Heterogeneous mapped redundant array of independent nodes for data storage

Patent metadata

Field	Value
Publication number	US-11435910-B2
Application number	US-201916670715-A
Country	US
Kind code	B2
Filing date	Oct 31, 2019
Priority date	Oct 31, 2019
Publication date	Sep 6, 2022
Grant date	Sep 6, 2022

Abstract

A mapped redundant array of independent nodes (mapped RAIN) for data storage is disclosed. A mapped RAIN cluster can be allocated on top of one or more real data clusters, wherein the real clusters can comprise storage devices of different storage capacities. Mapping of data storage locations for a mapped RAIN cluster to real storage devices can be based on an affinity value determined for pairs of real nodes of the real data clusters. A normalized affinity can be employed to enable allocation of real storage to mapped nodes of mapped clusters that can be based on the heterogeneous capacities of the storage devices. This can provide improved data availability and data recovery over other techniques where heterogeneity of hardware can make efficient resource allocation a non-trivial task. The disclosed subject matter can facilitate more efficient allocation of Mapped RAINs in a heterogeneous cluster storage construct.

First claim

What is claimed is:

1. A system, comprising:
a processor; and
a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
determining a first mapped cluster scheme based on a real cluster storage system criterion for a real cluster storage system, wherein the first mapped cluster scheme is in accord with a data loss prevention rule, wherein the data loss prevention rule prohibits a mapping scheme from resulting in a mapped cluster storing first data via a first storage device of a first real node and further storing second data that is redundant to the first data via a second storage device of the first real node, wherein the real cluster storage system comprises the first storage device and the second storage device, and wherein the first storage device and the second storage device have different storage capacities;
allocating first storage space of the real cluster storage system as a first mapped cluster based on the first mapped cluster scheme;
allocating second storage space of the real cluster storage system as a second mapped cluster based on a second mapped cluster scheme, wherein the second mapped cluster scheme is in accord with the data loss prevention rule, and wherein the first mapped cluster and the second mapped cluster exist contemporaneously; and
facilitating a data operation corresponding to a data storage location comprised in the real cluster storage system according to the first mapped cluster based on the first mapped cluster scheme.

2. The system of claim 1 , wherein the real cluster storage system comprises 1 to L real data storage clusters.

3. The system of claim 2 , wherein a real data storage cluster of the 1 to L real data storage clusters comprises 1 to N hardware data storage nodes, wherein a hardware data storage node of the 1 to N hardware storage nodes comprises 1 to M data storage devices, and wherein the data storage location is comprised in a data storage device of the 1 to M data storage devices of the hardware data storage node of the 1 to N hardware data storage devices of the real data storage cluster of the 1 to L data storage clusters.

4. The system of claim 3 , wherein the first storage device is comprised in the 1 to M data storage devices of the hardware data storage node of the 1 to N hardware data storage devices of the real data storage cluster of the 1 to L data storage clusters.

5. The system of claim 3 , wherein the second storage device is comprised in the 1 to M data storage devices of the hardware data storage node of the 1 to N hardware data storage devices of the real data storage cluster of the 1 to L data storage clusters.

6. The system of claim 3 , wherein the second storage device is comprised in the 1 to M data storage devices of another hardware data storage node of the 1 to N hardware data storage devices of the real data storage cluster of the 1 to L data storage clusters.

7. The system of claim 3 , wherein the second storage device is comprised in the 1 to M data storage devices of the hardware data storage node of the 1 to N hardware data storage devices of another real data storage cluster of the 1 to L data storage clusters.

8. The system of claim 1 , wherein the allocating the first storage space of the real cluster is based on an overall amount of storage of the real cluster storage system.

9. The system of claim 1 , wherein the allocating the first storage space of the real cluster is based on an affinity matrix corresponding to the real cluster storage system.

10. The system of claim 1 , wherein the operations further comprise, ranking affinities of possible mapped cluster schema comprising the first mapped cluster scheme based on a uniformity of the affinities for each possible mapped cluster scheme of the possible mapped cluster schema.

11. The system of claim 1 , wherein the operations further comprise, ranking affinities of possible mapped cluster schema comprising the first mapped cluster scheme based on affinity magnitudes within each possible mapped cluster scheme of the possible mapped cluster schema.

12. A method, comprising:
allocating, by a system comprising a processor and a memory, first storage space of a real cluster storage system as a first mapped cluster according to a determined first mapped cluster scheme based on a real cluster storage system criterion, wherein the first mapped cluster scheme is in accord with a data loss prevention rule, wherein the data loss prevention rule prohibits a mapping scheme from resulting in a mapped cluster storing first data via a first storage device of a first real node and further storing second data that is redundant to the first data via a second storage device of the first real node, wherein the real cluster storage system comprises the first storage device of a first capacity and the second storage device of a second capacity, and wherein the first capacity and the second capacity are different capacities;
allocating, by the system, second storage space of the real cluster storage system as a second mapped cluster according to a second mapped cluster scheme, wherein the second mapped cluster scheme is in accord with the data loss prevention rule, and wherein the first mapped cluster and the second mapped cluster are supported by the system contemporaneously; and
causing, by the system, a data operation to occur in the first storage space of the real cluster storage system according to the first mapped cluster and based on the first mapped cluster schema.

13. The method of claim 12 , wherein the allocating the first storage space comprises allocating the first storage device that is comprised in a first hardware data storage node of the real cluster storage system.

14. The method of claim 13 , wherein the allocating the first storage space comprises allocating the second storage device that is comprised in the first hardware data storage node of the real cluster storage system.

15. The method of claim 13 , wherein the allocating the first storage space comprises allocating the second storage device that is comprised in a second hardware data storage node of the real cluster storage system, and wherein the second hardware data storage node is a different hardware data storage node than the first hardware data storage node.

16. The method of claim 12 , wherein the allocating the first storage space is based on an affinity matrix corresponding to the real cluster storage system.

17. A non-transitory computer-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
determining a first mapped cluster scheme based on a first request for first storage space in a real cluster storage system and based on an affinity score for two real nodes of the real cluster storage system, wherein the first mapped cluster scheme is in accord with a data loss prevention rule, wherein the data loss prevention rule prohibits a mapping scheme from resulting in a mapped cluster storing first data via a first storage device of a first real node and further storing second data that is redundant to the first data via a second storage device of the first real node, wherein the real cluster storage system comprises the first storage device of a first capacity that is a different capacity than a second capacity of the second storage device of the real cluster storage system;
allocating the first storage space of the real cluster storage system as a first mapped cluster, according to the first mapped cluster scheme, based on a criterion o

Assignees

• Emc Ip Holding Co Llc

Inventors

• Danilov Mikhail
• Altaye Yohannes

Classifications

• G06F3/0604

  Improving or facilitating administration, e.g. storage management · CPC title

• G06F3/061

  Improving I/O performance · CPC title

• G06F3/064

  Management of blocks · CPC title

• G06F3/0608

  Saving storage space on storage systems · CPC title

• G06F3/0631 Primary

  by allocating resources to storage systems · CPC title