Temperature monitoring device, temperature monitoring method, and temperature monitoring program

Abstract

To contribute to determining whether electronic components and modules requiring heat dissipation are not being properly cooled, and to identifying the root cause thereof.SOLUTION: A temperature monitoring device is configured to: acquire the temperatures of an electronic component and its cooling device at a first time, a second time, and a third time included in each of a plurality of measurement periods; calculate a first temperature change between the temperature of the electronic component acquired at the first time and the temperature of the electronic component acquired at the second time; calculate a second temperature change between the temperature of the cooling device acquired at the second time and the temperature of the cooling device acquired at the third time; and perform processing for determining the occurrence of a cooling abnormality in the electronic component on the basis of the calculated first and second temperature changes.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a temperature monitoring device, a temperature monitoring method, and a temperature monitoring program for monitoring the temperature of electronic components and the like. [Background technology]

[0002] Devices such as computers use electronic components such as a central processing unit (CPU) and modules such as a hard disk drive (HDD). These electronic components and modules consume power and generate heat, requiring appropriate cooling. In the following description, electronic components and modules are referred to as "electronic components." In particular, in information processing devices such as computers and servers, the CPU has the greatest impact on information processing performance and generally consumes the most power of all electronic components, generating the most heat. When the CPU becomes excessively hot, its internal protection functions are activated, suppressing or halting operation. Thus, when the CPU becomes too hot, the processing performance of the information processing device decreases or even becomes unable to process.

[0003] To prevent such situations and maintain normal operation, a cooling device using a cooling fan or other cooling components is typically attached to the CPU via a heat sink (heat sink) or a thermal grease that enhances heat transfer. Mounting a component on a circuit board or the like is also commonly referred to as "mounting." When a cooling device using a cooling fan is mounted on a CPU, the fan's rotation speed may be controlled according to the measured CPU temperature. Furthermore, a method for diagnosing whether a CPU's cooling device is operating normally is known, for example, by comparing the temperature measured when the CPU load is maintained constant with the temperature measured beforehand when the CPU is being cooled normally, thereby detecting a cooling device malfunction (see Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-187347 Summary of the Invention [Problem to be solved by the invention]

[0005] The disclosures of the above-mentioned prior art documents are incorporated herein by reference.The following analysis was conducted by the inventors.

[0006] However, the method disclosed in Patent Document 1 can detect an abnormality in the CPU cooling device, but cannot detect whether heat conduction from the CPU to the cooling device is normal. If heat conduction from the CPU to the cooling device is abnormal, even if a cooling device failure is detected, the underlying cause of the CPU cooling failure may not be identified. In other words, for example, if the underlying cause of the CPU cooling failure is a decrease in the efficiency of heat conduction between the cooling device and the surrounding air, the CPU will not be cooled normally even if the cooling device is replaced.

[0007] In view of the above-mentioned problems, the present disclosure aims to determine whether electronic components and modules that require heat dissipation in devices such as information processing devices are not being cooled properly, and to contribute to identifying the root cause of this. [Means for solving the problem]

[0008] In a first aspect of the present disclosure, there is provided a temperature monitoring device that monitors the temperature of an electronic device, the temperature monitoring device including one or more processors, an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component and measuring the temperature of the electronic component, and a second temperature sensor attached to the cooling device and measuring the temperature of the cooling device. The one or more processors of the temperature monitoring device are configured to acquire the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods, acquire the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time after the first time included in each of the plurality of predetermined measurement periods, acquire the temperature of the cooling device measured by at least the second temperature sensor at a third time after the second time included in each of the plurality of predetermined measurement periods, calculate a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the plurality of predetermined measurement periods and the temperature of the electronic component acquired at the second time, calculate a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the plurality of predetermined measurement periods and the temperature of the cooling device acquired at the third time, determine the occurrence of a cooling abnormality of the electronic component based on the calculated first temperature change and the second temperature change, and determine and report a cause of the occurrence of the cooling abnormality of the electronic component.

[0009] In a second aspect of the present disclosure, there is provided a temperature monitoring method for monitoring the temperature of an electronic device including an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component and measuring the temperature of the electronic component, and a second temperature sensor attached to the cooling device and measuring the temperature of the cooling device. The temperature monitoring method includes a first acquisition step, a second acquisition step, a third acquisition step, a first calculation step, a second calculation step, and a determination / reporting step. The first acquisition step acquires the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods. The second acquisition step acquires the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time included in each of the predetermined measurement periods after the first time. The third acquisition step acquires the temperature of the cooling device measured by at least the second temperature sensor at a third time included in each of the predetermined measurement periods after the second time. The first calculation step calculates a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the predetermined plurality of measurement periods and the temperature of the electronic component acquired at the second time. The second calculation step calculates a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the predetermined plurality of measurement periods and the temperature of the cooling device acquired at the third time. The determination and reporting step determines the occurrence of a cooling abnormality in the electronic component based on the calculated first temperature change and the calculated second temperature change, and determines and reports the cause of the occurrence of the cooling abnormality in the electronic component.

[0010] In a third aspect of the present disclosure, there is provided a temperature monitoring program for causing one or more processors of a temperature monitoring device that monitors the temperature of an electronic device including an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component and measuring the temperature of the electronic component, and a second temperature sensor attached to the cooling device and measuring the temperature of the cooling device to execute a first acquisition process, a second acquisition process, a third acquisition process, a first calculation process, a second calculation process, and a determination / reporting process. The first acquisition process acquires the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods. The second acquisition process acquires the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time after the first time included in each of the plurality of predetermined measurement periods. The third acquisition process acquires the temperature of the cooling device measured by at least the second temperature sensor at a third time after the second time included in each of the plurality of predetermined measurement periods. The first calculation process calculates a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the predetermined plurality of measurement periods and the temperature of the electronic component acquired at the second time. The second calculation process calculates a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the predetermined plurality of measurement periods and the temperature of the cooling device acquired at the third time. The determination and reporting process determines the occurrence of a cooling abnormality in the electronic component based on the calculated first temperature change and second temperature change, and determines and reports the cause of the occurrence of the cooling abnormality in the electronic component. The program may be recorded on a computer-readable storage medium. The storage medium may be a non-transitory medium such as a semiconductor memory, a hard disk, a magnetic recording medium, or an optical recording medium. The present disclosure may be embodied as a computer program product. [Effects of the Invention]

[0011] Each aspect of the present disclosure can contribute to determining when electronic components, modules, etc. that require heat dissipation in devices such as electronic equipment are not being cooled properly and to identifying the root cause of this. [Brief explanation of the drawings]

