Cloud system, control method thereof, management server and control method thereof

1. A cloud system, comprising:

a cloud database;

a first cache server to store first data in a first group among a first plurality of groups according to a first hit rate of the first data, the first plurality of groups being divided such that each group among the first plurality of groups corresponds to a different hit rate;

a second cache server to store second data in a second group among a second plurality of groups according to a second hit rate of the second data, the second plurality of groups being divided such that each group among the second plurality of groups corresponds to a different hit rate;

a first application server to access the first cache server to receive the first data and provide a first service based on the received first data;

a second application server to access the second cache server to receive the second data and provide a second service based on the received second data; and

a cloud management server to, when a resource of the first application server is exceeded:

copy the first data stored in the first group into the second group, the first hit rate of the first group being the same as the second hit rate of the first hit second group,

perform a control so that the second application server accesses the first data stored in the second cache server when a data processing request for data corresponds to the first data, and so that the second application server accesses the cloud database when the data processing request is for data not stored in the second cache server.

2. The system of claim 1 , wherein when the resource of the first application server is not exceeded the first application server is further configured to access the cloud database in response to a data processing request for data not stored in the first cache server.

3. The system of claim 1 , wherein the cloud management server is to execute a load balancing function and an auto scaling function when data processing requests cause the resource of the first application server to be exceeded.

4. A method, comprising:

storing, in a first cache server, first data in a first group among a first plurality of groups according to a first hit rate of the first data, the first plurality of groups being divided such that each group among the first plurality of groups corresponds to a different hit rate;

storing, in a second cache server, second data in a second group among a second plurality of groups according to a second hit rate of the second data, the second plurality of groups being divided such that each group among the second plurality of groups corresponds to a different hit rate;

accessing, by a first application server, the first cache server to receive the first data and providing, by the first application server, a first service based on the received first data;

accessing, by a second application server, the second cache server to receive the second data and providing, by the second application server, a second service based on the received second data; and

when a resource of the first application server is exceeded:

copying, by a cloud management server, the first data stored in the first group into the second group, the first hit rate of the first group being the same as the second hit rate hit, of the second group,

accessing, by the second application server, the first data stored in the second cache server when a data processing request for data corresponds to the first data, and

accessing, by the second application server, a cloud database when the data processing request is for data not stored in the second cache server.

5. The method of claim 4 , further comprising:

when the resource of the first application server is not exceeded:

receiving, by the first application server, a data processing request for data not stored in the first cache server,

accessing, by the first application server, the cloud database to receive the first data not stored in the first cache server, and

providing the first service based on the data received from the cloud database.

6. The method of claim 4 , further comprising executing, by the cloud management server, a load balancing function and an auto scaling function when data processing requests exceeding the resource of the first application server are received.

7. A management server of a cloud system, the management server comprising:

at least one memory to store instructions; and

at least one processor to execute the stored instructions to perform operations including:

receiving a data processing request,

determining whether the data processing request exceeds a resource of a first application server,

when the data processing request exceeds the resource of a first application server:

copying, by the management server, first data stored in a first group among a first plurality of groups in a first cache server, into a second group among a second plurality of groups in a second cache server, the first group and the second group having a same hit rate, the first plurality of groups being divided such that each group among the first plurality of groups corresponds to a different hit rate, and the second plurality of groups being divided such that each group among the second plurality of groups corresponds to a different hit rate,

performing a control so that a second application server accesses the first data stored in the second cache server when the data processing request is for data corresponding to the first data, and so that the second application server accesses a cloud database when the data processing request is for data not stored in the second cache server.

8. The management server of claim 7 , wherein the operations further include receiving a command to copy all of the first plurality of groups from the first cache server into the second cache server or a command to copy some of the first plurality of groups from the first cache server into the second cache server according to hit rates of each of the first plurality of groups.

9. The management server of claim 7 , further comprising:

a load balancer to distribute data processing requests; and

an auto scaler to provide an additional resource.

10. A method, comprising:

receiving a data processing request;

determining whether the data processing request exceeds a resource of a first application server; and

when the data processing request exceeds the resource of a first application server:

copying, by a management server, first data stored in a first group among a first plurality of groups in a first cache server, into a second group among a second plurality of groups in a second cache server, the first group and the second group having a same hit rate, the first plurality of groups being divided such that each group among the first plurality of groups corresponds to a different hit rate, and the second plurality of groups being divided such that each group among the second plurality of groups corresponds to a different hit rate, and

performing a control so that a second application server accesses the first data stored in the second cache server when the data processing request is for data corresponding to the first data, and so that the second application server accesses a cloud database when the data processing request is for data not stored in the second cache server.

11. The method of claim 10 , further comprising:

selectively receiving a command to copy all of the first plurality of groups from the first cache server into the second cache server or a command to copy some of the first plurality of groups from the first cache server into the second cache server according to hit rates of each of the first plurality of groups.

12. The method of claim 10 , further comprising:

distributing data processing requests; and

providing an additional resource.