WO2011007463A1 - 情報処理システム、情報処理方法および記憶媒体 - Google Patents
情報処理システム、情報処理方法および記憶媒体 Download PDFInfo
- Publication number
- WO2011007463A1 WO2011007463A1 PCT/JP2010/000284 JP2010000284W WO2011007463A1 WO 2011007463 A1 WO2011007463 A1 WO 2011007463A1 JP 2010000284 W JP2010000284 W JP 2010000284W WO 2011007463 A1 WO2011007463 A1 WO 2011007463A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- server
- load
- resource amount
- test program
- information
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2097—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements maintaining the standby controller/processing unit updated
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/815—Virtual
Definitions
- the present invention relates to an information processing system, an information processing method, and a storage medium.
- an information processing system, an information processing method, and a memory capable of estimating the load of a virtual machine running on one server and reproducing the load on one server in parallel with the above estimation on another server It relates to the medium.
- Patent Document 1 Japanese Patent Laid-Open No. 2008-146313 discloses the following technology. Here, it demonstrates using FIG. 1 of patent document 1.
- FIG. The production server 10 is a computer that performs production work.
- the standby server 20 is a computer that takes over production work from the production server 10 when a failure occurs in the production server 10.
- the new server 30 is a computer to be newly introduced.
- the management terminal 40 is a computer used by an administrator who evaluates the performance of the new server 30.
- the communication network 50 is, for example, the Internet or a LAN (Local Area Network).
- the management terminal 40 receives an input of a benchmark program that provides an input data generation function for generating input data and a CPU load generation function that uses a CPU of a computer in accordance with the input data. Then, each of the standby server 20 and the new server 30 is caused to execute a benchmark program.
- the standby server 20 measures the processing load on the standby server 20 associated with the execution of the benchmark program.
- the new server 30 measures the processing load on the new server 30 accompanying execution of the benchmark program.
- the management terminal 40 realizes a load simulation that can easily evaluate the performance of the computer by outputting the processing load of the standby server 20 and the processing load of the new server 30.
- an application program (benchmark program) that simulates the operation of a production service application program executed on the production server 10 with a high processing load is installed in the new server 30.
- the processing load (resource consumption) when the same input data as that of the production server 10 is executed by the benchmark program is measured. Thereby, the processing load equivalent to the case where the application program for production business is executed can be reproduced by the new server 30.
- Patent Document 1 also discloses that the same processing can be performed as a virtual machine instead of an application program.
- Patent Document 1 when Patent Document 1 is applied to a virtual machine, there is a problem in the reproducibility of the processing load. That is, the factors related to the operation of the virtual machine are more complex than those of the application program. Therefore, even if input data is generated in advance under certain conditions and the processing load is reproduced based on the input data, it is relatively unlikely that the virtual machine will be executed under exactly the same conditions. The consistency with the load is low.
- the present invention has been made in view of the above circumstances, and its purpose is to execute the virtual machine on the other server, reflecting the processing load of the virtual machine actually running on one server.
- An object is to provide an information processing system, an information processing method, and a storage medium that reproduce the processing load in the case.
- a first server and a second server that are communicable via a network wherein the first server executes an execution unit that executes a virtual machine, and the execution unit executes the virtual machine.
- Load information transmitting means for transmitting, to the second server, load information indicating the processing load generated in the first server with execution of the virtual machine, the second server,
- an information processing system including load generating means for generating a processing load based on the load information received from the first server.
- the first server when the first server executes the virtual machine and when the virtual machine is executed in the execution step, the first server generates the virtual machine along with the execution of the virtual machine.
- a load information transmission step for transmitting load information indicating the processing load to the second server via the network, and a load generation step for generating a processing load based on the load information received from the first server.
- a storage medium storing a program executed by a first server and a second server that can communicate via a network, and causing the first server to execute a virtual machine. And when the virtual machine is being executed by the execution process, load information that causes the second server to transmit load information indicating a processing load generated in the first server as the virtual machine is executed.
- the program that causes either the first server or the second server to execute a process and a load generation process that causes the second server to generate a processing load based on the load information received from the first server.
- a storage medium is provided that is characterized by being stored.
- an information processing system, an information processing method, and an information processing system that reflect the processing load of a virtual machine that is actually running on one server and reproduce the processing load when the virtual machine is executed on the other server A storage medium is provided.
- 1 is a configuration diagram of an information processing system according to a first embodiment. It is a figure which shows the architecture of the server with which the information processing system of 1st Embodiment is provided. It is a flowchart which shows the information processing method applied to the information processing system of 1st Embodiment. It is a block diagram of the information processing system of 2nd Embodiment. It is a flowchart which shows the information processing method applied to the information processing system of 2nd Embodiment. It is a flowchart which shows the information processing method applied to the information processing system of 2nd Embodiment. It is a block diagram of the information processing system of 3rd Embodiment.
- 10 is a flowchart showing the operation of the management server when moving a performance measurement virtual machine to server A. It is a flowchart showing operation
- movement of the virtual machine for performance measurement. 10 is a flowchart showing the operation of the management server showing the operation of the management server when moving the performance measurement virtual machine to the server B.
- FIG. 1 is a configuration diagram of an information processing system 1000 according to the first embodiment.
- the information processing system 1000 of this embodiment includes a server A100 and a server B200 that can communicate via a network 500.
- Server A100 and server B200 include CPUs 110 and 210 and storage units 120 and 220, respectively.
- the CPU 110 can read and process programs and data stored in the storage unit 120 and write the processed programs and data into the storage unit 120.
- the CPU 210 can read and process programs and data stored in the storage unit 220 and write the processed programs and data into the storage unit 220.
- the server A100 and the server B200 include communication units 130 and 230, respectively.
- the communication unit 130 can transmit programs, data, and the like processed by the CPU 110 to other devices such as the server B 200 via the network 500, and can receive programs, data, and the like from other devices via the network 500.
- the communication unit 230 transmits programs and data processed by the CPU 210 to other devices such as the server A 100 via the network 500, and receives programs and data from other devices via the network 500. can do.
- the storage unit 120 of the server A100 provides a host OS 121 that is an operation system installed in the server A100, a virtual machine 123 that is software for creating virtual hardware, and an environment in which the virtual machine 123 can be executed on the host OS 121. And a guest OS 124 which is an operation system installed in the virtual machine 123 is stored.
- the CPU 110 accesses the storage unit 120 and executes the host OS 121, the virtualization software 122, and the virtual machine 123, thereby realizing virtual hardware (virtual machine 123) on the server A100. Can do. That is, in this embodiment, the CPU 110, the host OS 121, and the virtualization software 122 function as the execution unit of the present invention.
