COMPUTER SYSTEM AND DATA MANAGEMENT METHOD

• US 20130144953A1
• Filed: 01/25/2011
• Published: 06/06/2013
• Est. Priority Date: 08/06/2010
• Status: Abandoned Application

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Watanabe, Satoru
• Application Number:
  US13/813,987
• Publication Number:
  US 20130144953A1
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06F 9/5088 involving task migration
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355

Abstract

Provided is a computer system provided with: a plurality of execution servers that execute a plurality of jobs; and a scheduling server that is connected to the execution servers. The execution servers hold a plurality of data that are processed by the jobs, and the scheduling server generates a plurality of first sets that each contain a plurality of data processed by the plurality of jobs that are continuously executed, extracts, from the plurality of first sets, second sets containing data held by one of the execution servers and data held by another execution server, and determines data contained in the extracted second sets to be data to be transferred to a newly added execution server.

Claims

1. A computer system comprising a plurality of execution servers that execute a plurality of jobs, and a scheduler server connected to the execution servers, wherein:

the execution servers each preserve a plurality of data items to be processed by the jobs;

the scheduler server produces a plurality of first pairs, each of which includes a plurality of data items to be processed by the plurality of jobs that is successively executed;

the scheduler server extracts a second pair, which includes data preserved by one of the execution servers and data preserved by any other execution server, from among the plurality of first pairs;

the scheduler server determines data items, which are included in the extracted second pair, as data items to be moved to a newly added execution server;

the computer system can enter a first state in which the data items included in the second pair have not been moved;

the scheduler server calculates a first frequency at which each of the data items is processed by the job in the first state, and a second frequency at which the plurality of data items included in the second pair is processed by the plurality of lobs to be successively executed;

the scheduler server performs first comparison of comparing the second frequency with a predetermined threshold;

if a decision is made through the first comparison that the second frequency in the first state is larger, the scheduler server determines the data items, which are included in the extracted second pair, as the data items to be moved to the newly added execution server; and

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates a load volume of each of the execution servers by summating the first frequencies, and determines data, which is extracted according to a plurality of calculated load volumes, as data to be moved to the newly added execution server.

2. (canceled)

3. (canceled)

4. A computer system comprising a plurality of execution servers that execute a plurality of jobs and a scheduler server connected to the execution servers, wherein:

the execution servers each preserve a plurality of data items to be processed by the jobs;

the scheduler server acquires first pairs including the plurality of data items to be successively processed;

the scheduler server extracts a second pair, which includes data preserved by one of the execution servers and data preserved by any other execution server, from among the plurality of first pairs;

the scheduler server determines data items, which are included in the extracted second pair, as data items to be moved to a newly added execution server;

the computer system can enter a first state in which the data items included in the second pair have not been moved;

the scheduler server calculates a first frequency at which each of the data items is processed by the job in the first state, and a second frequency at which the second pair is successively processed;

the scheduler server performs first comparison of comparing the second frequency with a predetermined threshold;

the computer system can enter a second state, in which the data extracted according to the plurality of calculated load volumes has not been moved, and a third state in which the data has been moved;

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates the second frequency in the third state, and performs second comparison of comparing the second frequency in the third state with the predetermined threshold;

if a decision is made through the second comparison that the second frequency in the third state is smaller, the scheduler server calculates a first difference between the load volume of each of the execution servers in the second state and the load volume of the newly added execution server, calculates a second difference between the load volume of each of the execution servers in the third state and the load volume of the newly added execution server, and performs third comparison of comparing the first difference with the second difference; and

if a decision is made through the third comparison that the second difference is smaller, the scheduler server determines the data, which is extracted according to the load volumes, as the data to be moved to the newly added execution server.

5. The computer system as set forth in claim 4, wherein:

if a decision is made through the first comparison that the second frequency in the first state is larger, the scheduler server determines the data items, which are included in the extracted second pair, as the data items to be moved to the newly added execution server; and

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates a load volume of each of the execution servers by summating the first frequencies, and determines data, which is extracted according to a plurality of calculated load volumes, as data to be moved to the newly added execution server.

