COMPUTER SYSTEM, DATA ALLOCATION MANAGEMENT METHOD, AND PROGRAM

• US 20150046399A1
• Filed: 04/12/2012
• Published: 02/12/2015
• Est. Priority Date: 04/12/2012
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Fukunaka, Katsuhiro
• Granted Patent: US 9,898,518 B2
• Time in Patent Office: Days
• US Class Current: 707/634
• CPC Class Codes: G06F 11/2094 Redundant storage or storage space G06F11/2056 takes precedence
• CPC Class Codes: G06F 11/3404 for parallel or distributed programming
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 16/178 Techniques for file synchronisation in file systems
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54

Abstract

A computer system comprises a plurality of computers for executing a service by using databases constructed of storage areas included in the plurality of computers. Each of the plurality of computers is configured to hold performance management information for managing respective performances of the plurality of computers. The each of the plurality of computers is allocated master data and replicated data of the master data managed by one of the plurality of computers other than the each of the plurality of computers. The computer system comprises a performance information management part configured to update the performance management information; and a cluster configuration management part configured to determine, based on the performance management information, the management range of the master data managed by a computer and a sub-computers configured to hold the replicated data of the master data managed by the computer.

Claims

1. A computer system, comprising a plurality of computers coupled to one another via a network, for executing a service by using databases constructed of storage areas included in the plurality of computers,

each of the plurality of computers including:

a processor;

a storage apparatus coupled to the processor; and

a network interface configured to communicate to and from the plurality of computers other than the each of the plurality of computers via the network,

the each of the plurality of computers being configured to hold performance management information for managing respective performances of the plurality of computers,

the database storing a plurality of pieces of data formed of a key and a data value,

the each of the plurality of computers being allocated thereto;

a plurality of pieces of master data managed by the each of the plurality of computers as a master based on a distributed algorithm for determining a management range indicating a range of the keys allocated to the each of the plurality of computers; and

a plurality of pieces of replicated data of the plurality of pieces of master data managed by one of the plurality of computers other than the each of the plurality of computers,

the computer system further comprising;

a performance information management part configured to obtain information on the performance from the each of the plurality of computers and update the performance management information based on the obtained information; and

a cluster configuration management part configured to determine, based on the performance management information, the management range of the plurality of pieces of master data managed by the each of the plurality of computers and a plurality of sub-computers configured to hold the plurality of pieces of replicated data of the plurality of pieces of master data managed by the each of the plurality of computers.

2. The computer system according to claim 1,

wherein the performance management information includes information on a storage capacity of the storage apparatus included in the each of the plurality of computers, and

wherein the cluster configuration management part is configured to:

refer to the performance management information to compare the storage capacities of the respective storage included in the plurality of computers with one another; and

determine the management range of the each of the plurality of computers and the plurality of sub-computers so that a difference between the storage capacity of the storage apparatus included in the one of the plurality of computers and the storage capacity of the storage apparatus included in one of the plurality of sub-computers for the one of the plurality of computers becomes smaller.

3. The computer system according to claim 2,

wherein the storage apparatus included in the each of the plurality of computers includes a memory and a disk apparatus,

wherein the database includes a memory store constructed of a storage area of the memory included in the each of the plurality of computers and a disk store constructed of the disk apparatus included in the each of the plurality of computers, and

wherein the cluster configuration management part is configured to:

calculate such a combination of one of the plurality of computers and one of the plurality of sub-computers that a difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller;

set the plurality of sub-computers for the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers;

determine an assigned width of the management range of the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers; and

apply the distributed algorithm based on the determined assigned width of the management range, to thereby determine the management range of the each of the plurality of computers.

4. The computer system according to claim 3,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database, and

wherein the cluster configuration management part is configured to:

refer to the index information to determine whether or not an access performance of the database is required;

calculate such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that the storage capacity of the memory included in the one of the plurality of computers is equal to or larger than the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers and that the difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller, in a case where it is determined that the access performance of the database is required; and

determine the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

5. The computer system according to claim 3,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database, and

wherein the cluster configuration management part is configured to:

refer to the index information to determine whether or not an access performance of the database and a usage efficiency of the storage capacity of the database are required;

calculate such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that differences among the storage capacity of the memory included in the one of the plurality of computers that manages the plurality of pieces of master data corresponding to the plurality of pieces of replicated data held by the one of the plurality of computers, the storage capacity of the memory held by the one of the plurality of computers, and the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers become small, in a case where it is determined that the access performance of the database and the usage efficiency of the storage capacity of the database are required; and

determine the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

6. The computer system according to claim 4,

wherein the cluster configuration management part is configured to display an entry screen for entering the index information, and

wherein the index information is obtained based on an operation performed through the entry screen.