[0012] [Figure 1A] FIG. 1A is a diagram illustrating an example of the hardware configuration of a server device that can form the basis of the present disclosure. [Figure 1B] FIG. 1B is a diagram illustrating a cross section of the CPU portion shown in FIG. 1A. [Figure 2] FIG. 2 is a diagram illustrating an example of a functional block of a temperature monitoring function realized by a monitoring device of a server device. [Figure 3A] FIG. 3A is a graph illustrating the change over time in the CPU temperature TC and the heat sink temperature TH during the first measurement period, including times t1, t2, and t3. [Figure 3B] FIG. 3B is a graph illustrating the change over time in the CPU temperature TC' and the heat sink temperature TH' during the period including times t1, t2, and t3 in the second and subsequent measurement periods. [Figure 3C] FIG. 3C is a graph illustrating the change over time in the CPU temperature TC' and the heat sink temperature TH' during the period including times t1, t2, and t3 in the second and subsequent measurement periods. [Figure 3D] FIG. 3D is a graph illustrating the change over time in the CPU temperature TC' and the heat sink temperature TH' during the period including times t1, t2, and t3 in the second and subsequent measurement periods. [Figure 3E] FIG. 3E is a graph illustrating the change over time in the CPU temperature TC' and the heat sink temperature TH' during the period including times t1, t2, and t3 in the second and subsequent measurement periods. [Figure 4A]FIG. 4A is a flowchart showing the processing of the temperature monitoring function shown in FIG. [Figure 4B] FIG. 4B is a flowchart showing the processing of the temperature monitoring function shown in FIG. [Figure 4C] FIG. 4C is a flowchart showing the processing of the temperature monitoring function shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. However, the present disclosure is not limited to the embodiments described below. Furthermore, in each drawing, the same or corresponding elements are appropriately designated by the same reference numerals, and the same or corresponding processes and communications are also appropriately designated by the same reference numerals. Furthermore, it should be noted that the drawings are schematic, and the dimensions and ratios between the elements may differ from reality. Furthermore, the threshold values ​​shown below are examples and may be changed as appropriate depending on the application and configuration of the embodiments of the present disclosure. Furthermore, the threshold values ​​shown below are rough values ​​and should be understood as values ​​with a certain range. There is no substantial difference between the terms "above threshold" and "greater than threshold," and there is no substantial difference between the terms "below threshold" and "below threshold."

[0014] FIG. 1A illustrates an example hardware configuration of a server device 1 that can form the basis of this disclosure. FIG. 1B illustrates a cross-sectional view of the CPU unit 10 shown in FIG. 1A. FIG. 2 illustrates an example functional block of a temperature monitoring function unit 2 implemented by a monitoring device 144 of the server device 1. The server device 1 is an example of an electronic device that uses a CPU (electronic component), such as a computer, a signal processing device, a sequencer, or a control device. As illustrated in FIG. 1A, the server device 1 is configured such that the CPU unit 10, a main memory device 142, a monitoring device 144, an auxiliary memory device 146, and an interface (IF (Interface)) device 148, all mounted on a motherboard 120, are connected via an internal bus of the server device 1 to enable data input and output. However, the configuration shown in FIG. 1A can be applied not only to so-called server devices but also to general devices capable of information processing, such as personal computers (PCs), personal digital assistants (PDAs), and smartphones.

[0015] As shown in FIG. 1B , the CPU unit 10 includes a CPU 100, grease 102, and a heat sink 104. The CPU 100 is mounted on a motherboard 120 and has a high thermal conductivity. The grease 102 is applied to the top surface of the CPU 100. The grease 102 efficiently transfers heat from the CPU 100 to the heat sink 104. The CPU 100 contacts the heat sink 104 via the grease 102, allowing efficient heat transfer from the CPU 100 to the heat sink 104. While the CPU 100 may have the configuration shown in FIG. 1B as an example, the CPU 100 may also be mounted via a socket rather than directly on the motherboard 120. Instead of the heat sink 104, the CPU unit 10 may use an air-cooled cooling system using a cooling fan or Peltier element, or a liquid-cooled cooling system using water or other refrigerant. The heat sink 104 is an example of a cooling system for the CPU 100.

[0016] 1A and 1B, a temperature sensor 152 used to measure the temperature of CPU 100 is attached, and a temperature sensor 150 used to measure the temperature of heat sink 104 is attached. Output terminals of temperature sensors 150 and 152 are connected to interface device 148 via wires or the like, and temperature sensors 150 and 152 output the measured temperatures of heat sink 104 and CPU 100 to interface device 148. In addition, interface device 148 is further connected, via a cable or the like, to a notification device 154 that notifies the user of server device 1 of the occurrence of an abnormality, such as a decrease in the cooling efficiency of CPU 100 in CPU section 10 (hereinafter referred to as a "cooling abnormality") and displays the cause to the user.

[0017] The notification device 154 includes at least one of a light-emitting device and an audio output device, and a display (neither of which are shown). The light-emitting device includes a light-emitting element such as an LED that outputs an optical signal indicating that a cooling abnormality has occurred in the CPU unit 10, and the audio output device includes a speaker and an audio synthesizer that output an audio signal indicating that a cooling abnormality has occurred in the CPU unit 10. The display device displays the cause of the cooling abnormality in the CPU unit 10 to the user. The notification device 154 can be configured using the light-emitting element, audio output device, and display included in the server device 1.

[0018] 1A includes volatile memory elements such as RAM (Random Access Memory) and non-volatile memory elements such as ROM (Read Only Memory) and flash memory. The non-volatile memory elements of main memory 142 store, for the medium or long term, programs including instructions for realizing the functions of OS (operating system) 106, the functions of applications running on this OS (operating system) 106, the functions of a boot loader, and the like, as well as data required for executing these programs.

[0019] 1A, OS 106 includes a load execution function that causes CPU 100 to execute a given program, thereby increasing its utilization rate and imposing a load, and a function that measures the utilization rate of CPU 100, which indicates the percentage of processing time that a program being executed by CPU 100 occupies. Furthermore, the boot loader function includes a function that starts OS 106 when the power of server device 1 is switched from an OFF state to an ON state. The volatile memory element of main storage device 142 temporarily stores data required for CPU 100 to execute programs such as OS 106, application programs, and the boot loader.

[0020] The CPU unit 10 can include one or more CPUs (processors) and executes programs stored in the main storage device 142, the auxiliary storage device 146, etc. However, in the following description, for the sake of specificity and clarity, as shown in FIG. 1B, a specific example will be given in which the CPU unit 10 includes only one CPU 100.

[0021] The auxiliary storage device 146 includes a nonvolatile storage device such as an HDD or SSD (Solid State Drive). Similar to the nonvolatile storage element of the main storage device 142, the auxiliary storage device 146 can also store programs and data necessary for executing these programs. The auxiliary storage device 146 also includes a USB interface used to connect a USB (Universal Serial Bus) memory or the like, and can write data to and read data from a USB device such as a USB memory.

[0022] The interface device 148 performs processing for interfacing with an input device such as a keyboard that accepts user operations and an output device such as a display that outputs information to the user, and the server device 1. The interface device 148 also accepts the temperature values ​​of the heat sink 104 and the CPU 100 measured by the temperature sensors 150, 152, and outputs them to the monitoring device 144. The interface device 148 also displays on the display any occurrence of a cooling abnormality in the CPU 100 detected by the monitoring device 144 and the cause of the abnormality, and notifies the user.

