JP6550822B2 - Information processing resource management device, information processing resource management method, and information processing resource management program - Google Patents

Description

  The present invention relates to an information processing resource management apparatus that manages an execution environment related to information processing for information processing resources that perform information processing related to a specific job.

  In the modern society where computerization is highly developed, various operations such as online trading that can buy and sell securities such as stocks are processed by computer systems. For this reason, the expectation for the technique which implement | achieves such a computer system performing the information processing which a user satisfies is increasing.

  In addition, in such computer systems, client server systems such as cloud computing are widely used to implement security measures, cost reductions, and the like. In such a client server system, a virtual machine that can flexibly use information processing resources is often constructed. Therefore, the use of virtual machines has also increased the expectation for technology that realizes providing a flexible operating environment for computer systems.

  As an example of a technique related to such a technique, Patent Document 1 discloses a predetermined stored in advance when accepting an application for sale from a securities holder and recruiting applicants for purchase of the securities. Discloses a system for extracting investors (priority investors) to be preferentially treated according to the priority order judgment conditions. This system notifies the priority investor of the conditions for selling the securities via e-mail, a member page on the WEB, or the like. This system executes a sales transaction when a purchase order is received from the priority investor. If there is no order from the priority investor, this system extracts the next priority investor and similarly notifies the sale conditions. As a result, this system easily provides investment opportunities to investors who want to invest in securities.

  Further, in Patent Document 2, a system used when reassigning a virtual machine as a load characteristic regarding the user, a load expected value provided by a user using a virtual machine and a past load actual value is used. It is disclosed. As a result, this system performs a process of rearranging the virtual machine before the virtual machine enters a high load state.

  Patent Document 3 discloses a restriction condition for ending a virtual machine (batch VM (Virtual Machine)) that performs batch processing by a specified end time, and a performance degradation of a virtual machine (online VM) that performs online processing. An apparatus to which virtual machines including an online VM and a batch VM are allocated by the control server apparatus is disclosed as an apparatus satisfying the constraint for avoiding the above. When there is an online VM in the assigned virtual machine group, this apparatus preferentially executes the online VM. For example, this apparatus preferentially uses CPU (Central Processing Unit) resources when executing online VMs, and uses CPU resources that are not used for executing online VMs when executing batch VMs.

  Further, Patent Document 4 discloses a system for detecting a resource conflict by using measurement information on a resource use condition regarding the entire server apparatus and a resource use condition by a virtual machine executed by the server apparatus. In this system, when a resource conflict is detected in any of the server devices, the virtual machine being executed by the server device is moved to another server device having a low resource usage rate.

  Further, in Patent Document 5, when the movement cost necessary for moving a virtual machine is less than or equal to the movement threshold, the arrangement of the virtual machine is changed so that the communication line in the data center is efficiently used. An apparatus is disclosed. This apparatus arranges virtual machines so that the movement cost does not exceed the movement threshold.

JP 2005-157719 A JP 2010-224756 A JP 2013-196062 International Publication No. 2008-062864 JP 2013-089166

  For example, in a business area such as the above-mentioned online trading, the importance of the trade usually changes with time because it relates to the stock price fluctuation situation and the like. Also, with the advancement of IT (Information Technology) technology, the speed of processing transactions in such business areas is increasing year by year.

  In such a business environment, a significant loss may occur when the response of the computer system is slightly delayed due to the state of the execution environment for information processing at the timing of important transactions. Therefore, it is a problem to prevent the processing performance of the computer system from being lowered at an important transaction timing. With the techniques described in Patent Documents 1 to 5, it is difficult to solve this problem. The main object of the present invention is to provide an information processing resource management apparatus and the like that solves this problem.

  An information processing resource management apparatus according to an aspect of the present invention relates to information indicating processing performance required for the information processing related to the state of an event handled by information processing executed using an information processing resource, The information processing is performed on the information processing resource based on calculation means for calculating based on prediction information for predicting the state of the event, and information indicating the processing performance calculated by the calculation means. And setting means for setting information indicating an execution environment.

  In another aspect of achieving the above object, an information processing resource management method according to an aspect of the present invention relates to a state of an event handled by information processing executed using an information processing resource by an information processing device. Information indicating processing performance required for the information processing is calculated based on prediction information for predicting the state of the event, and the information processing resource is calculated based on the information indicating the calculated processing performance. Setting information indicating an execution environment in which the information processing is executed.

