JP2013190879A - Computer system and system control method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To suppress deterioration of productivity concerning development of an application by a developer who develops the application.SOLUTION: A computer system according to an embodiment includes: a plurality of information processors which execute the same application; and a management device which manages the information processors. The management device determines whether or not there is difference in progress concerning execution of the application among the plurality of information processors. In addition, the management device makes the plurality of information processors transfer continuation according to the presence/absence of the difference in progress.

Description

  Embodiments described herein relate generally to a computer system and a system control method.

  In general, various applications (also referred to as “application programs”, “applications”, etc.) are executed on various computers. For example, the application may be executed in a physical device that physically exists, or may be executed in a virtual device that is virtually formed. Examples of physical devices include mobile terminals (also called “mobile terminals”) such as mobile phones and PDAs (Personal Digital Assistants), PCs (Personal Computers), server devices, and the like. Examples of virtual devices include virtual mobile terminals, PCs, server devices, and the like.

  The application is not limited to the above example, and may be executed in cooperation with a physical device group formed by a mobile terminal, a PC, a server device, a communication device, an external storage device, and the like that physically exist. Similarly, an application is executed in cooperation by a virtual device group formed by a virtual mobile terminal, a virtual PC, a virtual server device, a virtual communication device, a virtual external storage device, and the like. There is also a case. Note that various virtual devices are often formed on a cloud server, for example.

  In recent years, applications have been required to be executed continuously even in a diversified execution environment. For example, a mobile terminal such as a smart phone may change its IP address during movement, be placed in an environment where radio waves do not reach, or may run out of battery. Even when the execution environment changes in this way, the application executed on the mobile terminal is required to be executed continuously.

  Under such circumstances, the application may be executed cooperatively by the physical device and the virtual device. For example, an application may be executed on a resource of a physical device or a virtual device in a local environment or a remote environment.

Hideo Kinan “Google Android (Registered Product) Application Development Introduction”, Nikkei Business Publications, Inc. 274-275, June 18, 2009

  However, in the above-described conventional technology, there is a possibility that productivity of an application developer (hereinafter sometimes referred to as “application developer”) may be reduced. Specifically, when an application developer develops an application that is executed in cooperation with a physical device and a virtual device, an execution environment such as the location of resources, performance, design information, and unique functions in the physical device and virtual device. It is necessary to understand and carefully design. For this reason, the application developer needs to code execution control logic that is conscious of the execution environment in addition to coding logic for realizing the main functions of the application. This causes a decrease in productivity in application development.

  The technology disclosed in the present application has been made in view of the above, and an object thereof is to provide a computer system and a system control method capable of suppressing a decrease in productivity of an application.

  A computer system according to an embodiment is a computer system including a plurality of information processing apparatuses that execute the same application and a management apparatus that manages the information processing apparatus, and the information processing apparatus controls execution of the application An execution control unit, a collection unit that collects progress information indicating the progress of execution of the application in the execution control unit, and a calculation state in the execution control unit that is executing the application according to an instruction of the management device A generation unit that generates calculation state information to be displayed; and an application unit that applies the calculation state indicated by the calculation state information to the calculation state in the execution control unit when the calculation state information is provided from the management device. The management device collects data by the collection unit in the plurality of information processing devices. A determination unit that determines whether or not there is a difference in the progress of execution of the application among the plurality of information processing devices by comparing each progress information, and whether or not there is a difference in progress by the determination unit In response, the second information processing apparatus in which the execution of the application is proceeding more than the first information processing apparatus generates the calculation state information, and the generated calculation state information is transmitted to the first information processing apparatus. And a providing unit to provide.

  The computer system and the system control method according to the embodiment have an effect of being able to suppress a decrease in application productivity.

FIG. 1 is a diagram illustrating a configuration example of a computer system according to the first embodiment. FIG. 2 is an explanatory diagram for explaining an example of processing by the computer system according to the first embodiment. FIG. 3 is a diagram illustrating a configuration example of each device included in the computer system according to the first embodiment. FIG. 4 is a flowchart illustrating a processing procedure performed by the computer system according to the first embodiment. FIG. 5 is a diagram illustrating a configuration example of each device included in the computer system according to the second embodiment. FIG. 6 is a diagram conceptually illustrating an example of an execution profile generated by the profile generation unit according to the second embodiment. FIG. 7 is a diagram illustrating a computer that executes a management program.

  Hereinafter, embodiments of a computer system and a system control method according to the present application will be described in detail with reference to the drawings. The computer system and the system control method according to the present application are not limited by this embodiment.

(First embodiment)
[Configuration of Computer System According to First Embodiment]
First, the computer system according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating a configuration example of a computer system 1 according to the first embodiment. As illustrated in FIG. 1, the computer system 1 according to the first embodiment includes a management device 100, a mobile terminal 200, and a cloud server 300.

  In the computer system 1 according to the first embodiment, the same application is executed in the mobile terminal 200 and the cloud server 300. The management device 100 manages the execution status of applications in the mobile terminal 200 and the cloud server 300. The management apparatus 100 is connected to the mobile terminal 200 via the network N so as to be communicable. The management apparatus 100 is also connected to the cloud server 300 so as to be communicable.

  The mobile terminal 200 is an information processing apparatus such as a mobile phone or a PDA, and is connected to the management apparatus 100 so as to be communicable by performing wireless communication with the network N. The mobile terminal 200 executes an application according to an operation by a user, executes an application when a predetermined time comes, and always executes a resident application during startup.

  Note that the mobile terminal 200 according to the first embodiment is a smartphone, and a mobile OS (Operating System) such as Android (registered trademark) is installed. That is, the mobile terminal 200 according to the first embodiment executes an application that operates on the mobile OS, for example.

  The cloud server 300 includes one or more physical devices, and a virtual mobile terminal, a virtual PC, a virtual server device, a virtual communication device, a virtual external storage device, and the like are included in the physical device. A virtual device group is formed. The cloud server 300 according to the first embodiment forms a virtual mobile terminal 301 corresponding to the mobile terminal 200. Then, the cloud server 300 uses the virtual mobile terminal 301 to execute the same application as the application executed on the mobile terminal 200.

  In the example illustrated in FIG. 1, the management apparatus 100 may be a physical apparatus that physically exists, a virtual apparatus that is realized by the cloud server 300, or another cloud that is not illustrated. It may be a virtual device realized by a server.

[Example of Processing by Computer System According to First Embodiment]
Next, processing performed by the computer system 1 according to the first embodiment will be described with reference to FIG. FIG. 2 is an explanatory diagram for explaining an example of processing by the computer system 1 according to the first embodiment.

  In the example illustrated in FIG. 2, the mobile terminal 200 and the cloud server 300 simultaneously execute the same application X. The execution environment of the application X in the mobile terminal 200 corresponds to the physical execution environment P indicating that it is executed by a physical device. Further, the execution environment of the application X in the cloud server 300 corresponds to a virtual execution environment V indicating that it is executed by the virtual virtual mobile terminal 301.

  The application X is converted into an intermediate code (byte code) so as to be a common execution mode for the mobile terminal 200 and the cloud server 300. That is, the mobile terminal 200 and the cloud server 300 obtain the same execution result by executing the same binary code corresponding to the application X, respectively. The entire process performed when the application X is executed can be classified for each predetermined partial process. An example of partial processing includes “function” in the case of a functional program, and “method” in the case of an object-oriented program. FIG. 2 shows an example in which the entire process by the application X is divided into partial processes J1 to J10.

  In addition, when the mobile terminal 200 and the cloud server 300 execute various applications, a check point that is a timing for confirming the execution status of the application is set. Then, the mobile terminal 200 and the cloud server 300 notify the management apparatus 100 of progress information indicating how far the application has been executed when the check point is reached. In the first embodiment, it is assumed that checkpoints are set at regular time intervals (for example, 1 minute, 5 minutes, 30 minutes, etc.).