[0023] The monitoring device 144 is also called a BMC (Baseboard Management Controller) and may be, for example, a general-purpose one-chip microcomputer mounted on the motherboard 120. The monitoring device 144 includes, for example, one or more processors that perform processing independent of the CPU 100, and storage elements such as a ROM and a RAM (neither of which are shown). The ROM built into the monitoring device 144 can store a program including instructions and commands for implementing the temperature monitoring function unit 2 shown in FIG. 2 and the function as a BMC.

[0024] The processor built into the monitoring device 144 executes a program stored in ROM and, as a BMC function, manages the server device 1 and monitors events, such as failures, that occur within the server device 1. The processor built into the monitoring device 144 also implements the function of the temperature monitoring function unit 2 shown in FIG. 2 . However, a program containing instructions for implementing the BMC function and the temperature monitoring function unit 2 may be stored in the main memory device 142 or the auxiliary memory device 146. In this case, the monitoring device 144 implements the BMC function and the temperature monitoring function unit 2 by executing the program stored in the monitoring device 144 or the auxiliary memory device 146. The BMC function and the temperature monitoring function unit 2 function may be implemented by dedicated hardware that does not involve the execution of a program. The BMC function may be included in the OS 106, and the temperature monitoring function unit 2 function may be additionally included in the OS 106. In this case, the monitoring device 144 is omitted.

[0025] 2, the temperature monitoring function unit 2 includes a temperature information collection unit 200, a temperature monitoring unit 202, a temperature change monitoring table database (temperature change monitoring table DB (Data Base)) 204, a cooling abnormality determination unit 212, and a cooling abnormality notification unit 214. The temperature monitoring unit 202 includes a first factor counter 206, a second factor counter 208, and a third factor counter 210. With these components, the temperature monitoring function unit 2 measures the temperatures of the heat sink 104 and the CPU 100 using the temperature sensors 150, 152, and detects the occurrence of a cooling abnormality in the CPU 100.

[0026] The temperature monitoring function unit 2 determines which of the first to third factors caused the occurrence of the cooling abnormality, and notifies the user of the server device 1 of the occurrence of the cooling abnormality and which of the first to third factors caused the cooling abnormality. If the server device 1 includes multiple CPU units 10, temperature sensors 150, 152 are connected to the CPUs 100 and heat sinks 104 of the multiple CPU units 10, respectively. In this case, the temperature monitoring function unit 2 measures the temperature using the temperature sensors 152, 150 attached to the heat sinks 104 and CPUs 100 included in each of the multiple CPU units 10, and detects the occurrence of a cooling abnormality in the CPUs 100.

[0027] The first cause of the cooling abnormality is a decrease in the efficiency of heat conduction due to an abnormality in the heat conduction from the CPU 100 to the heat sink 104. The second cause is a decrease in the efficiency of heat dissipation from the heat sink 104 to the surrounding air even though the heat conduction from the CPU 100 to the heat sink 104 is normal. The third cause of the cooling abnormality is the simultaneous occurrence of both the first and second causes.

[0028] First, the conditions under which it is determined that no cooling abnormality has occurred in the CPU 100 and the conditions under which it is determined that a cooling abnormality has occurred in the CPU 100 due to any of the first to third causes will be described with reference to FIGS. 3A to 3E and Tables 1 to 4. The processes of measuring the temperatures of the CPU 100 and the heat sink 104 and determining whether a cooling abnormality has occurred by the temperature monitoring function unit 2 executed in the monitoring device 144 are performed during each of a plurality of predetermined measurement periods. FIG. 3A is a diagram illustrating, in graph form, the changes over time in the temperature TC (unit: °C) of the CPU 100 and the temperature TH of the heat sink 104 during the first measurement period, including times t1, t2, and t3 (first to third times).

[0029] 3A includes temperature changes ΔTC (=TC1-TC2) and ΔTH (=TH1-TH2) of CPU 100 and heat sink 104 calculated during the first measurement period. The temperature changes ΔTC and ΔTH (first temperature change, second temperature change) calculated during the first measurement period are used as reference values ​​in the process of determining whether a cooling abnormality in CPU 100 has occurred due to the first to third factors during the second and subsequent measurement periods. However, these reference temperature changes do not need to be calculated during a single measurement period; for example, the average value of the temperature changes ΔTC and ΔTH calculated during several predetermined measurement periods from the first measurement period to the next may be used as the reference.

[0030] 3B to 3E are graphs illustrating the changes over time in the temperature TC' of the CPU 100 and the temperature TH' of the heat sink 104 during a period including times t1, t2, and t3 in the second and subsequent measurement periods. Note that Figures 3B to 3E further include temperature changes ΔTC and ΔTH used as references, and temperature changes ΔTC' (= TC1' - TC2') and ΔTH' (= TH1' - TH2') calculated during the second and subsequent measurement periods.

[0031] In each of Figures 3B to 3E, the dotted lines indicate the changes in temperatures TC' and TH' when a cooling abnormality occurs in the CPU 100 due to any of the first to third factors, and the solid lines indicate the temperatures TC and TH shown in Figure 3A. Of course, times t1, t2, and t3 do not have to coincide in each of the multiple measurement periods, but the time interval between times t1 and t2 coincides, and the time interval between times t2 and t3 coincides. Here, a specific example is given in which the temperatures of the CPU 100 and the heat sink 104 are measured at three times t1, t2, and t3 in one measurement period. However, the temperature measurements may be performed according to the time difference between the temperature changes of the CPU 100 and the heat sink 104. For example, temperature measurements at four or more times and processing based on the measured temperatures are within the scope of the present disclosure. More specifically, temperature TC2 may be measured at time t2, and temperature TH2 may be measured at time t2', which is slightly shifted from time t2.

[0032] 3A is, for example, the timing when the power of the server device 1 installed in a predetermined location is first turned on from an off state and the OS 106 is started, after which the CPU 100 is in a low usage rate and is in an unloaded state. Alternatively, the initial measurement period is the timing when the power of the server device 1 is first turned on from an off state after maintenance on the server device 1 is completed, for example, and the OS 106 is started, after which the CPU 100 is in an unloaded state.

[0033] 3B to 3E are times when the CPU 100 is in an almost unloaded state, for example, late at night when the company where the server device 1 is installed is closed, and there are no or very few users using the server device 1. Alternatively, the second and subsequent measurement periods are times when the power of the server device 1 is turned on from an off state for some reason, such as after maintenance on the server device 1 is completed, and the OS 106 is started, and the CPU 100 is in an unloaded state.

[0034] The predetermined time in the first and second and subsequent measurement periods is time t1. Furthermore, time t2 in these measurement periods is time t2 after time t1 when OS 106 increases the utilization rate of CPU 100, applying a load and a time Δt (unit: seconds) has elapsed. Furthermore, time t3 is time after a predetermined time has elapsed since OS 106 puts CPU 100 into an unloaded state after time t2.