  In a further aspect of achieving the above object, an information processing resource management program according to an aspect of the present invention relates to the information processing related to a state of an event handled by information processing executed using the information processing resource. A calculation function for calculating information indicating the processing performance required for the event based on prediction information for predicting the state of the event, and the information processing based on the information indicating the processing performance calculated by the calculation function. A computer is caused to realize a setting function for setting information indicating an execution environment in which the information processing is executed for a resource.

  Furthermore, the present invention can be realized by a computer-readable non-volatile recording medium in which the information processing resource management program (computer program) is stored.

  The present invention makes it possible to secure in advance, in the information processing resource, processing performance according to the magnitude of the influence when the magnitude of the influence caused by the delay of the information processing changes.

FIG. 1 is a block diagram showing the configuration of an information processing resource management system according to a first embodiment of the present invention. It is a figure which illustrates the composition of load state information concerning a 1st embodiment of the present invention. It is a figure which illustrates the composition of the prediction function management information concerning a 1st embodiment of the present invention. It is a figure which illustrates the structure of the processing performance rank information which concerns on 1st Embodiment of this invention. It is a figure which illustrates the structure of the virtual machine management information which concerns on 1st Embodiment of this invention. It is a figure which illustrates the composition of execution environment setting information concerning a 1st embodiment of the present invention. It is a flowchart which shows operation | movement of the information processing resource management system which concerns on the 1st Embodiment of this invention. It is a block diagram which shows the structure of the information processing resource management apparatus which concerns on the 2nd Embodiment of this invention. It is a block diagram which illustrates the composition of the information processor which can execute the information processing resource management device concerning each embodiment of the invention in this application.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

First Embodiment
FIG. 1 is a block diagram conceptually showing an information processing resource management system 1 according to a first embodiment of the present invention. The information processing resource management system 1 is, for example, a system that performs online trading capable of trading securities such as stocks. The information processing resource management system 1 according to the present embodiment is roughly divided into an information processing resource management device 10 and host server devices 20 and 30. The host server devices 20 and 30 are communicably connected to the information processing resource management device 10. The information processing resource management system 1 according to the present embodiment may include a host server device connected to the information processing resource management device 10 in addition to the host server devices 20 and 30.

  Each of the host server apparatuses 20 and 30 is a single (separate) information processing apparatus, and in this embodiment, a virtual machine environment is constructed as shown in FIG. In other words, the host server device 20 executes the hypervisor 200 and the virtual machines 210 to 213. The hypervisor 200 is software that manages the construction and execution environment of the virtual machines 210 to 213. Each of the virtual machines 210 to 213 is constructed for each task that the user processes. The host server device 30 also has the same function as the host server device 20, and executes the hypervisor 300 and the virtual machines 310 to 312.

  The information processing resource management apparatus 10 includes a calculation unit 11, a setting unit 12, a monitoring unit 13, and a storage unit 14. The calculation unit 11, the setting unit 12, and the monitoring unit 13 may be an electronic circuit, or may be realized by a computer program and a processor that operates according to the computer program. The storage unit 14 is a storage device such as an electronic memory or a magnetic disk. The storage unit 14 may be provided in an external storage device or the like that is communicably connected to the information processing resource management device 10.

  The monitoring unit 13 sequentially monitors the state of the load via the hypervisors 200 and 300 for the host server devices 20 and 30, and stores the monitoring result as the load state information 140 in the storage unit 14. The configuration of the load state information 140 is illustrated in FIG. As illustrated in FIG. 2, the load status information 140 has items of “CPU usage rate”, “memory usage rate”, and “I / O (Input / Output) usage rate” associated with each host server device. Information. The monitoring unit 13 updates the load state information 140 at a predetermined timing. The load state information 140 illustrated in FIG. 2 is an example, and the load state information 140 may include an item not illustrated in FIG. 2.

  The calculation unit 11 refers to the prediction function management information 141 stored in the storage unit 14. The configuration of the prediction function management information 141 is illustrated in FIG. As illustrated in FIG. 3, the prediction function management information 141 is information in which items of “user ID (Identification)”, “brand number”, and “stock price prediction function” are associated. The “user ID” is information that can identify a user who uses the information processing resource management system 1. The “brand number” is information that can identify the brand of the stock held by the user. The “stock price prediction function” is a function that uses time t as a variable, and is information indicating a mathematical formula that predicts the stock price at time t for the stock specified by the “user ID” and the “brand number”. The “stock price prediction function” in the prediction function management information 141 is created by the user and input to the prediction function management information 141.

