JP2005339335A - Resource utilization management program and resource utilization management system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a resource utilization management program and a system for managing the utilization of a number of resources connected to a network, wherein a provider of a resource group can arbitrarily set or change a utilization point for differentiation, the preferential use of the resource group is allowed by giving priority to the user, or the resource group is preferentially utilized by paying a permission point to the user of the resource group. <P>SOLUTION: The system is provided with a step of accepting utilization points of resources to register or change them in a table in association with the resources, a step of returning a list of the resources and the utilization points registered in a table according to the utilization request from a user terminal and receiving resource information utilized and selected from the list, and a step of allocating processings to the corresponding resources for execution based on the received resource information, returning the result to the user, and storing the point utilized. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a resource use management program and a resource use management system for managing use of a large number of resources connected to a network.

  Conventionally, computers connected to a grid computer environment or the like are classified according to resource capability, and points are assigned in advance when using the classified resource group. Paying usage fees).

In addition, points are given to computing resources (resources) provided from a large number of clients connected to the network, and the user pays fees according to their use (Patent Document 1).
JP 2003-6171 A

  As described above, conventionally, since points are given to resource groups in advance and the user pays for them according to the points, the increase / decrease of the usage points according to the demand and supply for the resource group Could not be specified.

  For this reason, there has been a problem in that use points cannot be arbitrarily set or changed for the purpose of differentiating the resource group from the provider providing the resource group.

  In addition, when a user conflict occurs in a resource group, if the resource group is allocated equally, there is a problem that a user who needs an emergency cannot use the resource group preferentially and process quickly. .

  In the present invention, in order to solve these problems, when a provider grants and registers an arbitrary use point to a resource and the user competes for a resource selected from the list of resources, the priority of the user In order to permit the use of resources, or when a preferential use permission is obtained for the user in use, the use is preferentially performed and a license point is paid.

  Therefore, it becomes possible for the provider of the resource group to arbitrarily set and change the use point to differentiate the user, and to give priority to the user to permit the use of the resource group. It is possible to preferentially use the resource group by paying permission points to the user of the resource group.

  The invention of the present application aims to differentiate the resource group provider by arbitrarily setting and changing the use point, and giving priority to the user to permit the use of the resource group, It is possible to preferentially use the resource group by paying the user of the resource group.

  The present invention aims to differentiate by making it possible for the resource group provider to arbitrarily set and change the use point, and give priority to the user to allow the use of the resource group, The resource group is paid to users of the resource group and the resource group is used preferentially.

FIG. 1 shows a system configuration diagram of the present invention.
In FIG. 1, a terminal 1 is connected to a network 4 (for example, the Internet, LAN, WAN, etc.) and is operated by a user and is a resource. Here, the terminal 1 is used for processing using the grid computer 2. The job request unit 11, the display device 12, the input device 13, and the like are included.

  The job requesting unit 11 requests a job from the grid computer 2 (described later with reference to FIGS. 2 to 7).

The display device 12 displays a screen.
The input device 13 inputs various instructions and data, and is a keyboard, a mouse, or the like.

  The grid computer 2 is a parallel computer system, and is an example of a resource (computer system comprising a CPU, a memory, an application program, etc.) that operates an application program and executes processing. It is comprised from. Here, the grid computer 2 is uniquely identified by being given a computer name (G1, G2, G3...), And when each administrator uses (uses) the grid computer 2, its use point (P1, P2, P3...) Are arbitrarily set and changed.

  When each manager determines (or changes) the use point of the grid computer 2, the charge setting unit 21 connects to the host 3 via the network 4 and notifies the charge reception unit 31 of the use point. In the table 36, an identifier (for example, a usage point (for example, usage point “P1”) and a registration point “T1”) of the grid computer 2 is registered and changed in association with “G1”. Thereby, about the grid computer 2, the administrator can register and change a use point arbitrarily and can attain differentiation.

The host 3 is connected to the network 4 and a number of grid computers 2 that are resources.
, A grid computer 2 is allocated in response to usage requests from a large number of terminals 1 (to be described later with reference to FIGS. 2 to 7), charge receiving means 31, The job receiving unit 32, the job assigning unit 33, the priority updating unit 34, the totaling unit 35, the point table 36, the usage table 37, the priority coefficient table 38, and the like are included.

