Power efficiency calculation device, power efficiency calculation method, power efficiency calculation system, and program

Abstract

This power efficiency computation device (1) comprises: a metrics collecting unit (101) that collects metrics from a physical server group (30); a task execution quantity normalization unit (102) that determines a normalization coefficient per task of each application (3); a degree-of-importance group setting unit (103) that sets degree-of-importance groups for each application (3) and each task, and determines weighting; and a power efficiency computation unit (104) that normalizes task execution quantity using the normalization coefficients, calculates a total work result quantity using said normalized task execution quantity and the weighting of the degree-of-importance groups of the applications (3) and the tasks, and computes power efficiency.

Description

[Technical Field]

[0001] The present invention relates to a power efficiency calculation device, a power efficiency calculation method, a power efficiency calculation system, and a program for calculating power efficiency for application processing. [Background technology]

[0002] To date, various definitions have been proposed for data center power efficiency indicators. Among them, the only indicator that can measure and calculate in real time how power-efficiently a specific application is being operated is DCeP (Data Center energy Productivity) (see Non-Patent Document 1). DCeP is defined by the following formula (1):

[0003]

number

[0004] DCeP (Power Efficiency) is defined as "Useful Work Produced" (referred to herein as "Work Output") divided by "Total Energy Consumed to Perform that Work" (referred to herein as "Power Consumption"). In addition, "Useful Work Produced" is defined by the following formula (2).

[0005]

number

[0006] where "M" is the number of tasks started during the evaluation window, "V i ” is the normalization coefficient obtained by summing the task values, “U i“(t,T)” is the time-based utility function for each task, “t” is the elapsed time from the start to the completion of the task, and “T” is the absolute time of task completion. Non-Patent Document 1 proposes setting a weighting factor for tasks that are the target of "Useful Work Produced" (amount of work output) and adjusting the balance of values between tasks. However, there is no mention of how this should be adjusted specifically. Furthermore, with regard to the assessment window, which is the measurement interval, it is only stated that "an interval of 20 or more task executions is desirable."

[0007] Furthermore, Non-Patent Document 2 defines "Useful Work Produced" as the energy consumed when various applications process data in an HPC (High Performance Computing) data center, and describes the results of calculating DCeP. However, Non-Patent Document 2 treats all tasks equally without considering the weight of each application type or the importance of processing between tasks.

[0008] In addition, Non-Patent Document 3 defines "Useful Work Produced" as the number of times two types of applications are executed within a certain period of time (Useful Computational Units), and normalizes the number of times each application is executed using a weighting coefficient (1:0.08). [Prior art documents] [Non-patent literature]

[0009] [Non-Patent Document 1] D. Anderson, et al., “A framework for data center energy productivity.” The Green Grid, 2008. [Non-patent document 2] A. Grishina, et al., “DC energy data measurement and analysis for productivity and waste energy assessment,” 2018 IEEE International Conference on Computational Science and Engineering (CSE), IEEE, 2018. [Non-patent document 3] Landon H. Sego, et al., “Implementing the data center energy productivity metric,” ACM Journal on Emerging Technologies in Computing Systems (JETC) 8.4 (2012): 1-22. Summary of the Invention [Problem to be solved by the invention]

[0010] The DCeP calculations described in Non-Patent Documents 1 to 3 do not take into account the weighting of each application type or the importance of processing between tasks. Therefore, even if there are differences in the importance of processing or SLAs (Service Level Agreements) between applications or between tasks within the same application, it is not possible to calculate the amount of processing ("Useful Work Produced") that takes into account the weighting between applications or tasks, and it is not possible to calculate an appropriate power efficiency value. In other words, Non-Patent Documents 1 to 3 do not define a method for setting weighting for each application type or the importance of processing between tasks when calculating DCeP.

[0011] For example, as shown in Figure 7, the number of times an application is executed is defined as the amount of task processing, and power efficiency is calculated as the total for two types of tasks (task A and task B). In this case, if the number of times each task is executed per unit time is 1,000 and 1, respectively, and no weights are set, the power efficiency will almost entirely reflect the results of task A. Therefore, even if task B is an important process, it will not be taken into account.

