Method, device, and product for managing scrubbing operation in storage system

1. A method for managing scrubbing operations in a storage system, the method comprising:

obtaining usage states of a plurality of extents in the storage system,

wherein each of the plurality of extents is a pre-defined storage space within the storage system allocated for storing a predetermined amount of data,

wherein a usage state of an extent comprises a first plurality of states of the extent and a second plurality of states of a storage device to which the extent belongs;

detecting, from the plurality of extents, a group of target extents in which a failure will occur based on the usage states, and features of extents determined from the usage states, of the plurality of extents,

wherein the failure will cause the extent to become completely unusable for storage operations of the storage system,

wherein a feature of the extent comprises a multi-dimensional data structure reflecting values corresponding to at least a subset of a combination of the first and second pluralities of states, the values respective to the extent;

adjusting, according to the detected group of target extents, a scrubbing interval of a scrubbing operation to be performed on the storage system; and

performing, according to the adjusted scrubbing interval, the scrubbing operation on at least one part of the plurality of extents in the storage system; and

identifying, based on the scrubbing operation, a failed extent of the plurality of extents,

wherein the failed extent is no longer usable for storage operations of the storage system.

2. The method of claim 1 ,

wherein adjusting, according to the detected group of target extents, the scrubbing interval of the scrubbing operation to be performed on the storage system comprises:

setting the scrubbing interval to “execute immediately” in response to determining the group of target extents satisfy a predetermined condition; and

wherein performing, according to the adjusted scrubbing interval, the scrubbing operation on the at least one part of the plurality of extents in the storage system comprises:

immediately performing a partial scrubbing operation on the group of target extents.

3. The method of claim 1 , wherein detecting from the plurality of extents the group of target extents in which the failure will occur based on the usage states, and the features of extents determined from the usage states, of the plurality of extents comprises:

obtaining an association between failures in the plurality of extents and the features of the plurality of extents; and

identifying from the plurality of extents the group of target extents in which latent failures will occur based on the features of the plurality of extents and the association.

4. The method of claim 3 ,

wherein the usage states of the plurality of extents comprises a response time of each extent of the plurality of extents for an access time,

wherein determining the features of extents of the plurality of extents comprises:

for a given extent of the plurality of extents, determining a feature of the given extent in response to the response time of the given extent being higher than a predetermined threshold.

5. The method of claim 4 ,

wherein the usage states of the plurality of extents further comprises failure information and a failure identifier of each extent of the plurality of extents, and

determining the features of extents of the plurality of extents further comprises:

regarding the given extent, determining the feature of the given extent additionally based on the failure information and the failure identifier of the given extent.

6. The method of claim 3 , wherein obtaining the association comprises:

training the association based on features of the plurality of extents included in a plurality of storage devices of the storage system and failures in the plurality of extents included in the plurality of storage devices of the storage system.

7. The method of claim 1 , wherein adjusting, according to the detected group of target extents, the scrubbing interval of the scrubbing operation to be performed on the storage system comprises:

determining a wear level of the plurality of extents in response to determining no target extent in which a latent failure will occur is detected; and

adjusting the scrubbing interval according to the determined wear level.

8. The method of claim 7 , wherein adjusting the scrubbing interval according to the determined wear level comprises any of:

reducing the scrubbing interval in response to determining the wear level in any of an early stage and a late stage of a lifecycle of a storage device in the storage system; and

increasing the scrubbing interval in response to determining the wear level in a middle stage of the lifecycle of the storage device in the storage system.

9. The method of claim 7 , wherein performing, according to the adjusted scrubbing interval, the scrubbing operation on the at least one part of the plurality of extents in the storage system:

performing a global scrubbing operation on the plurality of extents according to the adjusted scrubbing interval.

10. The method of claim 1 , further comprising:

selecting a free storage device from storage devices other than a storage device comprising the failed extent among a plurality of storage devices in the storage system; and

rebuilding data in the failed extent to a free extent in the free storage device.