  The fee receiving means 31 receives usage points and registration points of the grid computer 2 from the grid computer 2 via the network 4 and registers and changes them in the point table 36. By providing the fee receiving means 31 in the host 3, the manager of the grid computer 2 can freely register and change usage points and differentiate the fee from other grid computers 2. It becomes.

  The job accepting means 32 accepts a job from the terminal 1, transmits a list of the grid computer 2 and its use points to the terminal 1 and displays it on the screen (for example, (a) in FIG. 7), A job selected by the user (business processing by an application operating on the grid computer 2) is accepted.

  The job assigning means 33 assigns the job received from the user received by the job accepting means 32 to the corresponding grid computer 2 and executes it (described later with reference to FIGS. 2 to 7).

  The priority update unit 34 updates the priority when a job is assigned to the grid computer 2 (described later with reference to FIGS. 4 to 7).

  The counting means 35 counts charges for each user and for each grid computer 2 (to be described later with reference to FIG. 5).

  The point table 36 registers and manages use points in association with the grid computer 2 that is a resource (see FIG. 6A).

  The usage table 37 registers and manages grid computers, usage points, usage times, and permission points, which are resources used for each user (see FIG. 6B).

  The priority coefficient table 38 registers priorities for assigning jobs (see FIG. 6C).

  The network 4 is a network that connects a large number of terminals 1, a grid computer 2 that is a large number of resources, and a host 3 to transmit and receive data, and is the Internet, a LAN, a WAN, or the like.

  Next, according to the order of the flowchart of FIG. 2, the resources in the point table 36 in the configuration of FIG. 1, where the identifier, resource information, use point, registration point, etc. of the grid computer 2 are stored in each grid computer 2. The operation when the administrator registers is described in detail.

FIG. 2 is a flowchart for explaining the operation of the present invention (initial setting).
In FIG. 2, in S1, each grid computer sets a use point. This is because each manager of the grid computer 2 in FIG. 1 decides (or changes) a usage point when the grid computer is used, activates the fee setting means 21, and uses the usage point from a screen not shown. Enter and set. Here, for example, the administrator of each grid computer 2 makes the settings as shown below.

Grid computer usage points G1: P1
G2: P2
G3: P3
S2 connects to the host. This corresponds to the fee setting means 21 accepting the fee of the host 3 via the network 4 in response to the administrator of each grid computer 2 deciding (changing) the use point and inputting and setting it from the screen in S 1. Connect to means 31.

  In S3, the host stores the point information in the point table 36. In this case, the fee receiving means 31 of the host 3 connected in S2 stores (registers) the notified usage points for each grid computer 2 in the point table 36 of FIG. Here, in addition to the identifier (eg, G1) of the grid computer 2, resource information (CPU speed, memory capacity, application name, etc.), and further, a registration point (host obtained by registering the usage information of the grid computer 2 in the host 3) 3 management points (management costs)) are also saved.

  As described above, each administrator of the grid computer 2 displays the identifier (including address, URL, etc.), resource information, usage points, and registration points for the grid computer 2 with respect to the point table 36 of the host 3 as shown in FIG. As shown in the point table 36 of (a), registration and change can be performed.

  Next, in accordance with the order of the flowchart of FIG. 3, the operation when the user operates the terminal 1 to select the corresponding one from the list of grid computer information and execute the job in the configuration of FIG. This will be described in detail.

  FIG. 3 is a flowchart for explaining the operation of the present invention (part 1). Here, the terminal 1, the host 3, and the grid computer 2 correspond to the terminal 1, the host 3, and the grid computer 2 of FIG.

In FIG. 3, the grid computer 2 initially sets S11.
S12 is initially set by the host 3.

  S13 sets a point. In S11 to S13, as described above with reference to FIG. 2, the grid computer 2 is connected to the host 3 via the network 2, points (use points, registration points), and resource information (CPU speed, memory). The capacity, usable application (business application) name, etc.) are also registered (registered in the point table 36 in FIG. 6A).