[0035] Tables 1 to 4 show temperature change management tables corresponding to FIGS. 3B to 3E, respectively. Each entry in the temperature change management tables shown in Tables 1 to 4 includes, in association with each other, reference temperature changes ΔTC, ΔTH, temperature changes ΔTC', ΔTH' calculated at each measurement timing from the second measurement onwards, and differences α, β between the temperature changes ΔTC, ΔTH and the temperature changes ΔTC', ΔTH'. Note that α = ΔTC' - ΔTC, and β = ΔTH' - ΔTH. Table 1 shows the above numerical values ​​when no cooling abnormality occurs in CPU 100. Tables 2 to 4 show the above numerical values ​​when a cooling abnormality occurs in CPU 100 due to each of the first to third factors.

[0036] In calculating the temperature changes ΔTC, ΔTH, ΔTC', and ΔTH', it is not essential which temperature is subtracted from another. Specifically, to calculate the temperature difference ΔTC, it is not essential whether temperature TC2 is subtracted from temperature TC1 or temperature TC1 is subtracted from temperature TC2. The reason for the former subtraction in this description is to concretize and clarify the description of the invention. Similarly, it is not essential whether temperature changes ΔTC and ΔTH are subtracted from temperature changes ΔTC' and ΔTH' or temperature changes ΔTC' and ΔTH' are subtracted from temperature changes ΔTC and ΔTH to calculate the differences α and β. Regardless of which temperature is subtracted from another temperature, the positive and negative values ​​of the threshold values ​​(described below) used to determine cooling abnormalities of the CPU 100 are simply changed appropriately depending on the relationship between these temperatures.

[0037] First, with reference to FIG. 3B and Table 1, the conditions under which the temperature monitoring function unit 2 determines that no cooling abnormality has occurred in the CPU 100 will be described. As shown in FIG. 3A, when no cooling abnormality has occurred in the CPU 100, the temperature TC of the CPU 100 rises and reaches a peak between time t1 and time t2, and then drops between time t2 and time t3. The temperature of the heat sink 104 begins to rise with a delay from time t1, reaches a peak between time t2 and time t3, and then drops after time t3. In this way, there is a delay between the change in the temperature TC of the CPU 100 and the change in the temperature TH of the heat sink 104.

[0038] [Table 1]

[0039] As shown by the dotted and solid lines in FIG. 3B, if the temperature TC of the CPU 100 and the temperature changes ΔTC', ΔTH' of the heat sink 104 are substantially the same as those shown in FIG. 3A (ΔTC ≈ ΔTC = TC1' - TC2', ΔTH ≈ ΔTH' = TH2 - TH3'), it can be determined that no cooling abnormality has occurred in the CPU 100. The fact that the temperature changes ΔTC', ΔTH' are substantially the same as those shown in FIG. 3A also means that the differences α, β between the reference temperature changes ΔTC, ΔTH and the temperature changes ΔTC', ΔTH' are within a range that can be considered to be within the error range (e.g., approximately ±1°). As described above, if the differences α, β between the reference temperature changes ΔTC, ΔTH and the temperature changes ΔTC', ΔTH' are small enough to be considered to be within the error range in the second or subsequent measurement periods, the temperature monitoring function unit 2 can determine that no cooling abnormality has occurred in the CPU 100.

[0040] Next, with reference to Fig. 3C and Table 2, the conditions under which the temperature monitoring function unit 2 determines that a cooling abnormality in the CPU 100 has occurred due to an abnormality in heat conduction from the CPU 100 to the heat sink 104 via the grease 102 (first cause) will be described. During the second and subsequent measurement periods, as shown in Fig. 3C, the temperature TC' of the CPU 100, indicated by the dotted line, is higher than the reference temperature TC, indicated by the solid line. On the other hand, the temperature TH' of the heat sink 104, indicated by the dotted line, is lower than the reference temperature TC, indicated by the solid line.

[0041] These mean that the temperature of the heat sink 104 remains low despite the steep temperature gradient from the CPU 100 to the heat sink 104, that is, that an abnormality has occurred in the heat conduction from the CPU 100 via the grease 102, causing a cooling abnormality. This also means that the difference α exceeds the error range and becomes large on the positive side, and the difference β exceeds the error range and becomes large on the negative side. In such a case, the temperature monitoring function unit 2 can determine that a cooling abnormality of the CPU 100 has occurred due to the first factor.

[0042] [Table 2]

[0043] Next, with reference to FIG. 3D and Table 3, the conditions under which the temperature monitoring unit 2 determines that a cooling abnormality in the CPU 100 has occurred due to an abnormality (second factor) in the efficiency of heat dissipation from the heat sink 104 to the ambient air are present will be described. During the second and subsequent measurement periods, as shown in FIG. 3D, the temperatures TC′ and TH′ of the CPU 100, indicated by the dotted lines, are higher than the reference temperatures TC and TH, indicated by the solid lines. These indicate that the temperatures of the CPU 100 and the heat sink 104 are rising despite the normal temperature gradient from the CPU 100 to the heat sink 104 and the normal heat conduction from the CPU 100 to the heat sink 104 via the grease 102. In other words, the efficiency of heat dissipation from the heat sink 104 to the ambient air is decreasing. This also indicates that both the differences α and β exceed the error range and become large on the positive side. In such a case, the temperature monitoring unit 2 can determine that a cooling abnormality in the CPU 100 has occurred due to the second factor.

[0044] [Table 3]

[0045] Next, with reference to FIG. 3E and Table 4, the conditions under which the temperature monitoring function unit 2 determines that a cooling abnormality in the CPU 100 has occurred due to both the first and second factors (third factors) will be described. During the second and subsequent measurement periods, as shown in FIG. 3E, the temperature TC of the CPU 100, indicated by the dotted line, is higher than the reference temperature TC, indicated by the solid line, exceeding the margin of error. Meanwhile, the temperature TH of the heat sink 104, indicated by the dotted line, is the same as the reference temperature TH, indicated by the solid line, within the margin of error. This also means that the difference α becomes larger on the positive side, exceeding the margin of error, and the difference β becomes 0 within the margin of error.

[0046] These indicate the possibility that an abnormality has occurred in the heat conduction from the CPU 100 to the heat sink 104 via the grease 102, and that the efficiency of heat dissipation from the heat sink 104 to the surrounding air has decreased. In such a case, the temperature monitoring function unit 2 can determine that an abnormality in the cooling of the CPU 100 has occurred due to the third factor.

[0047] [Table 4]

[0048] Referring again to FIG. 2, the temperature information collection unit 200 of the temperature monitoring function unit 2 acquires the utilization rate of the CPU 100 via the OS 106 when it is time to start the second or subsequent measurement period from the first. When the temperature information collection unit 200 confirms that the utilization rate of the CPU 100 has remained sufficiently low and that an unloaded state has continued, it applies a load to the CPU 100 via the OS 106 for a period of time Δt. The temperature information collection unit 200 acquires the utilization rate of the CPU 100 from the OS 106 to confirm that a load is being applied to the CPU 100 during this period. Furthermore, when this period ends, the temperature information collection unit 200 reduces the utilization rate of the CPU 100 via the OS 106, returning the CPU 100 to an unloaded state.