11. A device, the device comprising:

at least one processor;

a volatile memory; and

a memory coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, causing the device to perform acts for managing scrubbing operations in a storage system, the acts comprising:

obtaining usage states of a plurality of extents in the storage system,

wherein each of the plurality of extents is a pre-defined storage space within the storage system allocated for storing a predetermined amount of data,

wherein a usage state of an extent comprises a first plurality of states of the extent and a second plurality of states of a storage device to which the extent belongs;

detecting, from the plurality of extents, a group of target extents in which a failure will occur based on the usage states, and features of extents determined from the usage states, of the plurality of extents,

wherein the failure will cause the extent to become completely unusable for storage operations of the storage system,

wherein a feature of the extent comprises a multi-dimensional data structure reflecting values corresponding to at least a subset of a combination of the first and second pluralities of states, the values respective to the extent;

adjusting, according to the detected group of target extents, a scrubbing interval of a scrubbing operation to be performed on the storage system; and

performing, according to the adjusted scrubbing interval, the scrubbing operation on at least one part of the plurality of extents in the storage system; and

identifying, based on the scrubbing operation, a failed extent of the plurality of extents,

wherein the failed extent is no longer usable for storage operations of the storage system.

12. The device of claim 11 ,

wherein adjusting, according to the detected group of target extents, the scrubbing interval of the scrubbing operation to be performed on the storage system comprises:

setting the scrubbing interval to “execute immediately” in response to determining the group of target extents satisfy a predetermined condition; and

wherein performing, according to the adjusted scrubbing interval, the scrubbing operation on the at least one part of the plurality of extents in the storage system comprises:

immediately performing a partial scrubbing operation on the group of target extents.

13. The device of claim 11 , wherein detecting from the plurality of extents the group of target extents in which the failure will occur based on the usage states, and the features of extents determined from the usage states, of the plurality of extents comprises:

obtaining an association between failures in the plurality of extents and the features of the plurality of extents; and

identifying from the plurality of extents the group of target extents in which latent failures will occur based on the features of the plurality of extents and the association.

14. The device of claim 13 ,

wherein the usage states of the plurality of extents comprises a response time of each extent of the plurality of extents for an access time,

wherein determining the features of extents of the plurality of extents comprises:

for a given extent of the plurality of extents, determining a feature of the given extent in response to the response time of the given extent being higher than a predetermined threshold.

15. The device of claim 14 ,

wherein the usage states of the plurality of extents further comprises failure information and a failure identifier of each extent of the plurality of extents, and

determining the features of extents of the plurality of extents further comprises:

regarding the given extent, determining the feature of the given extent additionally based on the failure information and the failure identifier of the given extent.

16. The device of claim 13 , wherein obtaining the association comprises:

training the association based on features of the plurality of extents included in a plurality of storage devices of the storage system and failures in the plurality of extents included in the plurality of storage devices of the storage system.

17. The device of claim 11 , wherein adjusting, according to the detected group of target extents, the scrubbing interval of the scrubbing operation to be performed on the storage system comprises:

determining a wear level of the plurality of extents in response to determining no target extent in which a latent failure will occur is detected; and

adjusting the scrubbing interval according to the determined wear level.

18. The device of claim 17 , wherein adjusting the scrubbing interval according to the determined wear level comprises any of:

reducing the scrubbing interval in response to determining the wear level in any of an early stage and a late stage of a lifecycle of a storage device in the storage system; and

increasing the scrubbing interval in response to determining the wear level in a middle stage of the lifecycle of the storage device in the storage system.

19. The device of claim 17 , wherein performing, according to the adjusted scrubbing interval, the scrubbing operation on the at least one part of the plurality of extents in the storage system:

performing a global scrubbing operation on the plurality of extents according to the adjusted scrubbing interval.

20. A computer program product, tangibly stored on a non-transient computer readable medium and comprising machine executable instructions, which are used to perform a method, the method comprising:

obtaining usage states of a plurality of extents in the storage system,

wherein each of the plurality of extents is a pre-defined storage space within the storage system allocated for storing a predetermined amount of data,

wherein a usage state of an extent comprises a first plurality of states of the extent and a second plurality of states of a storage device to which the extent belongs;

detecting, from the plurality of extents, a group of target extents in which a failure will occur based on the usage states, and features of extents determined from the usage states, of the plurality of extents,

wherein the failure will cause the extent to become completely unusable for storage operations of the storage system,

wherein a feature of the extent comprises a multi-dimensional data structure reflecting values corresponding to at least a subset of a combination of the first and second pluralities of states, the values respective to the extent;

adjusting, according to the detected group of target extents, a scrubbing interval of a scrubbing operation to be performed on the storage system; and

performing, according to the adjusted scrubbing interval, the scrubbing operation on at least one part of the plurality of extents in the storage system; and

identifying, based on the scrubbing operation, a failed extent of the plurality of extents,

wherein the failed extent is no longer usable for storage operations of the storage system.