Scalable Storage Protection

• US 20140064048A1
• Filed: 11/29/2012
• Published: 03/06/2014
• Est. Priority Date: 09/04/2012
• Status: Active Grant

• Current Assignee: Seagate Technology LLC (Seagate Technology Holdings Plc)
• Original Assignee: LSI Corporation (Broadcom, Inc.)
• Inventors: Cohen, Earl T., Quinn, Robert F.
• Granted Patent: US 9,613,656 B2
• Time in Patent Office: Days
• US Class Current: 369/47.15
• CPC Class Codes: G06F 11/1076 Parity data used in redundant arrays of independent storages, e.g. in RAID systems
• CPC Class Codes: G06F 12/0842 for multiprocessing or multitasking
• CPC Class Codes: G06F 2211/1028 Distributed, i.e. distributed RAID systems with parity
• CPC Class Codes: G06F 2212/62 Details of cache specific to multiprocessor cache arrangements
• CPC Class Codes: G06F 3/0607 by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
• CPC Class Codes: G06F 3/0613 in relation to throughput
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/0629 Configuration or reconfiguration of storage systems
• CPC Class Codes: G06F 3/065 Replication mechanisms
• 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 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0689 Disk arrays, e.g. RAID, JBOD
• CPC Class Codes: G11B 20/1803 by redundancy in data representation

Abstract

The disclosure is directed to protecting data of a scalable storage system. A scalable storage system includes a plurality of nodes, each of the nodes having directly-attached storage (DAS), such as one or more hard-disk drives and/or solid-state disk drives. The nodes are coupled via an inter-node communication network, and a substantial entirety of the DAS is globally accessible by each of the nodes. The DAS is protected utilizing intra-node protection to keep data stored in the DAS reliable and globally accessible in presence of a failure within one of the nodes. The DAS is further protected utilizing inter-node protection to keep data stored in the DAS reliable and globally accessible if at least one of the nodes fails.

Claims

1. A storage system, comprising a plurality of processing nodes in communication with one another, each processing node including:

a plurality of disks;

at least one host, the at least one host configured to write data to a selected disk of the plurality of disks;

a local redundancy computation unit configured to determine local redundant data utilizing the data written to the selected disk by the at least one host, the local redundancy computation unit further configured to store the local redundant data on at least one disk of the plurality of disks;

a delta computation unit configured to determine delta data utilizing the data written to the selected disk by the at least one host, the delta computation unit further configured to send the determined delta data to at least one other processing node; and

a global redundancy computation unit configured to receive delta data from at least one other of the processing nodes, the global redundancy computation unit further configured to determine global redundant data utilizing the received delta data, the global redundancy computation unit further configured to store the global redundant data on at least one disk of the plurality of disks.

2. The system of claim 1, wherein the local redundancy computation unit is further configured to recover the data written to the selected disk utilizing the local redundant data when the selected disk fails.

3. The system of claim 1, wherein the global redundancy computation unit is further configured to recover data of the at least one other processing node utilizing the global redundant data when the at least one other processing node fails.

4. The system of claim 1,

wherein the local redundant data is first local redundant data,

wherein the local redundancy computation unit is further configured to determine second local redundant data utilizing the global redundant data, and

wherein the local redundancy computation unit is further configured to store the second local redundant data on at least one disk of the plurality of disks.

5. The system of claim 4,

wherein the local redundancy computation unit is further configured to recover the data written to the selected disk utilizing the local redundant data when the selected disk fails,

wherein the global redundancy computation unit is further configured to recover data of the at least one other processing node utilizing the global redundant data when the at least one other processing node fails, and

wherein the local redundancy computation unit is further configured to recover the global redundant data utilizing the second local redundant data when the at least one disk storing the global redundant data fails.

6. The system of claim 1, wherein the plurality of processing nodes includes a first set of disks of the pluralities of disks among the processing nodes protected via a first global coding type and a second set of disks of the pluralities of disks among the processing nodes protected via a second global coding type, wherein the first global coding type is different from the second global coding type.