  In S14, the host 3 downloads the menu information. For example, the user accesses the home page of the host 3 by operating the terminal 1 shown in FIG. 1 and clicks the job request screen from the home page, so that the menu information is downloaded to the terminal 1.

  In step S15, the job request unit 11 of the terminal 1 displays a menu on the display device 12 of the terminal 1. For example, a menu screen shown in FIG. 7A (to be described later) is displayed on the display device 12. Here, resource information (CPU speed, memory capacity, external storage capacity, application name, etc.) and usage are associated with the grid computer name. Displays a list of status, usage points, waiting number (number of waiting users), etc.

  In S16, selection and parameter setting are performed. This is because the user of the terminal 1 selects the grid computer 2 that executes the job on the menu screen (for example, FIG. 7A) displayed in S15, and on the parameter setting screen shown in FIG. To set parameters (in this case, input file name, output file name, etc.) and send them to the host 3.

  In S17, it is determined whether the grid computer is free. This is to determine whether the grid computer 2 selected in S16 is empty and not being used by another user. If YES, the process proceeds to S18. In the case of NO, since it has been found that another user has already used the grid computer 2, the process proceeds to (X) in FIG.

  In S18, execution is instructed. This is because the grid computer 2 is found to be empty at YES in S17, so the job assigning means 3 of the host 3 assigns a job to the grid computer 2 and gives an execution instruction.

In S19, the grid computer 2 instructed to execute in S18 executes the job.
S20 displays an execution status.

  In S <b> 21, the terminal 1 that has received the execution status display transmission in S <b> 20 displays the execution status on the display device 12.

In S22, the execution is finished in the grid computer 2 in S23, and the result is received by the terminal 1.
In S <b> 24, the host 3 receives an end notification from the grid computer 2.

  S25 is registered in the usage table 37. Here, the host 3 associates the name of the grid computer used, the usage point, the usage time, and the license point (if necessary) with the usage table, for example, the usage table 37 of FIG. (Described later in FIG. 4).

  As described above, the menu screen of FIG. 7A downloaded from the host 3 by the user is displayed on the display device 12 of the terminal 1, the grid computer to be used is selected, and the parameter setting of FIG. 7B is set. When parameters are set on the screen and sent to the host 3, the host 3 accepts the job. Here, since the accepted grid computer 2 is empty and not used by other users, the grid computer 2 is assigned and executed. The execution status is transmitted to the terminal 1, and the execution result is transmitted to the terminal 1 when the execution is completed, and the usage point is transmitted to the host 3 and registered in the usage table 37 of FIG. It becomes possible to do.

  FIG. 4 shows a flowchart (part 2) for explaining the operation of the present invention. FIG. 4 explains in detail the operation when the grid computer 2 is not empty and is being used by another user (a conflict occurs) in S17 of FIG. 3 described above.

In FIG. 4, in S31, the host 3 transmits a menu of addition points.
In S <b> 32, the terminal 1 displays a menu of addition points on the display device 12. For example, an addition point screen shown in FIG. 7C, which will be described later, is displayed. Here, the illustrated message and the addition point input field are displayed.

  S33 is selected. For example, on the addition point screen of FIG. 7C, the addition point is input and “OK” is selected or “return” is selected.

  In S34, it is determined whether the host 3 has an addition point. In S33, the user inputs the addition point on the addition point screen of FIG. 7C and selects “OK”, that is, selects to pay the addition point to the currently used user. To determine. If YES, the process proceeds to S35. In the case of NO, since it has been found that there is no additional point, it is stored in the job queue in the order of priority points in S40 (stored in the job queue position in the order determined by the priority points given to the user to be used this time). ).

  S35 discriminate | determines whether it is a negotiation process with an executing user. This is because when YES in S34, there is an addition point, and it is further determined whether or not a license is negotiated with the user of the job currently being executed (the addition point is input on the addition point screen in FIG. 7C), and , It is determined whether the “OK” button is selected). If YES, the process proceeds to S36. If NO, the job queue is stored in order of priority points in S40.

