IP Library › Granted Patent US 9,349,012
Granted Patent B2
US 9,349,012 · App. 13/736,473 · Granted May 24, 2016

Distributed processing system, distributed processing method and computer-readable recording medium

Inventor: Junichi Yasuda (Tokyo, JP)
Assignee: NEC CORPORATION
G06F21/577
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,349,012
App. No.
13/736,473
Granted
May 24, 2016
Kind
B2
Abstract

A distributed processing system 100 is used in which a plurality of machines including a virtual machine constructed by cloud computing perform distributed execution of a task. Machines 2 to 9 each include: a communication unit 302 that acquires environment information relating to the environment of another machine other than the own machine; an information acquisition unit 303 that acquires environment information relating to the environment of the own machine; a risk calculation unit 305 that calculates a risk for the case where the own machine executes the task based on the acquired environment information; a risk determination unit 306 that determines whether or not the calculated risk is equal to or higher than a predetermined threshold; and an execution control unit 307 that stops execution of the task on the own machine when the risk determination unit 306 determines that the risk is equal to or higher than the predetermined threshold.

Claims (46)

1. A distributed processing system including a plurality of machines that perform distributed execution of a task, the plurality of machines including a master machine and slave machines, the master machine distributes tasks to the slave machines, each machine comprising:

a hardware processor that

acquires environment information relating to an environment of another machine;

acquires environment information relating to an environment of its own machine;

calculates a risk for a case where its own machine executes the task based on the acquired environment information of said another machine and the acquired environment information of its own machine;

determines whether or not the calculated risk is equal to or higher than a predetermined threshold; and

stops execution of the task on its own machine when the risk determination unit determines that the risk is equal to or higher than the predetermined threshold,

wherein the risk is calculated by comparing the environment information of its own machine with the environment information of said another machine to determine risk coefficients for each other machine executing the task and a risk coefficient for its own machine executing the task, wherein each slave machine determines the risk coefficient for each other slave machine executing the task and the risk coefficient for its own machine executing the task, and wherein the environment information includes execution environment information and proximity environment information,

wherein the execution environment information includes data items representing at least one of date and time, hardware, operating system, network and security policy, and

the proximity environment information includes data items representing at least one of date and time, policy administrator, master distributed execution foundation, policy agent in proximity, executed task in proximity and round-trip times, and

wherein determining the risk coefficients includes using at least one data item of the execution environment information, and at least one data item of the proximity environment information.

2. The distributed processing system according to claim 1 , wherein any of the plurality of machines is a virtual machine constructed by cloud computing.

3. The distributed processing system according to claim 1 , wherein the environment information is acquired either each time execution of the task is started or periodically.

4. The distributed processing system according to claim 1 , wherein

the execution environment information includes information relating to a security policy.

5. A distributed processing method for performing distributed execution of a task using a plurality of machines, the plurality of machines including a master machine and slave machines, the master machine distributes tasks to the slave machines, comprising:

(a) a step in which each of the plurality of machines acquires environment information relating to an environment of another machine;

(b) a step in which each of the plurality of machines acquires environment information relating to an environment of itself;

(c) a step in which each of the plurality of machines calculates a risk for a case where the machines themselves execute the task based on the environment information acquired in step (a) and the environment information acquired in step (b);

(d) a step in which each of the plurality of machines determines whether or not the risk calculated in step (c) is equal to or higher than a predetermined threshold; and

(e) a step in which each of the plurality of machines stops execution of the task on itself when step (d) determines that the risk is equal to or higher than the predetermined threshold,

wherein for each of the plurality of machines step (c) calculates the risk by comparing the environment information of said another machine acquired in step (a) with the environment information of itself acquired in step (b), and wherein the environment information of said another machine includes execution environment information and proximity environment information,

wherein each slave machine determines a risk coefficient for each other slave machine executing the task and a risk coefficient for its own machine executing the task,

wherein the execution environment information includes data items representing at least one of date and time, hardware, operating system, network and security policy, and

the proximity environment information includes data items representing at least one of date and time, policy administrator, master distributed execution foundation, policy agent in proximity, executed task in proximity and round-trip times, and

wherein determining the risk coefficients includes using at least one data item of the execution environment information, and at least one data item of the proximity environment information.

6. The distributed processing method according to claim 5 , wherein any of the plurality of machines is a virtual machine constructed by cloud computing.

7. The distributed processing method according to claim 5 , wherein steps (a) and (b) are executed either each time execution of the task is started or periodically.

8. The distributed processing method according to claim 5 , wherein

the execution environment information includes information relating to a security policy.

9. A non-transitory computer readable storage medium having recorded therein a program for, when performing distributed execution of a task using a plurality of computers, causing one of the plurality of computers to execute the divided task, the plurality of computers including a master computer and slave computers, the master computer distributes the task to the slave computers, the program including an instruction for causing said one of the plurality of computers to execute:

(a) a step of acquiring environment information relating to an environment of another computer;

(b) a step of acquiring environment information relating to an environment of said one of the plurality of computers;

(c) a step of calculating a risk for a case where said one of the plurality of computers executes the task based on the environment information acquired in step (a) and the environment information acquired in step (b);

(d) a step of determining whether or not the calculated risk is equal to or higher than a predetermined threshold; and

(e) a step of stopping execution of the task on said one of the plurality of computers when step (d) determines that the risk is equal to or higher than the predetermined threshold,

wherein step (c) calculates the risk by comparing the environment information of said another computer acquired in step (a) with the environment information of said one of the plurality of computers acquired in step (b), and wherein the environment information of said another computer includes execution environment information and proximity environment information,

wherein each slave computer determines a risk coefficient for each other slave computer executing the task and a risk coefficient for its own computer executing the task,

wherein the execution environment information includes data items representing at least one of date and time, hardware, operating system, network and security policy, and

the proximity environment information includes data items representing at least one of date and time, policy administrator, master distributed execution foundation, policy agent in proximity, executed task in proximity and round-trip times, and

wherein the determining the risk coefficients includes using at least one data item of the execution environment information, and at least one data item of the proximity environment information.

10. The non-transitory computer readable storage medium according to claim 9 , wherein

any of the plurality of computers is a virtual machine constructed by cloud computing.

11. The non-transitory computer readable storage medium according to claim 9 , wherein

steps (a) and (b) are executed either each time execution of the task is started or periodically.

12. The non-transitory computer readable storage medium according to claim 9 , wherein the execution environment information includes information relating to a security policy.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 8, 2013
From: YASUDA, JUNICHI
To: NEC CORPORATION
Reel/Frame 029587/0766 →
Priority Claims (1)
JP 2012-006167 · Jan 16, 2012 · national
Continuity (1)
Related Publication 20130185763A1 · Jul 18, 2013