the temperature data between the server groups in the server cluster are relatively different, and thus the respective fan speeds can be adjusted according to the temperature partitioning conditions of the different server groups in the server cluster. To this end, when the temperature difference data is greater than or equal to the temperature difference threshold, for each server group in the server cluster, the speed of one or more fans corresponding to the server group can be adjusted according to the temperature data of the server group, thereby realizing refined fan speed control. Specifically, the fan speed control strategy can be used to adjust the fan speed. For example, a unified fan speed control strategy can be set for the server cluster. Then, for each server group in the server cluster, the speed of one or more fans corresponding to the server group can be adjusted according to the temperature data of the server group using the unified fan speed control strategy. For another example, fan speed control strategies can also be set for different server groups in the server cluster. Then, for each server group in the server cluster, the fan speed control strategy corresponding to the server group can be selected from the fan speed control strategy set, and the fan speed control strategy corresponding to the server group can be used to adjust the speed of one or more fans corresponding to the server group.

[0034] The above fan speed control strategy is used to characterize the mapping relationship between temperature and fan speed. By substituting temperature data into the mapping relationship, the risk speed corresponding to the temperature data can be obtained. There can be a positive correlation between temperature and fan speed. The higher the temperature, the higher the fan speed. The lower the temperature, the lower the fan speed.

[0035] In some embodiments, second representative temperature data of the server cluster may be calculated based on the temperature data of the multiple server groups. The second representative temperature data is used to characterize the overall load of the server cluster. For example, the sum or mean of the temperature data of the multiple server groups may be calculated as the second representative temperature data of the server cluster.

[0036] By determining the second representative temperature data of the server cluster, the overall load condition of the server cluster can be obtained, which is of great significance for the selection of fan speed control strategies under subsequent different load conditions.

[0037] In some embodiments, the second representative temperature data of the server cluster can also be determined according to the temperature distribution data of the server cluster. Depending on the temperature distribution data, the method of calculating the second representative temperature data can be different. Several possible implementation methods are introduced below. For example, when the temperature distribution data directly includes the temperature data of multiple server groups, the sum or mean of the temperature distribution data (that is, the temperature data of all server groups) can be calculated as the second representative temperature data of the server cluster, or the weighted sum or weighted mean of all temperature distribution data, that is, the temperature data of all server groups, can be calculated as the second representative temperature data of the server cluster. For another example, when the temperature distribution data includes a temperature distribution curve, the area of ​​the temperature distribution curve can be calculated using integral as the second representative temperature data of the server cluster. For another example, when the temperature distribution data includes a temperature histogram, the median of the temperature intervals of all server groups can be obtained, and the weighted sum of the medians of all temperature intervals can be calculated as the second representative temperature data of the server cluster. The larger the second representative temperature data of the server cluster, the greater the temperature of the server cluster. The greater the heat emitted by each server group in the server cluster, the greater the load of the server cluster. The smaller the second representative temperature data of the server cluster is, the lower the temperature of the server cluster is, the smaller the heat emitted by each server group in the server cluster is, and the smaller the load of the server cluster is.

[0038] In some embodiments, after calculating the temperature difference data between the multiple server groups and calculating the second representative temperature data of the server cluster based on the temperature data of the multiple server groups, the fan speed of the entire server cluster or part of the server groups can be adjusted based on the temperature difference data between the multiple server groups and the second representative temperature data of the server cluster.

[0039] In some embodiments, when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is less than the temperature threshold, the fan of the server cluster can be turned off; when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is greater than or equal to the temperature threshold, the fan speed of the multiple server groups can be adjusted according to the second representative temperature data; when the temperature difference data is greater than or equal to the temperature difference threshold and the second representative temperature data is less than the temperature threshold, the speed of the corresponding fan can be adjusted according to the temperature data of each server group; when the temperature difference data is greater than or equal to the temperature difference threshold and the second representative temperature data is greater than or equal to the temperature threshold, the speed of the corresponding fan can be adjusted according to the temperature data of each server group.