- the storage unit 120 further stores application software 126 executed on the guest OS 124 and application software 125 executed on the host OS 121.
- FIG. 2 is a diagram showing the architecture of the server A100.
- a hardware resource provided by the server A 100 exists in the lowest layer, and a host OS 121 exists on the hardware resource.
- application software 125 and virtualization software 122 are executed on the host OS 121.
- the server A 100 executes the virtual machine 123 on the virtualization software 122, and the guest OS 124 is executed on the virtual machine 123.
- application software 126 is executed on the guest OS 124.
- the server A 100 can execute the application software 125 and the application software 126 at different layers in the above architecture. However, actually, the application software 125 and the application software 126 stored in the storage unit 120 are only executed by the CPU 110 included in the server A100.
- the server A100 can transmit load information indicating the processing load generated in the server A100 as the virtual machine 123 is executed to the server B200.
- the usage rate of the resources used by the virtual machine 123 collected by the resource management function of the host OS 121 is processed as load information, and the communication unit 130.
- the server B200 the CPU 110, the communication unit 130, the virtual machine 123, and the host OS 121 function as the load information transmission unit of the present invention.
- the resource usage rate is, for example, the usage rate R n of the CPU 110 (the processing load of the CPU 110 accompanying the execution of the virtual machine 123 at a certain time point / the maximum allowable processing load of the CPU 110).
- n is a positive integer.
- the processing load generated in the server A 100 due to the execution of the virtual machine 123 is not only the execution of the virtual machine 123 but also the guest OS 124 executed in the hierarchy above the virtual machine 123 and The processing load accompanying execution of the application software 126 is also included.
- the storage unit 220 included in the server B200 stores a host OS 221 that is an operation system installed in the server B200.
- the storage unit 220 stores a test program 223 that generates a processing load based on the load information received from the server A100.
- the test program 223 is executed on the host OS 221.
- the communication unit 230 receives load information from the server A 100, the load information is processed by the CPU 210 and stored in the storage unit 220.
- the CPU 210 reads and executes the test program 223 stored in the storage unit 220.
- the test program 223 first collects data indicating the maximum amount of resources of the server B200.
- the data indicating the maximum amount of resources is, for example, the maximum allowable processing load M of the CPU 210. In the present embodiment, it is assumed that these data are managed by the host OS 221.
- the test program 223 calculates a target resource amount using the following equation (1) for the received load information and collected data.
- V n used in the following equation (1) is a predicted value of the processing load generated in the server B 200 when the server B 200 causes the virtual machine 123 to execute, and the processing load given to the CPU 210 by the test program 223. It is a target value.
- test program 223, the processing load of the CPU host OS221 is managed, to generate a processing load until the calculated target value V n.
- the test program 223 can generate a processing load that is predicted to occur in the server B 200 when the server B 200 executes the virtual machine 123. That is, in the present embodiment, the CPU 210, the host OS 221 and the test program 223 function as the load generation unit of the present invention.
- timing at which the server A 100 transmits the load information is any time when the virtual machine 123 is being executed.
- the server A100 intermittently transmits load information to the server B200.
- the server B 200 (CPU 210) executes the test program 223, and the test program 223 increases or decreases the processing load generated each time load information is received from the server A 100 according to the received load information. Let In the present embodiment, it is assumed that the intermittently transmitted every interval T 1 constant time, or may be randomly not limited thereto.
- test program 223 uses the equation (1) for the newly received usage rate R n of the CPU 110 and the maximum allowable processing load M of the CPU 210 to set the new processing load target value V n .
- the CPU 210 generates a processing load corresponding to the calculation.
- the information processing system 1000 realizes the execution means, load information transmission means, and load generation means of the present invention when the CPU 110 or the CPU 210 executes software.
- the information processing system 1000 causes the server A 100 to execute the virtual machine 123 when the virtual machine 123 is executed by the execution process that causes the server A 100 to execute the virtual machine 123 and the execution process.
- the server A100 (CPU 110) or the server B200 includes a load information transmission process that causes the server B200 to transmit load information indicating a processing load and a load generation process that causes the server B200 to generate a processing load based on the load information received from the server A100. This is realized by a program executed by any of (CPU 210).
- FIG. 3 is a flowchart showing an information processing method applied to the information processing system 1000 of the present embodiment.
- This information processing method includes an execution step (step S1) in which the server A100 executes the virtual machine 123.
- this information processing method displays the load information indicating the processing load generated in the server A100 as the virtual machine 123 is executed in the network 500.
- the load information transmission step (step S2) which transmits to server B200 via is provided.
- this information processing method includes a load generation step (step S3) for generating a processing load based on the load information received from the server A100 by the server B200.
- Load information transmission step from (step S2) is executed until the time T 1 is elapsed (NO in step S4), and the server B200 may continue generation of was generated by the load generation step (Step S3) processing load.
- Step S2 Load information transmission step when the time T 1 from (step S2) is executed has elapsed (YES in step S4), and the server A100 again executes the load information transmitting step (step S2).
- step S3 Each time the server B 200 receives the load information transmitted in the load information transmission step (step S2), the load generation step (step S3) newly predicts the processing load according to the received load information and generates the load information. Increase or decrease the processing load.
- This information processing method is repeatedly executed while the virtual machine executed in the execution step (step S1) is operating (NO in step S5). However, this information processing method ends when the virtual machine stops (YES in step S5).
- processing that is predicted to occur when the virtual machine 123 is executed by the server A100 information indicating the processing load is transmitted from the server A100 to the server B200, and the server B200 executes the virtual machine 123 based on the received information. Generate a load.
- the server B 200 can reproduce the processing load when the virtual machine 123 is executed by reflecting the processing load of the virtual machine 123 that is actually being executed by the server A 100.
- the server A100 intermittently transmits load information, and the server B200 newly predicts a processing load based on the load information and increases / decreases the generated processing load.
- the server B 200 can reproduce the processing load generated by the virtual machine 123 in the server A 100 in substantially real time.
- substantially real time means that there is a slight time lag due to various information transmissions and information processing, so that it is not complete real time. Therefore, even if the environmental conditions including the network 500 change from time to time and the resource amount of the server A100 used by the virtual machine 123 changes, the server B200 can reproduce the processing load according to the change.
- FIG. 4 is a configuration diagram of an information processing system 2000 according to the second embodiment.
- the information processing system 2000 includes a server A 100, a server B 200, a server C 300, and a management server 400, which are communicably connected via a network 500.