[0049] As described above, the temperature information collecting unit 200 controls the load on the CPU 100 during each of the first, second, and subsequent measurement periods. Furthermore, during each of the first, second, and subsequent measurement periods, the temperature information collecting unit 200 acquires the temperatures TC1 to TC3 (at least TC1, TC2), TC1' to TC3' (at least TC1', TC2') of the CPU 100 and the temperatures TH1 to TH3 (at least TH2, TH3), TH1' to TH3' (at least TH2', TH3') of the heat sink 104 from the temperature sensor 150. The temperature information collecting unit 200 outputs the temperatures TC1 to TC3, TC1' to TC3', TH1 to TH3, and TH1' to TH3' acquired during each of the first, second, and subsequent measurement periods to the temperature monitoring unit 202.

[0050] The temperature monitoring unit 202 calculates temperature changes ΔTC, ΔTC', ΔTH, and ΔTH' from temperatures TC1-TC3, TC1'-TC3', TH1-TH3, and TH1'-TH3' input from the temperature information collecting unit 200 during each of the first, second, and subsequent measurement periods, and further calculates the differences α and β between them. The temperature monitoring unit 202 associates the calculated temperature changes ΔTC, ΔTC', ΔTH, and ΔTH' with the differences α and β as shown in Tables 1 to 4, and stores them in the respective entries of the temperature change management table stored in the temperature change monitoring table DB 204.

[0051] Furthermore, the temperature monitoring unit 202 processes the temperature change monitoring table stored in the temperature change monitoring table DB 204, and determines whether or not a cooling abnormality has occurred in the CPU 100 due to the first to third factors. If the temperature monitoring unit 202 determines that a cooling abnormality has occurred in the CPU 100 due to each of the first to third factors, the temperature monitoring unit 202 increments the count values ​​of the first factor counter 206, the second factor counter 208, and the third factor counter 210 (adds 1 to the measured value).

[0052] At the start of the first measurement period and when the user of the server device 1 is notified of a cooling abnormality in the CPU 100, the temperature monitoring unit 202 sets the measurement values ​​of the first factor counter 206, the second factor counter 208, and the third factor counter 210 to 0. At the end of each of the first, second, and subsequent measurement periods, the temperature monitoring unit 202 outputs the measurement values ​​of the first factor counter 206, the second factor counter 208, and the third factor counter 210 to the cooling abnormality determination unit 212.

[0053] Cooling anomaly determination unit 212 processes the measured values ​​of first factor counter 206, second factor counter 208, and third factor counter 210, and outputs information indicating whether a cooling anomaly has occurred in CPU 100 and which of the first to third factors is the cause thereof to cooling anomaly notification unit 214. First to third threshold values ​​are set for the measured values ​​of first factor counter 206, second factor counter 208, and third factor counter 210, respectively. When any of the measured values ​​of first factor counter 206, second factor counter 208, and third factor counter 210 reaches any of the first to third threshold values, cooling anomaly determination unit 212 notifies cooling anomaly notification unit 214 that a cooling anomaly has occurred in CPU 100 and outputs the cause (any of the first to third threshold values) to cooling anomaly notification unit 214.

[0054] When the cooling abnormality notification unit 214 is notified by the cooling abnormality determination unit 212 that a cooling abnormality has occurred in the CPU 100 and the cause of the abnormality is input, the cooling abnormality notification unit 214 controls the notification device 154 to notify a user, such as the administrator of the server device 1, of the occurrence of the cooling abnormality by means of an optical signal and an audio signal. The cooling abnormality notification unit 214 further displays the cause of the occurrence of the cooling abnormality (any of the first to third causes) on a display to show the user.

[0055] When the temperature monitoring function unit 2 notifies the user of the occurrence of a cooling abnormality and indicates the cause, the user takes action to resolve the cause of the cooling abnormality. When a cooling abnormality of the CPU 100 caused by a first factor is notified, the user takes action such as bringing the CPU 100 and the heat sink 104 closer together, changing the mounting position of the heat sink 104, or reapplying the grease 102. When a cooling abnormality of the CPU 100 caused by a second factor is notified, the user takes action to improve the cooling effect of the heat sink 104, such as cleaning the area around the heat sink 104. When a cooling abnormality of the CPU 100 caused by a third factor is notified, the user takes action (actions to resolve the first and second factors) such as bringing the CPU 100 and the heat sink 104 closer together, changing the mounting position of the heat sink 104, reapplying the grease 102, or cleaning the area around the heat sink 104.

[0056] The processing of the temperature monitoring function unit 2 shown in Fig. 2 will be described below with reference to a flowchart. Fig. 4A to Fig. 4C are flowcharts showing the processing of the temperature monitoring function unit 2 shown in Fig. 2. As shown in Fig. 4A, in S100, after the user of the server device 1 sets the server device 1 to a company or the like, the user first switches the power of the server device 1 from an OFF state to an ON state.

[0057] In S102, a boot loader stored in the main memory device 142 (FIG. 1A) of the server device 1 reads out an OS also stored in the monitoring device 144, loads it into the main memory device 142, and starts up the OS 106. The OS 106 starts up the temperature monitoring function unit 2, and the temperature change monitoring table DB 204 of the temperature monitoring function unit 2 clears the count values ​​of the first factor counter 206, second factor counter 208, and third factor counter 210 to zero (sets them to 0). The temperature monitoring function unit 2 proceeds to the processing of S2 shown in FIGS. 4B and 4C.

[0058] 4B, in S200, the temperature information collecting unit 200 of the temperature monitoring function unit 2 acquires the utilization rate of the CPU 100 via the OS 106 and compares the acquired utilization rate with a predetermined threshold. As a result of this comparison, if the temperature information collecting unit 200 determines that the acquired utilization rate is equal to or less than the predetermined threshold, the CPU 100 is in an unloaded state, and the first or i-th (2≦i)th measurement period has started, the process proceeds to S202 (Y in S200). If the temperature information collecting unit 200 determines that the acquired utilization rate is greater than the predetermined threshold, and the CPU 100 is not in an unloaded state, the process remains at S200 (N in S200).

[0059] In S202, when a predetermined time has elapsed since the start of the first measurement period and time t1 has arrived, the temperature information collection unit 200 reads out temperatures TC1 and TH1 of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. When a predetermined time has elapsed since the start of the i-th measurement period and time t1 has arrived, the temperature information collection unit 200 reads out temperatures TC1' and TH1' of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. However, reading out temperature TH1' of the heat sink 104 is not essential. In S204, the temperature information collection unit 200 causes the CPU 100 to execute a given program via the OS 106, and increases the utilization rate of the CPU 100 to apply a load between times t1 and t2, that is, for a period of time Δt.