  Under such a premise, in the example shown in FIG. 2, the mobile terminal 200 (physical execution environment P) has completed the execution of the partial process J1 at the time of the first checkpoint CP1. At this time, the mobile terminal 200 notifies the management apparatus 100 of progress information indicating that the execution of the partial process J1 is completed. Similarly, the cloud server 300 (virtual execution environment V) has completed the execution of the partial process J1 at the time of the checkpoint CP1, and sends progress information indicating that the execution of the partial process J1 has been completed to the management apparatus 100. Notice.

  The management device 100 receives progress information from the mobile terminal 200 and the cloud server 300 at the time of the checkpoint CP1. Here, since there is no difference in the progress information received from the mobile terminal 200 and the cloud server 300, the management apparatus 100 does not perform processing on the mobile terminal 200 and the cloud server 300.

  Subsequently, at the time of the second checkpoint CP2, it is assumed that the mobile terminal 200 has completed execution up to the partial process J2 indicated by the dotted line in the drawing. In such a case, the mobile terminal 200 notifies the management apparatus 100 of progress information indicating that the execution of the partial processes J1 and J2 has been completed. On the other hand, it is assumed that the cloud server 300 has completed the execution of the partial process J5 at the time of the checkpoint CP2. In such a case, the cloud server 300 notifies the management apparatus 100 of progress information indicating that the execution of the partial processes J1 to J5 has been completed.

  The management device 100 has completed execution up to the partial process J2 in the mobile terminal 200 based on the progress information received from the mobile terminal 200 and the cloud server 300 at the time of the checkpoint CP2, but the partial process is not performed in the cloud server 300. It is detected that execution has been completed up to J5. In such a case, the management apparatus 100 determines whether or not the difference in the number of partial processes already executed in the mobile terminal 200 and the cloud server 300 is equal to or greater than a predetermined process number threshold. When the difference in the number of executed partial processes is equal to or greater than the process number threshold (here, the process number threshold is “3”), the management apparatus 100 determines whether the application X of the mobile terminal 200 and the cloud server 300 Synchronize execution status.

  Specifically, the management apparatus 100 acquires “continuation” from the cloud server 300 with a large number of executed partial processes. Here, “continuation” means data in which the calculation process to be executed is embodied as data, and snaps the calculation state (CPU, stack, heap, program counter) reached in the previous calculation process This corresponds to the data structure cut out as a shot.

  In the example of FIG. 2, since the difference “3” in the number of executed partial processes is greater than or equal to the process number threshold “3”, the management apparatus 100 continues the continuation at the time when the partial process J5 is completed. The continuation acquired from 300 is transmitted to the mobile terminal 200. The mobile terminal 200 can advance the execution status of the application X until the execution of the partial process J5 is completed by executing the continuation received from the management apparatus 100.

  Subsequently, at the time of the check point CP3, it is assumed that the mobile terminal 200 has completed the execution up to the partial process J8 indicated by the dotted line in the drawing. In such a case, the mobile terminal 200 notifies the management apparatus 100 of progress information indicating that the execution of the partial processes J1 to J8 has been completed. On the other hand, it is assumed that the cloud server 300 has completed execution up to the partial process J10 at the time of the checkpoint CP3. In such a case, the cloud server 300 notifies the management apparatus 100 of progress information indicating that the execution of the partial processes J1 to J10 has been completed.

  The management apparatus 100 determines that the difference “2” in the number of partial processes already executed in the mobile terminal 200 and the cloud server 300 is not greater than or equal to the process number threshold “3” at the time of the checkpoint CP3. In such a case, the management apparatus 100 does not synchronize the execution status of the application X in the mobile terminal 200 and the cloud server 300. That is, the management apparatus 100 does not perform continuation delivery between the mobile terminal 200 and the cloud server 300.

  As described above, in the computer system 1 according to the first embodiment, the execution states of applications in the mobile terminal 200 and the cloud server 300 that are a plurality of information processing apparatuses are synchronized. Specifically, in the computer system 1, the execution of the application is progressed in the other information processing apparatus (mobile terminal 200 or cloud server 300) than in the one information processing apparatus (mobile terminal 200 or cloud server 300). The execution status of one information processing device whose execution is delayed is synchronized with the execution status of the other information processing device whose execution is progressing.

  Thereby, in the computer system 1 according to the first embodiment, when the execution state of the application in the mobile terminal 200 is delayed from the cloud server 300, the execution state of the application in the mobile terminal 200 is executed in the cloud server 300. You can make progress to the situation. In the computer system 1 according to the first embodiment, when the execution state of the application in the cloud server 300 is behind the mobile terminal 200, the execution state of the application in the cloud server 300 is changed to the execution state in the mobile terminal 200. Can be advanced. That is, the computer system 1 can maintain application execution even when the execution environment of the information processing apparatus such as the mobile terminal 200 changes.

  For example, the mobile terminal 200 may change its IP address, be placed in an environment where radio waves do not reach, or run out of battery during execution of an application. When the execution environment changes in this way, the mobile terminal 200 may delay, interrupt, or stop the execution of the application. However, in the computer system 1 according to the first embodiment, even when a delay or the like occurs in the execution of the application in the mobile terminal 200, the execution of the application is maintained in the cloud server 300. For this reason, in the computer system 1, when the execution environment of the mobile terminal 200 is improved, the execution status of the mobile terminal 200 can be synchronized with the execution status of the cloud server 300. For this reason, the computer system 1 according to the first embodiment can continuously execute an application even when the execution environment of the mobile terminal 200 such as a smartphone changes.

  In the computer system 1, applications are executed in a plurality of execution environments such as the mobile terminal 200 (physical execution environment P) and the cloud server 300 (virtual execution environment V). Executed in the environment. In other words, an application developer who develops an application to be executed in the computer system 1 only needs to develop an application to be executed in the physical device. It is not necessary to understand and carefully design the execution environment, and to code execution control logic that is conscious of the execution environment. Thus, the computer system 1 according to the first embodiment can execute an application continuously even when the execution environment in the information processing apparatus such as the mobile terminal 200 changes. Can be provided, and a decrease in productivity of application development can be suppressed.

  2 shows an example in which the partial processes J1, J2,..., J10 are executed in this order, but the execution order of the partial processes is not limited to this example. For example, when the application is executed, the same partial process may be repeatedly executed, or there may be a partial process that is not executed by the branch process. Accordingly, the progress information transmitted from the mobile terminal 200 or the virtual mobile terminal 301 to the management apparatus 100 includes an example of “partial process J1 = 1 execution, partial process J2 = 3 execution”.

[Configuration of each apparatus according to the first embodiment]
Next, the configuration of each device included in the computer system 1 according to the first embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of each apparatus according to the first embodiment. Each processing unit included in the cloud server 300 illustrated in FIG. 3 is realized by the virtual mobile terminal 301. As illustrated in FIG. 3, the management device 100 includes a checkpoint definition unit 111, a checkpoint synthesis unit 112, a distributed data sharing unit 120, and a continuous distribution sharing unit 130.

  The checkpoint definition unit 111 generates checkpoint setting data in which a checkpoint that is a timing for confirming the execution status of the application is defined. The checkpoint definition unit 111 according to the first embodiment generates checkpoint setting data defined to be every predetermined time interval. Then, the checkpoint definition unit 111 outputs the application source code and checkpoint setting data to the checkpoint synthesis unit 112.