  The calculation unit 11 calculates the stock price fluctuation rate at a predetermined time interval at predetermined time intervals for each stock whose “stock price prediction function” is registered in the prediction function management information 141. The calculation unit 11 calculates the stock price fluctuation rate after 5 minutes, for example, at 5-minute intervals. In this case, for example, the calculation unit 11 calculates the stock price fluctuation rate after 5 minutes by calculating the stock price of each stock after 5 and a half minutes and after calculating the difference between the calculated values.

  The calculation unit 11 collates the calculated stock price fluctuation rate with the processing performance rank information 142 stored in the storage unit 14 for each stock. The configuration of the processing performance rank information 142 is illustrated in FIG. As illustrated in FIG. 4, the processing performance rank information 142 is information in which items of “stock price fluctuation rate classification” and “processing performance rank” are associated. The “stock price fluctuation rate class” is a value indicating a class related to the stock price fluctuation rate calculated by the calculation unit 11 according to the above-described procedure. The “processing performance rank” is a value indicating an index related to processing performance required for a virtual machine that processes online trading. In the present embodiment, the “processing performance rank” indicates that the higher the value, the higher the processing performance required. Therefore, since the processing performance rank information 142 illustrated in FIG. 4 is more important transaction timing as the stock price fluctuation rate is higher for stocks targeted for online trading, the processing performance required for the virtual machine also increases. Is shown. The calculation unit 11 inputs, to the setting unit 12, the value indicated by the processing performance rank obtained by comparing the calculated stock price fluctuation rate with the processing performance rank information 142 for each stock.

  The setting unit 12 constructs a virtual machine in the host server devices 20 and 30 in the host server device 20 via the hypervisor 200 and in the host server device 30 via the hypervisor 300. The setting unit 12 sets a value indicating an execution environment related to the constructed virtual machine to the host server apparatuses 20 and 30 via the hypervisors 200 and 300. The setting unit 12 generates virtual machine management information 143 and stores the generated virtual machine management information 143 in the storage unit 14. The setting unit 12 updates the virtual machine management information 143 when the execution environment related to the virtual machine is changed. The configuration of the virtual machine management information 143 is illustrated in FIG.

  As illustrated in FIG. 5, the virtual machine management information 143 is information in which items of “user ID”, “virtual machine”, “host server device”, “use”, and “level of importance” are associated. The “user ID” is information that can identify a user who uses the information processing resource management system 1, similarly to the “user ID” included in the prediction function management information 141. The “virtual machine” is information that can identify a virtual machine executed by the host server 20 or 30 according to a user instruction indicated by the “user ID”. The “host server device” is information that can identify the host server device that executes the associated “virtual machine”. "Use" indicates the work content processed by the associated "virtual machine". “Importance” is information indicating whether or not the job processed by the virtual machine is important.

  According to the virtual machine management information 143 illustrated in FIG. 5, for example, a user whose user ID is “User1” is constructed in the host server device 20, and the virtual machine 210 that processes the trading work, and the information collection work It can be seen that the virtual machine 211 for processing is used. In the present embodiment, a virtual machine is constructed for each task for each user. Trading operations are defined as important, and information collection operations and general affairs are defined as non-important. The setting unit 12 arranges a virtual machine for processing important tasks and a virtual machine for processing unimportant tasks on the host server apparatus in a well-balanced manner. That is, the setting unit 12 arranges virtual machines that process important tasks so as not to be biased to any host server device.

  The setting unit 12 collates the value indicated by the processing performance rank for each stock, which is input from the calculation unit 11, with the execution environment setting information 144 stored in the storage unit 14. The configuration of the execution environment setting information 144 is illustrated in FIG. As illustrated in FIG. 6, the execution environment setting information 144 is information associated with items “processing performance rank” and “execution environment setting item”. The “processing performance rank” is, like the “processing performance rank” included in the processing performance rank information 142, a value indicating an index related to the processing performance required for the virtual machine processing the trading job. The “execution environment setting item” is information indicating an item to be set as an execution environment for a virtual machine that processes online trading according to the value indicated by the processing performance rank.