- the server A100 is an apparatus equivalent to the server A100 of the first embodiment.
- the server B200 is an apparatus equivalent to the server B200 of the first embodiment, but the test program 223 is not stored in the storage unit 220.
- the server C300 is an apparatus equivalent to the server B200 of this embodiment, and includes a CPU 310, a storage unit 320, and a communication unit 330.
- the storage unit 320 stores a host OS 321 that is an operation system installed in the server C300. is doing.
- the management server 400 includes a CPU 410, a storage unit 420, a communication unit 430, an operation input unit 440, and a display unit 450.
- the storage unit 420 stores a host OS 421 that is an operation system installed in the management server 400, and further stores a management program 422 and test programs 423 and 424. Note that the test program 423 and the test program 424 are equivalent programs.
- the display unit 450 displays and outputs an operation screen and the like to the operator of the information processing system 2000. Specifically, a display apparatus etc. are mentioned.
- the operation input unit 440 receives an operation input from the operator of the information processing system 2000. Specific examples include a keyboard, a mouse pad, and a touch panel. Note that the management server 400 may appropriately display an operation screen on the display unit 450 in order to receive an operator's operation input from the operation input unit 440.
- Test program 423 and the test program 424 generates a processing load in response to an input index value I n, increase or decrease the processing load of generating the magnitude of the index value I n.
- index value I n is a generic name of an index value used to generate the processing load on the test program of the present invention, individually index value appearing in the text below I 1 and I A, etc. and n They are distinguished from each other by assigning numerical values or letters instead of.
- the management server 400 operates as follows when the management program 422 is executed by the CPU 410. First, the management server 400 transmits the test program 423 or the test program 424 to the server B200 or the server C300 selected according to the operation input received by the operation input unit 440. Here, it is assumed that the test program 423 is transmitted to the server B200 and the test program 424 is transmitted to the server C300. That is, the management server 400 that executes the management program 422 functions as a test program transmission unit of the present invention.
- the server B 200 stores the test program 423 in a part of the storage area of the storage unit 220. Further, the server C300 stores the test program 424 in a part of the storage area of the storage unit 320. That is, the storage unit 220 and the storage unit 320 function as a test program storage unit of the present invention.
- the management server 400 that executes the management program 422 transmits a request for transmitting load information to the server A100 to the server B200 that transmitted the test program 423 and the server C300 that transmitted the test program 424. That is, the management server 400 that executes the management program 422 functions as a load information transmission request unit of the present invention.
- the server A100 transmits load information to the server B200 and the server C300 in response to the received request.
- the server A100 if you enter the first index value I 1 in the test program 423 or 424 in the server A100, the amount of resources of the server A100 to test program 423 or 424 is used by the processing load of generating
- the first resource amount P 1 indicating the first index value I 1 is stored in advance in a part of the storage area of the storage unit 120. That is, the storage unit 120 functions as a calculation reference storage unit of the present invention.
- the server A 100 executes the test program 423 or a test program equivalent to the first resource amount P 1 before executing the virtual machine. 1 and the first index value I 1 may be acquired by measuring the. Or, the server A100, the amount of the first resource P 1 and a first index value I 1 from the outside of the device may be received via a network 500.
- the server A100 obtains the second resource amount P 2 indicating the amount of resources of the server A100 used by the virtual machine 123 is executed. Furthermore, the server A100 is based on the second index value I 2 corresponding to the second resource amount P 2 obtained, to the first resource amount P 1 stored in the storage unit 120 and the first index value I 1 calculated Te, to the server B200 or server C300 a second index value I 2 which is calculated as the load information.
- the server A100 is the second resource amount P 2 obtained, the second by multiplying the first index value I 1 and the ratio of the first resource amount P 1 to calculate the index value I 2. That is, the following equation (2) is obtained.
- the server B 200 reads the test program 423 from the storage unit 220 and inputs the index value (second index value I 2 ) received from the server A 100 to the read test program 423 to generate a processing load.
- the server C300 reads the test program 424 from the storage unit 320, and inputs the index value (second index value I 2 ) received from the server A100 to the read test program 424 to generate a processing load.
- Server B200 transmits the third resource amount P 31 indicating the amount of resources of the server B200 used by caused the processing load on the management server 400.
- the server C300 transmits the third resource amount P 32 indicating the amount of resources of the server C300 used by caused the processing load on the management server 400.
- the time interval at which the server B 200 transmits the third resource amount P 31 or the time interval at which the server C 300 transmits the third resource amount P 32 may be constant or random.
- each server (server B200, server C300) in shall be transmitted at the time interval T 2.
- the management server 400 that executes the management program 422 receives the third resource amounts P 31 and P 32 from the server B 200 that has received the test program 423 or the server C 300 that has received the test program 424. Then, the management server 400 displays the received third resource amounts P 31 and P 32 on the display unit 450 and presents them to the administrator. That is, the management server 400 that executes the management program 422 functions as a resource amount receiving unit and a resource amount presenting unit of the present invention.
- the management server 400 intermittently receives the third resource amounts P 31 and P 32 from the server B 200 or the server C 300. Then, every time the management server 400 receives the third resource amounts P 31 and P 32 , the management server 400 presents the received third resource amounts P 31 and P 32 to the administrator.
- intermittent means that the time interval may be constant or random.
- the server B 200 or the server C 300 transmits the third resource amounts P 31 and P 32 at the time interval T 2 , respectively, and these are not synchronized. Therefore, the management server 400 has the third resource amount P 31 , receiving a P 32 at different time intervals.
- FIG. 5 is a flowchart of an information processing method applied to the information processing system 2000 of the second embodiment.
- the information processing method includes a first shown if you enter the first index value I 1 in the test program 423 and 424 in the server A100, the amount of resources of the server A100 to be used by the processing load test program 423, 424 is to generate comprises one resource amount P 1, calculation reference storage step of storing in association with the first index value I 1 a (step S101).
- This information processing method includes an execution step (step S102) in which the server A100 executes the virtual machine 123.
- the server A100 may autonomously execute the virtual machine 123, or may receive an execution request from the management server 400 and execute the virtual machine 123 accordingly.
- the management server 400 that receives an operation input from the administrator transmits a test program 423 or a test program 424 to the server B 200 or the server C 300 selected according to the received operation input ( Step S103).
- the management server 400 transmits the test program 423 to the server B200 and transmits the test program 424 to the server C300.
- the server B200 stores the received test program 423 in the storage unit 220
- the server C300 stores the received test program 424 in the storage unit 320.