  Note that the checkpoint definition unit 111 holds, for example, a source code of an application that can be executed by the mobile terminal 200 in a storage unit (not shown). Then, when a predetermined application is executed by the mobile terminal 200, the checkpoint definition unit 111 receives information identifying the application from the mobile terminal 200, thereby corresponding to the application executed on the mobile terminal 200. The source code is acquired from the storage unit. Further, for example, the checkpoint definition unit 111 does not hold the source code, but the mobile terminal 200, the cloud server 300, the virtual mobile terminal 301, or a storage unit (not shown) may hold the source code. In such a case, the checkpoint definition unit 111 acquires the source code corresponding to the application executed on the mobile terminal 200 from the device that holds the source code.

  The checkpoint synthesis unit 112 generates intermediate code in which checkpoints are defined based on the checkpoint setting data generated by the checkpoint definition unit 111. The checkpoint synthesis unit 112 according to the first embodiment generates an intermediate code in which it is defined that the checkpoint is every predetermined time interval. Then, the checkpoint synthesis unit 112 outputs the checkpoint-defined intermediate code to the mobile terminal 200 and the virtual mobile terminal 301. Note that the checkpoint synthesis unit 112 converts the source code output from the checkpoint definition unit 111 into an intermediate code so that the execution mode is common to the mobile terminal 200 and the virtual mobile terminal 301.

  The distributed data sharing unit 120 determines whether or not to allow continuation to be transferred between the mobile terminal 200 and the virtual mobile terminal 301 based on progress information transmitted from the mobile terminal 200 and the virtual mobile terminal 301. Determine. The processing by the distributed data sharing unit 120 will be described later.

  The continuous distribution sharing unit 130 acquires continuation from one of the mobile terminal 200 and the virtual mobile terminal 301 when the distributed data sharing unit 120 determines that continuation needs to be delivered, and acquires the continuation. (Continuation) is provided to the other of the mobile terminal 200 and the virtual mobile terminal 301.

  As shown in FIG. 3, the mobile terminal 200 includes a program placement unit 211, an execution control unit 212, a checkpoint trigger unit 220, a collection unit 230, a continuous data conversion unit 241, and a continuous application unit 242. Have

  The program placement unit 211 receives the checkpoint-defined intermediate code from the checkpoint synthesis unit 112, and outputs the received intermediate code to the execution control unit 212. Thereby, the program placement unit 211 causes the execution control unit 212 to execute the application.

  The execution control unit 212 executes the application by processing the checkpoint-defined intermediate code output from the program placement unit 211. The execution control unit 212 executes the application using the calculation resources (calculation resources such as CPU time and memory usage) in the mobile terminal 200 which is the physical execution environment P.

  The checkpoint trigger unit 220 monitors the checkpoints defined by the checkpoint definition unit 111 for the operation process of execution control by the execution control unit 212. And when it becomes a checkpoint, the checkpoint trigger part 220 generates an event, and makes the collection part 230 measure various information regarding the execution state in the mobile terminal 200 (physical execution environment P).

  Also, the checkpoint trigger unit 220 according to the first embodiment notifies the collection unit 230 of progress information indicating the partial processing that has been executed by the execution control unit 212. Specifically, in the intermediate code executed by the execution control unit 212, a marking code serving as a mark for the execution control unit 212 to notify the completion when the execution of the partial process is completed is embedded for each predetermined partial process. Such a marking code is embedded by, for example, a programmer who is an application developer. Also, for example, even if the application developer does not explicitly embed the marking code, it uses metaprogramming (aspect-oriented programming) etc. to automatically obtain the logical milestones for obtaining the function evaluation results and messages sent back by the method. The marking code may be embedded by a technique capable of marking the mark. When such a method is used, it is possible to manage the execution status by recording which processing unit (function evaluation, method execution) and how many times it is executed at the time of execution in a meta-level hash table or the like. The checkpoint trigger unit 220 can acquire progress information by the execution control unit 212 by receiving the completion notification from the execution control unit 212.

  In the first embodiment, the checkpoint trigger unit 220 wakes up an independent thread at the execution control level (meta-execution level), and whenever a certain time elapses while referring to the local timer (the checkpoint is reached). At that time, an interrupt may be generated so that the collection unit 230 measures various information related to the execution state. Here, when a certain time interval serving as a checkpoint is set in the mobile terminal 200 (physical execution environment P), the checkpoint definition unit 111 does not have to generate checkpoint setting data. The checkpoint synthesis unit 112 does not have to generate intermediate code in which checkpoints are defined.

  When the collection unit 230 receives a notification that the check point is a check point from the check point trigger unit 220, the collection unit 230 performs various types related to the execution state in the mobile terminal 200 (physical execution environment P) (resource information about resources consumed by the mobile terminal 200, etc.) ). The collection unit 230 according to the first embodiment includes a power measurement unit 231.

  The power measurement unit 231 measures the power consumption required by the mobile terminal 200 as an element of the execution state in the mobile terminal 200 (physical execution environment P). For example, the power measurement unit 231 measures the accumulation of power consumption required by the mobile terminal 200 from the start of execution of the application by the execution control unit 212 to the current checkpoint. For example, the power measurement unit 231 measures the power consumption required by the mobile terminal 200 from the previous check point to the current check point. In the first embodiment, the power measurement unit 231 measures the accumulation of power consumption. Note that the power measuring unit 231 can acquire the power consumed by the mobile terminal 200 by, for example, a dedicated device for monitoring power consumption. In addition, for example, since an application or a mechanism for monitoring power consumption is generally installed in a smartphone or the like, the power measurement unit 231 can acquire power consumption using such an application or mechanism.

  Then, the collection unit 230 transmits the progress information notified from the checkpoint trigger unit 220 and the power consumption information indicating the power consumption measured by the power measurement unit 231 to the distributed data sharing unit 120.

  Here, in the first embodiment, the distributed data sharing unit 120 of the management device 100 receives the progress information and the power consumption information from the collection unit 230 of the mobile terminal 200 at each checkpoint, and on the cloud server 300. The progress information and the power consumption information are also received from the collection unit 330 of the virtual mobile terminal 301 formed in the above. The distributed data sharing unit 120 determines whether or not there is a difference in the progress of application execution between the mobile terminal 200 and the virtual mobile terminal 301 by comparing the progress information received from both sides. Specifically, the distributed data sharing unit 120 determines whether the difference between the number of partial processes executed in the mobile terminal 200 and the number of partial processes executed in the virtual mobile terminal 301 is equal to or greater than a predetermined process number threshold. Determine whether or not.

  Further, although omitted in the description of FIG. 2, the distributed data sharing unit 120 is configured so that the mobile terminal 200 and the virtual mobile terminal 301 can be used even when the difference in the number of executed partial processes is equal to or greater than a predetermined process number threshold. Whether or not to continue transmission / reception between the mobile terminal 200 and the virtual mobile terminal 301 is determined based on the power consumption information received from the mobile terminal 200. Specifically, the distributed data sharing unit 120 calculates the difference between the power consumption of the mobile terminal 200 and the power consumption of the virtual mobile terminal 301. Then, the distributed data sharing unit 120 uses the calculated power consumption difference that is assumed to be necessary for the mobile terminal 200 or the virtual mobile terminal 301 to receive continuation (hereinafter, “assumed power consumption”). It is determined whether or not it is larger. Then, when the difference in power consumption is larger than the assumed power consumption, the distributed data sharing unit 120 determines that continuation should be transmitted and received, and the difference in power consumption is less than or equal to the assumed power consumption on the receiving side. If it is, it is determined that continuation should not be transmitted / received.

  An example of processing performed by the distributed data sharing unit 120 will be described. Here, it is assumed that the processing number threshold is “3”. Also, the distributed data sharing unit 120 receives the progress information “J1 to J5” and the power consumption information “50” from the mobile terminal 200, and the progress information “J1 to J10” and the power consumption information “200” from the virtual mobile terminal 301. Is received.