  According to the execution environment setting information 144 illustrated in FIG. 6, for example, the execution environment setting items for a virtual machine whose processing performance rank is “5” are “CPU affinity setting” and “NUMA (Non-Uniform Memory Access) setting”. “I / O priority setting” and “network priority setting”. “CPU affinity setting” represents an execution environment for controlling a task to be associated with a specific CPU in task scheduling. That is, a virtual machine for which “CPU affinity setting” is set as the execution environment can use the CPU in preference to other virtual machines. “NUMA setting” represents an execution environment in which a memory area with a high access speed is allocated as an area for storing programs and data when the access speed from the CPU to the memory differs depending on the address. That is, a virtual machine in which “NUMA setting” is set as an execution environment can access the memory at high speed. A virtual machine for which “I / O priority setting” and “network priority setting” are set as an execution environment can use I / O resources and network resources in preference to other virtual machines.

  According to the execution environment setting information 144 illustrated in FIG. 6, the execution environment setting items for the virtual machine whose processing performance rank is “4” are “CPU affinity setting” and “I / O priority setting”. The execution environment setting item for the virtual machine with the processing performance rank “3” is only “CPU affinity setting”. That is, the execution environment setting information 144 illustrated in FIG. 6 indicates that the execution environment is set such that the processing performance becomes higher as the value indicated by the processing performance rank is higher. In addition, a virtual machine with a processing performance rank of “1” moves preferentially to another host server device when the load level of the host server device executing the virtual machine exceeds a reference level. Set to the target.

  The execution environment setting information 144 is created by, for example, an administrator who manages the information processing resource management system 1 and stored in the storage unit 14. The execution environment setting information 144 illustrated in FIG. 6 is an example, and the execution environment setting information 144 may include information representing an execution environment having contents different from the execution environment setting items illustrated in FIG.

  The setting unit 12 executes the virtual machine execution based on the content indicated by the execution environment setting item obtained by collating the value indicated by the processing performance rank related to each stock and input from the calculation unit 11 with the execution environment setting information 144. Set a value indicating the environment. The setting unit 12 refers to the virtual machine management information 143 when setting the execution environment. For example, the setting unit 12 obtains, from the calculation unit 11, a value indicated by the processing performance rank regarding the stocks having the brand numbers “0001” and “0002” held by the user having the user ID “User1”. The setting unit 12 refers to the virtual machine management information 143 to acquire that the trading operation relating to “User 1” is processed by the virtual machine 210 disposed in the host server device 20. In this case, the setting unit 12 has execution environment setting items obtained by checking the higher one of the processing performance ranks related to stocks with the stock numbers “0001” and “0002” with the execution environment setting information 144. Based on the contents shown, a value indicating the execution environment for the virtual machine 210 is set.

  The setting unit 12 refers to the load state information 140 stored in the storage unit 14 and loads the host server 200 or 300 based on the CPU usage rate, the memory usage rate, and the I / O usage rate. Check whether the height (size) of the is above the standard. When the height of the load is greater than or equal to the reference for either of the host server 200 or 300, the setting unit 12 sets a virtual machine with a processing performance rank of 1 executed in the host server apparatus or an importance level of A virtual machine that is “unimportant” is moved to another host server device by changing a value indicating an execution environment related to the virtual machine. The setting unit 12 sets a value indicating an execution environment related to the virtual machine so that the virtual machine is executed by the host server device that is the migration destination.

  For example, in the environment where the host server apparatuses 20 and 30 are executing virtual machines as indicated by the virtual machine management information 143 illustrated in FIG. 5, the load level of the host server apparatus 20 exceeds the standard. Think about the case. In this case, among the virtual machines 210 to 213 executed by the host server device 20, the setting unit 12 targets virtual machines 211 and 213 whose importance is “non-important” to move to the host server device 30. To do. When at least one of the virtual machines 210 and 212 processing trading operations has a processing performance rank of “1”, the setting unit 12 also sets the virtual machine as a target to be moved to the host server device 30 as well. To do.

  The setting unit 12 refers to the load state information 140 updated by the monitoring unit 13 after moving any of the virtual machines to be moved to the host server device 30 to the host server device 30. The setting unit 12 further sets another virtual machine to be moved to the host server device 30 as a target to be moved to the host server device 30 when the state in which the load height is equal to or higher than the reference for the host server device 20 has not been resolved. Move to. The setting unit 12 repeats the operation of moving the virtual machine to be moved to the host server device 30 to the host server device 30 until the state where the load height is equal to or higher than the reference is eliminated for the host server device 20 .