[0012] The present invention has been made in view of the above points, and an object of the present invention is to calculate power efficiency that reflects the importance of applications and tasks. [Means for solving the problem]

[0013] A power efficiency calculation device according to the present invention is a power efficiency calculation device that calculates the power efficiency resulting from the execution of an application installed on a group of physical servers, the group of physical servers being installed with one or more applications that execute one or more tasks, the power efficiency calculation device comprising: a metrics collection unit that collects metrics from the group of physical servers, which are evaluation indexes required for power efficiency calculation, and which include task execution amounts and power consumption of the group of physical servers, and stores the metrics in a metrics collection DB in a storage unit; a task execution amount normalization unit that acquires the task execution amounts stored in the metrics collection DB and determines a normalization coefficient for each task of each of the applications using the task execution amounts measured at predetermined measurement times; an importance group setting unit that sets importance groups based on a predetermined importance group setting logic and sets weights according to the importance of each of the importance groups of the applications and the importance groups of each of the tasks; and a power efficiency calculation unit that acquires metrics for a predetermined evaluation period collected by the metrics collection unit, normalizes the task execution amounts included in the metrics using the normalization coefficient for each task of each of the applications, calculates a total work result amount using the normalized task execution amounts and the importance group weights of each of the applications and each of the tasks, and calculates power efficiency from the power consumption included in the metrics and the total work result amount. [Effects of the Invention]

[0014] According to the present invention, it is possible to calculate power efficiency that reflects the importance of applications and tasks. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 10 is a diagram showing a calculation formula for "Useful Work Produced" according to the present embodiment. [Figure 2]FIG. 10 is a diagram for explaining a calculation formula for "Useful Work Produced" according to the present embodiment. [Figure 3] 1 is a diagram showing the overall configuration of a power efficiency calculation system including a power efficiency calculation device according to an embodiment of the present invention. [Figure 4] 10 is a diagram showing the maximum number of requests processed for each task within a certain period of time collected by the power efficiency calculation device according to the present embodiment. FIG. [Figure 5] 10 is a flowchart showing the flow of processing executed by the power efficiency calculation device according to the present embodiment. [Figure 6] FIG. 2 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the power efficiency calculation device according to the present embodiment. [Figure 7] FIG. 1 is a diagram for explaining a problem in a conventional calculation of power efficiency that does not take into account weights between applications or tasks. DETAILED DESCRIPTION OF THE INVENTION

[0016] Next, an embodiment of the present invention (hereinafter referred to as "the present embodiment") will be described. First, an overview of a power efficiency calculation device 1 (see FIG. 3 described later) according to the present embodiment will be described.

[0017] <Summary> The power efficiency calculation device 1 according to this embodiment is a device that calculates power efficiency while taking into consideration the importance of one or more applications (App) and one or more tasks executed by the applications. As an index of power efficiency, DCeP (power efficiency) shown in the above formula (1) is used. In this embodiment, weighting factors are defined for applications and tasks in calculating "Useful Work Produced" (amount of work product) to calculate DCeP (power efficiency).

[0018] In this embodiment, a "task" refers to a series of processes in which an application is started (by receiving information within the device) and begins processing a request until it is completed, or a series of processes in which an application in a running state receives a request from outside, begins processing, and returns a completion notification to the requestor.

[0019] In this embodiment, the power efficiency calculation device 1 calculates the "Useful Work Produced" (amount of work produced) in the above formula (1) as the total value of the execution amounts of all tasks to be measured that are executed by multiple applications, as shown in formula (3) in FIG. 1. Note that one application executes one or multiple types of tasks. The weighting coefficients are defined as "application weighting coefficient: W" and "task weighting coefficient: V."

[0020] The power efficiency calculation device 1 also uses two methods for determining the weights: (1) normalization of task execution amounts, and (2) group classification according to importance.

[0021] (1) "Normalization of task execution amount" is performed for multiple tasks including multiple applications, each of which has an Assessment window T A The amount of tasks completed in C ij TA The task execution volume C that is completed in a certain time ij T0 This is to calculate the power efficiency independent of the task execution amount, such as the number of tasks processed (e.g., the number of requests processed). The normalized task amount C ij is shown in equation (4) in Figure 2.