  In this case, in the distributed data sharing unit 120, the virtual mobile terminal 301 has five more partial processes that have been executed than the mobile terminal 200, and the difference in the number of partial processes that have been executed is the process number threshold “3”. It determines with it being above. In the case of this example, the distributed data sharing unit 120 determines whether to provide the continuation of the virtual mobile terminal 301 to the mobile terminal 200 based on the power consumption information. Specifically, the distributed data sharing unit 120 calculates a difference “150” between the power consumption information “200” of the virtual mobile terminal 301 and the power consumption information “50” of the mobile terminal 200. Thereby, the distributed data sharing unit 120 can estimate that the power consumption “150” is required for the mobile terminal 200 to execute the partial processes “J6 to J10”.

  Here, the distributed data sharing unit 120 acquires power consumption that is assumed to be required for the mobile terminal 200 to receive the continuation of the virtual mobile terminal 301. For example, the distributed data sharing unit 120 stores a known assumed power consumption required for the mobile terminal 200 to receive and apply continuation in a predetermined storage unit, and obtains the assumed power consumption from the storage unit. To do. Here, it is assumed that the assumed power consumption acquired by the distributed data sharing unit 120 is “100”. That is, in this example, the power consumption information difference “150” calculated above is larger than the assumed power consumption “100”. In this case, the distributed data sharing unit 120 receives the power consumption “150” required for the mobile terminal 200 to execute the partial processing “J6 to J10”, and the mobile terminal 200 receives the continuation of the virtual mobile terminal 301. It can be determined that the power consumption is greater than the assumed power consumption “100” required for the operation. For this reason, the distributed data sharing unit 120 determines that the continuation of the virtual mobile terminal 301 should be transmitted to and received from the mobile terminal 200 because it can reduce power consumption. To do.

  In the above example, the distributed data sharing unit 120 receives the progress information “J1 to J7” and the power consumption information “150” from the mobile terminal 200, and the progress information “J1 to J10” and the power consumption from the virtual mobile terminal 301. It is assumed that the information “200” is received. In the case of this example, the distributed data sharing unit 120 determines whether to provide the continuation of the virtual mobile terminal 301 to the mobile terminal 200 based on the power consumption information.

  Specifically, the distributed data sharing unit 120 calculates a difference “50” between the power consumption information “200” of the virtual mobile terminal 301 and the power consumption information “150” of the mobile terminal 200. Thereby, the distributed data sharing unit 120 can estimate that the power consumption “50” is required for the mobile terminal 200 to execute the partial processing “J8 to J10”. Similarly to the above example, the distributed data sharing unit 120 acquires the power consumption “100” that is assumed to be required for the mobile terminal 200 to receive continuation. In such a case, the distributed data sharing unit 120 receives the power consumption “50” required for the mobile terminal 200 to execute the partial processing “J8 to J10”, and the mobile terminal 200 receives the continuation of the virtual mobile terminal 301. It can be determined that the power consumption is “100” or less. For this reason, the distributed data sharing unit 120 determines that the continuation should not be transmitted and received because the power consumption can be suppressed if the continuation of the virtual mobile terminal 301 is not provided to the mobile terminal 200. .

  Such a distributed data sharing unit 120 continues the continuation of the other information processing device (mobile terminal 200 or virtual mobile terminal 301) with respect to one information processing device (mobile terminal 200 or virtual mobile terminal 301). If it is determined that it should be provided, the other information processing apparatus is instructed to generate a continuation. For example, when the distributed data sharing unit 120 determines that the continuation of the virtual mobile terminal 301 should be provided to the mobile terminal 200, the distributed data sharing unit 120 continues to the continuous data conversion unit 341 of the virtual mobile terminal 301. (Continuation) is generated.

  The continuation data conversion unit 241 generates a continuation corresponding to a data structure in which a calculation state (CPU, stack, heap, program counter) at an arbitrary time point is saved as a snapshot. The continuous data converting unit 241 generates a continuation according to an instruction from the distributed data sharing unit 120 and transmits the generated continuation to the continuous distribution sharing unit 130. The continuous distribution sharing unit 130 transmits the continuation received from the continuous data conversion unit 241 to the continuation application unit 342 of the virtual mobile terminal 301. When the continuation sharing unit 130 receives a continuation from the continuation data converting unit 341 of the virtual mobile terminal 301, the continuation sharing unit 130 transmits the received continuation to the continuation application unit 242 of the mobile terminal 200.

  The continuation application unit 242 applies the received continuation to the execution control unit 212 when the continuation generated by the continuous data generation unit 341 of the virtual mobile terminal 301 is received from the continuous distribution sharing unit 130. To do. Specifically, the continuation application unit 242 synchronizes the execution status of the application in the mobile terminal 200 and the virtual mobile terminal 301 by executing the continuation provided from the continuous distribution sharing unit 130.

  As shown in FIG. 3, the cloud server 300 includes a program placement unit 311, an execution control unit 312, a checkpoint trigger unit 320, a collection unit 330, a continuous data conversion unit 341, and a continuous application unit 342. Have Each of these processing units is a processing unit realized by the virtual mobile terminal 301 illustrated in FIG. 1, and is the same as each processing unit included in the mobile terminal 200 in the cloud server 300 (virtual execution environment V). Perform the process. In general, the computing resources (memory, CPU power, power, storage) of the cloud server 300 can be expected to be stably supplied. There is an expectation that a reliable execution result can be achieved from the mobile terminal 200 in an unstable communication state due to the high speed, stable power supply, and reliable data storage capability.

[Processing Procedure by Computer System According to First Embodiment]
Next, the procedure of processing by the computer system 1 according to the first embodiment will be described with reference to FIG. FIG. 4 is a flowchart illustrating a processing procedure performed by the computer system 1 according to the first embodiment.

  As illustrated in FIG. 4, the checkpoint synthesis unit 112 of the management apparatus 100 generates a checkpoint-defined intermediate code, and the generated checkpoint-defined intermediate code is formed in the mobile terminal 200 and the cloud server 300. Is transmitted to the virtual mobile terminal 301 (step S101).

  The execution control unit 212 of the mobile terminal 200 controls the execution of the application by processing the checkpoint-defined intermediate code transmitted from the management apparatus 100 (step S102). Similarly, the execution control unit 312 of the virtual mobile terminal 301 performs execution control of the application by processing the checkpoint-defined intermediate code transmitted from the management apparatus 100 (step S103).

  Then, the checkpoint trigger unit 220 of the mobile terminal 200 monitors whether or not the application has been executed by the execution control unit 212 (step S104). Similarly, the checkpoint trigger unit 320 of the virtual mobile terminal 301 monitors whether or not the application has been executed by the execution control unit 312 (step S105).

  When the power measuring unit 231 of the mobile terminal 200 becomes a checkpoint (Yes at Step S104), the power measuring unit 231 measures the power consumption (Step S106). Then, the collection unit 230 transmits progress information and power consumption information to the management apparatus 100 (step S107). Similarly, the power measuring unit 331 of the virtual mobile terminal 301 measures the power consumption when the check point is reached (Yes at Step S105) (Step S108). Then, the collection unit 330 transmits progress information and power consumption information to the management apparatus 100 (step S109).

  Subsequently, the distributed data sharing unit 120 of the management apparatus 100 continues between the mobile terminal 200 and the virtual mobile terminal 301 based on progress information transmitted from the mobile terminal 200 and the virtual mobile terminal 301. It is determined whether or not delivery is to be performed (step S110).

  Here, it is assumed that the distributed data sharing unit 120 determines to continue the continuation of the virtual mobile terminal 301 to the mobile terminal 200. In such a case, the distributed data sharing unit 120 instructs the virtual mobile terminal 301 to generate a continuation (step S111). The continuous data converting unit 341 of the virtual mobile terminal 301 that has received such an instruction generates a continuation and transmits it to the management device 100 (step S112).

