Job allocation program for allocating jobs to each computer without intensively managing load state of each computer

• US 8,510,742 B2
• Filed: 09/20/2007
• Issued: 08/13/2013
• Est. Priority Date: 12/19/2006
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Yoshida, Taketoshi
• Primary Examiner(s): Truong, Camquy
• Application Number:
  US11/901,982
• Publication Number:
  US 20080148272A1
• Time in Patent Office: 2,154 Days
• Field of Search: None
• US Class Current: 718/104
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5088 involving task migration

Abstract

This job allocation method for allocating jobs to each computer that processes the job without intensively managing a load state of each computer includes: identifying computers having a configuration necessary for a processing of a generated job by using a profile management data storage storing data of a configuration of each computer; identifying a job allocation mode according to a current job generation state by using an allocation mode data storage storing data concerning an allocation mode of computers to the jobs in association with the job generation state; transmitting a job generation notification to at least one of the identified computers according to the identified job allocation mode; and when a job acquisition refusal notification is received in response to the job generation notification, resending a job generation notification to a computer having a configuration necessary for the generated job. Thus, by sending the job generation notification, not a job allocation notification, without intensively managing the load state of each computer, which processes the jobs, it is possible to reduce the processing load of a master computer.

Claims

1. A method for allocating a job to one or plural computers among a plurality of computers, without intensively managing a load state of each of said plurality of computers, said method comprising:

identifying, from among said plurality of computers, one or plural certain computers having a configuration necessary for a processing of a generated job by using a profile management data storage storing data concerning a configuration of each of the plurality of computers;

identifying a job allocation mode at a current time based on a number of the one or plural certain computers and a number of jobs including the generated job;

transmitting a job generation notification to at least one of the identified one or plural certain computers according to the identified job allocation mode;

upon receipt of a job acquisition notification as a response to said job generation notification, registering identification information of a transmission source computer of the identified one or plural certain computers, which sent said job acquisition notification in association with the generated job in a job allocation data storage;

searching said job allocation data storage to extract a certain job to which a processing result is not registered;

determining whether duplicate computer allocation to the extracted certain job is allowed; and

upon determining that the duplicate computer allocation to the extracted certain job is allowed, transmitting another job generation notification to a computer of said plurality of computers, which has a configuration necessary for a processing of the extracted certain job and has capability higher than capability of a computer of said plurality of computers, which currently processes the extracted certain job.

2. A non-transitory computer-readable storage medium storing a program for causing a computer to carry out a procedure to allocate a job to one or plural computers among a plurality of computers, without intensively managing a load state of each of said plurality of computers, said procedure comprising:

identifying, from among said plurality of computers, one or plural certain computers having a configuration necessary for a processing of a generated job by using a profile management data storage storing data concerning a configuration of each of said plurality of computers;

identifying a job allocation mode at a current time based on a number of the one or plural certain computers and a number of jobs including the generated job;

transmitting a job generation notification to at least one of the identified one or plural certain computers according to the identified job allocation mode;

upon receipt of a job acquisition notification as a response to said job generation notification, registering identification information of a transmission source computer of the identified one or plural certain computers, which sent said job acquisition notification in association with the generated job in a job allocation data storage;

searching said job allocation data storage to extract a certain job to which a processing result is not registered;

determining whether duplicate computer allocation to the extracted certain job is allowed; and

upon determining that the duplicate computer allocation to the extracted certain job is allowed, transmitting another job generation notification to a computer of said plurality of computers, which has a configuration necessary for a processing of the extracted certain job and has capability higher than capability of a computer of said plurality of computers, which currently processes the extracted certain job.

3. A method for managing a job, the method comprising:

extracting, by using a computer, for a job to be processed, a plurality of processing apparatuses, each of which satisfies a processing requirement of the job, which is allowed to be duplicately processed by the processing apparatuses;

sending out, by using the computer, same notification concerning the job to each of the extracted plurality of processing apparatuses, wherein the same notification includes data that is sufficient for execution of the job;

waiting, by using the computer, for each of the extracted plurality of processing apparatuses, receipt of a determination result made in each of the extracted plurality of processing apparatuses in response to the same notification, wherein one or plural processing apparatuses of the extracted plurality of processing apparatuses respectively determine to begin the execution of the job by using the data; and

upon receipt of one or more specific responses, each of which includes a determination result representing that a response source processing apparatuses of the extracted plurality of processing apparatuses began the execution of the job by using the data, storing, by using the computer, identification information of all of processing apparatuses that sent back the specific responses into a storage device.

4. A non-transitory computer-readable storage medium storing a program for causing a computer to execute a procedure for managing a job, the procedure comprising:

extracting, for a job to be processed, a plurality of processing apparatuses, each of which satisfies a processing requirement of the job, which is allowed to be duplicately processed by the processing apparatuses;

sending out same notification concerning the job to each of the extracted plurality of processing apparatuses, wherein the same notification includes data that is sufficient for execution of the job;

waiting, for each of the extracted plurality of processing apparatuses, receipt of a determination result made in each of the extracted plurality of processing apparatuses in response to the same notification, wherein one or plural processing apparatuses of the extracted plurality of processing apparatuses respectively determine to begin the execution of the job by using the data; and

upon receipt of one or more specific responses, each of which includes a determination result representing that a response source processing apparatuses of the extracted plurality of processing apparatuses began the execution of the job by using the data, storing identification information of all of processing apparatuses that sent back the specific responses into a storage device.

5. An apparatus for managing a job, the apparatus comprising:

a storage device;

a processor configured to execute a procedure, comprising;

extracting, for a job to be processed, a plurality of processing apparatuses, each of which satisfies a processing requirement of the job, which is allowed to be duplicately processed by the processing apparatuses;

sending out same notification concerning the job to each of the extracted plurality of processing apparatuses, wherein the same notification includes data that is sufficient for execution of the job;

waiting, for each of the extracted plurality of processing apparatuses, receipt of a determination result made in each of the extracted plurality of processing apparatuses in response to the same notification, wherein one or plural processing apparatuses of the extracted plurality of processing apparatuses respectively determine to begin the execution of the job by using the data; and

upon receipt of one or more specific responses, each of which includes a determination result representing that a response source processing apparatuses of the extracted plurality of processing apparatuses began the execution of the job by using the data, storing identification information of all of processing apparatuses that sent back the specific responses into the storage device.