[0022] (2) In "Group classification by importance," weighting factors are set for each importance group for each application and task. As shown in formula (5-1) in Figure 2, the number of importance groups for applications, "m", is a number equal to or less than the number of application types, "M", and applications are classified into "m" importance groups. i ” is the weight coefficient for each group of applications {w0, w1, . m}. Also, as shown in equation (5-2) in Figure 2, the number of task importance groups, “n i " is the number of task types "N i " and "n i The tasks are classified into importance groups. ij ” is the weight coefficient for each group of tasks {v0, v1, ,vn i}.

[0023] In other words, application importance groups are classified into a number equal to or less than the number of types of target applications, and a weighting factor is defined for each importance group. Each application is assigned to an importance group in advance according to its importance. Similarly, tasks are classified into a number equal to or less than the number of types of target tasks, and a weighting factor is defined for each importance group. Each task is assigned to an importance group in advance according to its importance. The task volume of a given application is calculated by multiplying the application weighting factor by the task weighting factor.

[0024] In this way, the power efficiency calculation device 1 can calculate DCeP (power efficiency) for the "Useful Work Produced" (amount of work produced) of multiple applications or an application with multiple tasks, in a manner that reflects the importance of the applications and tasks, regardless of the processing volume.

[0025] FIG. 3 is a diagram showing the overall configuration of a power efficiency calculation system 1000 including a power efficiency calculation device 1 according to this embodiment. The power efficiency calculation system 1000 includes a group of physical servers 30 configured by a data center or the like, and a power efficiency calculation apparatus 1 connected to the group of physical servers 30 for communication.

[0026] The physical server group 30 is operated by, for example, building a virtualization infrastructure on a physical server, and one or more applications 3 are installed in a virtual machine (VM) or container on a virtual OS to execute processing. Each application 3 realizes a service by executing one or more tasks. The power efficiency calculation device 1 collects metrics, which are evaluation indices required for calculating DCeP (power efficiency), from the physical server group 30, and calculates power efficiency taking into account the importance of applications and tasks. The functions of the power efficiency calculation device 1 will be specifically described below.

[0027] As shown in FIG. 3, the power efficiency calculation device 1 includes a control unit 10, an input / output unit 11, and a storage unit 12.

[0028] The input / output unit 11 inputs and outputs information to and from each server of the physical server group 30. The input / output unit 11 is composed of a communication interface that transmits and receives information via a communication line, and an input / output interface that inputs and outputs information to and from an input device such as a keyboard and an output device such as a monitor (not shown).

[0029] The storage unit 12 is configured by a hard disk, a flash memory, a RAM (Random Access Memory), or the like. The storage unit 12 temporarily stores programs for executing the functions of the control unit 10 and information necessary for the processing of the control unit 10. The storage unit 12 also stores metrics required for calculating DCeP (power efficiency) collected from each physical server in the physical server group 30, an OS (virtual OS), a VM, a container, an application, and the like, and stores the collected metrics in a metrics collection database (DB: Database) 100.

[0030] The control unit 10 controls all the processes executed by the power efficiency calculation device 1, and as shown in FIG. 3, includes a metrics collection unit 101, a task execution amount normalization unit 102, an importance group setting unit 103, and a power efficiency calculation unit 104.

[0031] The metrics collection unit 101 collects metrics (evaluation indexes for performance, etc.) required for power efficiency calculation from the physical server group 30 and stores them in the metrics collection DB 100. The metrics collector 101 collects metrics from the physical servers, OSs (virtual OSs), VMs / containers, applications, etc. that make up the physical server group 30 using existing resource monitoring software (for example, Prometheus, etc.). For example, the metrics collector 101 collects information on the number of requests processed as the amount of task execution and power consumption [W] from the physical server group 30 and stores it in the metrics collection DB 100 . The metrics collection unit 101 collects metrics from the physical server group 30 in advance of calculating DCeP (power efficiency) (the "preparation stage" described below), and also collects metrics when calculating DCeP (power efficiency) (the "operation stage" described below).