  The continuous distribution sharing unit 130 of the management apparatus 100 provides the continuation received from the virtual mobile terminal 301 to the mobile terminal 200 (step S113). Then, the continuation application unit 242 of the mobile terminal 200 applies the continuation received from the management device 100 to the execution control unit 212 (step S114).

[Effect of the first embodiment]
As described above, the computer system 1 according to the first embodiment includes the mobile terminal 200 and the virtual mobile terminal 301 as a plurality of information processing apparatuses that execute the same application. The computer system 1 also includes a management device 100 that manages the mobile terminal 200 and the virtual mobile terminal 301. Then, the mobile terminal 200 executes an application according to an instruction from the execution control unit 212 that controls the execution of the application, a collection unit 230 that collects progress information indicating the progress of execution of the application in the execution control unit 212, and the management device 100. In the case where the continuation data generation unit 241 that generates continuation as calculation state information indicating the calculation state in the execution control unit 212 being executed and the management device 100 are provided with continuation, the continuation is performed. Is applied to the calculation state in the execution control unit 212. Further, the virtual mobile terminal 301 has the same configuration as the mobile terminal 200. In addition, the management apparatus 100 compares the progress information collected by the collection units of the mobile terminal 200 and the virtual mobile terminal 301, thereby making a difference in the progress of application execution between the mobile terminal 200 and the cloud server 300. Is generated by causing the mobile terminal 200 or the cloud server 300 to generate a continuation according to whether there is a difference in progress between the distributed data sharing unit 120 and the distributed data sharing unit 120. And a continuous distribution sharing unit 130 that provides the continuation to the mobile terminal 200 or the cloud server 300.

  As a result, the computer system 1 according to the first embodiment provides an execution environment capable of continuously executing an application even when the execution environment in the information processing apparatus such as the mobile terminal 200 changes. In addition, it is possible to suppress a decrease in productivity related to application development by application developers.

  Also, for example, highly specialized and complex applications such as photo editing processing have been implemented with original stand-alone programs. However, recently, the use of smartphones (multifunctional telephone devices) has been accelerated. ing. On the other hand, the trend toward power saving and cost reduction of devices is accelerating, and the need for computing with low-speed devices is still high. In other words, it can be said that conflicting computing needs such as wanting to use sophisticated and complicated applications on low-speed moving devices are expanding.

  In the computer system 1 according to the first embodiment, the execution status of the application in the mobile terminal 200 and the virtual mobile terminal 301 is synchronized. For example, even when the low-speed device being moved executes an advanced application Response results can be obtained at high speed with low power consumption. In addition, application developers can design and implement applications without being aware of device differences (high speed and low speed) in advance, so they can design and implement existing application development styles (know-how) without bold changes. Can be implemented.

  In the first embodiment, the distributed data sharing unit 120 determines that the difference between the power consumption of the mobile terminal 200 and the power consumption of the virtual mobile terminal 301 indicates that the mobile terminal 200 or the virtual mobile terminal 301 continues (continuation). It is determined whether or not it is larger than the power consumption (assumed power consumption) assumed to be required for reception. However, the determination process by the distributed data sharing unit 120 is not limited to this example.

  For example, in order to reduce the total power consumption of both the mobile terminal 200 and the virtual mobile terminal 301 as much as possible, the distributed data sharing unit 120 determines that the difference in power consumption between the mobile terminal 200 and the virtual mobile terminal 301 is the mobile terminal 200 or the virtual mobile terminal 301. It may be determined whether or not the mobile terminal 301 is larger than the power consumption assumed to be required for transmitting and receiving continuation.

  For example, in the cloud server 300 environment in which the virtual mobile terminal 301 is realized, when there is a premise that stable power supply is possible and reduction in power consumption is not important, the distributed data sharing unit 120 is A reduction in power consumption at 200 may be prioritized. Specifically, when the distributed data sharing unit 120 transmits the continuation of the virtual mobile terminal 301 to the mobile terminal 200, the difference in power consumption between the mobile terminal 200 and the virtual mobile terminal 301 as in the above example. However, it is determined whether or not the mobile terminal 200 is larger than the power consumption assumed to be required for the continuation of the virtual mobile terminal 301 to be received.

  Further, the distributed data sharing unit 120 accumulates past power consumption in the mobile terminal 200 and the virtual mobile terminal 301 as a profile, and assumes the assumed power consumption based on the ratio of the power consumption in the mobile terminal 200 and the virtual mobile terminal 301. May be estimated. For example, the distributed data sharing unit 120 estimates the power consumption of the mobile terminal 200 by converting the power consumption of the virtual mobile terminal 301 into the power consumption of the mobile terminal 200 using the ratio.

(Second Embodiment)
In the first embodiment, an example is shown in which checkpoints are set at regular time intervals. However, checkpoints may be set for each predetermined partial process. In the second embodiment, an example in which checkpoints are set for each predetermined partial process will be described. In the second embodiment, it is assumed that the same application is repeatedly executed over a long period of time by the mobile terminal 500 and the cloud server 600 described below. For example, the application in the second embodiment corresponds to a permanent residence program that is repeatedly executed.

[Configuration of Each Device According to Second Embodiment]
First, the configuration of each device included in the computer system 2 according to the second embodiment will be described with reference to FIG. FIG. 5 is a diagram illustrating a configuration example of each device according to the second embodiment. As shown in FIG. 5, the computer system 2 according to the second embodiment includes a management device 400, a mobile terminal 500, and a cloud server 600. In addition, below, the detailed description is abbreviate | omitted as attaching | subjecting the same code | symbol to the site | part which has the function similar to the already shown component site | part. The configuration of the computer system 2 according to the second embodiment is the same as the configuration example shown in FIG.

  As illustrated in FIG. 5, the management apparatus 400 includes a checkpoint definition unit 411, a checkpoint synthesis unit 412, a distributed data sharing unit 420, a profile storage unit 440, and a checkpoint modification unit 450. In addition, the mobile terminal 500 includes a checkpoint trigger unit 520, a collection unit 530, and a profile generation unit 540. Further, the cloud server 600 forms a virtual mobile terminal (hereinafter referred to as “virtual mobile terminal 601”) corresponding to the mobile terminal 500, and as a processing unit realized by the virtual mobile terminal 601, a collection unit 630, And a profile generation unit 640. Note that the collection unit 630 and the profile generation unit 640 are processing units corresponding to the collection unit 530 and the profile generation unit 540, and thus description thereof will be omitted below. Hereinafter, the processing units included in the management device 400 and the mobile terminal 500 will be described in the order of processing.

  The checkpoint definition unit 411 of the management apparatus 400 generates checkpoint setting data in which checkpoints are defined for each predetermined partial process (function or method) included in the application source code. The position where the checkpoint is embedded is specified by a programmer who is an application developer. For example, the checkpoint definition unit 411 according to the second embodiment interacts with a programmer who is an application developer by displaying source code on a display device of a terminal device used by the programmer who is an application developer. To specify where to embed checkpoints. As described in the first embodiment, by utilizing meta-programming (aspect-oriented programming) or the like, checkpoints are automatically embedded even if the application developer does not explicitly embed checkpoints. You can also.

  Based on the checkpoint setting data generated by the checkpoint definition unit 411, the checkpoint synthesis unit 412 of the management apparatus 400 generates an intermediate code in which checkpoints are defined. For example, the checkpoint synthesis unit 412 according to the second embodiment has checkpoints defined by synthesis and translation of program code based on the definition of metalogic that is an aspect-oriented interception logic weaving or reflection model. Generate intermediate code.

