US 8,010,829 B1Granted

Distributed hot-spare storage in a storage cluster

AssigneeAmerican Megatrends, Inc.

InventorsParesh Chatterjee, Ajit Narayanan, Anandh Mahalingam, Srikumar Subramanian

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method, system, apparatus, and computer-readable medium are described for providing distributed hot-spare storage in a redundant storage cluster. According to one method, a portion of the unutilized space on the storage cluster is utilized as a distributed hot-spare storage node. Through this mechanism, a redundant storage cluster with N storage nodes may be contracted to a redundant array with N−1 nodes. Thin provisioning and intelligent data placement may also be utilized to implement the distributed hot-spare storage node. Through repeated application of such methods and systems, the failure of any storage node or the sequential failure of multiple storage nodes within a redundant storage cluster results in the recreation of the cluster as a redundant storage array with one fewer node, but with the same redundancy.

Claims13

Dependent claims

A method for providing distributed hot-spare storage in a storage cluster, the method comprising:

detecting a failure of a storage server computer in a redundant storage cluster having N active storage server computers, wherein N is greater than or equal to three;
and
reforming the storage cluster as a redundant storage cluster having N−1 active storage server computers in response to detecting the failure by copying mirrored data of the data stored on the failed storage server computer from the remaining active storage server computers to a distributed hot-spare storage node comprising a portion of unutilized storage space distributed across the remaining active storage server computers, wherein copying the mirrored data comprises:
creating exception tables for each of the remaining active storage server computers of the storage cluster, each exception table comprising positive tabs identifying areas of the associated remaining active storage server computer that need to be copied to the distributed hot-spare storage node and negative tabs identifying areas of the distributed hot-spare storage node that need to be migrated from the other remaining active storage server computers;
and
copying the data from the remaining active storage server computers to the distributed hot-spare storage node according to the contents of the exception tables.

3 more elements

A computer storage medium having computer-executable instructions stored thereon which, when executed by a storage server computer in a redundant storage cluster having N active storage server computers, wherein N is three or greater, cause the storage server computer to:

detect a failure of a storage server computer in the storage cluster;
and
in response to detecting the failure, reform the storage cluster as a redundant storage cluster having N−1 active storage server computers by copying mirrored data of the data on the failed storage server computer from the remaining active storage server computers of the storage cluster to a distributed hot-spare storage node comprising a portion of the unutilized storage space of the remaining active storage server computers of the storage cluster, wherein copying the mirrored data comprises:
creating exception tables for each of the remaining active storage server computers of the storage cluster, each exception table comprising positive tabs identifying areas of the associated remaining active storage server computer that need to be copied to the distributed hot-spare storage node and negative tabs identifying areas of the distributed hot-spare storage node that need to be migrated from the other remaining active storage server computers;
and
migrating data from the remaining active storage server computers to the distributed hot-spare storage node according to the contents of the exception tables.

3 more elements

A system for providing a distributed hot-spare storage node in a storage cluster, the system comprising:

two or more storage server computers that together comprise a redundant storage cluster and a distributed hot-spare storage node, wherein the distributed hot-spare storage node comprises a portion of the unutilized storage space on the storage server computers and wherein the storage cluster is operative to detect the failure of one of the storage server computers and to reform itself following the failure as a redundant storage cluster having one less storage server computer utilizing the distributed hot-spare storage node, wherein data stored on the storage cluster is mirrored on two of the storage server computers, and wherein reforming the storage cluster comprises copying data that was mirrored on the failed storage server computer to the distributed hot-spare storage node, wherein copying the data comprises:
creating exception tables for each of the storage server computers of the storage cluster, each exception table comprising positive tabs identifying areas of the associated storage server computer that need to be copied to the distributed hot-spare storage node and negative tabs identifying areas in the distributed hot-spare storage node that need to be migrated from the other storage server computers;
and
migrating data from the storage server computers to the distributed hot-spare storage node according to the contents of the exception tables.

1 more element

Dependencies are inferred from the claim text.

Facts

Application: 11/551,311Filed 20 Oct 2006 · us provisional application
Priority: 20 Oct 2005
Granted: 30 Aug 2011
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 11/2061
By mirroring: combined with de-clustering of data
G06F 11/2094
Where persistent mass storage functionality or persistent mass storage control functionality is redundant: redundant storage or storage space
G06F 11/2082
By mirroring: data synchronisation
G06F 2211/1028
Indexing scheme relating to G06F11/1076: distributed, i.e. distributed RAID systems with parity

Family

Application60/728,453Us provisional application · filed 20 Oct 2005
Application60/728,667Us provisional application · filed 20 Oct 2005
Application60/728,680Us provisional application · filed 20 Oct 2005
Application60/728,666Us provisional application · filed 20 Oct 2005
US 8,010,829 B1This patent

From the US filing history. Foreign family members aren’t listed.