[0032] The task execution amount normalization unit 102 determines a normalization coefficient using the task execution amount (for example, the number of processed requests) stored as metrics in the metrics collection DB 100. Specifically, the task execution amount normalization unit 102 acquires information on the task execution amount (number of processed requests) executed for each task of each application over a certain period (e.g., one day), extracts the maximum value of the task execution amount (maximum number of processed requests within a period) in a predetermined data interval (each predetermined measurement time), and determines the reciprocal of the extracted maximum value of the task execution amount as a normalization coefficient for each task of each application.

[0033] 4, for example, assume that the maximum number of requests processed within a period is "100" for Task "1-1" of App "1," "200" for Task "2-1" of App "2," and "10" for Task "2-2" of App "2." In this case, the task execution amount normalization unit 102 determines the normalization coefficient for each task to be (1 / 100, 1 / 200, 1 / 10). The task execution amount normalization unit 102 calculates the task execution amount C ij T0 Let,be the maximum number of requests processed during the period,and,be,1 / C,. ij T0 " is determined as the normalization factor.

[0034] Returning to FIG. 3, the importance group setting unit 103 sets importance groups related to applications and tasks based on a predetermined importance group setting logic. The importance group setting unit 103 employs, for example, the following three logics as the predetermined importance group setting logic.

[0035] <Importance group setting logic "1"> Importance group setting logic "1" is a "method that uses business-related KPIs (Key Performance Indicators)." KPIs are indicators for performance management evaluation such as sales figures. The importance group setting unit 103 sets importance groups for applications and tasks using business-related KPIs such as sales and profits.

[0036] For example, the importance group setting unit 103 sets four groups based on the sales ranking of each application from all applications: top 5%, 5-15%, 15-50%, and below 50%. Also, for example, the sales ratio of each task is used as a coefficient, and importance groups are set as many as the number of tasks. In this way, the importance group setting logic "1" uses business-related KPIs to set importance groups for applications and tasks.

[0037] <Importance group setting logic "2"> Importance group setting logic "2" is a "method that utilizes the functional classification of applications." The importance group setting unit 103 sets importance groups for applications and tasks using the importance of each function classification of the application or task.

[0038] For example, in the case of an application relating to resource control, the importance group setting unit 103 sets importance groups in the order of increasing importance for Create, Update, Delete and Read among the controls Create, Read, Update and Delete. Furthermore, in the case of an application relating to session control, for example, importance group setting unit 103 sets importance groups in descending order of importance: session establishment, session update, session disconnection, session maintenance, and retransmission processing. In this way, importance group setting logic "2" sets importance groups according to the functional classification of applications and tasks.

[0039] <Importance group setting logic "3"> Importance group setting logic "3" is a "method that utilizes task processing metrics of an application." The importance group setting unit 103 sets importance groups using metrics related to the task processing results of the application.

[0040] The importance group setting unit 103 sets four types of groups for each metric, such as CPU usage rate, memory usage rate, number of requests, task processing TAT (Turn Around Time), and I / O throughput: top 5%, 5-15%, 15-50%, and below 50%. In this way, the importance group setting logic "3" uses the task processing metrics of the application to set the importance group.

[0041] The importance group setting unit 103 sets importance groups for applications and tasks using the importance group setting logic described above, and then sets a weighting coefficient for each importance group according to its importance (the more important the importance group, the higher the weighting coefficient value).

[0042] The power efficiency calculation unit 104 uses the metrics (for example, the number of processed requests and power consumption) collected by the metrics collection unit 101 to calculate DCeP (power efficiency). Specifically, the power efficiency calculation unit 104 first calculates "Useful Work Produced" (amount of work product) using the above-mentioned formula (3). At this time, the normalized task amount C ij is the pre-set measurement period (predetermined evaluation period), the Assessment window T A The amount of tasks completed in C ij TA is multiplied by the normalization coefficient calculated by the task execution amount normalization unit 102. i ” and task weighting factor “V ij " is the weighting coefficient {w0, w1, . . . , w m} and the weight coefficients for each group of tasks {v0, v1, ,vn i} is used.