In S36, a negotiation menu is transmitted to the user who is currently executing.
S37 displays a menu. In these S36 and S37, the negotiation menu (the user who intends to use pays the permission point to you because you are paying permission points to the terminal 2 of the user who is currently executing, so you interrupt the job execution and ask the user of the grid computer 2 Displays a menu that asks if you want to give up.

  In S37, an acceptance notification is transmitted. In this case, on the negotiation menu displayed in S37, the user of the terminal 2 who is currently using the grid computer 2 transmits an acceptance notification that the use of the grid computer 2 is transferred to the host 3.

  In step S38, it is determined whether the negotiation is accepted. This determines whether the acceptance notification in S37 accepts that the user of the terminal 2 currently using the grid computer 2 interrupts the job and transfers it to the user of the terminal 1. If YES, the process proceeds to S41. In the case of NO, since the negotiation is broken, the job is stored in the job queue in order of priority points in S40.

  In S41, since it is determined that the negotiation is accepted in YES in S39, an instruction to interrupt the job being executed is transmitted to the grid computer 2. In step S45, the grid computer 2 interrupts execution of the current job.

In step S42, the job being executed is added to the tail of the queue.
In step S43, a new execution job is transmitted. In step S46, the grid computer 2 starts executing a new job, and proceeds to step S20 in FIG.

  In S44, the client point is increased. Reduce acceptor points. Here, the usage points of the user (requester) of the terminal 1 are increased (increased by the additional points), and the usage points of the user (trustee) of the terminal 2 are decreased (reduced by the additional points, or FIG. 6). The license point of the user 1 in the usage table 37 of (b) is given “−10” (reduction of 10 points)).

    As described above, when a conflict occurs in the requested job (grid computer 2), when the user (requester) wishes to pay additional points and negotiate, the user of the terminal 2 currently in use is notified. When accepting or inquiring, if the job is accepted, the job being used is interrupted and the additional points are paid, and a new user can start the job using the grid computer 2.

FIG. 5 shows a flowchart (counting) for explaining the operation of the present invention.
In FIG. 5, S51 determines whether a predetermined time has elapsed. This is determined whether the totaling means 35 of the host 3 in FIG. In the case of YES, the priority point (0.1 point per hour) of the waiting job is added in S52, and the process proceeds to S53. If NO, skip S52 and go to S53.

  When a waiting job is generated in the grid computer 2 by the above S51 and S52, for example, 0.1 point is added to the priority point for every predetermined time for the waiting job, and the priority of the job (user) as time passes Even if jobs with high priority (users) are continuously requested, the grid computer can be used when the high priority is exceeded.

  In S53, it is determined whether it is a closing date. In the case of YES, it progresses to S54 and S60. If NO, the process ends.

  In S54, the usage points are totaled for each user. Here, the sum of the usage points × the usage time is calculated for each user in the usage table 37 of FIG.

  In S55, the permission points are totaled. This sums up the permission points in the usage table 37 of FIG. 6B (permission points paid in return for interrupting the job and giving up the use of the grid computer 2) for each user.

  In S56, total points are calculated. This calculates the sum total of the use points multiplied by the usage time in S54 and the usage time totaled in S55.

  In S57, a priority coefficient is assigned. This is the total point calculated in S56, and a priority point is determined with reference to the priority coefficient table 38 of FIG. 6C and given to the user. Thereby, it becomes possible to give a big priority point to a heavy user and to use the grid computer 2 preferentially when competing.

  In S58, a heavy user discount is performed. This refers to a table not shown in the figure for the total points calculated in S56, and performs so-called heavy user discount in which the unit price per point is reduced as the points are larger when converted into charges.

  In S59, a charge is calculated. This calculates a fee after applying a heavy user discount in S58.

  In S60, the use points are totaled for each grid computer. In S59, a fee is calculated for each grid computer.

  By the above, the total points of usage points x usage time and permission points are calculated for each user, the priority coefficient is given to the user, the fee is calculated after heavy user discount, and the usage points are calculated for each grid computer. It is possible to calculate charges by counting.