[0040] In some embodiments, when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is less than the temperature threshold, it indicates that the overall temperature of the server cluster is low and the temperature difference between each server group is small. The difference in the temperature data of each server group in the server cluster is small, indicating that the load of the server cluster is relatively balanced. The overall temperature data of the server cluster is small, indicating that the overall load of the server cluster is small. Therefore, it can be considered that the heat dissipation capacity of the natural environment or the radiator cold source in the cabinet can evenly dissipate the heat generated by the server cluster. To this end, the fan of the server cluster can be turned off, and the heat dissipation capacity of the natural environment or the radiator cold source in the cabinet can be fully utilized to dissipate the heat of the server cluster. By turning off the fans of all server groups in the server cluster, the heat dissipation capacity of the natural environment or the radiator cold source in the cabinet can be effectively utilized for heat dissipation, thereby improving the PUE value of the cabinet and extending the service life of the fan.

[0041] In some embodiments, when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is greater than or equal to the temperature threshold, it indicates that the overall temperature of the server cluster is high, but the temperature difference of each server group is small. The difference in the temperature data of each server group in the server cluster is small, indicating that the load of the server cluster is relatively balanced. The overall temperature data of the server cluster is large, indicating that the overall load of the server cluster is large. Therefore, it can be considered that the heat dissipation capacity of the natural environment or the radiator cold source in the cabinet cannot dissipate the heat generated by the server cluster. To this end, the fan of the server cluster can be turned on for heat dissipation. At the same time, considering that the temperature difference between each server group is small, the fan speed of each server group in the server cluster can be uniformly adjusted according to the second representative temperature data of the server cluster for heat dissipation. According to the second representative temperature data of the server cluster, the fan speed of each server group in the server cluster is uniformly adjusted, and the server cluster can be quickly cooled, thereby improving the PUE value of the cabinet and extending the service life of the server and fan.

[0042] Specifically, the fan speed control strategy can be used to adjust the fan speed. The fan speed control strategy may include a mapping relationship between temperature and fan speed. The second representative temperature data of the server cluster can be substituted into the mapping relationship to calculate the speed, and then adjust the fan speed of each server group in the server cluster to the speed. For example, a linear mapping relationship formula between temperature and fan speed can be established using a one-variable first-order equation, or a nonlinear mapping relationship formula between temperature and fan speed can be established using a one-variable multi-order equation, and the second representative temperature data of the server cluster can be substituted into the established linear or nonlinear mapping relationship formula to calculate the speed.

[0043] In some embodiments, when the temperature difference data is greater than or equal to the temperature difference threshold, and the second representative temperature data is less than the temperature threshold, it indicates that the temperature data of each server group in the server cluster is relatively different, but the temperature data of the server cluster as a whole is relatively small. The temperature data of each server group in the server cluster is relatively different, indicating that the load of the server cluster is unbalanced. The temperature data of the server cluster as a whole is relatively small, indicating that the load of the server cluster as a whole is small. Therefore, although the temperature data of the server cluster as a whole is relatively small, it is possible that the temperature data of one or more server groups is relatively large. Thus, the rotation speed of the corresponding fan can be adjusted according to the temperature data of each server group.

[0044] Specifically, for each server group in the server cluster, the rotation speed of one or more fans corresponding to the server group can be adjusted according to the temperature data of the server group, so as to achieve refined fan speed control. Specifically, the fan speed can be adjusted using a fan speed control strategy. For example, a unified fan speed control strategy can be set for the server cluster. Then, for each server group in the server cluster, the rotation speed of one or more fans corresponding to the server group can be adjusted according to the temperature data of the server group using the unified fan speed control strategy. For another example, fan speed control strategies can also be set separately for different server groups in the server cluster. Then, for each server group in the server cluster, the fan speed control strategy corresponding to the server group can be selected from the fan speed control strategy set, and the fan speed control strategy corresponding to the server group can be used to adjust the rotation speed of one or more fans corresponding to the server group.

[0045] Specifically, the fan speed control strategy can be used to adjust the fan speed. The fan speed control strategy may include a mapping relationship between temperature and fan speed. The temperature data of each server group can be substituted into the mapping relationship to calculate the speed, and then adjust the fan speed of the server group to the speed.

[0046] In some embodiments, when the temperature difference data is greater than or equal to the temperature difference threshold, and the second representative temperature data is greater than or equal to the temperature threshold, it indicates that the temperature data of each server group in the server cluster is relatively different, and the temperature data of the server cluster as a whole is also relatively large. The temperature data of each server group in the server cluster is relatively different, indicating that the load of the server cluster is unbalanced. The temperature data of the server cluster as a whole is relatively large, indicating that the load of the server cluster as a whole is large. As a result, the heat generated by the server cluster cannot be evenly dissipated by the natural environment or the radiator cold source in the cabinet. Therefore, the speed of the corresponding fan can be adjusted according to the temperature data of each server group. The specific adjustment process can be referred to the aforementioned embodiment.