7. The computer system according to claim 1, wherein the cluster configuration management part is configured to generate display information for displaying a difference in performance between the each of the plurality of computers and each of the plurality of sub-computers for the each of the plurality of computers and an assigned width of the management range of the each of the plurality of computers.

8. A data allocation management method to be performed in a computer system,

the computer system including a plurality of computers coupled to one another via a network and being configured to execute a service by using databases constructed of storage areas included in the plurality of computers,

each of the plurality of computers including:

a processor;

a storage apparatus coupled to the processor; and

a network interface configured to communicate to and from the plurality of computers other than the each of the plurality of computers via the network,

the each of the plurality of computers being configured to hold performance management information for managing respective performances of the plurality of computers,

the database storing a plurality of pieces of data formed of a key and a data value,

the each of the plurality of computers being allocated thereto;

a plurality of pieces of master data managed by the each of the plurality of computers as a master based on a distributed algorithm for determining a management range indicating a range of the keys allocated to the each of the plurality of computers; and

a plurality of pieces of replicated data of the plurality of pieces of master data managed by one of the plurality of computers other than the each of the plurality of computers,

the data allocation management method including;

a first step of obtaining, by the each of the plurality of computers, information on the performance from the each of the plurality of computers and updating the performance management information based on the obtained information; and

a second step of determining, by the each of the plurality of computers, based on the performance management information, the management range of the plurality of pieces of master data managed by the each of the plurality of computers and a plurality of sub-computers configured to hold the plurality of pieces of replicated data of the plurality of pieces of master data managed by the each of the plurality of computers.

9. The data allocation management method according to claim 8,

wherein the performance management information includes information on a storage capacity of the storage apparatus included in the each of the plurality of computers, and

wherein the second step includes:

a third step of referring to the performance management information to compare the storage capacities of the respective storage apparatus included in the plurality of computers with one another; and

a fourth step of determining the management range of the each of the plurality of computers and the plurality of sub-computers so that a difference between the storage capacity of the storage apparatus included in the one of the plurality of computers and the storage capacity of the storage apparatus included in one of the plurality of sub-computers for the one of the plurality of computers becomes smaller.

10. The data allocation management method according to claim 9,

wherein the storage apparatus included in the each of the plurality of computers includes a memory and a disk apparatus,

wherein the database includes a memory store constructed of a storage area of the memory included in the each of the plurality of computers and a disk store constructed of the disk apparatus included in the each of the plurality of computers, and

wherein the fourth step includes:

a fifth step of calculating such a combination of one of the plurality of computers and one of the plurality of sub-computers that a difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller;

a sixth step of setting the plurality of sub-computers for the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers;

a seventh step of determining an assigned width of the management range of the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers; and

an eight step of applying the distributed algorithm based on the determined assigned width of the management range, to thereby determine the management range of the each of the plurality of computers.

11. The data allocation management method according to claim 10,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database,

wherein the fifth step includes:

a step of referring to the index information to determine whether or not an access performance of the database is required; and

a step of calculating such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that the storage capacity of the memory included in the one of the plurality of computers is larger than the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers and that the difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller, in a case where it is determined that the access performance of the database is required, and

wherein the seventh step includes a step of determining the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

12. The data allocation management method according to claim 10,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database,

wherein the fifth step includes:

a step of referring to the index information to determine whether or not an access performance of the database and a usage efficiency of the storage capacity of the database are required; and

a step of calculating such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that differences among the storage capacity of the memory included in the one of the plurality of computers that manages the plurality of pieces of master data corresponding to the plurality of pieces of replicated data held by the one of the plurality of computers, the storage capacity of the memory held by the one of the plurality of computers, and the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers become small, in a case where it is determined that the access performance of the database and the usage efficiency of the storage capacity of the database are required, and

wherein the seventh step includes a step of determining the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

13. The data allocation management method according to claim 11, further including displaying an entry screen for entering the index information,

wherein the index information is obtained based on an operation performed through the entry screen.

14. The data allocation management method according to claim 8, further including a step of generating display information for displaying a difference in performance between the each of the plurality of computers and each of the plurality of sub-computers for the each of the plurality of computers and an assigned width of the management range of the each of the plurality of computers.