FIG. 6 shows an example table of the present invention.
FIG. 6A shows an example of a point table. The point table 36 is registered and changed in association with the following information shown in the figure.

・ Grid computer information:
・ Identifier: G1
Resource information: CPU speed, memory capacity, external storage capacity, application name ...
・ Use points:
・ Registration points:
·Usage situation:
・ Other:
Here, the grid computer information is an identifier, resource information, and the like of a target grid computer 2 connected to the network 4 in FIG. 1 and used as a resource. The use points are points per unit time when the grid computer 2 is used. The registration points are commission points when the grid computer 2 is registered in the point table 36 of the host 3 and the user is allowed to use it. The usage status is information on whether or not the grid computer 2 is being used (in the case of 1 unit, information is being used = 100%, in the case of not being used = 0%, in the case of 2 units, information is that 50% is being used for only one unit). is there.

  As described above, since the administrator of the grid computer 2 can arbitrarily register and change the use points of the grid computer 2 in the point table 36, the use points of other grid computers 2 can be arbitrarily checked. It can be changed as needed to enable differentiation.

  FIG. 6B shows an example of a usage table. The usage table 37 is for the user to register and manage information using the grid computer 2, and here, the following information shown in FIG.

·User name:
-Grid computer name (identifier):
・ Use points:
·Utilization time:
・ Permission points:
・ Other:
Here, the user name is a user name using the grid computer 2. The grid computer name (identifier) is the name of the grid computer used by the user registered in the point table 36 of FIG. The use point is a point used by the user (for example, a use point of the grid computer 2 used in the point table 36 of FIG. 6A). The permission point is a point paid by another user when the job is interrupted and the use of the grid computer 2 is given to another user.

  As described above, by registering and managing the name of the grid computer used in association with the user name, the use point, the use time, and the permission point, according to the above-described flowchart of FIG. Charges can be calculated for each grid computer.

  FIG. 6C shows an example of a priority coefficient table. The priority coefficient table 38 is a table in which priority points are registered in association with the user's usage points. As described above with reference to the flowchart of FIG. A priority point having a high priority is given to the user, and the grid computer can be used preferentially at the next use.

FIG. 7 shows an example of the screen of the present invention.
FIG. 7A shows an example of a menu screen. The illustrated menu screen is an example of a screen displayed on the display device 12 of the terminal 1 in S15 of FIG. 3 described above, and information registered and changed in the point table 36 of FIG. 6A described above. The user selects a grid computer 2 to be used from the list and requests the host 3 for processing. The waiting number is the number of users waiting for the use of the grid computer 2.

  FIG. 7B shows an example of a parameter setting screen. The parameter setting screen shown is displayed in S15 of FIG. 3 described above, and is used for inputting and setting parameters (here, input file name, output file name,...) In S16.

  FIG. 7C shows an example of the addition point screen. The addition point screen is an example of a screen displayed on the display device 12 of the terminal 1 in S32 of FIG. 4 described above, and displays the following message, input field, and selection button shown in the figure.

    ・ Because you are using a grid computer, paying additional points will increase the job waiting priority. If no additional point is specified (if it is blank), it will be added to the corresponding priority position waiting for job execution.

・ Additional points (30)
・ Do you negotiate with the user during the job?

If the user accepts during job execution, the job will be executed.
In this case, additional points are transferred to the user during job execution.

(OK button) (Back button)
(Appendix 1)
In a resource use management program that manages the use of many resources connected to the network,
On the computer,
Receiving a usage point of a resource connected to the network and registering or changing the usage point corresponding to the resource in a table;
Returning a list of resources and usage points registered in the table in response to a usage request from a user terminal connected to the network, and receiving resource information to be used selected from the list; ,
A resource usage management program for allocating a process to a corresponding resource based on the received resource information and executing the process, causing the user to respond to the result, and operating as a step of storing the used points.

(Appendix 2)
When assigning a process to a corresponding resource based on the resource information, if another user has already competed using the resource, the user of the terminal to be used is inquired whether to pay a license point. When a response is received that a license point is paid, when a response is given to the user of the terminal that is currently using the license to confirm whether or not the license has been approved, a resource is allocated preferentially and the license point is granted The resource use management program according to appendix 1, wherein the use point is reduced by assigning to the resource.