[0047] In some embodiments, when the temperature difference data is greater than or equal to the temperature difference threshold, the fan of the server group can be used to dissipate heat for the server group. However, it is possible that the load of one or more server groups in the server cluster is too large, so that the temperature of the one or more server groups is too high, so that the fan speed of the one or more server groups exceeds the speed threshold. The speed threshold can be, for example, 80% of the maximum speed. In this way, for a server group with an overload, sufficient heat dissipation cannot be achieved only through its own fan, so it is possible to fail due to excessive temperature. To this end, when the temperature difference data is greater than or equal to the temperature difference threshold, a target server group with a fan speed greater than or equal to the speed threshold can be selected from multiple server groups in the server cluster; an adjacent server group of the target server group can be determined from the multiple server groups; the speed of the fan of the adjacent server group can be increased; the distance between the adjacent server group and the target server group meets the adjacent condition. Thus, the fan speed of the adjacent server group can be increased to assist in dissipating heat for the target server group. Therefore, the fan speed of the target server group is greater than or equal to the speed threshold, indicating that the target server group is a server group with a large load. For a target server group with a heavy load, in addition to using the target server group's own fans for heat dissipation, fans of adjacent server groups can also be used to assist in cooling the target server group, thereby fully cooling the target server group.

[0048] In this way, by considering the heat dissipation impact of adjacent server groups, the overall heat dissipation effect of the server cluster is further optimized, making the load of different server groups more balanced, achieving reasonable allocation of fan resources and balanced distribution of temperature in the cabinet, more effectively avoiding waste of resources and extending the life of servers and fans.

[0049] The speed of the fan corresponding to each server group in the server cluster can be detected; whether the speed is greater than or equal to the set speed threshold can be determined; one or more server groups whose speed is greater than or equal to the speed threshold can be selected as the target server group. The number of the target server groups can be one or more. The multiple server groups of the server cluster can be set in different partitions of the cabinet, and each partition of the cabinet can include a server group. The spatial location data of the partition where each server group in the server cluster is located can be obtained. The distance between the target server group and one or more other server groups can be calculated according to the spatial location data; other server groups whose distances meet the adjacent conditions can be selected from the one or more other server groups as adjacent server groups. The adjacent condition can be that the distance is less than or equal to the distance threshold. Thus, the adjacent server group can include other server groups whose distances are less than or equal to the distance threshold. Alternatively, the adjacent condition can also be N (N is a natural number greater than or equal to 1) with the smallest distance. Thus, the adjacent server can also include N other server groups with the smallest distance. The other server groups here include server groups other than the target server group in the server cluster.

[0050] The temperature data of the target server group is greater than the temperature data of the adjacent server group. The temperature data of the target server group can be used to determine the rotation speed of the fans of each adjacent server group. This can increase the rotation speed of the fans of the adjacent server groups. For example, the temperature data of the target server group can be used to determine the fan rotation speed of the adjacent server group based on the fan rotation speed control strategy of the adjacent server group. Specifically, for example, the fan rotation speed control strategy can include a mapping relationship between temperature and fan rotation speed. The temperature data of the target server group can be substituted into the mapping relationship to obtain the fan rotation speed of the adjacent server group.

[0051] Of course, other methods may be used to increase the speed of the fans of the adjacent server groups. For example, the difference between the fan speed of the target server group and the speed threshold may be calculated, and the fan speed of the adjacent server group may be increased by the difference.

[0052] In some embodiments, fan speed control policies may be set for different server groups in a server cluster.

[0053] The historical temperature data of each server group can be collected; the fan speed control strategy of the server group can be determined based on the historical temperature data; the fan speed control strategy of each server group can be used to adjust the speed of the fan of the server group.