  The checkpoint trigger unit 520 of the mobile terminal 500 monitors the checkpoint defined by the checkpoint definition unit 411 for the operation process of execution control by the execution control unit 212. Then, the checkpoint trigger unit 520 generates an event and causes the collection unit 530 to measure the execution state in the mobile terminal 500 (physical execution environment P) when it becomes a checkpoint.

  In addition, when a checkpoint becomes a checkpoint, the checkpoint trigger unit 520 according to the second embodiment notifies the collection unit 530 as progress information (CP information) for specifying the checkpoint.

  The collection unit 530 of the mobile terminal 500 includes a power measurement unit 531 and a timer unit 532 as illustrated in FIG. The power measurement unit 531 according to the second embodiment measures the power consumption required by the mobile terminal 500 from the previous checkpoint to the current checkpoint as an element of the execution state in the mobile terminal 500 (physical execution environment P). .

  The timer 532 measures the application processing time in the mobile terminal 500 as an element of the execution state in the mobile terminal 500 (physical execution environment P). For example, the time measuring unit 532 measures the elapsed time from the previous check point to the current check point as the processing time. Further, for example, the time counting unit 532 counts the accumulated elapsed time from the start of execution of the application by the execution control unit 212 to the current check point as the processing time. In the second embodiment, it is assumed that the time measuring unit 532 measures the elapsed time between check points as a processing time.

  The collection unit 530 uses the progress information (CP information) notified from the checkpoint trigger unit 220 at each checkpoint, the power consumption information indicating the power consumption measured by the power measurement unit 531, and the time measuring unit 532. The processing time information indicating the measured processing time is output to the profile generation unit 540, and the progress information (CP information) is transmitted to the distributed data sharing unit 420.

  The profile generation unit 540 uses the progress information, power consumption information, and processing time information output from the collection unit 530 to generate an execution profile of an application that is a resident program. Specifically, the profile generation unit 540 generates power consumption and processing time between partial processes as an execution profile, and stores the generated execution profile in the profile storage unit 440 of the management apparatus 400.

  Here, the execution profile generated by the profile generation unit 540 will be described with reference to FIG. FIG. 6 is a diagram conceptually illustrating an example of an execution profile generated by the profile generation unit 540 according to the second embodiment.

  As shown in FIG. 6, the profile generation unit 540 records power consumption information and processing time information between checkpoints. In the example illustrated in FIG. 6, the example following the checkpoint CP11 shows an example passing through the checkpoint CP12 or CP13, and the example following the checkpoint CP12 shows an example passing through the checkpoint CP14 or CP15. This is because a branch process exists in the application, and the checkpoints CP11, CP12,..., CP19 defined in the application are not necessarily executed in this order.

  Then, the profile generation unit 540 maps the CP information, which is progress information sequentially output from the collection unit 530, as in the example illustrated in FIG. For example, when the CP information indicating the checkpoint CP12 is output after the CP information indicating the checkpoint CP11 is output by the collection unit 530, the profile generation unit 540, as shown in FIG. Connect from CP11 to checkpoint CP12. Further, the profile generation unit 540 uses the power consumption information output from the collection unit 530 at the checkpoint CP12 as the power consumption “Δe” required by the mobile terminal 500 from the checkpoint CP11 to the checkpoint CP12 (in FIG. e12 "). Further, the profile generation unit 540 sets the processing time information (“t12” in FIG. 6) output from the collection unit 530 at the checkpoint CP12 as the processing time “Δt” from the checkpoint CP11 to the checkpoint CP12. .

  In addition, when the execution control unit 212 repeatedly executes the intermediate code, the CP information indicating the checkpoint CP13 is output after the collection unit 530 outputs the CP information indicating the checkpoint CP11 again. The profile generation unit 540 connects from the checkpoint CP11 to the checkpoint CP13 as shown in FIG. Then, the profile generation unit 540 sets the power consumption “Δe” (“e13” in FIG. 6) from the checkpoint CP11 to the checkpoint CP13 and the processing time “Δt” (“t13” in FIG. 6). To do.

  That is, the execution profile generated by the profile generation unit 540 indicates the power consumption and processing time between checkpoints as the application execution status by the execution control unit 212.

  Note that the profile generation unit 640 of the virtual mobile terminal 601 also generates the execution profile illustrated in FIG. Here, the virtual mobile terminal 601 executes the same application as the mobile terminal 500. Therefore, each execution profile generated by the profile generation unit 540 and the profile generation unit 640 has the same connection relationship between checkpoints. However, since the application execution speed and the like in the mobile terminal 500 and the virtual mobile terminal 601 are not the same, the power consumption “Δe” and the processing time “Δt” set in both execution profiles are different.

  The profile storage unit 440 of the management device 400 stores the execution profile generated by the profile generation units 540 and 640. That is, the profile storage unit 440 stores the execution profile illustrated in FIG. 6 in a predetermined data structure (for example, a hash table, Key-Value-Store, etc.).

  The distributed data sharing unit 420 of the management apparatus 400 receives progress information from the collection unit 530 of the mobile terminal 500 and also receives progress information from the collection unit 630 of the virtual mobile terminal 601 at every checkpoint. However, since the processing time required for application execution differs between the mobile terminal 500 and the virtual mobile terminal 601, the distributed data sharing unit 420 may not receive progress information from both the mobile terminal 500 and the virtual mobile terminal 601 at the same time. Many.

  The distributed data sharing unit 420 compares the progress information received from the mobile terminal 500 and the virtual mobile terminal 601 to determine whether or not there is a difference in the progress of application execution between the mobile terminal 500 and the virtual mobile terminal 601. Determine whether.

  Specifically, when the distributed data sharing unit 420 according to the second embodiment receives progress information from the mobile terminal 500, the distributed data sharing unit 420 accumulates checkpoints passed by the mobile terminal 500, and from the virtual mobile terminal 601. When the progress information is received, the check points that have passed in the virtual mobile terminal 601 are accumulated. For example, the distributed data sharing unit 420 accumulates information such as “CP11, CP12, CP14,...” As a passing checkpoint of the mobile terminal 500 or the virtual mobile terminal 601.

  When the distributed data sharing unit 420 receives progress information from the mobile terminal 500, the shared check point of the virtual mobile terminal 601 and the passing checkpoint indicated by the progress information (CP information) are stored. It is determined whether or not there is a difference. In addition, when the distributed data sharing unit 420 receives progress information from the virtual mobile terminal 601, the passing checkpoint indicated by the progress information (CP information) and the passing checkpoint of the stored mobile terminal 500 are stored. It is determined whether or not there is a difference. For example, the distributed data sharing unit 420 determines whether or not the difference between the number of passing checkpoints of the mobile terminal 500 and the number of passing checkpoints of the virtual mobile terminal 601 is greater than or equal to a predetermined CP threshold.

  Then, when there is a difference in the passage check point, the distributed data sharing unit 420 determines whether the mobile terminal 500 and the virtual mobile terminal 601 are based on the power consumption or processing time of the execution profile stored in the profile storage unit 440. It is determined whether or not a continuation should be sent and received.

  An example of processing by the distributed data sharing unit 420 will be described. Here, it is assumed that the CP threshold is “1”. In addition, it is assumed that the connection relationship of checkpoints is the example shown in FIG. Further, it is assumed that the distributed data sharing unit 420 accumulates “CP11” as the passage check point of the mobile terminal 500 and similarly accumulates “CP11” as the passage check point of the virtual mobile terminal 601. Further, it is assumed that the distributed data sharing unit 420 has received the progress information “CP12” from the virtual mobile terminal 601.

  In such a case, the distributed data sharing unit 420 adds “CP12” to the passing checkpoint of the virtual mobile terminal 601 and accumulates “CP11, CP12”. In this example, the number of passing checkpoints of the mobile terminal 500 is “1”, the number of passing checkpoints of the virtual mobile terminal 601 is “2”, and the difference is equal to or greater than the CP threshold “1”. At this time, the distributed data sharing unit 420 determines whether to provide the mobile terminal 500 with continuation of the virtual mobile terminal 601 based on the power consumption or the processing time in the execution profile of the mobile terminal 500.