- the management server 400 transmits a load information transmission request to the server A100 to the server B200 and the server C300 to which the test programs 423 and 424 are transmitted in the test program transmission step (step S103).
- a request step (step S104) is provided.
- This information processing method includes a load information transmission step (step S105) in which the server A100 transmits load information to the server B200 and the server C300 in response to the request transmitted in the load information transmission request step (step S104).
- the server A100 transmits the index value I n to be input to the test program 423 or the test program 424 as the load information. More specifically, in the load information transmitting step (step S105), obtains the second resource amount P 2 indicating the amount of resources of the server A100 used by the virtual machine 123 is executed, the second resource acquired The second index value I 2 corresponding to the amount P 2 is calculated based on the first resource amount P 1 and the first index value I 1 stored in the calculation reference storing step (step S101), and the calculated second index value I 2 is calculated. to the server B200 index values I 2 as load information.
- the server B200 or the server C300 reads the test program 423 or the test program 424, and reads the index value (second index value I 2 ) transmitted in the load information transmission step (step S105). 423 or a test program 424, and a load generation step (step S106) for generating a processing load.
- Load information transmitting step up step S105) time T 1 after is executed has elapsed (NO in step S107), the server B200 and the server C300 continues to occurrence of generated in the load generating step (step S106) the processing load .
- Load information transmitting step (step S105) is when the time T 1 from being executed has elapsed (YES in step S107), the server A100 again executes the load information transmitting step (step S105).
- the server B200 or the server C300 receives the load information transmitted in the load information transmission step (step S105)
- the server B200 or the server C300 generates the load information in the load generation step (step S106) according to the received load information. Increase or decrease the processing load.
- This information processing method is repeatedly executed while the virtual machine 123 executed in the execution step (step S102) is operating (NO in step S108). However, this information processing method ends when the virtual machine 123 stops (YES in step S108).
- FIG. 6 is a flowchart of an information processing method applied to the information processing system 2000 according to the second embodiment.
- This information processing method indicates the third resource amount P 31 indicating the amount of resources of the server B 200 or the amount of resources of the server C 300 used by the processing load generated by the management server 400 in the load generating step (step S106). comprising a resource amount receiving step of receiving a third resource amount P 32 (step S202).
- the management server 400 receives the third resource amounts P 31 and P 32 from the server B 200 that has received the test program 423 or the server C 300 that has received the test program 424, respectively. .
- the information processing method further includes a resource amount presentation step (step S203) in which the management server 400 presents the third resource amounts P 31 and P 32 received in the resource amount reception step (step S202) to the administrator.
- step S201 While the third resource amounts P 31 and P 32 are newly received from the server B 200 or the server C 300 (NO in step S201), this information processing method is in a standby state.
- the process proceeds to a resource amount receiving step (step S202). Then, the resource amount receiving step (step S202) is repeated intermittently.
- step S203 each time the third resource amounts P 31 and P 32 are received, the received third resource amounts P 31 and P 32 are presented to the administrator.
- This information processing method is repeatedly executed while the virtual machine executed in the execution step (step S102) is operating (NO in step S204), as in the flowchart shown in FIG. However, this information processing method ends when the virtual machine is stopped (YES in step S204).
- the server A100 transmits the index value I n as the load information
- the server B200 or server C300 generates a running by entering the index value I n received test program processing load.
- the server A100 may be transmitted by the same index value I n each server B200 or server C300, the arithmetic processing can be reduced, the data capacity of the load information transmitted and received between the server is reduced.
- the server B200 or the server C300 the prior processing for generating the load is reduced, and the processing load can be generated promptly. Therefore, the time lag from when the processing load caused by the virtual machine 123 occurs in the server A100 to when the processing load is reproduced in the server B200 or the server C300 is reduced, and reproduction close to real time is possible.
- the server A100 is because the pre-stored first resource amount P 1 and a first index value I 1 in association with the process of calculating the second index value I 2 is simplified Alleviated. Therefore, the time lag from when the processing load due to the virtual machine 123 occurs in the server A100 to when the processing load is reproduced in the server B200 or the server C300 is reduced, and reproduction close to real time is possible.
- the test program can be transmitted to a server selected according to an operation input by the operator.
- the processing load of the virtual machine 123 can be reproduced according to the intention of the operator.
- the resource amount used by the reproduced processing load can be presented to the operator.
- the operator can check the amount of resources used by the reproduced processing load.
- a plurality of servers can execute the equivalent test program to reproduce the processing load of the virtual machine 123.
- the processing load of the virtual machine 123 can be reproduced in a plurality of servers in parallel.
- FIG. 7 is a configuration diagram of an information processing system 3000 according to the third embodiment.
- Server A100, server B200, server C300, server D600, management server 400, and server E700 are communicably connected via a network 500.
- Server A100, server B200, server C300, management server 400, server D600, and server E700 each include a CPU 110, a CPU 210, a CPU 310, a CPU 410, a CPU 610, and a CPU 710, and each CPU has the same processing performance.
- the processing performance may be different.
- the server A100, server B200, server C300, management server 400, server D600, and server E700 each include a storage unit 120, a storage unit 220, a storage unit 320, a storage unit 420, a storage unit 620, and a storage unit 720.
- the storage units may have the same storage capacity or different storage capacities.
- the server A100, the server B200, the server C300, the management server 400, the server D600, and the server E700 each include a communication unit 130, a communication unit 230, a communication unit 330, a communication unit 430, a communication unit 630, and a communication unit 730.
- the amount of communication that can be processed by each may be the same or different.
- the storage unit 120 stores a host OS 121, virtualization software 122, and a virtual machine 123. Although not shown here, it is assumed that the virtual machine 123 includes software corresponding to the guest OS 124 and the application software 126 illustrated in FIG. 1 or 4.
- the storage unit 220 stores a host OS 221 and virtualization software 222, and the server B200 has an environment in which virtual hardware such as the virtual machine 123 can be realized, like the server A100.
- the storage unit 320 stores a host OS 321 and virtualization software 322, and the server C300 has an environment capable of realizing virtual hardware, similar to the server A100.
- the storage unit 620 stores a host OS 621 and virtualization software 622, and the server D600 has an environment capable of realizing virtual hardware, like the server A100.
- the storage unit 720 stores a host OS 721 and virtualization software 722, and the server E700 has an environment capable of realizing virtual hardware, like the server A100.
- the management server 400 includes an operation input unit 440 and a display unit 450 in addition to the CPU 410, the storage unit 420, and the communication unit 430 described above.
- the operation input unit 440 and the display unit 450 are the same as the operation input unit 440 and the display unit 450 of the second embodiment, respectively.