[0060] In S206, at time t2 during the first measurement period, the temperature information collection unit 200 reads out temperatures TH2 and TC2 of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. At time t2 during the i-th measurement period, the temperature information collection unit 200 reads out temperatures TH2' and TC2' of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. Furthermore, the temperature information collection unit 200 causes the CPU 100 to stop executing a given program via the OS 106, and brings the utilization rate of the CPU 100 close to 0 between times t2 and t3, placing it in an unloaded state.

[0061] In S208, at time t3 during the first measurement period, the temperature information collecting unit 200 reads out temperatures TH3 and TC3 of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. Also, at time t3 during the i-th measurement period, the temperature information collecting unit 200 reads out temperatures TH3' and TC3' of the heat sink 104 and CPU 100 from the temperature sensors 150 and 152. However, reading out temperature TC3' from the CPU 100 is not essential.

[0062] In S210, the temperature monitoring unit 202 calculates the temperature changes ΔTC (= TC1 - TC2) and ΔTH (= TH1 - TH2) during the first measurement period (see FIG. 3A). Furthermore, during the i-th measurement period, the temperature monitoring unit 202 calculates the temperature changes ΔTC' (= TC1' - TC2') and ΔTH' (= TC1' - TC2'). In S212, the temperature monitoring unit 202 calculates the differences α (= ΔTC' - ΔTC) and β (= ΔTH' - ΔTH) between the temperature changes ΔTC, ΔTH and the temperature changes ΔTC', ΔTH'. The temperature monitoring unit 202 associates the temperature changes ΔTC, ΔTC', ΔTH, ΔTH' with these differences α and β as shown in Tables 1 to 4, creates one entry to be included in the temperature change monitoring table, and stores it in the temperature change monitoring table DB 204.

[0063] In S214, the temperature information collecting unit 200 determines whether the processes of S200 to S212 have been performed in the first measurement period. If the processes of S200 to S212 have been performed in the first measurement period (Y in S214), the temperature monitoring function unit 2 proceeds to S220. If the processes of S200 to S212 have been performed in the i-th measurement period (N in S214), the temperature monitoring function unit 2 proceeds to S230 (FIG. 4C).

[0064] In S220, the temperature information collecting unit 200 determines whether the second measurement period has started. If the second measurement period has started (Y in the process of S220), the temperature monitoring function unit 2 returns to the process of S200. If the second measurement period has not started, the temperature monitoring function unit 2 remains in the process of S220.

[0065] As shown in Fig. 4C, in S230, the temperature monitoring unit 202 determines whether the difference α calculated during the i-th measurement period is higher than a predetermined threshold value of +3°C (α≦+3). If the difference α calculated during the i-th measurement period is +3°C or less, the temperature monitoring unit 202 determines that no cooling abnormality has occurred in the CPU 100, as explained with reference to Figs. 3A, 3B, and Tables 1 and 2, and returns to the processing of S200 (see Fig. 3B and Table 1). If the difference α is higher than +3°C, the temperature monitoring unit 202 proceeds to the processing of S232.

[0066] In S232, the temperature monitoring unit 202 determines whether the difference β calculated in the i-th measurement period is lower than a predetermined threshold of −2° C. If the difference α calculated in the i-th measurement period is lower than −2° C. (Y in S232), the temperature monitoring unit 2 proceeds to S234. If the difference α is higher than −2° C. (N in S232), the temperature monitoring unit 2 proceeds to S240.

[0067] 3C and Table 2, that is, an abnormality in the cooling of the CPU 100 has occurred due to a decrease in the efficiency of heat conduction caused by an abnormality in the heat conduction from the CPU 100 to the heat sink 104. In S236, the temperature monitoring unit 202 increments the count value of the first cause counter 206.

[0068] In S240, the temperature monitoring unit 202 determines whether the difference β calculated during the i-th measurement period is higher than a predetermined threshold of +2° C. If the difference β is higher than +2° C. (Y in the process of S240), the temperature monitoring unit 2 proceeds to the process of S242. If the difference β is equal to or lower than +2° C. (N in the process of S240), the temperature monitoring unit 2 proceeds to the process of S250.

[0069] 3D and Table 3, that is, a decrease in the efficiency of heat dissipation from the heat sink 104 to the surrounding air despite normal heat conduction from the CPU 100 to the heat sink 104. In S244, the temperature monitoring unit 202 increments the count value of the second factor counter 208.

[0070] In S250, the temperature monitoring unit 202 determines that the cooling abnormality of the CPU 100 has occurred due to the third factor described with reference to Fig. 3E and Table 4, i.e., due to both the first and second factors. In S252, the temperature monitoring unit 202 increments the count value of the third factor counter 210.

[0071] In S260, the cooling abnormality determination unit 212 determines whether or not one or more of the count values ​​of the first factor counter 206, the second factor counter 208, and the third factor counter 210 exceed a predetermined threshold value for each of the first factor counter 206, the second factor counter 208, and the third factor counter 210. When one or more of the count values ​​of the first factor counter 206, the second factor counter 208, and the third factor counter 210 exceed a threshold value, the cooling abnormality determination unit 212 determines that a cooling abnormality in the CPU 100 has actually occurred, rather than that it has occurred temporarily due to some cause (Y in the process of S260). Furthermore, the temperature monitoring function unit 2 proceeds to the process of S262. When the cooling abnormality determination unit 212 determines that a cooling abnormality in the CPU 100 has not actually occurred (N in the process of S260), the temperature monitoring function unit 2 returns to the process of S200.

[0072] In S262, the cooling abnormality notification unit 214 notifies the user of the server device 1 of the occurrence of a cooling abnormality in the CPU 100 and the cause thereof by means of an optical signal, an audio signal and a display on the display.

[0073] According to the processing of the temperature monitoring function unit 2 described above, when a cooling abnormality occurs in the CPU 100, the fact and the cause can be appropriately notified to the user of the server device 1. Therefore, the user of the server device 1 can appropriately and fundamentally eliminate the cause of the cooling abnormality in the CPU 100, preventing problems such as slowdowns or shutdowns of the operation of the server device 1. Furthermore, the temperature monitoring function unit 2 can be applied to a CPU unit 10 that uses a cooling device that uses a fan or the like to cool the CPU 100 instead of the heat sink 104. Even in such a case, the temperature monitoring function unit 2 prevents increases in noise and power consumption from the cooling device compared to when a cooling abnormality in the CPU 100 is prevented by constantly rotating a cooling fan at high speed.