6. (canceled)

7. A data management method that is a moving data determination method implemented by a scheduler server connected to a plurality of execution servers that execute a plurality of jobs, wherein:

the execution servers each preserve in a memory a plurality of data items to be processed by the jobs; and

the method is such that;

the scheduler server produces a plurality of first pairs each including a plurality of data items to be processed by the plurality of jobs that is successively executed, and stores the produced first pairs in the memory;

the scheduler server extracts a second pair, which includes data preserved by one of the execution servers and data preserved by any other execution server, from among the plurality of first pairs stored in the memory;

the scheduler server determines data items, which are included in the extracted second pair, as data items to be moved to a newly added execution server;

the plurality of execution servers and scheduler server are included in a computer system;

the computer system can enter a first state in which the data items included in the second pair have not been moved, a second state in which the data has not been moved, and a third state in which the data has been moved;

the scheduler server calculates a first frequency at which each of the data items is processed by the job in the first state, and a second frequency at which the plurality of data items included in the second pair is processed by the plurality of lobs to be successively executed;

the scheduler server performs first comparison of comparing the second frequency with a predetermined threshold;

if a decision is made through the first comparison that the second frequency in the first state is larger, the scheduler server determines the data items, which are included in the extracted second pair, as the data items to be moved to the newly added execution server;

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates a load volume of each of the execution servers by summating the first frequencies, and determines data, which is extracted according to a plurality of calculated load volumes, as the data to be moved to the newly added execution server;

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates the second frequency in the third state, and performs second comparison of comparing the second frequency in the third state with the predetermined threshold;

if a decision is made through the second comparison that the second frequency in the third state is smaller, the scheduler server calculates a first difference between the load volume of each of the execution servers in the second state and the load volume of the newly added execution server, and a second difference between the load volume of each of the execution servers in the third state and the load volume of the newly added execution server, and performs third comparison of comparing the first difference with the second difference; and

if a decision is made through the third comparison that the second difference is smaller, the scheduler server determines the data, which is extracted according to the load volumes, as the data to be moved to the newly added execution server.

8. (canceled)

9. A data management method that is a moving data determination method implemented by a scheduler server connected to a plurality of execution servers that execute a plurality of jobs, wherein:

the execution servers each preserve a plurality of data items to be processed by the jobs; and

the method is such that;

the scheduler server stores a plurality of first pairs, which includes the plurality of data items to be successively processed, in a memory;

the scheduler server extracts a second pair, which includes data preserved by one of the execution servers and data preserved by any other execution server, from among the plurality of first pairs stored in the memory;

the scheduler server determines data items, which are included in the extracted second pair, as data items to be moved to a newly added execution server;

the plurality of execution servers and scheduler server are included in a computer system;

the computer system can enter a first state in which the data items included in the second pair have not been moved, a second state in which the data has not been moved, and a third state in which the data has been moved;

the scheduler server calculates a first frequency, at which each of the data items is processed by the job in the first state, and a second frequency at which the second pair is successively processed;

the scheduler server performs first comparison of comparing the second frequency with a predetermined threshold;

if a decision is made through the first comparison that the second frequency in the first state is larger, the scheduler server determines the data items, which are included in the extracted second pair, as the data items to be moved to the newly added execution server;

if a decision is made through the first comparison that the second frequency in the first state is smaller, the scheduler server calculates a load volume of each of the execution servers by summating the first frequencies, and determines the data, which is extracted according to a plurality of calculated load volumes, as the data to be moved to the newly added execution server;

if a decision is made that the second frequency in the first state is smaller, the scheduler server calculates the second frequency in the third state, and performs second comparison on the second frequency in the third state and the predetermined threshold;

if a decision is made through the second comparison that the second frequency in the third state is smaller, the scheduler server calculates a first difference between the load volume of each of the execution servers in the second state and the load volume of the newly added execution server, and a second difference between the load volume of each of the execution servers in the third state and the load volume of the newly added execution server, and performs third comparison of comparing the first difference with the second difference; and

if a decision is made through the third comparison that the second difference is smaller, the scheduler server determines the data, which is extracted according to the load volumes, as the data to be moved to the newly added execution server.

10. (canceled)