Method and apparatus for selectively active dispersed storage memory device utilization

• US 8,281,181 B2
• Filed: 05/12/2010
• Issued: 10/02/2012
• Est. Priority Date: 09/30/2009
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Resch, Jason K.
• Primary Examiner(s): Manoskey, Joseph D
• Application Number:
  US12/778,647
• Publication Number:
  US 20110078503A1
• Time in Patent Office: 874 Days
• Field of Search: 714/6.1, 714/6.2, 714/6.3, 714/6.31, 714/20, 714/42, 714/54, 714/52, 711/154, 711/163
• US Class Current: 714/6.2
• CPC Class Codes: G06F 11/10 Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/2053 where persistent mass storage functionality or persistent mass storage control functionality is redundant error detection or correction in information storage based on relative movement between record carrier and transducer G11B20/18
• CPC Class Codes: G06F 11/2089 Redundant storage control functionality
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/1827 Management specifically adapted to NAS management of storage area networks [SAN] G06F3/067
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0665 at area level, e.g. provisioning of virtual or logical volumes
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 3/068 Hybrid storage device
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

The method begins with a processing unit receiving an encoded slice for storage. The method continues with the processing unit determining whether to store the encoded slice in one of a first set of memory devices or in one of a second set of memory devices based on metadata associated with the encoded slice, wherein the first set of memory devices are continually active and the second set of memory devices are selectively active. The method continues with the processing unit stores the encoded slice in the one of the second set of memory devices when the encoded slice is to be stored in the one of the second set of memory devices. The method continues with the processing unit de-activating the one of the second set of memory devices, in accordance with a deactivation protocol, after storing the encoded slice.

Claims

1. A dispersed storage (DS) unit comprises:

a plurality of memory devices that includes a first set of memory devices that are continually active and a second set of memory devices that are selectively active, wherein the first set of memory devices stores a plurality of first encoded data slices having a rate of retrieval in a first interval retrieval rate range and the second set of memory devices stores a plurality of second encoded data slices having a rate of retrieval in a second interval retrieval rate range, wherein a first encoded data slice of the plurality of first encoded data slices is a first encoded data slice of a first set of encoded data slices and a second encoded data slice of the plurality of second encoded data slices is a first encoded data slice of a second set of encoded data slices, and wherein the first set of encoded data slices is a dispersed storage error encoded representation of a first data segment and the second set of encoded data slices is a dispersed storage error encoded representation of a second data segment; and

a processing unit operable to;

determine when to activate a memory device of the second set;

when the memory device is to be activated, activate the memory device to produce an activated memory device;

retrieve an encoded data slice of the plurality of second encoded data slices from the activated memory device to produce a retrieved encoded data slice;

determine whether the retrieved encoded data slice has an error; and

when the retrieved encoded data slice has an error, initiate a rebuilding function to rebuild the retrieved encoded data slice producing a rebuilt encoded data slice.

2. The DS unit of claim 1, wherein the processing unit further functions to determine when to activate the memory device of the second set based on at least one of:

a retrieval request for the encoded data slice;

elapsed inactive state time of the memory device of the second set;

a command;

an irregular power indicator;

an earthquake indicator;

a bad weather indicator;

a retrieval frequency indicator; and

an indicator to improve the life of the memory device.

3. The DS unit of claim 1, wherein the processing unit further functions to:

determine when to de-activate the memory device; and

when the memory device is to be de-activated, de-activate the memory device to produce a de-activated memory device.

4. The DS unit of claim 3, wherein the processing unit further functions to determine when to de-activate the memory device based on at least one of:

elapsed time since a retrieval request for the encoded data slice;

elapsed time since a store request for the activated memory device;

elapsed active state time of the memory device;

a command;

an irregular power indicator;

an earthquake indicator;

a bad weather indicator;

a retrieval frequency indicator; and

an indicator to improve the life of the memory device.

5. The DS unit of claim 1, wherein the processing unit further functions to determine whether the retrieved encoded data slice has an error by at least one of:

a missing slice test;

an outdated slice revision test;

a slice name comparison to at least one other slice name from a slice name list;

a slice revision comparison to at least one other slice revision from a slice revision list;

a slice name comparison to at least one other slice name from another DS unit;

a slice revision comparison to at least one other slice revision from another DS unit; and

a stored checksum comparison to a re-calculated checksum.

6. The DS unit of claim 1, wherein the processing unit further functions to:

store the rebuilt encoded data slice in the activated memory device; and

de-activate the activated memory device.