[0043] Then, the power efficiency calculation unit 104 calculates DCeP (power efficiency) using the above-mentioned formula (1). Here, the value calculated by formula (3) is used as "Useful Work Produced" (amount of work result). Also, "Total Energy Consumed to Perform that Work" (amount of power consumption) is calculated by calculating the DCeP (power efficiency) over the Assessment window T A In this calculation, the total amount of power consumption consumed by the physical server group 30 is used. The total amount of power consumption consumed by the physical server group 30 is calculated by adding up the power consumption collected as metrics during a preset measurement period (predetermined evaluation period).

[0044] <Processing of power efficiency calculation device> Next, the flow of processing executed by the power efficiency calculation device 1 will be described. FIG. 5 is a flowchart showing the flow of processing executed by the power efficiency calculation device 1 according to this embodiment. The processing executed by this power efficiency calculation device 1 can be roughly divided into a preparatory stage and an operational stage. In the preparatory stage, a normalization coefficient for the task execution amount is calculated using metrics collected in advance from the physical server group 30, and importance groups for applications and tasks are set and a weighting coefficient for each importance group is determined. Then, in the operational stage, DCeP (power efficiency) is calculated using the normalization coefficient and the weighting coefficient for each importance group calculated in the preparatory stage. Here, as shown in Figure 3, an example will be described in which two applications, App "1" and App "2", are installed on the physical server group 30, and App "1" executes one task (Task1-1), and App "2" executes two tasks (Task2-1, Task2-2).

[0045] First, in the advance preparation stage, the metrics collection unit 101 of the power efficiency calculation device 1 collects metrics (evaluation indexes for performance, etc.) required for power efficiency calculation from the physical server group 30 and stores them in the metrics collection DB 100 (step S10). The metrics collector 101 collects metrics using, for example, resource monitoring software (Prometheus). The collected metrics include, for example, the number of processed requests as the amount of task execution, and power consumption [W]. The metrics collection unit 101 may collect metrics by, for example, applying a test load to the application 3, or by collecting metrics obtained by executing actual request processing.

[0046] Next, the metrics collector 101 outputs, from the collected metrics, information on the task execution amount (number of processed requests) obtained over a certain period (for example, one day's worth) to the task execution amount normalizer 102.

[0047] The task execution amount normalization unit 102 of the power efficiency calculation device 1 determines a normalization coefficient for each task using the acquired task execution amount (number of processed requests) (step S11). For example, the task execution amount normalization unit 102 extracts the maximum task execution amount (maximum number of requests processed within a period) for a predetermined data interval (each predetermined measurement time, for example, 10 minutes) from the acquired task execution amounts for one day for each task of each application (see FIG. 4). Then, the task execution amount normalization unit 102 determines the reciprocal of the extracted maximum task execution amount as the normalization coefficient for each task of each application. In the example shown in FIG. 4, the task execution amount normalization unit 102 determines the normalization coefficients for Tasks "1-1", "2-1", and "2-2" to be (1 / 100, 1 / 200, 1 / 10).

[0048] Next, the importance group setting unit 103 of the power efficiency calculation device 1 sets importance groups for the applications and tasks based on a predetermined importance group setting logic (step S12). The predetermined importance group setting logic is preset to include "a method using business-related KPIs," "a method using application functional classifications," "a method using application task processing metrics," and the like.

[0049] Next, the importance group setting unit 103 sets a weighting factor for the set importance group according to its importance (step S13). The importance group setting unit 103 sets a weighting factor for the importance groups of applications and tasks according to their importance, with the weighting factor being set such that the more important the importance group, the higher the weighting factor.

[0050] Here, it is assumed that the "method using business-related KPIs" is used as the predetermined importance group setting logic. If the sales amount of each application 3 is App1 / App2=90 / 10, the importance group setting unit sets two importance groups, App1 and App2, and then sets the weight coefficient of each importance group as, for example, {W APP1 ,W APP2}={0.9,0.1}.