[0074] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. [Appendix 1] A temperature monitoring device that includes one or more processors and monitors the temperature of an electronic device, the temperature monitoring device comprising: an electronic component; a cooling device attached to the electronic component; a first temperature sensor attached to the electronic component and measuring the temperature of the electronic component; and a second temperature sensor attached to the cooling device and measuring the temperature of the cooling device. The one or more processors of the temperature monitoring device are configured to acquire the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods, acquire the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time after the first time included in each of the plurality of predetermined measurement periods, acquire the temperature of the cooling device measured by at least the second temperature sensor at a third time after the second time included in each of the plurality of predetermined measurement periods, calculate a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the plurality of predetermined measurement periods and the temperature of the electronic component acquired at the second time, calculate a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the plurality of predetermined measurement periods and the temperature of the cooling device acquired at the third time, determine the occurrence of a cooling abnormality of the electronic component based on the calculated first temperature change and the second temperature change, and determine and report a cause of the occurrence of the cooling abnormality of the electronic component. [Appendix 2] 2. A temperature monitoring device according to claim 1, which notifies the occurrence of a determined cooling abnormality in the electronic component and the cause of the determined cooling abnormality in the electronic component. [Appendix 3] 3. The temperature monitoring device of claim 1, wherein at the first time, the electronic component is in an unloaded state, from the first time until the second time when a predetermined first time has elapsed, the electronic component is in a loaded state, and from the second time until the third time when a predetermined second time has elapsed, the electronic component is in an unloaded state, and during each of the plurality of measurement periods, the temperature of the electronic component is highest between the first time and the second time, and the temperature of the cooling device is highest between the second time and the third time. [Appendix 4] A temperature monitoring device according to any one of appendices 1 to 3, which determines that a cooling abnormality has occurred in the electronic component when a value obtained by subtracting a reference first temperature change obtained from the first temperature change acquired in one or more predetermined measurement periods from the first temperature change obtained in each of the plurality of predetermined measurement periods is higher than a predetermined first threshold value. [Appendix 5] A temperature monitoring device as described in any one of appendices 1 to 4, which determines that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the electronic component to the cooling device when a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the predetermined plurality of measurement periods is lower than a predetermined second threshold value. [Appendix 6] A temperature monitoring device as described in any of Appendices 1 to 5, which determines that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the cooling device to the surroundings when a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the predetermined plurality of measurement periods is lower than a predetermined second threshold. [Appendix 7] A temperature monitoring device as described in any of Appendices 1 to 6, which determines that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the electronic component to the cooling device and a decrease in efficiency of heat conduction from the cooling device to the surroundings when a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the predetermined plurality of measurement periods is higher than a predetermined second threshold. [Appendix 8] A temperature monitoring device as described in any one of appendices 1 to 7, which determines that a cooling abnormality has occurred in the electronic component due to a decrease in the efficiency of heat conduction from the electronic component to the cooling device, which reports the occurrence of the determined cooling abnormality in the electronic component and the cause of the determined cooling abnormality in the electronic component when any of the following occurs more than a predetermined number of times: a determination that a cooling abnormality in the electronic component has occurred due to a decrease in the efficiency of heat conduction from the cooling device to the surroundings, or a determination that a cooling abnormality in the electronic component has occurred due to a decrease in the efficiency of heat conduction from the electronic component to the cooling device and a decrease in the efficiency of heat conduction from the cooling device to the surroundings. [Appendix 9] A temperature monitoring method for monitoring the temperature of an electronic device including an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component for measuring the temperature of the electronic component, and a second temperature sensor attached to the cooling device for measuring the temperature of the cooling device. The temperature monitoring method includes a first acquisition step, a second acquisition step, a third acquisition step, a first calculation step, a second calculation step, and a determination / notification step. The first acquisition step acquires the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods. The second acquisition step acquires the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time included in each of the predetermined measurement periods after the first time. The third acquisition step acquires the temperature of the cooling device measured by at least the second temperature sensor at a third time included in each of the predetermined measurement periods after the second time. The first calculation step calculates a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the predetermined plurality of measurement periods and the temperature of the electronic component acquired at the second time. The second calculation step calculates a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the predetermined plurality of measurement periods and the temperature of the cooling device acquired at the third time. The determination and notification step determines the occurrence of a cooling abnormality in the electronic component based on the calculated first temperature change and second temperature change, and determines and notifies the cause of the occurrence of the cooling abnormality in the electronic component. [Appendix 10] A temperature monitoring program causes one or more processors of a temperature monitoring device that monitors the temperature of an electronic device, the temperature monitoring device including an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component for measuring the temperature of the electronic component, and a second temperature sensor attached to the cooling device for measuring the temperature of the cooling device, to execute a first acquisition process, a second acquisition process, a third acquisition process, a first calculation process, a second calculation process, and a determination / notification process. The first acquisition process acquires the temperature of the electronic component measured by at least the first temperature sensor at a first time included in each of a plurality of predetermined measurement periods. The second acquisition process acquires the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time after the first time included in each of the plurality of predetermined measurement periods. The third acquisition process acquires the temperature of the cooling device measured by at least the second temperature sensor at a third time after the second time included in each of the plurality of predetermined measurement periods. The first calculation process calculates a first temperature change between the temperature of the electronic component acquired at least at the first time during each of the predetermined plurality of measurement periods and the temperature of the electronic component acquired at the second time. The second calculation process calculates a second temperature change between the temperature of the cooling device acquired at least at the second time during each of the predetermined plurality of measurement periods and the temperature of the cooling device acquired at the third time. The determination and notification process determines the occurrence of a cooling abnormality in the electronic component based on the calculated first temperature change and second temperature change, and determines and notifies the cause of the occurrence of the cooling abnormality in the electronic component. It goes without saying that combinations of the various aspects of the appendices of the present disclosure, or arbitrary combinations of the elements described in the various aspects and embodiments (including the non-selection of some elements) can be made by those skilled in the art at any time in accordance with the basic concept of the present disclosure. Alternatively, the present disclosure also includes the temperature monitoring method and temperature monitoring program described in appendices 9 and 10 being implemented in the configuration of the temperature monitoring device described in appendices 2 to 8.

[0075] The disclosures of the above-cited patent documents and other documents are incorporated herein by reference. Modifications and adjustments of the embodiments and examples are possible within the scope of the entire disclosure of the present invention (including the claims), and further based on the basic technical concept thereof. Furthermore, various combinations and selections (including partial deletions) of various disclosed elements (including elements of each claim, each element of each embodiment or example, each element of each drawing, etc.) are possible within the scope of the entire disclosure of the present invention. In other words, the present invention naturally includes various modifications and alterations that would be possible by those skilled in the art in accordance with the entire disclosure and technical concept, including the claims. In particular, the numerical ranges set forth herein should be construed as specifically describing any numerical value or subrange within the range, even if not otherwise specified. Furthermore, the disclosures of the above-cited documents are deemed to be included in the disclosure of this application, in part or in whole, which may be used in combination with the disclosures herein, as part of the disclosure of the present invention, in accordance with the spirit of the present invention, as necessary. [Explanation of symbols]