7. The system of claim 6, wherein the first set of disks includes at least one disk of a first processing node of the plurality of processing nodes and at least one disk of a second processing node of the plurality of processing nodes.

8. The system of claim 1, wherein the local redundancy computation unit is further configured to process data utilizing a first erasure-correcting code type, wherein the global redundancy computation unit is further configured to process data utilizing a second erasure-correcting code type, and wherein the first erasure-correcting code type is different from the second erasure-correcting code type.

9. A storage system, comprising a plurality of processing nodes in communication with one another, each processing node including:

a plurality of disks;

at least one host, the at least one host configured to write data to a selected disk of the plurality of disks; and

a controller in communication with the plurality of disks, the controller configured to;

determine local redundant data utilizing the data written to the selected disk;

store the local redundant data on at least one disk of the plurality of disks;

determine delta data utilizing the data written to the selected disk;

send the determined delta data to at least one other of the processing node;

receive delta data from at least one other of the processing nodes;

determine global redundant data utilizing the received delta data; and

store the global redundant data on at least one disk of the plurality of disks.

10. The system of claim 9, wherein the controller is further configured to:

recover the data written to the selected disk utilizing the local redundant data when the selected disk fails; and

recover data of the at least one other processing node utilizing the global redundant data when the at least one other processing node fails.

11. The system of claim 10,

wherein the local redundant data is first local redundant data, and

wherein the controller is further configured to:

determine second local redundant data utilizing the global redundant data;

store the second local redundant data on at least one disk of the plurality of disks; and

recover the global redundant data utilizing the second local redundant data when the at least one disk storing the global redundant data fails.

12. The system of claim 9, wherein the plurality of processing nodes includes a first set of disks of the pluralities of disks among the processing nodes protected via a first global coding type and a second set of disks of the pluralities of disks among the processing nodes protected via a second global coding type, wherein the first global coding type is different from the second global coding type.

13. The system of claim 12, wherein the first set of disks includes at least one disk of a first processing node of the plurality of processing nodes and at least one disk of a second processing node of the plurality of processing nodes.

14. The system of claim 9, wherein the controller is further configured to:

determine the local redundant data utilizing a first erasure-correcting code type; and

determine the global redundant data utilizing a second erasure-correcting code type, wherein the first erasure-correcting code type is different from the second erasure-correcting code type.

15. A method of storage protection, comprising:

writing data to a selected disk of a plurality of disks of a first processing node of a plurality of processing nodes, the plurality of processing nodes being in communication with one another;

determining local redundant data utilizing the data written to the selected disk;

storing the local redundant data on at least one disk of the plurality of disks;

determining first delta data utilizing the data written to the selected disk;

sending the first delta data to at least one other processing node;

receiving second delta data from at least one other processing node;

determining global redundant data utilizing the second delta data; and

storing the global redundant data on at least one disk of the plurality of disks.

16. The method of claim 15, wherein the method further includes:

recovering the data written to the selected disk utilizing the local redundant data when the selected disk fails; and

recovering data of the at least one other processing node utilizing the global redundant data when the at least one other processing node fails.

17. The method of claim 16,

wherein the local redundant data is first local redundant data, and

wherein the method further includes:

determining second local redundant data utilizing the global redundant data;

storing the second local redundant data on at least one disk of the plurality of disks; and

recovering the global redundant data utilizing the second local redundant data when the at least one disk storing the global redundant data fails.

18. The method of claim 15, wherein the method further includes:

protecting a first set of disks of the processing nodes utilizing a first global coding type; and

protecting a second set of disks of the processing nodes utilizing a second global coding type, wherein the first global coding type is different from the second global coding type.

19. The system of claim 18, wherein the first set of disks includes at least one disk of the first processing node and at least one disk of a second processing node of the plurality of processing nodes.

20. The method of claim 15, wherein the method further includes:

determining the local redundant data utilizing a first erasure-correcting code type; and

determining the global redundant data utilizing a second erasure-correcting code type, wherein the first erasure-correcting code type is different from the second erasure-correcting code type.