Doubly mapped cluster contraction
Contraction of a doubly mapped redundant array of independent nodes, e.g., a doubly mapped cluster, is disclosed. Different mappings of data for a doubly mapped cluster corresponding to different uses of computing resources. Where a computing resource parameter indicates the computing resource is underutilized, an alternative mapping of the doubly mapped cluster can be undertaken. The alternative mapping can better utilize the computing resources. The contraction of the doubly mapped cluster can maintain access to stored data. The contraction can preserve data protection set integrity. The contraction can result in the doubly mapped cluster comprising fewer mapped nodes after the contraction but can avoid wholesale moving of corresponding data stored in a real cluster. As such, contraction of a doubly mapped cluster can be distinct from scaling-in of a doubly mapped cluster.
1. A system, comprising:
a processor; and
a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
initiating, based on a first computer resource parameter, contraction of a doubly mapped cluster employing a first mapping scheme;
selecting a contraction scheme based on a difference between the first computer resource parameter and a second computer resource parameter, wherein the second computer resource parameter is predicted based on substituting a second mapping scheme for the first mapping scheme employed by the doubly mapped cluster, and wherein the second mapping scheme corresponds to the contraction scheme; and
updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
2. The system of claim 1 , wherein the operations further comprise:
moving a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the first mapping scheme prior to the updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
3. The system of claim 2 , wherein the moving the data protection set fragment prior to the updating the doubly mapped cluster is in response to at least determining that the integrity of the data protection set is preserved prior to the updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
4. The system of claim 2 , wherein the moving the data protection set fragment prior to the updating the doubly mapped cluster is in response to at least determining that the integrity of the data protection set will be preserved after the updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
5. The system of claim 2 , wherein the data protection set corresponds to a 12+4 erasure coding scheme.
6. The system of claim 2 , wherein the data protection set corresponds to a 10+2 erasure coding scheme.
7. The system of claim 1 , wherein the operations further comprise:
moving a data protection set fragment to a different logical location in the doubly mapped cluster according to the second mapping scheme after the updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
8. The system of claim 7 , wherein prior to the moving the data protection set fragment the integrity of the data protection set is compromised by the updating the doubly mapped cluster to employ the second mapping in place of the first mapping.
9. The system of claim 8 , wherein after the moving the data protection set fragment the integrity of the data protection set is restored.
10. The system of claim 1 , wherein the updating the doubly mapped cluster to employ the second mapping in place of the first mapping comprises moving no corresponding data stored in a real cluster.
11. The system of claim 1 , wherein the updating the doubly mapped cluster to employ the second mapping in place of the first mapping comprises moving at least some corresponding data stored in a real cluster.
12. The system of claim 1 , wherein the operations further comprise releasing at least one mapped node of the doubly mapped cluster, resulting in the doubly mapped cluster comprising at least one fewer mapped nodes after the contraction of the doubly mapped cluster than before the contraction of the doubly mapped cluster.
13. A method, comprising:
in response to determining, by a system comprising a processor, that a first computer resource parameter does not satisfy a rule related to a threshold value, triggering contraction of a doubly mapped cluster employing a first mapping scheme;
ranking, by the system, a contraction scheme among contraction schemes, wherein the ranking is based, at least in part, on a difference between the first computer resource parameter and a second computer resource parameter, wherein the second computer resource parameter is predicted based on the doubly mapped cluster employing a second mapping scheme, and wherein the second mapping scheme is indicated by the contraction scheme; and
in response to selecting, by the system, the contraction scheme based on the rank, updating the doubly mapped cluster by transitioning from a first mapping according to the first mapping scheme to a second mapping according to the second mapping scheme.
14. The method of claim 13 , further comprising:
causing, by the system, movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the first mapping scheme prior to the updating the doubly mapped cluster, wherein the movement of the data protection set fragment to the different logical location results in the data protection set satisfying a fragment distribution rule related to an integrity of the data protection set before the updating the doubly mapped cluster.
15. The method of claim 13 , further comprising:
causing, by the system, movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the first mapping scheme prior to the updating the doubly mapped cluster, wherein the movement of the data protection set fragment to the different logical location results in the data protection set satisfying a fragment distribution rule related to an integrity of the data protection set after the updating the doubly mapped cluster.
16. The method of claim 13 , further comprising:
causing, by the system, movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the second mapping scheme after the updating the doubly mapped cluster, wherein the movement of the data protection set fragment to the different logical location results in the data protection set satisfying a fragment distribution rule related to an integrity of the data protection set after the updating the doubly mapped cluster.
17. A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
triggering, based on a first computer resource parameter, contraction of a doubly mapped cluster employing a first mapping scheme;
selecting a contraction scheme based on a rank of the contraction scheme among possible contraction schemes, wherein the rank is based, at least in part, on a difference between the first computer resource parameter and a second computer resource parameter, wherein the second computer resource parameter is predicted based on the doubly mapped cluster employing a second mapping scheme in lieu of the first mapping scheme, and wherein the second mapping scheme corresponds to the contraction scheme; and
updating, according to the contraction scheme, the doubly mapped cluster by transitioning from a first mapping according to the first mapping scheme to a second mapping according to the second mapping scheme.
18. The non-transitory machine-readable medium of claim 17 , wherein, the operations further comprise:
initiating movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the first mapping scheme prior to the updating the doubly mapped cluster, wherein the data protection set is determined to satisfy a fragment distribution rule related to an integrity of the data protection set after the movement of the data protection set fragment and before the updating the doubly mapped cluster.
19. The non-transitory machine-readable medium of claim 17 , wherein, the operations further comprise:
initiating movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the first mapping scheme prior to the updating the doubly mapped cluster, wherein the data protection set is determined to satisfy a fragment distribution rule related to an integrity of the data protection set after the movement of the data protection set fragment and after the updating the doubly mapped cluster.
20. The non-transitory machine-readable medium of claim 17 , wherein, the operations further comprise:
initiating movement of a data protection set fragment of a data protection set to a different logical location in the doubly mapped cluster according to the second mapping scheme after the updating the doubly mapped cluster, wherein the data protection set is determined to satisfy a fragment distribution rule related to an integrity of the data protection set after the updating the doubly mapped cluster and after the movement of the data protection set fragment.