[0051] In addition, since the task of App1 is one of Task “1-1”, the weight coefficient of Task “1-1” is set to {V App1 Task1}={1}. Also, assume that the "method of using the functional classification of applications" is used as the logic for setting the predetermined importance group for tasks. If Task "2-1" / Task "2-2" of App2 are processes corresponding to Create / Delete, respectively, the importance group setting unit 103 sets the weight coefficient of the task of App2 as, for example, {V App2 Task1 ,V App2 Task2}={2,1} is determined. The processes from steps S10 to S13 are carried out in the advance preparation stage.

[0052] Next, the processing in the operation stage will be described. The power efficiency calculation unit 104 of the power efficiency calculation device 1 calculates DCeP (power efficiency) for a predetermined evaluation period (assessment window T A), the metrics (task execution amount (number of processed requests), power consumption) collected by the metrics collection unit 101 are obtained from the metrics collection DB 100, and DCeP (power efficiency) is calculated (step S14). Then, the power efficiency calculation unit 104 repeats the process of calculating this DCeP (power efficiency) for each predetermined evaluation period.

[0053] Specifically, the power efficiency calculation unit 104 calculates "Useful Work Produced" (amount of work output) by the above-mentioned formula (3) using the normalization coefficient calculated by the task execution amount normalization unit 102 and the weighting coefficients of the application and task determined by the importance group setting unit 103. In addition, the power efficiency calculation unit 104 calculates "Total Energy Consumed to Perform that Work" (amount of power consumption) in the above-mentioned formula (1) by multiplying the power consumption collected by the metrics collection unit 101 by the amount of power consumption over a predetermined evaluation period (assessment window T A ) and calculates the DCeP (power efficiency) by using the calculated "Useful Work Produced" (amount of work result) and "Total Energy Consumed to Perform that Work" (amount of power consumption). Then, the power efficiency calculation unit 104 calculates DCeP (power efficiency) by using the formula (1).

[0054] In this way, the power efficiency calculation device 1 can calculate the amount of work performed by one or more applications and tasks of the applications as a quantitative numerical value that reflects the importance of the applications and tasks, without relying on the mere processing volume of the applications.The power efficiency calculation device 1 can then calculate the power efficiency that reflects the importance of the applications and tasks.

[0055] <Hardware configuration> The power efficiency calculation device 1 according to this embodiment is realized by a computer 900 having a configuration as shown in FIG. 6, for example. 6 is a hardware configuration diagram showing an example of a computer 900 that realizes the functions of the power efficiency calculation device 1 according to this embodiment. The computer 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM 903, an HDD (Hard Disk Drive) 904, an input / output I / F (Interface) 905, a communication I / F 906, and a media I / F 907.

[0056] The CPU 901 operates based on a program stored in the ROM 902 or the HDD 904, and performs control by the control unit 10 (FIG. 3). The ROM 902 stores a boot program executed by the CPU 901 when the computer 900 starts up, programs related to the hardware of the computer 900, and the like.

[0057] The CPU 901 controls an input device 910 such as a mouse or keyboard, and an output device 911 such as a display or printer, via an input / output I / F 905. The CPU 901 acquires data from the input device 910 via the input / output I / F 905, and outputs generated data to the output device 911.

[0058] The HDD 904 stores programs executed by the CPU 901 and data used by the programs. The communication I / F 906 receives data from other devices via a communication network (e.g., NW (Network) 920) and outputs the data to the CPU 901, and also transmits data generated by the CPU 901 to other devices via the communication network.

[0059] The media I / F 907 reads a program or data stored in the recording medium 912 and outputs it to the CPU 901 via the RAM 903. The CPU 901 loads a program related to a target process from the recording medium 912 onto the RAM 903 via the media I / F 907, and executes the loaded program. The recording medium 912 is an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto Optical Disk), a magnetic recording medium, a semiconductor memory, or the like.

[0060] For example, when a computer 900 functions as the power efficiency calculation device 1 according to this embodiment, a CPU 901 of the computer 900 executes a program loaded onto a RAM 903, thereby realizing the functions of the power efficiency calculation device 1. Furthermore, data in the RAM 903 is stored in an HDD 904. The CPU 901 reads and executes a program related to a target process from a recording medium 912. Alternatively, the CPU 901 may read a program related to a target process from another device via a communication network (NW 920).