[0076] 1. Server device 10 CPU section 100 CPU 102 Grease 104 Heatsink 106 OS 120 motherboard 142 Main storage 144 Monitoring equipment 146 Auxiliary storage 148 Interface Device 150,152 Temperature Sensor 154 Notification device 2 Temperature monitoring function section 200 Temperature Information Collection Unit 202 Temperature monitoring section 204 Temperature change monitoring table database (DB) 206 First Factor Counter 208 Second Factor Counter 210 Third Factor Counter 212 Cooling abnormality determination section 214 Cooling Abnormality Reporting Department

Claims

1. 1. A temperature monitoring device for monitoring a temperature of an electronic device, the temperature monitoring device including one or more processors, the temperature monitoring device comprising: an electronic component; a cooling device attached to the electronic component; a first temperature sensor attached to the electronic component for measuring a temperature of the electronic component; and a second temperature sensor attached to the cooling device for measuring a temperature of the cooling device, The one or more processors: At a first time point included in each of a plurality of predetermined measurement periods, the temperature of the electronic component measured by at least the first temperature sensor is acquired; At a second time point after the first time point included in each of the plurality of predetermined measurement periods, the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor are acquired; acquiring a temperature of the cooling device measured by at least the second temperature sensor at a third time point that is included in each of the plurality of predetermined measurement periods and that is subsequent to the second time point; calculating a first temperature change between the temperature of the electronic component acquired at least at the first time and the temperature of the electronic component acquired at the second time during each of the predetermined plurality of measurement periods; calculating a second temperature change between the temperature of the cooling device acquired at least at the second time and the temperature of the cooling device acquired at the third time during each of the predetermined plurality of measurement periods; Based on the calculated first temperature change and second temperature change, occurrence of a cooling abnormality in the electronic component is determined, and the cause of the occurrence of the cooling abnormality in the electronic component is determined and reported. A temperature monitoring device configured to perform a process.

2. The occurrence of the determined cooling abnormality of the electronic component and the cause of the determined cooling abnormality of the electronic component are notified.

2. The temperature monitoring device of claim 1.

3. At the first time, the electronic component is in an unloaded state; the electronic component is in a state where a load is applied from the first time to the second time when a predetermined first time has elapsed, the electronic component is in a no-load state from the second time to the third time when a predetermined second time has elapsed, In each of the plurality of measurement periods, the temperature of the electronic component reaches its highest between the first time and the second time, and the temperature of the cooling device reaches its highest between the second time and the third time.

3. The temperature monitoring device of claim 2.

4. When a value obtained by subtracting a reference first temperature change obtained from the first temperature change acquired in one or more predetermined measurement periods from the first temperature change obtained in each of the predetermined plurality of measurement periods is higher than a predetermined first threshold value, it is determined that a cooling abnormality has occurred in the electronic component.

4. The temperature monitoring device of claim 3.

5. When a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the predetermined plurality of measurement periods is lower than a predetermined second threshold value, it is determined that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the electronic component to the cooling device.

5. The temperature monitoring device of claim 4.

6. When a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the predetermined plurality of measurement periods is lower than a predetermined second threshold value, it is determined that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the cooling device to the surroundings.

5. The temperature monitoring device of claim 4.

7. When a value obtained by subtracting a reference second temperature change obtained from the second temperature change acquired in one or more predetermined measurement periods from the second temperature change obtained in each of the plurality of predetermined measurement periods is higher than a predetermined second threshold value, it is determined that a cooling abnormality has occurred in the electronic component due to a decrease in efficiency of heat conduction from the electronic component to the cooling device and a decrease in efficiency of heat conduction from the cooling device to the surroundings.

7. The temperature monitoring device of claim 6.

8. When any of the following occurs more than a predetermined number of times: determining that a cooling abnormality of the electronic component has occurred due to a decrease in efficiency of heat conduction from the electronic component to the cooling device; that a cooling abnormality of the electronic component has occurred due to a decrease in efficiency of heat conduction from the cooling device to the surroundings; and that a cooling abnormality of the electronic component has occurred due to a decrease in efficiency of heat conduction from the electronic component to the cooling device and a decrease in efficiency of heat conduction from the cooling device to the surroundings, reporting the occurrence of the determined cooling abnormality of the electronic component and the cause of the determined cooling abnormality of the electronic component.

8. The temperature monitoring device of claim 7.

9. 1. A temperature monitoring method for monitoring a temperature of an electronic device including an electronic component, a cooling device attached to the electronic component, a first temperature sensor attached to the electronic component to measure a temperature of the electronic component, and a second temperature sensor attached to the cooling device to measure a temperature of the cooling device, comprising: a first acquisition step of acquiring temperatures of the electronic component measured by at least the first temperature sensor at first times included in each of a plurality of predetermined measurement periods; a second acquisition step of acquiring the temperatures of the electronic component measured by the first temperature sensor and the temperatures of the cooling device measured by the first temperature sensor at second times subsequent to the first time included in each of the plurality of predetermined measurement periods; a third acquisition step of acquiring a temperature of the cooling device measured by at least the second temperature sensor at a third time point that is included in each of the plurality of predetermined measurement periods and that is after the second time point; a first calculation step of calculating a first temperature change between the temperature of the electronic component acquired at least at the first time and the temperature of the electronic component acquired at the second time during each of the predetermined plurality of measurement periods; a second calculation step of calculating a second temperature change between the temperature of the cooling device acquired at least at the second time and the temperature of the cooling device acquired at the third time during each of the predetermined plurality of measurement periods; a determining and reporting step of determining whether a cooling abnormality has occurred in the electronic component based on the calculated first temperature change and the calculated second temperature change, and determining and reporting a cause of the cooling abnormality in the electronic component; A temperature monitoring method including:

10. a temperature monitoring device for monitoring the temperature of an electronic device, the temperature monitoring device comprising: an electronic component; a cooling device attached to the electronic component; a first temperature sensor attached to the electronic component for measuring a temperature of the electronic component; and a second temperature sensor attached to the cooling device for measuring a temperature of the cooling device; a first acquisition process for acquiring temperatures of the electronic component measured by at least the first temperature sensor at first times included in each of a plurality of predetermined measurement periods; a second acquisition process for acquiring the temperature of the electronic component measured by the first temperature sensor and the temperature of the cooling device measured by the first temperature sensor at a second time point after the first time point included in each of the plurality of predetermined measurement periods; a third acquisition process for acquiring the temperature of the cooling device measured by at least the second temperature sensor at a third time point that is included in each of the plurality of predetermined measurement periods and that is after the second time point; a first calculation process for calculating a first temperature change between the temperature of the electronic component acquired at least at the first time and the temperature of the electronic component acquired at the second time during each of the predetermined plurality of measurement periods; a second calculation process for calculating a second temperature change between the temperature of the cooling device acquired at least at the second time and the temperature of the cooling device acquired at the third time during each of the predetermined plurality of measurement periods; a determination and notification process for determining the occurrence of a cooling abnormality in the electronic component based on the calculated first temperature change and the calculated second temperature change, and determining and notifying the cause of the occurrence of the cooling abnormality in the electronic component; A temperature monitoring program that runs.

Images