Writing data slices to ready and non-ready distributed storage units in a distributed storage network

• US 8,918,534 B2
• Filed: 05/11/2010
• Issued: 12/23/2014
• Est. Priority Date: 09/29/2009
• Status: Active Grant

• Current Assignee: Pure Storage, Inc.
• Original Assignee: Cleversafe Incorporated (International Business Machines Corporation)
• Inventors: Baptist, Andrew
• Primary Examiner(s): Murray, Daniel C
• Application Number:
  US12/777,864
• Publication Number:
  US 20110078277A1
• Time in Patent Office: 1,687 Days
• Field of Search: 709/217, 709/232, 707/812, 707/827, 711/114
• US Class Current: 709/232
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 2211/1011 Clustered RAID, i.e. clustered or de-clustered RAID where data and parity are spread over more disks than blocks in a parity group
• CPC Class Codes: G06F 3/0617 in relation to availability
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• 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 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• 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]
• CPC Class Codes: H04N 21/231 Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
• CPC Class Codes: H04N 21/2405 Monitoring of the internal components or processes of the server, e.g. server load allocation of resources in multiprogramming arrangements G06F9/50; performance measurement of computer activity G06F11/34
• CPC Class Codes: H04N 21/442 Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00

Abstract

A distributed storage network includes a distributed storage processing unit, which generates multiple data slices from a single data segment, and multiple different storage units to store the data slices. Each data slice is assigned to a particular storage unit for storage. The distributed storage processing unit determines which of the storage units are in a ready state, and sends data slices to the ready storage units. Data slices assigned to storage units that are not in a ready state are temporarily stored in a temporary memory, e.g. cache memory, until the storage unit becomes ready. If the intended storage unit remains in a non-ready status for too long, the slices stored in cache memory can be sent to a substitute storage unit, or discarded and reconstructed at a later time.

Claims

1. A method of operating a distributed storage processing unit, the method comprising:

creating a plurality of data slices from a data segment in accordance with an error coding function, wherein n number of data slices are created when error coding the data segment and wherein at least a threshold number k of the n data slices are needed to reconstruct the data segment, where k is less than n, in which n data slices are to be stored in n storage units of a distributed storage network;

identifying the n storage units for respective ones of the n storage units to store a different data slice of the n data slices;

determining which of the n storage units are in a ready status, wherein a ready status indicates a readiness to receive respective data slices for storage;

when all n storage units are in the ready status, sending n data slices to the n storage units for storage in the n storage units;

when less than k storage units are in the ready status, not sending the data slices to the storage units; and

when less than n, but more than or equal to k storage units are in the ready status, sending respective data slices to respective storage units that are in the ready status for storage and temporarily storing in a temporary memory, data slice or slices destined to storage unit or units in a non-ready status.

2. The method of claim 1, further comprising:

discarding the temporarily stored data slices in accordance with a discard policy.

3. The method of claim 1, further comprising:

determining that a particular storage unit in the non-ready status has changed to the ready status; and

moving a corresponding temporarily stored data slice from the temporary memory into the particular storage unit now in the ready status.

4. The method of claim 1, further comprising:

determining that a particular storage unit in the non-ready status has remained in the non-ready status longer than a timeout threshold;

selecting a replacement storage unit; and

moving a corresponding temporarily stored data slice from the temporary memory into the replacement storage unit.

5. The method of claim 1, further comprising:

temporarily storing temporarily stored data slices in a common temporary memory for the n storage units.

6. The method of claim 1, further comprising:

temporarily storing temporarily stored data slices in separate temporary memories that are associated with individual storage units.

7. A distributed storage processing unit comprising:

a memory; and

a processor coupled to the memory, wherein the memory stores operational instructions that, when executed by the processor, causes the processor to;

create a plurality of data slices from a data segment in accordance with an error coding function, wherein n number of data slices are created when error coding the data segment and wherein at least a threshold number k of the n data slices are needed to reconstruct the data segment, where k is less than n, in which n data slices are to be stored in n storage units of a distributed storage network;

identify the n storage units for respective ones of the n storage units to store a different data slice of the n data slices;

determine which of the n storage units are in a ready status, wherein a ready status indicates a readiness to receive respective data slices for storage;

when all n storage units are in the ready status, send n data slices to the n storage units for storage in the n storage units;

when less than k storage units are in the ready status, not send the data slices to the storage units; and

when less than n, but more than or equal to k storage units are in the ready status, send respective data slices to respective storage units that are in the ready status for storage and temporarily store in a temporary memory, data slice or slices destined to storage unit or units in a non-ready status.

8. The distributed storage processing unit of claim 7, wherein the processor is operable to discard the temporarily stored data slices in accordance with a discard policy.

9. The distributed storage processing unit of claim 7, wherein the processor is operable to:

determine that a particular storage unit in the non-ready status has changed to the ready status; and

direct movement of a corresponding temporarily stored data slice from the temporary memory into the particular storage unit now in the ready status.

10. The distributed storage processing unit of claim 7, wherein the processor is operable to:

determine that a particular storage unit in the non-ready status has remained in the non-ready status longer than a timeout threshold;

select a replacement storage unit; and

direct movement of a corresponding temporarily stored data slice from the temporary memory into the replacement storage unit.

11. The distributed storage processing unit of claim 7, wherein the processor is operable to direct storage of temporarily stored data slices in a common temporary memory for the n storage units.

12. The distributed storage processing unit of claim 7, wherein the processor is operable to direct storage of temporarily stored data slices in separate temporary memories that are associated with individual storage units.

13. A distributed storage network comprising:

a plurality of distributed storage units, including memory devices, to receive data slices for storage;

a distributed storage processing unit, implementing a hardware processor, to;

create a plurality of data slices from a data segment in accordance with an error coding function, wherein n number of data slices are created when error coding the data segment and wherein at least a threshold number k of the n data slices are needed to reconstruct the data segment, where k is less than n, in which n data slices are to be stored in n storage units of the plurality of distributed storage units;

identify the n storage units for respective ones of the n storage units to store a different data slice of the n data slices;

determine which of the n storage units are in a ready status, wherein a ready status indicates a readiness to receive respective data slices for storage;

when all n storage units are in the ready status, send n data slices to the n storage units for storage in the n storage units;

when less than k storage units are in the ready status, not send the data slices to the storage units; and

when less than n, but more than or equal to k storage units are in the ready status, send respective data slices to respective storage units that are in the ready status for storage and temporarily store in a temporary memory, data slice or slices destined to storage unit or units in a non-ready status.

14. The distributed storage network of claim 13, further comprising:

the distributed storage processing unit to discard the temporarily stored data in accordance with a discard policy.

15. The distributed storage network of claim 13, further comprising:

the distributed storage processing unit to determine that a particular storage unit in the non-ready status has changed to the ready status; and

the distributed storage processing unit to direct movement of a corresponding temporarily stored data slice from the temporary memory into the particular storage unit now in the ready status.

16. The distributed storage network of claim 13, further comprising:

the distributed storage processing unit to;

determine that a particular storage unit in the non-ready status has remained in the non-ready status longer than a timeout threshold;

select a replacement storage unit; and

direct movement of a corresponding temporarily stored data slice from the temporary memory into the replacement storage unit.

17. The distributed storage network of claim 13, wherein the temporary memory is a local memory

associated with the distributed storage processing unit to store temporarily stored data slices for the n storage units.

18. The distributed storage network of claim 13, wherein the temporary memory is comprised of separate distributed memories to store corresponding temporarily stored data slice associated with individual storage units.