  Next, the operation (process) of the information processing resource management system 1 according to the present embodiment will be described in detail with reference to the flowchart of FIG.

  The calculation unit 11 uses the prediction function management information 141 to calculate the stock price fluctuation rate after a predetermined time for the stocks registered in the prediction function management information 141 (step S101). The calculation unit 11 calculates the processing performance rank for each stock by comparing the calculated stock price fluctuation rate with the processing performance rank information 142 (step S102).

  The setting unit 12 collates the processing performance rank calculated by the calculation unit 11 with the execution environment setting information 144, thereby obtaining an execution environment setting item related to a virtual server that performs trading for each stock (step S103). The setting unit 12 sets the acquired execution environment setting items for the virtual machines being executed by the host server devices 20 and 30 via the hypervisors 200 and 300 (step S104).

  The setting unit 12 refers to the load state information 140 and confirms whether the load height is greater than or equal to the reference for the host server device 200 or 300 (step S105). If the height of the load is not equal to or higher than the reference for the host server device 200 or 300 (No in step S106), the process proceeds to step S110. When the height of the load is equal to or higher than the reference for the host server device 200 or 300 (Yes in step S106), the setting unit 12 performs the processing performance being executed in the host server device whose height is equal to or higher than the reference Either a virtual machine of rank “1” or a virtual machine of importance “non-significant” is moved to another host server device (step S 107).

  The setting unit 12 updates the virtual machine management information 143 (step S108). The monitoring unit 13 updates the load state information 140 (step S109), and the process returns to step S105. If the predetermined time (period) has not elapsed (No in step S110), the process waits in step S110. If the predetermined time has elapsed (Yes in step S110), the process returns to step S101.

  In the information processing resource management system 1 according to the present embodiment, when the magnitude of the influence caused by the delay of the information processing changes, the processing performance according to the magnitude of the influence is secured in advance in the information processing resource. Can do. The reason is that the calculation unit 11 calculates information indicating the processing performance required for the virtual machine related to the state of the event handled by the virtual machine based on the prediction function management information 141, and the setting unit 12 calculates the information. This is because the information indicating the execution environment related to the virtual machine is set based on the information indicating the processing performance calculated by the unit 11.

  For example, in business areas such as online trading, the importance of transactions usually changes with time because it is related to stock price fluctuations. Further, with the progress of IT technology, the speed of processing transactions in such business areas is increasing year by year. In such a business environment, a significant damage may occur due to a slight delay in the response of the computer system due to the state of the execution environment related to information processing at the timing of important transactions. Therefore, there is an increasing expectation for a technology that realizes that the processing performance of a computer system does not deteriorate at an important transaction timing.

  According to the information processing resource management system 1 according to the present embodiment, the calculation unit 11 predicts the stock price of the stock, which is the target of the trading operation processed by the virtual machine, using the prediction function management information 141. The calculation unit 11 calculates a value indicating processing performance required for the virtual machine based on the predicted stock price and the processing performance rank information 142. The setting unit 12 sets a value indicating the execution environment related to the virtual machine based on the value indicating the processing performance calculated by the calculation unit 11, the virtual machine management information 143, and the execution environment setting information 144. Thereby, when the magnitude of the influence caused by the delay of the information processing changes, the information processing resource management system 1 according to the present embodiment causes the information processing resource to process the processing performance according to the magnitude of the influence beforehand. Can be secured. That is, the information processing resource management system 1 according to the present embodiment can prevent the processing performance of the computer system from being lowered at an important transaction timing.

  Further, the setting unit 12 according to the present embodiment determines whether or not the height of the load of the host server device 20 or 30 is equal to or higher than the reference by referring to the load state information 140 generated by the monitoring unit 13. To do. When the load level is equal to or higher than the reference, the setting unit 12 moves a virtual machine that is executed in the host server device and processes a task that is not important to another host server device. Thus, the state in which the height of the load is equal to or higher than the reference is eliminated. Thus, the information processing resource management system 1 according to the present embodiment can avoid that the processing performance of the virtual machine is lowered due to the high load state at the timing of the important transaction.