(Appendix 3)
When a priority is assigned to each user and a process is assigned to the corresponding resource based on the resource information, the priority of the user is already waiting for other users to use the resource. The resource use management program according to supplementary note 1 or supplementary note 2, characterized by being inserted at the position of.

(Appendix 4)
The resource use management program according to appendix 3, wherein the priority is increased as the number of use points of the user increases.

(Appendix 5)
The resource usage management program according to appendix 3 or appendix 4, wherein when there is a waiting user in the resource, the priority of the user is increased by a predetermined value every time a predetermined time is waited.

(Appendix 6)
In a resource usage management system that manages the use of many resources connected to a network,
Means for accepting the use points of the resources connected to the network and registering or changing the corresponding points in the table;
Means for returning a list of resources and use points registered in the table in response to a use request from a user terminal connected to the network, and receiving resource information to be used selected from the list; ,
A resource usage management system comprising: means for assigning a process to a corresponding resource on the basis of the received resource information, executing the process, returning a result to the user, and storing the used points.

(Appendix 7)
In a resource usage management method for managing the use of a large number of resources connected to a network,
Receiving a usage point of a resource connected to the network and registering or changing the usage point corresponding to the resource in a table;
Returning a list of resources and usage points registered in the table in response to a usage request from a user terminal connected to the network, and receiving resource information to be used selected from the list; ,
A resource usage management method comprising the steps of: assigning and executing a process to a corresponding resource based on the received resource information, causing the user to respond to the result, and storing the used points.

  The present invention aims to differentiate by making it possible for the resource group provider to arbitrarily set and change the use point, and give priority to the user to allow the use of the resource group, It is possible to preferentially use the resource group by paying the user of the resource group.

It is a system configuration diagram of the present invention. It is operation | movement description flowchart (initial setting) of this invention. It is operation | movement explanatory flowchart (the 1) of this invention. It is operation | movement description flowchart (the 2) of this invention. It is operation | movement description flowchart (aggregation) of this invention. It is an example table of this invention. It is an example of a screen of the present invention.

Explanation of symbols

1: terminal 11: job request unit 12: display device 13: input device 2: grid computer 21: fee setting unit 3: host 31: fee reception unit 32: job reception unit 33: job allocation unit 34: priority update unit 35 : Totaling means 36: Point table 37: Usage table 38: Priority coefficient table 4: Network

Claims (5)

In a resource use management program that manages the use of many resources connected to the network,
On the computer,
Receiving a usage point of a resource connected to the network and registering or changing the usage point corresponding to the resource in a table;
Returning a list of resources and usage points registered in the table in response to a usage request from a user terminal connected to the network, and receiving resource information to be used selected from the list; ,
A resource usage management program for allocating a process to a corresponding resource based on the received resource information and executing the process, causing the user to respond to the result, and operating as a step of storing the used points.   When assigning a process to a corresponding resource based on the resource information, if another user has already competed using the resource, the user of the terminal to be used is inquired whether to pay a license point. When a reply is received that the license point is paid, the user who has used the terminal is allocating resources and granting the license point preferentially when the user of the terminal in use is inquired about permission or not and there is a response of permission The resource use management program according to claim 1, wherein the use point is reduced by assigning to a resource.   When a priority is assigned to each user and a process is assigned to the corresponding resource based on the resource information, the priority of the user is already waiting for other users to use the resource. The resource use management program according to claim 1 or 2, wherein the resource use management program is inserted at a position.   4. The resource use management program according to claim 3, wherein the priority is increased as the number of use points of the user increases. In a resource usage management system that manages the use of many resources connected to a network,
Means for accepting the use points of the resources connected to the network and registering or changing the corresponding points in the table;
Means for returning a list of resources and use points registered in the table in response to a use request from a user terminal connected to the network, and receiving resource information to be used selected from the list; ,
A resource usage management system comprising: means for assigning a process to a corresponding resource on the basis of the received resource information, executing the process, returning a result to the user, and storing the used points.

Images