- the storage unit 420 stores a performance measurement virtual machine 425.
- the performance measurement virtual machine 425 is virtual hardware, and can execute a test program equivalent to the test program 423 described in the second embodiment on the virtual hardware.
- the storage unit 420 stores a host OS 421 and a management program 422.
- the management server 400 operates as follows.
- FIG. 8 is a flowchart showing the operation of the management server 400 when moving the performance measurement virtual machine 425 to the server A100.
- the management server 400 acquires from the server A100 the amount of resources used in connection with the execution of the virtual machine 123 in the server A100 (step T1).
- the management server 400 copies the image of the performance measurement virtual machine 425 registered in the storage unit 420 onto the storage unit 720 of the server E700. Then, the management server 400 requests the server E700 to start the performance measurement virtual machine 425 (step T2).
- the management server 400 requests the server A100 and the server D600 to save the virtual machine 123 running on the server A100 to the server D600 (step T3).
- the management server 400 requests the server A100 and the server E700 to move the performance measurement virtual machine 425 on the server E700 to the server A100 (step T4).
- the management server 400 requests the performance measurement virtual machine 425 moved on the server A100 to generate a processing load using the resource amount acquired in step T1 as a target value. At the same time, the management server 400 requests the server A 100 and the performance measurement virtual machine 425 to periodically acquire the amount of resources used in the execution of the performance measurement virtual machine 425 in the server A 100. (Step T5).
- FIG. 9 is a flowchart showing the operation of the performance measurement virtual machine 425 executed on the server A100.
- the performance measurement virtual machine 425 receives the request from the management server 400 in step T5 (step T101).
- the performance measurement virtual machine 425 generates a processing load in response to the request received in step T101 (step T102).
- the index value I F for the first time to be entered when starting the test program on performance measurement virtual machine 425 are assumed to be predetermined.
- Index value I F for the first time may be provided for performance measurement virtual machine 425 from the management server 400 at step T5, it may be included in advance in the performance measurement for the virtual machine 425.
- the performance measurement virtual machine 425 acquires the resource amount used in connection with the execution of the performance measurement virtual machine 425 in the server A100 in response to the request received in step T101 (step T103).
- the performance measuring virtual machine 425 adds 1 to the value N of the resource amount acquisition count (step T104). If the value of N is equal to or greater than a predetermined number of skips (YES in step T105), the resource usage acquired in step T103 is employed (step T106). Further, (NO in Step T105) If the value of N is not reached the number skipping predetermined calculates an index value I A newly input performance measurement virtual machine 425 (step T112). Wait until step T103 is executed.
- the performance measurement virtual machine 425 compares the latest resource amount adopted in step T106 with the resource amount adopted in the previous step T106, and determines whether or not the difference is within a predetermined allowable range. Determination is made (step T107). If the difference is not within the allowable range (NO in step T108), calculates an index value I A newly input performance measurement virtual machine 425 (step T112). The calculation here is also as described above.
- step T108 When the difference falls within the range (YES in step T108), 1 is added to the value of the determination result good count X (step T109). Then, (NO in Step T110) If the value of X does not reach the number of continuations of predetermined calculates an index value I A newly input performance measurement virtual machine 425 (step T112). The calculation here is also as described above.
- step T112 If the index value I A at step T112 is calculated, again it proceeds to step T102, the performance measurement for the virtual machine 425 inputs the calculated index value I A to a test program, increase or decrease the processing load that is generating Let Then, the steps after step T103 are repeatedly executed. Again step T105, when it is judged NO at step T108 or step T110, step T112, the index value I A input at step T102 as the current index value I B, calculates an index value I A to enter new .
- the resource amount corresponding to the index value input at Step T102 (the index value I F for the first time, the index value I A calculated at Step T112 for the second and subsequent times) is obtained. I can do it. Also, the amount of resources acquired before reaching the processing load can be ignored by T105. Accuracy can be improved by keeping the load generated by T108 within a specified range. Whether or not the generated load is stable can be confirmed by T110. Further, the number of skips, the allowable range, and the number of continuations described above may be values fixed by default or values that can be changed as appropriate by the operator.
- step T111 corresponds to the calculation reference storage step S101 described in the second embodiment.
- FIG. 10 is a flowchart showing the operation of the management server 400 when the performance measurement virtual machine 425 is moved to the server B200.
- the management server 400 stores an index value I B sent in step T113 in a part of the storage area of the storage unit 420 (step T201).
- the management server 400 requests the server A100 and the server E700 to move the performance measurement virtual machine 425 on the server A100 to the server E700 (step T202).
- step T203 the management server 400 requests the server D600 and the server A100 to move the virtual machine 123 on the server D600 to the server A100 (step T203).
- the virtual machine 123 executed on the server D600 is executed on the server A100. That is, step T203 corresponds to step S102 described in the second embodiment.
- the management server 400 When the management server 400 receives an operation input from the operator (step T204), the management server 400 requests the server selected according to the received operation input to move the performance measurement virtual machine 425 on the server E700. (Step T205).
- the server B200 it is assumed that the server B200 is selected and the performance measurement virtual machine 425 moves to the server B200. Since the performance measurement virtual machine 425 can execute a test program equivalent to the test program 423 of the second embodiment, step T205 corresponds to step S103 of the second embodiment.
- the management server 400 transmits an index value I B stored in step T201 to the performance measurement virtual machine 425, requests to run by entering the index value I B on the test program (step T206). That is, the management server 400 by sending an index value I B to the performance measurement virtual machine 425 to implement the test program execution request means of the present invention.
- step T207 corresponds to step S104 of the second embodiment.
- the index value I c is an index value corresponding to the resource amount that the performance measuring virtual machine 425 periodically acquires.
- the processing load of the virtual machine 123 running on the server A100 can be reproduced on the server B200. This reproduction corresponds to step S105 to step S107 of the second embodiment.
- the server A100 is obtained for each resource amount of time T 1 of the server A100 used by the virtual machine 123 is executed, it is acquired the index value I C corresponding to the resource amount, calculated on the basis of the resource amount and the index value I B stored in step T111, and transmits to the server B200 the calculated index value I C as the load information. Note that the above equation (2) is used for this calculation.
- the server B 200 receives the index value I C from the server A 100, the server B 200 inputs the received index value I C to the test program of the performance measurement virtual machine 425 and increases or decreases the processing load with time.
- processing related to reproduction is processing executed on the server A 100 (virtual machine 123) or the server B 200 (performance measurement virtual machine 425), and thus represents the operation of the management server 400 in FIG. It is not shown in the flowchart.