[0054] The historical temperature data collected by some or all sensors of each server group can be obtained. The fan speed corresponding to the historical temperature data can also be obtained. Then, the fan speed control strategy of the server group can be constructed based on the historical temperature data of each server group and its corresponding fan speed. For example, the fan speed control strategy can be constructed by fitting. The fan speed control strategy can include a mapping relationship between temperature and speed. The mapping relationship can include a linear mapping relationship (such as a linear equation in one variable) and a nonlinear mapping relationship (such as a multi-time equation in one variable).

[0055] By setting different fan speed control strategies for different server groups, the overall heat dissipation effect of the server cluster is optimized, load balancing of different server groups and reasonable allocation of fan resources are achieved, effectively avoiding waste of resources and extending the life of servers and fans.

[0056] Based on the above liquid cooling fan control method, this specification also proposes an embodiment of a liquid cooling fan control device. Figure 3 As shown, the liquid cooling fan control device may specifically include the following modules:

[0057] The acquisition module 301 may be used to acquire temperature data of multiple server groups in the server cluster, each server group corresponding to a fan for heat dissipation;

[0058] A calculation module 302 may be used to calculate temperature distribution data of the server cluster according to the temperature data of the plurality of server groups;

[0059] A determination module 303 may be used to determine temperature difference data between the plurality of server groups according to the temperature distribution data;

[0060] Adding module 304, when the temperature difference data is greater than or equal to the temperature difference threshold, selects a target server group whose fan speed is greater than or equal to the speed threshold from the multiple server groups, increases the fan speed of the adjacent server group of the target server group, and the distance between the adjacent server group and the target server group meets the adjacent condition.

[0061] In some embodiments, the server cluster is arranged in a cabinet, the multiple server groups are arranged in different partitions of the cabinet, and each partition of the cabinet further comprises a fan for heat dissipation and a sensor for collecting temperature data. The acquisition module 301 can be specifically used to obtain temperature data collected by multiple sensors of each server group and to obtain first representative temperature data of the temperature data collected by the multiple sensors as the temperature data of the server group.

[0062] In some embodiments, the determination module 303 may be further configured to determine second representative temperature data of the server cluster according to the temperature data of the plurality of server groups.

[0063] In some embodiments, the adding module 304 may be specifically configured to turn off fans of the plurality of server groups when the temperature difference data is less than a temperature difference threshold and the second representative temperature data is less than a temperature threshold.

[0064] In some embodiments, the adding module 304 may be further configured to adjust the fan speeds of the plurality of server groups according to the second representative temperature data when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is greater than or equal to the temperature threshold.

[0065] In some embodiments, the adding module 304 may be further configured to adjust the rotation speed of the corresponding fan according to the temperature data of each server group.

[0066] In some embodiments, the above-mentioned adding module 304 can also be specifically used to collect historical temperature data of each server group; determine the fan speed control strategy of the server group based on the historical temperature data; and use the fan speed control strategy of each server group to adjust the speed of the corresponding fan.

[0067] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0068] As can be seen from the above, a liquid cooling fan control device provided in an embodiment of this specification provides a refined fan speed control strategy based on temperature differences, so that resources can be allocated reasonably, which is of great significance for reducing the PUE value of the server cabinet under normal working conditions and extending the service life of the server and the fan.

[0069] The embodiment of the present specification also provides a computer device for a liquid cooling fan control method, including a processor and a memory for storing processor executable instructions. When the processor is implemented, it can perform the following steps according to the instructions: obtain temperature data of multiple server groups in a server cluster, each server group corresponds to a fan for heat dissipation; calculate temperature distribution data of the server cluster according to the temperature data of the multiple server groups; determine temperature difference data between the multiple server groups according to the temperature distribution data; when the temperature difference data is greater than or equal to a temperature difference threshold, select a target server group whose fan speed is greater than or equal to a speed threshold from the multiple server groups, increase the fan speed of the adjacent server group of the target server group, and the distance between the adjacent server group and the target server group meets the adjacent condition.

[0070] In order to complete the above instructions more accurately, refer to Figure 4 As shown, the embodiment of this specification also provides another specific computer device, wherein the computer device includes a network communication port 401, a processor 402 and a memory 403, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0071] The processor 402 can be specifically used to obtain temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation; to calculate temperature distribution data of the server cluster based on the temperature data of the multiple server groups; to determine temperature difference data between the multiple server groups based on the temperature distribution data; when the temperature difference data is greater than or equal to a temperature difference threshold, select a target server group whose fan speed is greater than or equal to a speed threshold from the multiple server groups, increase the fan speed of an adjacent server group of the target server group, and the distance between the adjacent server group and the target server group meets the adjacent condition.

