Allocating RAID storage volumes across a distributed network of storage elements

Patent metadata

Field	Value
Publication number	US-9641615-B1
Application number	US-201414231282-A
Country	US
Kind code	B1
Filing date	Mar 31, 2014
Priority date	Mar 31, 2014
Publication date	May 2, 2017
Grant date	May 2, 2017

Abstract

A distributed network of storage elements (DNSE) is provided in which the physical capacity of each drive is split into a set of equal sized logical splits which are individually protected within the DNSE using separate RAID groups. To reduce restoration latency, members of the RAID groups having a member in common on a given drive are spread within the DNSE to minimize the number of sets of drives within the DNSE that have RAID members in common. By causing the splits to be protected by RAID groups, restoration of the splits may occur in parallel involving multiple drives within the DNSE. By minimizing the overlap between RAID members on various drives, failure of a given drive will not require multiple reads from another drive in the DNSE. Likewise, spare splits are distributed to enable write recovery to be performed in parallel on multiple drives within the DNSE.

First claim

What is claimed is:

1. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of a first of the storage elements using at least two RAID groups, each of the at least two RAID groups encompassing a plurality of other RAID members stored on splits of other storage elements of the distributed network of storage elements; and
distributing the other RAID members of the at least two RAID groups within the distributed network of storage elements;
wherein other RAID members of a first of the at least two RAID groups and other RAID members of the second of the at least two RAID groups are not commonly assigned to the same storage element.

2. The method of claim 1 , wherein each of the logical splits comprise a subset of the total storage volume of each of the storage elements.

3. The method of claim 1 , wherein the logical splits are of uniform size within each storage element of the distributed network of storage elements.

4. The method of claim 1 , wherein the RAID protection is provided by RAID groups, each RAID group providing RAID protection for at least one of the splits of a given storage element.

5. The method of claim 4 , wherein a separate RAID group is used to provide protection for each of the splits of the given storage element.

6. The method of claim 5 , wherein the step of distributing the other RAID members within the distributed network of storage element causes members of each of the separate RAID groups to be stored on sets of distinct storage elements within the distributed network of storage elements.

7. The method of claim 1 , further comprising grouping storage elements into at least two separate partitions, wherein each said partition may comprise one or more RAID types and wherein each partition may be treated as a separate distributed network of storage elements.

8. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of the storage elements; and
distributing the RAID protection within the distributed network of storage elements to minimize overlap between RAID Groups on at least two storage elements;
wherein different RAID protection schemes are used to provide RAID protection for different splits of a given storage element.

9. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of the storage elements; and
distributing the RAID protection within the distributed network of storage elements to minimize overlap between RAID Groups on at least two storage elements;
wherein the step of distributing the RAID protection within the distributed network of storage elements is implemented using a set of heuristics defining placement rules for members of the RAIDs.

10. The method of claim 9 , wherein the rules include a first rule prohibiting placement of two RAID members on a given storage element and a second rule requiring placement of RAID members in separate hardware protection zones within the distributed network of storage elements, the hardware protection zones comprising subsets of storage elements physically separated and supported by independent power supplies and network infrastructure.

11. The method of claim 10 , wherein the rules further comprise a third rule seeking to maintain RAID members of a given RAID group at a same device physical offset within a subset of storage members providing storage for the RAID group.

12. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of the storage elements; and
distributing the RAID protection within the distributed network of storage elements to minimize overlap between RAID Groups on at least two storage elements;
wherein the step of distributing the RAID protection within the distributed network of storage elements is implemented by defining a matrix based on a set of splits within a first hardware fault zone, and replicating the matrix into other fault zones until all RAIDs have a complete set of members.

13. The method of claim 12 , wherein the step of replicating the matrix comprises performing a sequence of matrix operations to define unique matrices in each of the other fault zones to cause members of each of the separate RAID groups to be stored on sets of distinct storage elements within the distributed network of storage element.

14. The method of claim 13 , wherein the sequence of matrix operations comprises shifting rows of the matrix or transposing aspects of the matrix.

15. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of the storage elements;
distributing the RAID protection within the distributed network of storage elements to minimize overlap between RAID Groups on at least two storage elements; and
combining two or more RAID groups to enable storage of erasure codes having a split drive fault span which exceeds a size of a single RAID group.

16. A method of allocating RAID storage volumes across a distributed network of storage elements, the method comprising the steps of:
defining at least two logical splits on each of the storage elements;
providing RAID protection for the splits of the storage elements;
distributing the RAID protection within the distributed network of storage elements to minimize overlap between RAID Groups on at least two storage elements; and
distributing spare capacity within the distributed network of storage element by defining splits to be used to store data in the event of failure of a storage element within the distributed network of storage elements.

17. A distributed network of storage elements, comprising:
a processor; and
instructions stored on a non-transitory tangible computer-readable media that, when executed, cause the processor to:
define at least two logical splits on each of the storage elements;
provide RAID protection for the splits of a first of the storage elements using at least two RAID groups, each of the at least two RAID groups encompassing a plurality of other RAID members stored on splits of other storage elements of the distributed network of storage elements; and
distribute the other RAID members of the at least two RAID groups within the distributed network of storage elements;
wherein other RAID members of a first of the at least two RAID groups and other RAID members of the second of the at least two RAID groups are not commonly assigned to the same storage element.

18. A distributed network of storage elements, comprising:
a processor; and
instructions stored on a non-transitory tangible computer-readable media that, when executed, cause the processor to:
define at least two logical splits on each of the storage elements;
provide RAID protection for the splits of the storage elements;

distribute the RAID protection within the distributed network of s

Assignees

• Emc Corp
• Emc Ip Holding Co Llc

Inventors

• Robins Edward
• Granlund Kevin E
• Pai Seema
• Malkevich Evgeny
• Ives Stephen Richard
• Raz Roii
• Bejerano Barak

Classifications

• H04L67/1097 Primary

  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 title

• G06F11/2094

  Redundant storage or storage space (G06F11/2056 takes precedence) · CPC title

• G06F11/1076

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title

• G06F11/1092

  Rebuilding, e.g. when physically replacing a failing disk · CPC title

• G06F3/0644

  Management of space entities, e.g. partitions, extents, pools · CPC title