  An example in which the distributed data sharing unit 420 determines based on power consumption will be described. When the distributed data sharing unit 420 receives the progress information from the virtual mobile terminal 601, the distributed data sharing unit 420 acquires the execution profile of the mobile terminal 500 as illustrated in FIG. 6 from the profile storage unit 440. At this time, the passing checkpoint of the mobile terminal 500 is CP11, and the passing checkpoint of the virtual mobile terminal 601 is CP12. Here, the distributed data sharing unit 420 refers to the execution profile shown in FIG. 6 and acquires the power consumption “Δe = e12” required for the mobile terminal 500 from the checkpoint CP11 to the checkpoint CP12.

  Further, the distributed data sharing unit 420 acquires the assumed power consumption that is assumed to be necessary for the mobile terminal 500 to receive the continuation of the virtual mobile terminal 601. When the power consumption “Δe = e12” acquired from the profile storage unit 440 is larger than the assumed power consumption by a predetermined power threshold or more, the distributed data sharing unit 420 causes the mobile terminal 500 to continue the virtual mobile terminal 601 ( continuation) should be provided. This is based on the assumption that the power consumption “Δe = e12” required for the mobile terminal 500 to pass from the checkpoint CP11 to the checkpoint CP12 is required for at least the mobile terminal 500 to receive the continuation of the virtual mobile terminal 601. This is because it can be determined that the power consumption is greater than or equal to the power consumption.

  On the other hand, the distributed data sharing unit 420 should provide continuation of the virtual mobile terminal 601 to the mobile terminal 500 when the power consumption “Δe = e12” is not larger than the assumed power consumption by a predetermined power threshold or more. It is determined that it is not.

  Next, an example in which the distributed data sharing unit 420 determines based on the processing time will be described. When the distributed data sharing unit 420 receives the progress information from the virtual mobile terminal 601, the distributed data sharing unit 420 acquires the execution profile of the mobile terminal 500 as illustrated in FIG. 6 from the profile storage unit 440. At this time, the passing checkpoint of the mobile terminal 500 is CP11, and the passing checkpoint of the virtual mobile terminal 601 is CP12. Here, the distributed data sharing unit 420 refers to the execution profile shown in FIG. 6 and acquires the processing time “Δt = t12” required for the mobile terminal 500 from the checkpoint CP11 to the checkpoint CP12.

  In addition, the distributed data sharing unit 420 acquires an assumed processing time that is required for the mobile terminal 500 to receive the continuation of the virtual mobile terminal 601. When the processing time “Δt = t12” acquired from the profile storage unit 440 is longer than the assumed processing time by a predetermined time threshold or more, the distributed data sharing unit 420 causes the mobile terminal 500 to continue the virtual mobile terminal 601 ( continuation) should be provided. This is because the processing time “Δt = t12” required for the mobile terminal 500 to pass from the checkpoint CP11 to the checkpoint CP12 is at least the processing required for the mobile terminal 500 to receive the continuation of the virtual mobile terminal 601. This is because it can be determined that the time is over.

  On the other hand, the distributed data sharing unit 420 should provide continuation of the virtual mobile terminal 601 to the mobile terminal 500 when the processing time “Δt = t12” is not larger than the assumed processing time by a predetermined power threshold or more. It is determined that it is not.

  The checkpoint modification unit 450 of the management device 400 analyzes the execution profile stored in the profile storage unit 440 and modifies the checkpoint defined in the intermediate code. The checkpoint modification unit 450 analyzes the execution profile stored in the profile storage unit 440 to determine that the checkpoint that can obtain the same power consumption and processing time every time is obvious, and determines the checkpoint. Instructs the checkpoint definition unit 411 to skip. For example, in the example shown in FIG. 6, when “Δe” and “Δt” in “CP11 → CP12” are the same values every time, the power consumption and processing time from the checkpoint CP11 to the checkpoint CP12 are as follows. It can be said that it is self-evident. In such a case, the checkpoint modification unit 450 instructs the checkpoint definition unit 411 to delete the checkpoint CP12.

  The checkpoint definition unit 411 generates checkpoint setting data in which a new checkpoint is defined in accordance with an instruction from the checkpoint modification unit 450. Then, the checkpoint synthesis unit 412 generates an intermediate code in which a new checkpoint is defined, and the execution control unit 212 executes and controls the intermediate code.

  As a result, in the computer system 2 according to the second embodiment, obvious checkpoints can be skipped without sticking to the checkpoints initially set by a programmer or the like, and the overhead generated at the checkpoints is reduced. can do.

[Effects of Second Embodiment]
As described above, in the computer system 2 according to the second embodiment, the execution environment in the information processing apparatus such as the mobile terminal 500 changes even when a checkpoint is set for each predetermined partial process. In the situation, it is possible to provide an execution environment in which an application can be continuously executed, and to suppress a decrease in productivity related to application development by an application developer.

  In the computer system 2 according to the second embodiment, since it is determined whether or not to continue the continuation based on the power consumption or the processing time, an application over distributed computing resources can be executed as a single program. Can be designed and implemented, and can be executed with a single program while avoiding performance degradation and failure troubles in different physical processing environment groups and virtual processing environment groups.

(Third embodiment)
The computer systems 1 and 2 described above may be implemented in various different forms other than the above embodiment. Therefore, in the third embodiment, another embodiment of the computer systems 1 and 2 will be described.

[Combination of devices]
In the above embodiment, for example, a mobile terminal and a virtual mobile terminal have been described as examples. That is, in the above-described embodiment, the example in which the same application is executed by the physical device and the virtual device has been described. However, the computer systems 1 and 2 described above may cause a plurality of physical devices to execute the same application to synchronize the execution status of the applications in the plurality of physical devices. Further, the present invention is not limited to this example, and the computer systems 1 and 2 described above may cause a plurality of virtual devices to execute the same application.

  In addition, the computer systems 1 and 2 described above do not cause the mobile terminal and the virtual mobile terminal to execute the same application, but perform virtual communication with physically existing communication devices (routers, mobile routers, home gateways, etc.). A device (such as a router) may be caused to execute the same application. The computer systems 1 and 2 described above do not cause a single mobile terminal and a single virtual mobile terminal to execute the same application, but a physical device group formed by a plurality of physical devices and a plurality of virtual devices. The same application may be executed for a virtual device group formed by the devices.

[Resource information]
Further, in the above embodiment, an example is shown in which the collection units 230 and 530 collect “power consumption”, “processing time”, and the like as resource information consumed by the mobile terminal 200 at the checkpoint. However, the collection units 230, 530, and the like may collect memory usage, network communication status (network load), and the like at checkpoints. For example, the distributed data sharing unit 120 performs virtual migration when the memory usage of the virtual mobile terminal 301 is equal to or greater than the threshold, or when the network load between the management apparatus 100 and the virtual mobile terminal 301 is equal to or greater than the threshold. It may be determined that continuation of the terminal 301 is not provided to the mobile terminal 200.

Execution profile
Further, the profile generation units 540 and 640 according to the second embodiment include the actual value of the number of calculations by the execution control units 212 and 312, the actual value of processing time, the actual value of power consumption, the actual value of memory usage, and the file A history such as an actual value of access and an actual value of network communication charges may be accumulated as an execution profile. Thereby, by referring to the execution profile stored in the profile storage unit 440, the optimal execution environment of the resident program can be selected. For example, in consideration of various parameters included in the execution profile, optimization is performed such that only specific partial processing is executed on the mobile terminal 500 side, and other partial processing is executed on the virtual mobile terminal 601 side. Can do.