  Further, the information processing resource management apparatus 10 according to the present embodiment sets the execution environment related to the virtual machine based on the prediction function management information 141 described above at a predetermined time interval. That is, the information processing resource management device 10 dynamically changes the execution environment related to the virtual machine based on the prediction function management information 141. As a result, the information processing resource management system 1 according to the present embodiment sets an execution environment according to the importance of transactions that change with the passage of time, and therefore, it is possible to suppress the information processing resources to the minimum necessary amount every time. it can.

  Note that the host server devices 20 and 30 according to the present embodiment do not have to construct a virtual machine environment. For example, the host server devices 20 and 30 may construct a real machine environment and execute a trading application, an information collection application, and the like for each login user. In this case, the setting unit 12 sets the value indicating the execution environment including the priority for using the CPU for the application using the application management function of the OS (Operating System) executed by the host server devices 20 and 30. To do.

  Further, the information processing resource management system 1 according to the present embodiment may be any system in which the state of the event to be handled can be predicted and the required processing performance fluctuates according to the state of the event, the online trading It is not limited to the system which performs. The information processing resource management system 1 according to the present embodiment may be, for example, a system that performs a process of providing a predetermined service to the accessed user from a website whose number of accesses can be predicted.

Second Embodiment
FIG. 8 is a block diagram conceptually showing the structure of the information processing resource management device 40 in the second embodiment.

  The information processing resource management apparatus 40 according to the present embodiment includes a calculation unit 41 and a setting unit 42.

  The calculation unit 41 predicts the state of the event related to the state of the event handled by the information processing 500 executed using the information processing resource 50 and indicating the processing performance required for the information processing 500. Calculation is performed based on the prediction information 400.

  The setting unit 42 sets information indicating an execution environment in which the information processing 500 is executed for the information processing resource 50 based on the information indicating the processing performance calculated by the calculation unit 41.

  The information processing resource management device 4 according to the present embodiment secures in advance, in the information processing resource, the processing performance according to the magnitude of the influence when the magnitude of the influence caused by the delay of the information processing changes. Can do. The reason is that the calculation unit 41 calculates information indicating the processing performance necessary for the information processing 500 related to the state of the event handled by the information processing 500 based on the prediction information 400, and the setting unit 42 calculates This is because the information indicating the execution environment related to the information processing 500 is set based on the information indicating the processing performance calculated by the unit 41.

<Hardware configuration example>
Each part shown in FIG. 1 and FIG. 8 in each embodiment described above can be realized by a dedicated HW (HardWare) (electronic circuit). Further, at least the calculation units 11 and 41 and the setting units 12 and 42 can be considered as a function (processing) unit (software module) of the software program. However, the division of each part shown in these drawings is a configuration for convenience of explanation, and various configurations can be assumed at the time of mounting. An example of the hardware environment in this case will be described with reference to FIG.

  FIG. 9 exemplarily illustrates the configuration of an information processing apparatus 900 (computer) capable of executing the information processing resource management apparatus according to each embodiment of the present invention. That is, FIG. 9 is a configuration of a computer (an information processing apparatus) capable of realizing the information processing resource management apparatus shown in FIG. 1 and FIG. 8, and a hardware environment capable of realizing each function in the embodiment described above. Represent.

The information processing apparatus 900 illustrated in FIG. 9 includes the following constituent elements.
CPU (Central_Processing_Unit) 901,
ROM (Read_Only_Memory) 902,
RAM (Random_Access_Memory) 903,
-Hard disk (storage device) 904,
A communication interface 905 with an external device,
A reader / writer 908 capable of reading and writing data stored in a recording medium 907 such as a CD-ROM (Compact_Disc_Read_Only_Memory),
-I / O interface 909,
The information processing apparatus 900 is a general computer in which these configurations are connected via a bus 906 (communication line).

  The present invention described by taking the above-described embodiment as an example supplies a computer program capable of realizing the following functions to the information processing apparatus 900 shown in FIG. The function is the function of the calculation units 11 and 41 and the setting units 12 and 42 or the flowchart (FIG. 7) in the block configuration diagram (FIGS. 1 and 8) referred to in the description of the embodiment. The present invention is then achieved by reading the computer program into the hardware CPU 901 for interpretation and execution. Further, the computer program supplied in the apparatus may be stored in a readable / writable volatile memory (RAM 903) or a non-volatile storage device such as a hard disk 904.

  Also, in the above case, the method of supplying the computer program into the hardware can adopt a general procedure at present. As the procedure, for example, there are a method of installing in the apparatus via various recording media 907 such as a CD-ROM, and a method of downloading from outside via a communication line such as the Internet. In such a case, the present invention can be understood to be configured by a code constituting the computer program or a recording medium 907 in which the code is stored.

