Storage system and failure handling method

1. A storage system for providing a storage area to a higher-level device, the storage system comprising:

one or a plurality of storage devices provided in a cloud system, and configured to provide the storage area;

a plurality of storage nodes provided in the cloud system, and configured to read and write data from and to the storage device allocated to the storage nodes themselves in response to a request from the higher-level device; and

a cloud control device configured to control the cloud system,

wherein the storage node is configured to;

request the cloud control device to prepare a new storage node when a failure of another storage node is detected;

determine whether the storage device allocated to the another storage node, in which a failure occurs, is failed; and

request the cloud control device to allocate the storage device allocated to the another storage node, in which the failure occurs, to the new storage node when the storage device is determined to be not failed, and

wherein the another storage node shares with remaining storage nodes storage configuration information, capacity configuration information, and operation status of control software such that the remaining storage nodes return a degraded redundancy group to a normal state.

2. The storage system according to claim 1 , wherein the new storage node is configured to write data requested to be written to the storage device allocated to the another storage node in which the failure occurs during occurrence of the failure, to the storage device allocated to the new storage node.

3. The storage system according to claim 2 , wherein the storage node is configured to

request the cloud control device to prepare a new storage device when the storage device allocated to the another storage node in which the failure occurs is determined to be failed, and

request the cloud control device to allocate the prepared new storage device to the new storage node, and

the new storage node is configured to

write data stored in the storage device determined to be failed to the new storage device.

4. The storage system according to claim 3 , wherein the storage node is configured to

generate an erasure correction code from the data stored in the storage device, and store the generated erasure correction code in the storage device different from the storage device in which the data is stored, and

the new storage node is configured to restore, by using the erasure correction code, the data stored in the storage device determined to be failed, and write the restored data in the new storage device.

5. The storage system according to claim 4 , wherein

a write destination of the data requested to be written to the storage device allocated to the another storage node in which the failure occurs during occurrence of a failure in the storage device is stored by the storage node other than the storage node in which the failure occurs, and

the new storage node is configured to

write the restored data to the write destination stored by the storage node other than the another storage node in which the failure occurs.

6. The storage system according to claim 4 , wherein the storage node is configured to

divide the storage area provided by the storage device allocated to the storage node into chunks having a predetermined size and manage the chunks, and manage, as a chunk group, one of the chunks in a predetermined number of the storage devices allocated to the plurality of storage nodes, and

store the data and the erasure correction code generated from the data separately in a plurality of the chunks constituting a same chunk group.

7. A failure handling method in a storage system for providing a storage area to a higher-level device,

the storage system including:

one or a plurality of storage devices provided in a cloud system, and configured to provide the storage area;

a plurality of storage nodes provided in the cloud system, and configured to read and write data from and to the storage device allocated to the storage nodes themselves in response to a request from the higher-level device; and

a cloud control device configured to control the cloud system, the failure handling method comprising:

a first step of requesting, by the storage node, the cloud control device to prepare a new storage node when a failure of another storage node is detected;

a second step of determining, by the storage node, whether the storage device allocated to the another storage node, in which the failure occurs, is failed; and

a third step of requesting, by the storage node, the cloud control device to allocate the storage device allocated to the another storage node, in which the failure occurs, to the new storage node when the storage device is determined to be not failed,

wherein the another storage node shares with remaining storage nodes storage configuration information, capacity configuration information, and operation status of control software such that the remaining storage nodes return a degraded redundancy group to a normal state.

8. The failure handling method according to claim 7 , further comprising:

a fourth step of writing, by the new storage node, data requested to be written to the storage device allocated to the another storage node in which the failure occurs during occurrence of a failure to the storage device allocated to the new storage node.

9. The failure handling method according to claim 8 , wherein in the third step, the storage node

requests the cloud control device to prepare a new storage device when the storage device allocated to the another storage node in which the failure occurs is determined to be failed, and

requests the cloud control device to allocate the prepared new storage device to the new storage node, and

in the fourth step, the new storage node writes data stored in the storage device determined to be failed to the new storage device.

10. The failure handling method according to claim 9 , wherein the storage node

generates an erasure correction code from the data stored in the storage device, and stores the generated erasure correction code in the storage device different from the storage device in which the data is stored, and

in the fourth step, the new storage node

restores, by using the erasure correction code, the data stored in the storage device determined to be failed, and write the restored data in the new storage device.

11. The failure handling method according to claim 10 , wherein a write destination of the data requested to be written to the storage device allocated to the another storage node in which the failure occurs during occurrence of a failure in the storage device is stored by the storage node other than the another storage node in which the failure occurs, and

in the fourth step, the new storage node

writes the restored data to the write destination stored by the storage node other than the another storage node in which the failure occurs.

12. The failure handling method according to claim 10 , wherein the storage node

divides the storage area provided by the storage device allocated to the storage node into chunks having a predetermined size and manages the chunks, and manages, as a chunk group, one of the chunks in a predetermined number of the storage devices allocated to the plurality of storage nodes, and

stores the data and the erasure correction code generated from the data separately in a plurality of the chunks constituting a same chunk group.