- Management server 400 the performance measurement virtual machine 425 while it does not receive a third resource amount P 31 from (server B200) (NO in step T208), the management server 400 enters a standby state. Further, when the third resource amount P 31 is received from the performance measurement virtual machine 425 (server B 200) (YES in step T 208), the management server 400 performs reception processing of the third resource amount P 31 (step T 209). the third resource amount P 31 received, and display output by the display unit 450 presents to the operator (step T210). That is, the series of processing described in this paragraph corresponds to Step S201 to Step S203 of the second embodiment.
- the management server 400 does not transmit a test program stop request to the performance measurement virtual machine 425 (NO in step T211), the above-described reproduction operation is repeatedly performed in the server A100 and the server B200.
- the management server 400 transmits a test program stop request to the performance measurement virtual machine 425 (YES in step T211)
- the performance measurement virtual machine 425 stops the test program, and the above-described reproduction operation ends.
- the management server 400 since the management server 400 directly requests the execution of the test program, the generation timing of the processing load by the test program can be controlled. Accordingly, when the test program is executed in a plurality of servers, the start timing can be synchronized.
- the copy of the performance measurement virtual machine 425 is moved to the server B 200 in a state where it is activated on another server, the processing load is quickly generated.
- the present embodiment is to temporarily move the performance measurement for the virtual machine 425 to the server A100 calculates an index value I B, then move the performance measurement for the virtual machine 425 to the server B200, using the index value I B Since the processing load is generated, the processing load of the virtual machine 123 can be reproduced with high accuracy from the rising point of the processing load generation.
- the processing load is generated based on the processing load and usage rate of the CPU 110 of the server A100, but the same processing may be executed based on the values related to other resources.
- the other resources are, for example, the memory usage of the server A100, the storage capacity of the hard disk of the server A100, the communication volume between the server A100 and the network 500, and the like. Any of these may be used, or a plurality may be used in combination.
- the server equivalent to the server B200 has been described with reference to only the server C300, but the number of servers equivalent to the server B200 may be further increased. Then, a test program equivalent to the test program 423 may be transmitted to each server to realize the same processing as the test program 423 in the second embodiment.
- the server D600 as a server for saving the virtual machine 123
- the server E700 as a server for pooling the performance measurement virtual machine 425
- the server A100 as a server for executing the virtual machine 123
- the performance measurement virtual machine 425 the description has been made by selecting the server B200 as the server to be executed, the present invention is not limited to this, and other combinations may be used.
- the third resource amounts P 31 and P 32 are displayed and output using the display unit 450 as the resource amount presenting unit.
- the present invention is not limited to this.
- the third resource amounts P 31 and P 32 may be output as audio using a speaker.
- the third resource amounts P 31 and P 32 may be printed out using a printing machine. A plurality of display outputs, audio outputs, or print outputs may be combined.
- step T104 and step T105 are described to be executed every time the resource amount is acquired in step T103, but the present invention is not limited to this. Good.
- the image of the performance measurement virtual machine 425 is copied to the storage unit of the other server of the movement destination.
- the performance measurement virtual machine 425 itself can be moved.
- the information processing method of the present invention describes a plurality of steps in order, the order of description does not limit the order in which the plurality of steps are executed. For this reason, when the information processing method of the present invention is executed, the order of the plurality of steps can be changed within a range that does not hinder the contents.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
Description
