Distributed storage network with replication control and methods for use therewith

• US 9,565,252 B2
• Filed: 05/27/2014
• Issued: 02/07/2017
• Est. Priority Date: 07/31/2013
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Kazi, Asimuddin
• Primary Examiner(s): Gu, Shawn X
• Application Number:
  US14/287,464
• Publication Number:
  US 20150039827A1
• Time in Patent Office: 987 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/07 Responding to the occurrence of a fault, e.g. fault tolerance
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 11/1092 Rebuilding, e.g. when physically replacing a failing disk
• CPC Class Codes: G06F 11/1448 Management of the data involved in backup or backup restore
• CPC Class Codes: G06F 11/1458 Management of the backup or restore process
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 2209/5017 Task decomposition
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0646 Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0668 adopting a particular infrastructure
• 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 3/0683 Plurality of storage devices
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/5066 Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs mappping at compile time, see G06F8/451
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

A method includes encoding input data into a plurality of slices. The plurality of slices are sent to a first plurality of distributed storage and task execution units for storage, the first plurality of distributed storage and task execution units being located at a corresponding first plurality of sites. Write slice data is received from the first plurality of distributed storage and task execution units. The method determines when replication is to be applied to the plurality of slices. When replication is to be applied to the plurality of slices, a second plurality of distributed storage and task execution units are selected, a plurality of replicated slices corresponding to the plurality of slices are generated, and the plurality of replicated slices are sent to the second plurality of distributed storage and task execution units.

Claims

1. A method for execution by one or more processing modules of one or more computing devices of a dispersed storage network (DSN), the method comprises:

encoding input data into a plurality of slices;

sending the plurality of slices to a first plurality of distributed storage and task execution units for storage, the first plurality of distributed storage and task execution units being located at a corresponding first plurality of sites;

receiving write slice data from the first plurality of distributed storage and task execution units;

determining, based on the received write slice data, when one or more unfavorable write slice responses have been received from one or more distributed storage and task execution units of a site of the first plurality of sites;

when one or more unfavorable write slice responses have been received, determining when replication is to be applied to slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site;

selecting a second one or more distributed storage and task execution units;

generating replicated slices corresponding to the slices sent to the one or more distributed storage and task execution units of the site; and

sending the replicated slices to the second one or more distributed storage and task execution units.

2. The method of claim 1 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site is based on at least one of:

analyzing write slice responses, a requester identification, a data identification, a data type indication, a vault identification, and a replication mode predetermination.

3. The method of claim 1, wherein determining when one or more unfavorable write slice responses have been received includes analyzing write slice responses to determine when at least one storage error occurred.

4. The method of claim 1, wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of storage errors;

and further determining when the number of storage errors compares unfavorably to a replication threshold.

5. The method of claim 1, wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of favorable write slice responses received and further determining when the number of favorable write slice responses compares unfavorably to a replication threshold.

6. The method of claim 1 wherein the second one or more distributed storage and task execution units are selected to correspond to at least one site that is disassociated from the first plurality of sites.

7. The method of claim 1 wherein the second one or more distributed storage and task execution units are selected based on at least one of:

a predetermined selection, a column availability, a reliability metric, a storage requirement associated with the plurality of slices, and one or more sites associated with the second one or more distributed storage and task execution units.

8. A dispersed storage and task (DST) processing unit comprises:

at least one module, when operable within a computing device, that causes the computing device to;

encode input data into a plurality of slices;

send the plurality of slices to a first plurality of distributed storage and task execution units for storage, the first plurality of distributed storage and task execution units being located at a corresponding first plurality of sites;

receive write slice data from the first plurality of distributed storage and task execution units;

determine, based on the received write slice data, when one or more unfavorable write slice responses have been received from one or more distributed storage and task execution units of a site of the first plurality of sites;

when one or more unfavorable write slice responses have been received, determine when replication is to be applied to slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site;

select a second one or more distributed storage and task execution units;

generate replicated slices corresponding to the slices sent to the one or more distributed storage and task execution units of the site; and

send the replicated slices to the second one or more distributed storage and task execution units.

9. The DST processing unit of claim 8 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site is based on at least one of:

analyzing write slice responses, a requester identification, a data identification, a data type indication, a vault identification, and a replication mode predetermination.

10. The DST processing unit of claim 8 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine when at least one storage error occurred.

11. The DST processing unit of claim 8 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of storage errors and further determining when the number of storage errors compares unfavorably to a replication threshold.

12. The DST processing unit of claim 8 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of favorable write slice responses and further determining when the number of favorable write slice responses compares unfavorably to a replication threshold.

13. The DST processing unit of claim 8 wherein the second one or more distributed storage and task execution units are selected to correspond to at least one site that is disassociated with the first plurality of sites.

14. The DST processing unit of claim 8 wherein the second one or more distributed storage and task execution units are selected based on at least one of:

a predetermined selection, a column availability, a reliability metric, a storage requirement associated with the plurality of slices, and one or more sites associated with the second one or more distributed storage and task execution units.

15. 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;

encode input data into a plurality of slices;

send the plurality of slices to a first plurality of distributed storage and task execution units for storage, the first plurality of distributed storage and task execution units being located at a corresponding first plurality of sites;

receive write slice data from the first plurality of distributed storage and task execution units;

determine, based on the received write slice data, when one or more unfavorable write slice responses have been received from one or more distributed storage and task execution units of a site of the first plurality of sites;

when one or more unfavorable write slice responses have been received, determine when replication is to be applied to slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site;

select a second one or more distributed storage and task execution units;

generate replicated slices corresponding to the slices sent to the one or more distributed storage and task execution units of the site; and

send the replicated slices to the second one or more distributed storage and task execution units.

16. The non-transitory computer readable storage medium of claim 15 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site is based on at least one of:

analyzing write slice responses, a requester identification, a data identification, a data type indication, a vault identification, and a replication mode predetermination.

17. The non-transitory computer readable storage medium of claim 15 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine when at least one storage error occurred.

18. The non-transitory computer readable storage medium of claim 15 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of storage errors and to determine when the number of storage errors compares unfavorably to a replication threshold.

19. The non-transitory computer readable storage medium of claim 15 wherein determining when replication is to be applied to the slices of the plurality of slices sent to the one or more distributed storage and task execution units of the site includes analyzing write slice responses to determine a number of favorable write slice responses and further determining when the number of favorable write slice responses compares unfavorably to a replication threshold.

20. The non-transitory computer readable storage medium of claim 15 wherein the second one or more distributed storage and task execution units are selected based on at least one of:

a predetermined selection, a column availability, a reliability metric, a storage requirement associated with the plurality of slices, and one or more sites associated with the second one or more distributed storage and task execution units.