REDISTRIBUTING ENCODED DATA SLICES IN A DISPERSED STORAGE NETWORK

• US 20160188253A1
• Filed: 10/29/2015
• Published: 06/30/2016
• Est. Priority Date: 12/31/2014
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Resch, Jason K., Leggette, Wesley, Motwani, Manish
• Granted Patent: US 10,126,974 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0644 Management of space entities, e.g. partitions, extents, pools
• CPC Class Codes: G06F 3/0647 Migration mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A method begins by storage units of a first pool of storage units of a plurality of pools detecting a change to a weighting factor of a pool of storage units and calculating an updated plurality of storage pool scores for a respective encoded data slice of a set of encoded data slices that is stored by a respective storage unit of the first pool of storage units. The method continues with each of the storage units of the first pool of storage units identifying one pool of storage units having a desired storage pool score based on the updated plurality of storage pool scores. When the one pool of storage units is not the first pool of storage units, each of the storage units of the first pool of storage units transfers the respective encoded data slice to a corresponding storage unit of the one pool of storage units.

Claims

1. A method comprises:

detecting, by storage units of a first pool of storage units of a plurality of pools of storage units, a change to a weighting factor of a pool of storage units of the plurality of pools of storage units;

calculating, by each of the storage units of the first pool of storage units, an updated plurality of storage pool scores for the plurality of pools of storage units for a respective encoded data slice of a set of encoded data slices that is currently stored by a respective storage unit of the first pool of storage units, wherein the storage pool score of the pool of storage units is based on the changed weighting factor of the pool of storage units;

identifying, by each of the storage units of the first pool of storage units, one pool of storage units of the plurality of pools of storage units having a desired storage pool score based on the updated plurality of storage pool scores; and

when the one pool of storage units is not the first pool of storage units, transferring, by each of the storage units of the first pool of storage units, the respective encoded data slice to a corresponding storage unit of the one pool of storage units.

2. The method of claim 1, wherein the detecting the change to the weighting factor of the pool of storage units comprises:

receiving, by each of the storage units of the first pool of storage units from one or more storage units of the pool of storage units, the changed weighting factor, wherein the one or more storage units of the pool of storage units determines the changed weighting factor based on a change to memory capabilities of the one or more storage units of the pool of storage units.

3. The method of claim 1, wherein the detecting the change to the weighting factor of the pool of storage units comprises:

determining, by a storage unit of the first pool of storage units, a change in memory capabilities of the storage unit; and

generating, by the storage unit of the first pool of storage units, the changed weighting factor based on the change in memory capabilities.

4. The method of claim 1 further comprises:

deleting, by each of the storage units of the first pool of storage units, the respective encoded data slice after successful transfer to the corresponding storage unit of the one pool of storage units.

5. The method of claim 1 further comprises:

when the one pool of storage units is the first pool of storage units, maintaining, by each of the storage units of the first pool of storage units, storage of the respective encoded data slice.

6. The method of claim 1, wherein the calculating the updated plurality of storage pool scores comprises:

performing a plurality of deterministic functions based on an identifier of the respective encoded data slice of the set of encoded data slices and a plurality of resource identifiers corresponding to each pool of storage units of the plurality of pools of storage units to produce a plurality of deterministic resultants;

normalizing the plurality of deterministic resultants to produce a plurality of normalized resultants; and

performing a plurality of weighting functions on the plurality of normalized resultants based on a plurality of weighting factors corresponding to the plurality of pools of storage units to produce the updated plurality of storage pool scores.

7. The method of claim 1 further comprises:

the first pool of storage units including one or more storage units; and

the one pool of storage units including another one or more storage units.

8. A non-transitory computer readable storage medium comprises:

at least one memory section that stores operational instructions that, when executed by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), causes the one or more computing devices to;

detect, by storage units of a first pool of storage units of a plurality of pools of storage units, a change to a weighting factor of a pool of storage units of the plurality of pools of storage units;

calculate, by each of the storage units of the first pool of storage units, an updated plurality of storage pool scores for the plurality of pools of storage units for a respective encoded data slice of a set of encoded data slices that is currently stored by a respective storage unit of the first pool of storage units, wherein the storage pool score of the pool of storage units is based on the changed weighting factor of the pool of storage units;

identify, by each of the storage units of the first pool of storage units, one pool of storage units of the plurality of pools of storage units having a desired storage pool score based on the updated plurality of storage pool scores; and

when the one pool of storage units is not the first pool of storage units, transfer, by each of the storage units of the first pool of storage units, the respective encoded data slice to a corresponding storage unit of the one pool of storage units.

9. The non-transitory computer readable storage medium of claim 8, wherein the one or more processing modules functions to execute the operational instructions stored by the at least one memory section to cause the one or more computing devices of the DSN to detect the change to the weighting factor of the pool of storage units by:

receiving, by each of the storage units of the first pool of storage units from one or more storage units of the pool of storage units, the changed weighting factor, wherein the one or more storage units of the pool of storage units determines the changed weighting factor based on a change to memory capabilities of the one or more storage units of the pool of storage units.

10. The non-transitory computer readable storage medium of claim 8, wherein the one or more processing modules functions to execute the operational instructions stored by the at least one memory section to cause the one or more computing devices of the DSN to the detect the change to the weighting factor of the pool of storage units by:

determining, by a storage unit of the first pool of storage units, a change in memory capabilities of the storage unit; and

generating, by the storage unit of the first pool of storage units, the changed weighting factor based on the change in memory capabilities.

11. The non-transitory computer readable storage medium of claim 8 further comprises:

the at least one memory section stores further operational instructions that, when executed by the one or more processing modules, causes the one or more computing devices of the DSN to;

delete, by each of the storage units of the first pool of storage units, the respective encoded data slice after successful transfer to the corresponding storage unit of the one pool of storage units.

12. The non-transitory computer readable storage medium of claim 8 further comprises:

the at least one memory section stores further operational instructions that, when executed by the one or more processing modules, causes the one or more computing devices of the DSN to;

when the one pool of storage units is the first pool of storage units, maintain, by each of the storage units of the first pool of storage units, storage of the respective encoded data slice.

13. The non-transitory computer readable storage medium of claim 8, wherein the one or more processing modules functions to execute the operational instructions stored by the at least one memory section to cause the one or more computing devices of the DSN to calculate the updated plurality of storage pool scores by:

performing a plurality of deterministic functions based on an identifier of the respective encoded data slice of the set of encoded data slices and a plurality of resource identifiers corresponding to each pool of storage units of the plurality of pools of storage units to produce a plurality of deterministic resultants;

normalizing the plurality of deterministic resultants to produce a plurality of normalized resultants; and

performing a plurality of weighting functions on the plurality of normalized resultants based on a plurality of weighting factors corresponding to the plurality of pools of storage units to produce the updated plurality of storage pool scores.

14. The non-transitory computer readable storage medium of claim 8 further comprises:

the first pool of storage units including one or more storage units; and

the one pool of storage units including another one or more storage units.