図1は、第1の実施形態の情報処理システム1000の構成図である。本実施形態の情報処理システム1000は、ネットワーク500を介して通信可能なサーバA100とサーバB200とを備える。サーバA100およびサーバB200は、それぞれCPU110、210および記憶部120、220を含んでいる。CPU110は、記憶部120に記憶されているプログラムやデータ等を読み出して処理したり、処理したプログラムやデータ等を記憶部120に書き込んだりすることができる。また、CPU210も同様に、記憶部220に記憶されているプログラムやデータ等を読み出して処理したり、処理したプログラムやデータ等を記憶部220に書き込んだりすることができる。
図4は、第2の実施形態の情報処理システム2000の構成図である。情報処理システム2000は、サーバA100、サーバB200、サーバC300および管理サーバ400を備え、それぞれネットワーク500を介して通信可能に接続されている。
図7は、第3の実施形態の情報処理システム3000の構成図である。サーバA100、サーバB200、サーバC300、サーバD600、管理サーバ400およびサーバE700が、ネットワーク500を介して通信可能に接続されている。
Claims (19)
- ネットワークを介して通信可能な第1サーバと第2サーバとを備え、
前記第1サーバは、
仮想マシンを実行する実行手段と、
前記実行手段により前記仮想マシンが実行されているとき、当該仮想マシンの実行に伴って前記第1サーバに発生している処理負荷を示す負荷情報を前記第2サーバに送信する負荷情報送信手段と、を含み、
前記第2サーバは、
前記第1サーバから受信した前記負荷情報に基づいて処理負荷を発生させる負荷発生手段を含むことを特徴とする情報処理システム。 - 請求項1に記載の情報処理システムであって、
前記第2サーバは、指標値の入力に応じて処理負荷を発生させ、前記指標値の大小によって前記処理負荷を増減させる試験プログラムを記憶している試験プログラム記憶手段を含み、
前記負荷情報送信手段は、前記指標値を前記負荷情報として送信し、
前記負荷発生手段は、前記試験プログラム記憶手段から前記試験プログラムを読み出し、前記負荷情報送信手段から受信した前記指標値を、読み出した前記試験プログラムに入力して前記処理負荷を発生させることを特徴とする情報処理システム。 - 請求項2に記載の情報処理システムであって、
前記第1サーバは、前記第1サーバにおいて前記試験プログラムに第1指標値を入力した場合に、前記試験プログラムが発生させる処理負荷によって使用される前記第1サーバのリソースの量を示す第1リソース量と、前記第1指標値とを対応付けて記憶する算出基準記憶手段を含み、
前記負荷情報送信手段は、前記仮想マシンが実行されることによって使用される前記第1サーバのリソース量を示す第2リソース量を取得し、取得された前記第2リソース量に対応する第2指標値を前記算出基準記憶手段に記憶されている前記第1リソース量と前記第1指標値とに基づいて算出し、算出された前記第2指標値を前記負荷情報として前記第2サーバに送信することを特徴とする情報処理システム。 - 請求項3に記載の情報処理システムであって、
前記負荷情報送信手段は、取得された前記第2リソース量に、前記第1指標値と前記第1リソース量との比率を乗算して前記第2指標値を算出することを特徴とする情報処理システム。 - 請求項1乃至4のいずれかに記載の情報処理システムであって、
前記負荷情報送信手段は、間欠的に前記負荷情報を前記第2サーバに送信し、
前記負荷発生手段は、発生させている処理負荷を、前記負荷情報送信手段から前記負荷情報を受信する毎に、受信された前記負荷情報に応じて増減させることを特徴とする情報処理システム。 - 請求項1乃至5のいずれかに記載の情報処理システムであって、
管理者の操作入力を受け付ける管理サーバを備え、
前記管理サーバは、
受け付けた操作入力に応じて選択された前記第2サーバに、試験プログラムを送信する試験プログラム送信手段と、
前記試験プログラム送信手段によって前記試験プログラムを送信された前記第2サーバに前記負荷情報を送信する要求を、前記第1サーバに送信する負荷情報送信要求手段と、
前記負荷発生手段が発生させた処理負荷によって使用される前記第2サーバのリソースの量を示す第3リソース量を受信するリソース量受信手段と、
前記リソース量受信手段により受信された前記第3リソース量を前記管理者に提示するリソース量提示手段と、を含むことを特徴とする情報処理システム。 - 請求項6に記載の情報処理システムであって、
前記試験プログラム送信手段は、複数の前記第2サーバに前記試験プログラムを送信し、
前記リソース量受信手段は、前記試験プログラムを受信した前記第2サーバそれぞれから前記第3リソース量を受信することを特徴とする情報処理システム。 - 請求項6または7に記載の情報処理システムであって、
前記リソース量受信手段は、間欠的に前記第3リソース量を前記第2サーバから受信し、
前記リソース量提示手段は、前記第3リソース量を受信する毎に、受信された前記第3リソース量を前記管理者に提示することを特徴とする情報処理システム。 - 請求項6乃至8いずれかに記載の情報処理システムであって、
前記管理サーバは、前記第2サーバに前記試験プログラムの実行を要求する試験プログラム実行要求手段を備えることを特徴とする情報処理システム。 - 第1サーバが仮想マシンを実行する実行ステップと、
前記実行ステップで前記仮想マシンが実行されているとき、当該仮想マシンの実行に伴って前記第1サーバに発生している処理負荷を示す負荷情報をネットワークを介して第2サーバに送信する負荷情報送信ステップと、
前記第1サーバから受信した前記負荷情報に基づいて処理負荷を発生させる負荷発生ステップと、
を備えることを特徴とする情報処理方法。 - 請求項10に記載の情報処理方法であって、
前記負荷情報送信ステップでは、指標値の入力に応じて処理負荷を発生させ、前記指標値の大小によって前記処理負荷を増減させる試験プログラムに入力される前記指標値を、前記第1サーバが前記負荷情報として送信し、
前記負荷発生ステップでは、前記試験プログラムを読み出し、前記負荷情報送信ステップで送信された前記指標値を、読み出した前記試験プログラムに入力して処理負荷を発生させることを特徴とする情報処理方法。 - 請求項11に記載の情報処理方法であって、
前記第1サーバにおいて前記試験プログラムに第1指標値を入力した場合に、前記試験プログラムが発生させる処理負荷によって使用される前記第1サーバのリソースの量を示す第1リソース量と、前記第1指標値とを対応付けて記憶する算出基準記憶ステップを備え、
前記負荷情報送信ステップでは、前記仮想マシンが実行されることによって使用される前記第1サーバのリソース量を示す第2リソース量を取得し、取得された前記第2リソース量に対応する第2指標値を前記算出基準記憶ステップで記憶した前記第1リソース量と前記第1指標値とに基づいて算出し、算出された前記第2指標値を前記負荷情報として前記第2サーバに送信することを特徴とする情報処理方法。 - 請求項12に記載の情報処理方法であって、
前記負荷情報送信ステップでは、取得された前記第2リソース量に、前記第1指標値と前記第1リソース量との比率を乗算して前記第2指標値を算出することを特徴とする情報処理方法。 - 請求項10乃至13のいずれかに記載の情報処理方法であって、
前記負荷情報送信ステップは間欠的に繰り返され、
前記負荷情報送信ステップで送信された前記負荷情報を受信する毎に、
前記負荷発生ステップでは、受信された負荷情報に応じて新たに処理負荷を予測し、発生させている処理負荷を増減させることを特徴とする情報処理方法。 - 請求項10乃至14のいずれかに記載の情報処理方法であって、
管理者の操作入力を受け付ける管理サーバが、受け付けた操作入力に応じて選択された前記第2サーバに、試験プログラムを送信する試験プログラム送信ステップと、
前記試験プログラム送信ステップで前記試験プログラムを送信された前記第2サーバに前記負荷情報を送信する要求を、前記第1サーバに送信する負荷情報送信要求ステップと、
前記負荷発生ステップで発生された処理負荷によって使用される前記第2サーバのリソースの量を示す第3リソース量を受信するリソース量受信ステップと、
前記リソース量受信ステップで受信された前記第3リソース量を前記管理者に提示するリソース量提示ステップと、
を備えることを特徴とする情報処理方法。 - 請求項15に記載の情報処理方法であって、
前記試験プログラム送信ステップでは、複数の前記第2サーバに前記試験プログラムを送信し、
前記リソース量受信ステップでは、前記試験プログラムを受信した前記第2サーバそれぞれから前記第3リソース量を受信することを特徴とする情報処理方法。 - 請求項15または16に記載の情報処理方法であって、
前記リソース量受信ステップは間欠的に繰り返され、
前記リソース量提示ステップでは、前記第3リソース量を受信する毎に、受信された前記第3リソース量を前記管理者に提示することを特徴とする情報処理方法。 - 請求項15乃至17いずれかに記載の情報処理方法であって、
前記管理サーバが前記第2サーバに前記試験プログラムの実行を要求する試験プログラム実行要求ステップを備えることを特徴とする情報処理方法。 - ネットワークを介して通信可能な第1サーバと第2サーバとで実行されるプログラムを格納している記憶媒体であって、
第1サーバに仮想マシンを実行させる実行処理と、
前記実行処理によって前記仮想マシンが実行されているとき、当該仮想マシンの実行に伴って前記第1サーバに発生している処理負荷を示す負荷情報を前記第2サーバに送信させる負荷情報送信処理と、
前記第1サーバから受信した前記負荷情報に基づいて前記第2サーバに処理負荷を発生させる負荷発生処理と、
を前記第1サーバまたは前記第2サーバのいずれかに実行させる前記プログラムを格納していることを特徴とする記憶媒体。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011522681A JP5522171B2 (ja) | 2009-07-17 | 2010-01-20 | 情報処理システム及び情報処理方法 |
US13/384,080 US8819174B2 (en) | 2009-07-17 | 2010-01-20 | Information processing system, information processing method, and storage medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2009-168497 | 2009-07-17 | ||
JP2009168497 | 2009-07-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011007463A1 true WO2011007463A1 (ja) | 2011-01-20 |