7. The DS unit of claim 1, wherein the processing unit further functions to:

when the retrieved encoded data slice does not have an error, determine condition for activating the memory device;

when the condition was a data access request, output, via an interface module, the retrieved encoded data slice and initiate deactivation of the memory device; and

when the condition was verification-based, initiate the deactivation of the memory device.

8. A method for execution by a dispersed storage (DS) unit comprises:

receiving an encoded data slice for storage, wherein the encoded data slice is a first encoded data slice of a set of encoded data slices, and wherein the set of encoded data slices is a dispersed storage error encoded representation of a data segment;

determining whether to store the encoded data slice in one of a first set of memory devices or in one of a second set of memory devices based on metadata associated with the encoded slice, wherein the first set of memory devices are continually active and the second set of memory devices are selectively active;

when the encoded data slice is to be stored in the one of the second set of memory devices, storing the encoded data slice in the one of the second set of memory devices; and

de-activating, in accordance with a deactivation protocol, the one of the second set of memory devices after storing the encoded data slice.

9. The method of claim 8 further comprises:

when the encoded data slice is to be stored in the one of the first set of memory devices, storing the encoded data slice in the one of the first set of memory devices.

10. The method of claim 9 further comprises:

determining whether to transfer the encoded data slice from the one of the first set of memory devices to the one of the second set of memory devices based a data transfer protocol; and

when the encoded data slice is to be transferred;

retrieving the encoded data slice from the one of the first set of memory devices; and

storing the encoded data slice in the one of the second set of memory devices.

11. The method of claim 8 further comprises:

storing the encoded data slice in the one of the first set of memory devices when the encoded data slice has a first retrieval likelihood; and

storing the encoded data slice in the one of the second set of memory devices when the encoded data slice has a second retrieval likelihood.

12. The method of claim 8, wherein the deactivation protocol comprises at least one of:

elapsed time since storing the encoded data slice in the one of the second set of memory devices;

elapsed time since a retrieval request for the encoded data slice;

elapsed active state time of the one of the second set of memory devices;

a command;

an irregular power indicator;

an earthquake indicator;

a bad weather indicator;

a retrieval frequency indicator; and

an indicator to improve the life of the memory device.

13. The method of claim 8, wherein the metadata comprises at least one of:

a data type;

a data size;

a data priority;

a data security index;

a reliability indicator;

a performance indicator;

an estimated storage time;

an estimated time between retrievals; and

a storage requirement.

14. A dispersed storage (DS) unit comprises:

an interface module operable to receive an encoded data slice, wherein the encoded data slice is a first encoded data slice of a set of encoded data slices, and wherein the set of encoded data slices is a dispersed storage error encoded representation of a data segment;

a plurality of memory devices that includes a first set of memory devices that are continually active and a second set of memory devices that are selectively active; and

a processing unit operable to;

determine whether to store the encoded data slice in one of the first set of memory devices or in one of the second set of memory devices based on metadata associated with the encoded data slice;

when the encoded data slice is to be stored in the one of the second set of memory devices, store the encoded data slice in the one of the second set of memory device; and

de-activate, in accordance with a deactivation protocol, the one of the second set of memory devices after storing the encoded data slice.

15. The DS unit of claim 14, wherein the processing unit further functions to:

when the encoded data slice is to be stored in the one of the first set of memory devices, store the encoded data slice in the one of the first set of memory devices.

16. The DS unit of claim 15, wherein the processing unit further functions to:

determine whether to transfer the encoded data slice from the one of the first set of memory devices to the one of the second set of memory devices based a data transfer protocol; and

when the encoded data slice is to be transferred;

retrieve the encoded data slice from the one of the first set of memory devices; and

store the encoded data slice in the one of the second set of memory devices.

17. The DS unit of claim 14, wherein the processing unit further functions to:

store the encoded data slice in the one of the first set of memory devices when the encoded data slice has a first retrieval likelihood; and

store the encoded data slice in the one of the second set of memory devices when the encoded data slice has a second retrieval likelihood.

18. The DS unit of claim 14, wherein the deactivation protocol comprises at least one of:

elapsed time since storing the encoded data slice in the one of the second set of memory devices;

elapsed time since a retrieval request for the encoded data slice;

elapsed active state time of the one of the second set of memory devices;

a command;

an irregular power indicator;

an earthquake indicator;

a bad weather indicator;

a retrieval frequency indicator; and

an indicator to improve the life of the memory device.

19. The DS unit of claim 14, wherein the metadata comprises at least one of:

a data type;

a data size;

a data priority;

a data security index;

a reliability indicator;

a performance indicator;

an estimated storage time;

an estimated time between retrievals; and

a storage requirement.