15. A program to be executed by each of a plurality of computers included in a computer system,

the computer system including the plurality of computers coupled to one another via a network and being configured to execute a service by using databases constructed of storage areas included in the plurality of computers,

the each of the plurality of computers including:

a processor;

a storage apparatus coupled to the processor; and

a network interface configured to communicate to and from the plurality of computers other than the each of the plurality of computers via the network,

the each of the plurality of computers being configured to hold performance management information for managing respective performances of the plurality of computers,

the database storing a plurality of pieces of data formed of a key and a data value,

the each of the plurality of computers being allocated thereto;

a plurality of pieces of master data managed by the each of the plurality of computers as a master based on a distributed algorithm for determining a management range indicating a range of the keys allocated to the each of the plurality of computers; and

a plurality of pieces of replicated data of the plurality of pieces of master data managed by one of the plurality of computers other than the each of the plurality of computers,

the program controlling the each of the plurality of computers to execute;

a first procedure of obtaining information on the performance from the each of the plurality of computers and updating the performance management information based on the obtained information; and

a second procedure of determining, based on the performance management information, the management range of the plurality of pieces of master data managed by the each of the plurality of computers and a plurality of sub-computers configured to hold the plurality of pieces of replicated data of the plurality of pieces of master data managed by the each of the plurality of computers.

16. The program according to claim 15,

wherein the performance management information includes information on a storage capacity of the storage apparatus included in the each of the plurality of computers, and

wherein the second procedure includes:

a third procedure of referring to the performance management information to compare the storage capacities of the respective storage apparatus included in the plurality of computers with one another; and

a fourth procedure of determining the management range of the each of the plurality of computers and the plurality of sub-computers so that a difference between the storage capacity of the storage apparatus included in the one of the plurality of computers and the storage capacity of the storage apparatus included in one of the plurality of sub-computers for the one of the plurality of computers becomes smaller.

17. The program according to claim 16,

wherein the storage apparatus included in the each of the plurality of computers includes a memory and a disk apparatus,

wherein the database includes a memory store constructed of a storage area of the memory included in the each of the plurality of computers and a disk store constructed of the disk apparatus included in the each of the plurality of computers, and

wherein the fourth procedure includes:

a fifth procedure of calculating such a combination of one of the plurality of computers and one of the plurality of sub-computers that a difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller;

a sixth procedure of setting the plurality of sub-computers for the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers;

a seventh procedure of determining an assigned width of the management range of the each of the plurality of computers based on the calculated combination of the one of the plurality of computers and the one of the plurality of sub-computers; and

an eighth procedure of applying the distributed algorithm based on the determined assigned width of the management range, to thereby determine the management range of the each of the plurality of computers.

18. The program according to claim 17,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database,

wherein the fifth procedure includes:

referring to the index information to determine whether or not an access performance of the database is required; and

calculating such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that the storage capacity of the memory included in the one of the plurality of computers is larger than the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers and that the difference in the storage capacity of the memory between the one of the plurality of computers and the one of the plurality of sub-computers becomes smaller, in a case where it is determined that the access performance of the database is required, and

wherein the seventh procedure includes determining the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

19. The program according to claim 17,

wherein the each of the plurality of computers is configured to hold index information designating a processing performance of the database,

wherein the fifth procedure includes:

referring to the index information to determine whether or not an access performance of the database and a usage efficiency of the storage capacity of the database are required; and

calculating such the combination of the one of the plurality of computers and the one of the plurality of sub-computers that differences among the storage capacity of the memory included in the one of the plurality of computers that manages the plurality of pieces of master data corresponding to the plurality of pieces of replicated data held by the one of the plurality of computers, the storage capacity of the memory held by the one of the plurality of computers, and the storage capacity of the memory included in the one of the plurality of sub-computers for the one of the plurality of computers become small, in a case where it is determined that the access performance of the database and the usage efficiency of the storage capacity of the database are required, and

wherein the seventh procedure includes determining the assigned width of the management range of the each of the plurality of computers based on a size of the storage capacity of the memory included in the each of the plurality of computers.

20. The program according to claim 16, further controlling the each of the plurality of computers to execute a procedure of generating display information for displaying a difference in performance between the each of the plurality of computers and each of the plurality of sub-computers for the each of the plurality of computers and an assigned width of the management range of the each of the plurality of computers.