  The present invention has been described above by taking the above-described embodiment as an exemplary example. However, the present invention is not limited to the embodiments described above. That is, the present invention can apply various modes that can be understood by those skilled in the art within the scope of the present invention.

DESCRIPTION OF SYMBOLS 1 Information processing resource management system 10 Information processing resource management apparatus 11 Calculation part 12 Setting part 13 Monitoring part 14 Storage part 140 Load state information 141 Prediction function management information 142 Processing performance rank information 143 Virtual machine management information 144 Execution environment setting information 20 and DESCRIPTION OF SYMBOLS 30 Host server apparatus 200 and 300 Hypervisor 210 thru | or 213 Virtual machine 310 thru | or 312 Virtual machine 40 Information processing resource management apparatus 41 Calculation part 42 Setting part 400 Prediction information 50 Information processing resource 500 Information processing 900 Information processing apparatus 901 CPU
902 ROM
903 RAM
904 hard disk (storage device)
905 Communication interface 906 Bus 907 Recording medium 908 Reader writer 909 I / O interface

Claims (10)

An event handled by information processing executed using information processing resources is represented by a prediction function having time as a variable, and processing performance required for the information processing varies in a predetermined period indicated by the prediction function. when depends on the amount, calculation means for calculating by the information indicating the processing performance, obtaining the variation amount,
A setting unit configured to set information indicating an execution environment in which the information processing is executed on the information processing resource based on the information indicating the processing performance calculated by the calculation unit;
An information processing resource management apparatus comprising: The information processing resource for executing a plurality of the information processing further includes monitoring means for monitoring a state of a load generated by the execution of the information processing,
The setting means changes the information indicating the execution environment based on load state information indicating a monitoring result by the monitoring means.
The information processing resource management device according to claim 1. The setting means sets information indicating the execution environment for controlling a task to be associated with a specific processor in task scheduling relating to the information processing resource.
The information processing resource management device according to claim 1. When the access speed from the processor in the information processing resource to the memory varies depending on the address, the setting means controls the execution environment for controlling to allocate an area of the memory having a high access speed as an area for storing a program and data. Set the information shown,
The information processing resource management device according to claim 1 . The calculation means calculates information indicating the processing performance by inputting information indicating that the predetermined time has elapsed to the prediction function at predetermined time intervals,
The setting means sets information indicating the execution environment at the predetermined time interval.
The information processing resource management device according to any one of claims 1 to 4 . The setting means sets, for the information processing resource executing a virtual machine, information indicating the execution environment via a hypervisor managing the virtual machine.
The information processing resource management device according to any one of claims 1 to 5 . The setting means indicates the processing performance when a load height indicated by the load status information for a specific host server device out of a plurality of host server devices included in the information processing resource is equal to or higher than a reference. It is the destination by updating the information indicating the execution environment after moving the information processing whose value represented by information is below the reference to any of the host server devices except the specific host server device. The host server device executes the information processing;
The information processing resource management device according to claim 2 . The setting means executes at least one non-critical information process, which is the information process having the importance level of “non-important”, when the importance level is expressed as “important” or “non-important”. After moving at least one of the non-critical information processing from the specific host server device among a plurality of host server devices to any of the host server devices excluding the specific host server device, Setting information indicating the execution environment so that the host server device executes the non-critical information processing;
The information processing resource management device according to claim 7 . Depending on the information processing device
An event handled by information processing executed using information processing resources is represented by a prediction function having time as a variable, and processing performance required for the information processing varies in a predetermined period indicated by the prediction function. In the case of being dependent on the amount, information indicating the processing performance is calculated by determining the amount of fluctuation ,
Information indicating an execution environment in which the information processing is to be executed is set to the information processing resource based on the information indicating the calculated processing performance.
Information processing resource management method. An event handled by information processing executed using information processing resources is represented by a prediction function having time as a variable, and processing performance required for the information processing varies in a predetermined period indicated by the prediction function. when depends on the amount, the calculation function of calculating by the information indicating the processing performance, obtaining the variation amount,
A setting function for setting information indicating an execution environment in which the information processing is to be executed on the information processing resource based on the information indicating the processing performance calculated by the calculation function;
An information processing resource management program that realizes a computer.

Images