Family
ID=43449077
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/000284 WO2011007463A1 (ja) | 2009-07-17 | 2010-01-20 | 情報処理システム、情報処理方法および記憶媒体 |
Country Status (3)
Country | Link |
---|---|
US (1) | US8819174B2 (ja) |
JP (1) | JP5522171B2 (ja) |
WO (1) | WO2011007463A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012215915A (ja) * | 2011-03-31 | 2012-11-08 | Toshiba Corp | リソース利用率測定装置及びプログラム |
JP2020123033A (ja) * | 2019-01-29 | 2020-08-13 | 株式会社リコー | シミュレーションシステム、情報処理装置、プログラム及びシミュレーション方法 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10705933B2 (en) * | 2017-07-18 | 2020-07-07 | The Boeing Company | System integration using virtualization |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006031178A (ja) * | 2004-07-13 | 2006-02-02 | Hitachi Ltd | 負荷テスト実施装置、負荷テスト実施方法、負荷テスト実施プログラム |
JP2007323245A (ja) * | 2006-05-31 | 2007-12-13 | Nec Corp | 計算機システムおよび性能計測方法ならびに管理サーバ装置 |
JP2008146313A (ja) * | 2006-12-08 | 2008-06-26 | Chugoku Electric Power Co Inc:The | コンピュータの性能評価支援システム及び性能評価支援方法 |
JP2009134687A (ja) * | 2007-11-29 | 2009-06-18 | Hitachi Ltd | アプリケーションマイグレーションのための候補データセンタを見つける方法および装置[0001] |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8250559B2 (en) * | 2006-04-12 | 2012-08-21 | Oracle America, Inc. | Supporting per-program classpaths with class sharing in a multi-tasking virtual machine |
JP4906686B2 (ja) * | 2007-11-19 | 2012-03-28 | 三菱電機株式会社 | 仮想マシンサーバサイジング装置及び仮想マシンサーバサイジング方法及び仮想マシンサーバサイジングプログラム |
-
2010
- 2010-01-20 US US13/384,080 patent/US8819174B2/en not_active Expired - Fee Related
- 2010-01-20 JP JP2011522681A patent/JP5522171B2/ja active Active
- 2010-01-20 WO PCT/JP2010/000284 patent/WO2011007463A1/ja active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006031178A (ja) * | 2004-07-13 | 2006-02-02 | Hitachi Ltd | 負荷テスト実施装置、負荷テスト実施方法、負荷テスト実施プログラム |
JP2007323245A (ja) * | 2006-05-31 | 2007-12-13 | Nec Corp | 計算機システムおよび性能計測方法ならびに管理サーバ装置 |
JP2008146313A (ja) * | 2006-12-08 | 2008-06-26 | Chugoku Electric Power Co Inc:The | コンピュータの性能評価支援システム及び性能評価支援方法 |
JP2009134687A (ja) * | 2007-11-29 | 2009-06-18 | Hitachi Ltd | アプリケーションマイグレーションのための候補データセンタを見つける方法および装置[0001] |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012215915A (ja) * | 2011-03-31 | 2012-11-08 | Toshiba Corp | リソース利用率測定装置及びプログラム |
JP2020123033A (ja) * | 2019-01-29 | 2020-08-13 | 株式会社リコー | シミュレーションシステム、情報処理装置、プログラム及びシミュレーション方法 |
JP7151514B2 (ja) | 2019-01-29 | 2022-10-12 | 株式会社リコー | シミュレーションシステム、情報処理装置、プログラム及びシミュレーション方法 |
Also Published As
Publication number | Publication date |
---|---|
US20120124166A1 (en) | 2012-05-17 |
US8819174B2 (en) | 2014-08-26 |
JPWO2011007463A1 (ja) | 2012-12-20 |
JP5522171B2 (ja) | 2014-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10459769B2 (en) | Elastic container management system | |
JP4240062B2 (ja) | 計算機システムおよび性能計測方法ならびに管理サーバ装置 | |
US8701108B2 (en) | Apparatus and method for controlling live-migrations of a plurality of virtual machines | |
CN110678844A (zh) | 基于租户排名来控制租户服务 | |
JP5600277B2 (ja) | クラウドサービス再配置システムと方法およびプログラム | |
Gupta et al. | Power and resource-aware virtual machine placement for IaaS cloud | |
US8910128B2 (en) | Methods and apparatus for application performance and capacity analysis | |
JP2010244524A (ja) | 仮想サーバの移動方法の決定方法及びその管理サーバ | |
US9794136B1 (en) | Distributed resource allocation | |
US20160156567A1 (en) | Allocation method of a computer resource and computer system | |
JPWO2010109681A1 (ja) | コンピュータシステム、コンピュータシステムのリソース資源管理サーバ、及びコンピュータシステムのリソース管理方法 | |
KR20170057558A (ko) | 가상 데스크탑 서비스 방법 및 장치 | |
JP2016537705A (ja) | 仮想マシンマイグレーション管理の方法、装置およびシステム | |
Jararweh et al. | Energy efficient dynamic resource management in cloud computing based on logistic regression model and median absolute deviation | |
JP5522171B2 (ja) | 情報処理システム及び情報処理方法 | |
JP5112277B2 (ja) | 再現処理方法、計算機システムおよびプログラム | |
US8255535B2 (en) | Method and system to generate execution-based scheduling signature for an application | |
JP6191695B2 (ja) | 仮想リソース制御システムおよび仮想リソース制御方法 | |
JP2011192187A (ja) | 管理装置、管理方法およびプログラム | |
JP2012181578A (ja) | 更新制御装置及びプログラム | |
CN109933287A (zh) | 基于物联网的数据迁移方法、装置及设备 | |
Sudevalayam et al. | Affinity-aware modeling of CPU usage with communicating virtual machines | |
JP2011013711A (ja) | サービスシステム、クラウドコンピューティングシステム及びサービスプログラム | |
JP2011186821A (ja) | 仮想化環境管理システム、装置、方法及びプログラム | |
Nayyer et al. | Revisiting VM performance and optimization challenges for big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10799527 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13384080 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011522681 Country of ref document: JP |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10799527 Country of ref document: EP Kind code of ref document: A1 |