  In addition, by referring to such an execution profile, for example, if the performance of file access or network traffic remains 0 for each partial process, the risk of failure or data loss is detected and avoided. Can be used. By utilizing the long-term execution profile in this way, the execution control after one day from one day ago, one week from one week ago, one month from one month ago is reviewed, and the optimal use of computing resources is re-planned. However, self-tuning according to the process control guidelines for high-speed processing, data maintenance, power-saving processing, and security compliance becomes easy.

[System configuration]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the order of passing checkpoints shown in FIG. 6 is an example and can be arbitrarily changed.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

[program]
In addition, it is possible to create a program in which processing executed by various devices such as the management device 100, the mobile terminal 200, and the virtual mobile terminal 301 described in the above embodiment is described in a language that can be executed by a computer. For example, a management program in which processing executed by the management apparatus 100 is described in a language that can be executed by a computer can be created. Further, for example, an information processing program in which processing executed by the mobile terminal 200 is described in a language that can be executed by a computer can be created. In this case, when the computer executes the management program or the information processing program, the same effect as in the above embodiment can be obtained. Further, the management program and the information processing program are recorded on a computer-readable recording medium, and the management program and the information processing program recorded on the recording medium are read into the computer and executed, thereby executing the same as in the above embodiment. Processing may be realized. Hereinafter, as an example, an example of a computer that executes a management program that realizes the same function as the management device 100 illustrated in FIG. 3 will be described.

  FIG. 7 is a diagram illustrating a computer 1000 that executes a management program. As illustrated in FIG. 7, the computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.

  The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 as illustrated in FIG. The ROM 1011 stores a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1031 as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1041 as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive. The serial port interface 1050 is connected to, for example, a mouse 1051 and a keyboard 1052 as illustrated in FIG. The video adapter 1060 is connected to a display 1061, for example, as illustrated in FIG.

  Here, as illustrated in FIG. 7, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the above management program is stored in, for example, the hard disk drive 1031 as a program module in which a command executed by the computer 1000 is described. For example, a checkpoint definition procedure for executing information processing similar to the checkpoint definition unit 111 illustrated in FIG. 3, a checkpoint synthesis procedure for executing information processing similar to the checkpoint synthesis unit 112, and a distributed data sharing unit 120 The hard disk drive 1031 stores a program module 1093 in which a determination procedure for executing the same information processing as described above and a provision procedure for executing the same information processing as the continuous distribution sharing unit 130 are described.

  Then, the CPU 1020 reads the program module 1093 and program data 1094 stored in the memory 1010 and the hard disk drive 1031 to the RAM 1012 as necessary, and executes a checkpoint definition procedure, a checkpoint composition procedure, a determination procedure, and a provision procedure.

  Note that the program module 1093 and the program data 1094 related to the management program are not limited to being stored in the hard disk drive 1031, but may be stored in, for example, a removable storage medium and read out by the CPU 1020 via the disk drive or the like. Good. Alternatively, the program module 1093 and the program data 1094 related to the management program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and via the network interface 1070. May be read by the CPU 1020.

DESCRIPTION OF SYMBOLS 1 Computer system 100 Management apparatus 120 Distributed data sharing part (determination part)
130 Continuously distributed sharing unit (providing unit)
DESCRIPTION OF SYMBOLS 200 Mobile terminal 212 Execution control part 230 Collection part 231 Power measurement part 241 Continuous data conversion part 242 Continuation application part 300 Cloud server 301 Virtual mobile terminal 532 Time measuring part 540 Profile generation part

Claims (7)

A computer system including a plurality of information processing devices that execute the same application and a management device that manages the information processing devices,
The information processing apparatus includes:
An execution control unit for controlling execution of the application;
A collection unit that collects progress information indicating the progress of execution of the application in the execution control unit;
A generation unit that generates calculation state information indicating a calculation state in the execution control unit that is executing the application in accordance with an instruction of the management device;
An application unit that applies the calculation state indicated by the calculation state information to the calculation state in the execution control unit when calculation state information is provided from the management device;
The management device
Judgment that determines whether or not there is a difference in the progress of execution of the application among the plurality of information processing devices by comparing the progress information collected by the collection unit in the plurality of information processing devices And
The calculation state information is generated by causing the second information processing device in which the execution of the application is progressing more than the first information processing device to generate the calculation state information according to whether there is a difference in progress by the determination unit. A computer system comprising: a providing unit that provides information to the first information processing apparatus. The information processing apparatus includes:
As the application, an application that can be divided into a plurality of partial processes is executed,
The collector is
Collect progress information indicating the partial processing executed by the execution control unit,
The determination unit
Determining whether a difference in the number of partial processes executed in the plurality of information processing apparatuses is equal to or greater than a predetermined threshold;
The providing unit includes:
When the determination unit determines that the number of partial processes executed in the second information processing apparatus is greater than the threshold value than the number of partial processes executed in the first information processing apparatus, 2. The computer system according to claim 1, wherein calculation state information generated by the two information processing devices is provided to the first information processing device. The collector is
When the application is executed by the execution control unit, collect resource information about the resource consumed by the information processing apparatus,
The determination unit
When there is a difference in the execution progress of the application among the plurality of information processing devices, the calculation state information is transmitted and received between the plurality of information processing devices based on the resource information collected by the collection unit. The computer system according to claim 1, wherein whether or not to perform the determination is determined. The information processing apparatus includes:
Information indicating the monitoring timing is defined for each predetermined partial process,
The collector is
When it is a monitoring timing while the application is being executed by the execution control unit, resource information regarding resources consumed by the information processing apparatus between the monitoring timings from the previous monitoring timing to the monitoring timing, Collect the processing time of the information processing device between the monitoring timings,
The information processing apparatus includes:
A profile generation unit that generates an execution profile in which resource information and processing time collected by the collection unit are associated with each other between monitoring timings;
The determination unit
Based on the execution profile generated by the profile generation unit, by estimating whether it is less waste of consumption resources or processing time to send and receive the calculation state information between the plurality of information processing devices, The computer system according to claim 2, wherein it is determined whether or not the calculation state information is transmitted and received between the plurality of information processing apparatuses. The management device
When a plurality of consumption resources corresponding to the same monitoring timing collected by the collection unit are similar, or when a plurality of processing times at the same monitoring timing collected by the collection unit are similar, the monitoring timing The computer system according to claim 4, further comprising: a modification unit that excludes from the monitoring timing. The plurality of information processing devices include:
It is one of a physical physical device, a virtual device formed virtually, a plurality of physical physical devices, or a plurality of virtual devices formed virtually. The computer system according to any one of the above. A system control method executed by a computer system including a first information processing apparatus and a second information processing apparatus that execute the same application, and a management apparatus that manages the first information processing apparatus and the second information processing apparatus There,
The first information processing apparatus and the second information processing apparatus are:
An execution control step for controlling the execution of the application;
A collection step of collecting progress information indicating a progress of execution of the application in the execution control step;
The management device
By comparing the progress information corresponding to the first information processing device and the second information processing device collected by the collecting step, the second information processing device is more likely to have the application information than the first information processing device. A determination step of determining whether or not execution is in progress;
In the determination step, when it is determined that the second information processing apparatus is executing the application more than the first information processing apparatus, the application is applied to the second information processing apparatus. An instruction step for instructing to generate calculation state information indicating a calculation state in the execution control step being executed,
The second information processing apparatus
Including a generation step of generating the calculation state information according to an instruction of the management device;
The management device
Including a providing step of providing the first information processing device with the calculation state information generated in the generating step of the second information processing device;
The first information processing apparatus
The system control method characterized by including the application process which applies the calculation state shown by the calculation state information provided from the said management apparatus to the calculation state in the execution control process of the said 1st information processing apparatus.

Images