[0061] <Effects> The effects of the power efficiency calculation device 1 and the like according to the present invention will be described below. The power efficiency calculation device according to the present invention is a power efficiency calculation device 1 that calculates the power efficiency resulting from the execution of an application 3 installed on a physical server group 30, the physical server group 30 being installed with one or more applications 3 that execute one or more tasks, and the power efficiency calculation device 1 includes a metrics collection unit 101 that collects metrics, which are evaluation indexes required for power efficiency calculation and include task execution amounts and power consumption of the physical server group 30, from the physical server group 30 and stores the metrics in a metrics collection DB 100 in a storage unit 12, a task execution amount normalization unit 102 that acquires the task execution amounts stored in the metrics collection DB 100 and determines a normalization coefficient for each task of each application 3 using the task execution amounts measured at predetermined measurement times, and a task execution amount normalization unit 103 that normalizes each application 3 and the task execution amount measured at predetermined measurement times. an importance group setting unit (103) that sets an importance group for each application (3) and each task based on a predetermined importance group setting logic, and sets a weight according to the importance of each importance group for each application (3) and each task; and a power efficiency calculation unit (104) that acquires metrics for a predetermined evaluation period collected by the metrics collection unit (101), normalizes the task execution amount included in the metrics using a normalization coefficient for each task of each application (3), calculates the total amount of work product using the normalized task execution amount and the weight of the importance group for each application (3) and each task, and calculates the power efficiency from the power consumption included in the metrics and the total amount of work product.

[0062] In this way, the power efficiency calculation device 1 can calculate the amount of work performed by one or more applications and tasks of the applications as a quantitative numerical value that reflects the importance of the applications and tasks, without relying on the mere processing volume of the applications. Therefore, the power efficiency calculation device 1 can calculate the power efficiency that reflects the importance of the applications and tasks.

[0063] Furthermore, in the power efficiency calculation device 1, the task execution amount normalization unit 102 extracts the maximum value of the task execution amount measured at each predetermined measurement time for each task of each application 3, and determines the reciprocal of the extracted maximum value of the task execution amount as a normalization coefficient for each task of each application 3.

[0064] In this way, the power efficiency calculation device 1 can determine the normalization coefficient so as not to depend on the amount of task execution (processing amount) for each task of each application, and normalize the task execution amount.

[0065] Furthermore, in the power efficiency calculation device 1, the predetermined importance group setting logic is a logic for setting importance groups using KPIs (Key Performance Indicators) including sales of each of the applications 3 and tasks.

[0066] In this way, the power efficiency calculation device 1 can use the KPI to set importance groups for applications and tasks and set weighting coefficients for each importance group.

[0067] Furthermore, the power efficiency calculation device 1 is characterized in that the predetermined importance group setting logic is logic that sets importance groups using functional classifications of applications 3 and tasks.

[0068] In this way, the power efficiency calculation device 1 can set importance groups for the applications 3 and tasks by using the functional classification of the applications 3 and tasks, and set a weighting coefficient for each importance group.

[0069] Furthermore, in the power efficiency calculation device 1, the predetermined importance group setting logic is a logic that sets importance groups using metrics that collect task processing results of each application 3.

[0070] In this way, the power efficiency calculation device 1 can use the task processing results of each application 3 to set importance groups for the applications 3 and tasks, and set weighting coefficients for each importance group.

[0071] The present invention is not limited to the above-described embodiments, and many modifications can be made by a person having ordinary skill in the art within the technical concept of the present invention. [Explanation of symbols]

[0072] 1. Power efficiency calculation device 3. Application 10 Control Unit 11 Input / output section 12 Storage section 30 physical servers 100 Metrics Collection DB 101 Metrics Collection Department 102 Task execution amount normalization unit 103 Importance group setting section 104 Power Efficiency Calculation Unit 1000 Power Efficiency Calculation System