[0072] The memory 403 may be specifically used to store corresponding instruction programs.

[0073] In the embodiment of this specification, the network communication port 401 can be a virtual port that is bound to different communication protocols to send or receive different data. For example, the network communication port 401 can be a port responsible for web data communication, or it can also be a port responsible for FTP data communication, or it can also be a port responsible for email data communication. In addition, the network communication port 401 can be a physical communication interface or communication chip. The network communication port 401 can be a wireless mobile network communication chip. For example, the network communication port 401 can be a wireless mobile network communication chip that supports protocols such as GSM and CDMA. The network communication port 401 can also be a Wifi chip or a Bluetooth chip, etc.

[0074] In this embodiment, the processor 402 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

[0075] In this embodiment, the memory 403 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function that has no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0076] Corresponds to Figure 1 In the method, an embodiment of the present invention further provides a computer-readable storage medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the above steps are executed.

[0077] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0079] These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A liquid cooling fan control method, characterized in that: include: Acquire temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation and multiple sensors; wherein, acquiring temperature data of multiple server groups in a server cluster comprises: acquiring temperature data collected by multiple sensors of each server group in the server cluster, acquiring first representative temperature data of the temperature data collected by the multiple sensors as the temperature data of the server group; Determining second representative temperature data of the server cluster according to temperature data of multiple server groups in the server cluster; Calculating temperature distribution data of the server cluster according to the temperature data of the multiple server groups; Determining temperature difference data between the plurality of server groups according to the temperature distribution data; When the temperature difference data is less than the temperature difference threshold and the second representative temperature data is less than the temperature threshold, the fans of the multiple server groups are turned off; when the temperature difference data is greater than or equal to the temperature difference threshold, a target server group whose fan speed is greater than or equal to the speed threshold is selected from the multiple server groups, and the fan speed of the adjacent server group of the target server group is increased, and the distance between the adjacent server group and the target server group meets the adjacent condition.

2. The method according to claim 1, characterized in that: The server cluster is arranged in a cabinet, the multiple server groups are arranged in different partitions of the cabinet, and each partition of the cabinet further includes a fan for heat dissipation and a sensor for collecting temperature data.

3. The method according to claim 1, characterized in that: When the temperature difference data is greater than or equal to the temperature difference threshold, the method further includes: The speed of the corresponding fan is adjusted according to the temperature data of each server group.

4. The method according to claim 1 or 3, characterized in that: The method further comprises: When the temperature difference data is smaller than the temperature difference threshold and the second representative temperature data is greater than or equal to the temperature threshold, the fan speeds of the plurality of server groups are adjusted according to the second representative temperature data.

5. The method according to claim 3, characterized in that: The adjusting the speed of the corresponding fan according to the temperature data of each server group includes: Collect historical temperature data for each server group; Determine the fan speed control strategy for the server group based on historical temperature data; Use the fan speed control strategy for each server group to adjust the speed of the corresponding fans.

6. A liquid cooling fan control device, characterized in that: include: An acquisition module is used to acquire temperature data of multiple server groups in a server cluster, each server group corresponding to a fan for heat dissipation and multiple sensors; wherein the acquisition of temperature data of multiple server groups in the server cluster includes: acquiring temperature data collected by multiple sensors of each server group in the server cluster, acquiring first representative temperature data of the temperature data collected by the multiple sensors as the temperature data of the server group; determining second representative temperature data of the server cluster according to the temperature data of the multiple server groups in the server cluster; A calculation module, used for calculating temperature distribution data of the server cluster according to the temperature data of the multiple server groups; A determination module, configured to determine temperature difference data between the plurality of server groups according to the temperature distribution data; An additional module is provided, which is used to turn off the fans of the multiple server groups when the temperature difference data is less than the temperature difference threshold and the second representative temperature data is less than the temperature threshold; when the temperature difference data is greater than or equal to the temperature difference threshold, select a target server group whose fan speed is greater than or equal to the speed threshold from the multiple server groups, increase the fan speed of the adjacent server group of the target server group, and the distance between the adjacent server group and the target server group meets the adjacent condition.

7. A computer device, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the instructions.

8. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images