Claims

1. A power efficiency calculation device that calculates power efficiency by executing an application installed on a group of physical servers, The physical servers are each equipped with one or more applications that perform one or more tasks; The power efficiency calculation device a metrics collection unit that collects metrics from the group of physical servers, which are evaluation indexes necessary for calculating power efficiency, and which include task execution amounts and power consumption of the group of physical servers, and stores the collected metrics in a metrics collection DB in a storage unit; a task execution amount normalization unit that acquires the task execution amounts stored in the metrics collection DB and determines a normalization coefficient for each task of each of the applications using the task execution amounts measured at predetermined measurement times; an importance group setting unit that sets importance groups for each of the applications and each of the tasks based on a predetermined importance group setting logic, and sets weights according to the importance of each of the application importance groups and each of the task importance groups; a power efficiency calculation unit that acquires metrics for a predetermined evaluation period collected by the metrics collection unit, normalizes the task execution amount included in the metrics using the normalization coefficient for each task of each of the applications, calculates a total work result amount using the normalized task execution amount and a weight of an importance group for each of the applications and each of the tasks, and calculates power efficiency from the power consumption included in the metrics and the total work result amount; A power efficiency calculation device comprising:

2. the task execution amount normalization unit extracts a maximum value of the task execution amounts measured at each predetermined measurement time for each task of each of the applications, and determines a reciprocal of the extracted maximum value of the task execution amount as the normalization coefficient for each task of each of the applications; 2. The power efficiency calculation device according to claim 1,

3. The predetermined importance group setting logic includes: The logic is to set importance groups using KPIs (Key Performance Indicators) including sales of the applications and the tasks, 3. The power efficiency calculation device according to claim 1 or 2, wherein:

4. The predetermined importance group setting logic includes: a logic for setting importance groups using functional classifications of the applications and tasks; 3. The power efficiency calculation device according to claim 1 or 2, wherein:

5. The predetermined importance group setting logic includes: a logic for setting importance groups using metrics collected from task processing results of each of the applications; 3. The power efficiency calculation device according to claim 1 or 2, wherein:

6. A power efficiency calculation method for a power efficiency calculation device that calculates power efficiency by executing an application installed on a group of physical servers, comprising: The physical servers are each equipped with one or more applications that perform one or more tasks; The power efficiency calculation device collecting metrics from the group of physical servers, which are evaluation indices necessary for calculating power efficiency, and which include task execution amounts and power consumption of the group of physical servers, and storing the collected metrics in a metrics collection DB in a storage unit; acquiring the task execution amounts stored in the metrics collection DB, and determining a normalization coefficient for each task of each application using the task execution amounts measured at each predetermined measurement time; setting an importance group for each of the applications and each of the tasks based on a predetermined importance group setting logic, and setting weights according to the importance of each of the application importance groups and each of the task importance groups; acquiring metrics collected during a predetermined evaluation period, normalizing the task execution amounts included in the metrics using the normalization coefficient for each task of each of the applications, calculating a total work output amount using the normalized task execution amounts and the importance group weights of each of the applications and each of the tasks, and calculating power efficiency from the power consumption included in the metrics and the total work output amount; A power efficiency calculation method comprising:

7. A power efficiency calculation system including: a group of physical servers on which one or more applications that execute one or more tasks are installed; and a power efficiency calculation device that calculates power efficiency resulting from execution of the applications installed on the group of physical servers, The power efficiency calculation device a metrics collection unit that collects metrics from the group of physical servers, which are evaluation indexes necessary for calculating power efficiency, and which include task execution amounts and power consumption of the group of physical servers, and stores the collected metrics in a metrics collection DB in a storage unit; a task execution amount normalization unit that acquires the task execution amounts stored in the metrics collection DB and determines a normalization coefficient for each task of each of the applications using the task execution amounts measured at predetermined measurement times; an importance group setting unit that sets importance groups for each of the applications and each of the tasks based on a predetermined importance group setting logic, and sets weights according to the importance of each of the application importance groups and each of the task importance groups; a power efficiency calculation unit that acquires metrics for a predetermined evaluation period collected by the metrics collection unit, normalizes the task execution amount included in the metrics using the normalization coefficient for each task of each of the applications, calculates a total work result amount using the normalized task execution amount and a weight of an importance group for each of the applications and each of the tasks, and calculates power efficiency from the power consumption included in the metrics and the total work result amount; A power efficiency calculation system comprising:

8. A program for causing a computer to function as the power efficiency calculation device according to claim 1 or 2.

Images