Netapp, Inc.

Network Appliance, Inc.

Stephen H Strange

Douglas P Doucette

Srinivasan Viswanathan

Rajesh Sundaram

Scott A Schoenthal

Susan M Coatney

Steven S Watanabe

James Leong

Steven Robert Kleiman

Atul Goel

Kayuri Hasmukh Patel

John A Muth

Edward Ramon Zayas

Randal Thelen

Bob Schatz

Dongfeng Li

Kimberly A Malone

Abhijeet Prakash Gole

Alan Rowe

Joydeep Sen Sarma

Douglas W Coatney

Kyle Diggs Sterling

Poonam P Dhavale

R Guy Lauterbach

Tomislav Grcanac

Richard Christopher Fore

A third vote consensus technique enables a first node, i.e., a surviving node, of a two-node cluster to establish a quorum and continue to operate in response to failure of a second node of the cluster. Each node maintains configuration information organized as a cluster database (CDB) which may be changed according to a consensus-based protocol. Changes to the CDB are logged on a third copy file system (TCFS) stored on a local copy of TCFS (L-TCFS). A shared copy of the TCFS (i.e., S-TCFS) may be stored on shared storage devices of one or more storage arrays coupled to the nodes. The local copy of the TCFS (i.e., L-TCFS) represents a quorum vote for each node of the cluster, while the S-TCFS represents an additional 'tie-breaker' vote of a consensus-based protocol. The additional vote may be obtained from the shared storage devices by the surviving node as a third vote to establish the quorum and enable the surviving node to cast two of three votes (i.e., a majority of votes) needed to continue operation of the cluster. That is, the majority of votes allows the surviving node to update the CDB with the configuration information changes so as to continue proper operation of the cluster.

Third vote consensus in a cluster using shared storage devices

A high availability (HA) failover manager maintains data availability of one or more input/output (I/O) resources in a cluster by ensuring that each I/O resource is available (e.g., mounted) on a hosting node of the cluster and that each I/O resource may be available on one or more partner nodes of the cluster if a node (i.e., a local node) were to fail. The HA failover manager (HA manager) processes inputs from various sources of the cluster to determine whether failover is enabled for a local node and each partner node in an HA group, and for triggering failover of the I/O resources to the partner node as necessary. For each I/O resource, the HA manager may track state information including (i) a state of the I/O resource (e.g., mounted or un-mounted); (ii) the partner node(s) ability to service the I/O resource; and (iii) whether a non-volatile log recording I/O requests is synchronized to the partner node(s). The HA manager interacts with various layers of a storage I/O stack to mount and un-mount the I/O resources on one or more nodes of the cluster through the use of well-defined interfaces, e.g., application programming interfaces.

High availability failover manager

The present invention uniquely names storage devices in a global storage environment with hierarchical storage domains. In particular, according to one or more embodiments of the present invention a storage device (e.g., a disk) is connected at a particular location within the global storage environment. That particular location is associated with a path of each of one or more hierarchical storage domains in which the storage device is located. Accordingly, a name is assigned to the storage device that is the path of the hierarchical storage domains in which the storage device is located.

Uniquely naming storage devices in a global storage environment

Methods and systems for a storage environment are provided. For example, one method includes receiving a request from a storage server at an offload engine for reconstructing data lost due to a failed storage device of a parity group having a plurality of storage devices; retrieving data and parity by the offload engine from the parity group storage devices that are operational; determining by the offload engine XOR of the retrieved data and parity; presenting XOR of data and parity by the offload engine to the storage server with context information associated with the retrieved data; and reconstructing lost data by the storage server using the XOR of data and parity and the context information provided by the offload engine.

Methods and systems for offloading RAID parity reconstruction

A data access request to a file system is decomposed into a plurality of lower-level I/O tasks. A logical combination of physical storage components is represented as a hierarchical set of objects. A parent I/O task is generated from a first object in response to the data access request. A child I/O task is generated from a second object to implement a portion of the parent I/O task. The parent I/O task is suspended until the child I/O task completes. The child I/O task is executed in response to an occurrence of an event that a resource required by the child I/O task is available. The parent I/O task is resumed upon an event indicating completion of the child I/O task. Scheduling of any child I/O task is not conditional on execution of the parent I/O task, and a state diagram regulates the child I/O tasks.

Method and apparatus for decomposing I/O tasks in a RAID system

Method and system for replacing a first node and a second of a clustered storage system by a third node and a fourth node are provided. The method includes migrating all storage objects managed by the first node to the second node; replacing the first node by the third node and migrating all the storage objects managed by the first node and the second node to the third node; and replacing the second node by the fourth node and then migrating the storage objects previously managed by the second node but currently managed by the third node to the fourth node. The nodes may also be replaced by operationally connecting the third node and the fourth node to storage managed by the first node and the second node; joining the third node and the fourth node to a same cluster as the first node and the second node.

Method and system for transparently replacing nodes of a clustered storage system

A slice manager module, in the operating system of a storage server, manages the virtual slicing of a mass storage device. The slice manager module receives a notification that a mass storage device has been added to an array of mass storage devices coupled to the storage system. The slice manager module reads header information in the mass storage device to determine a format of the mass storage device. If the mass storage device has not been previously sliced, the slice manager module virtually slices the mass storage device into a plurality of slices, where virtually slicing the mass storage device includes specifying an offset in the mass storage device where each of the plurality of slices is located.

Method and apparatus for slicing mass storage devices

A storage server receives a notification indicating a failure of a mass storage device in a storage array. The storage server determines whether a number of failures exceeds a fault tolerance level of the array and if the number of failures exceeds the fault tolerance level, recovers an address space corresponding to the failed storage device. When recovering the address space, the storage server replaces the failed storage device with a spare storage device having an identifiable pattern stored thereon and determines whether a file system on the storage system can automatically invalidate cached data blocks on the failed storage device.

Raid storage configuration for cached data storage

A computer storage system is described. A range of volume block numbers (VBNs) is assigned to a volume. A range of storage device block numbers (DBNs) is assigned to each of a plurality of storage devices. A first mapping parameters are created to map a first range of VBN numbers to a first selected range of DBNs using a first portion of a new storage device. A second mapping parameters are created to map a second range of VBN numbers to a second range of DBNs on a second portion of the new storage device.

Location-independent raid group virtual block management

A method and system manages ownership information about disks in a storage network without the need for an emulated, partner mode system. The method and system provides for ownership information, including a current owner and a home owner for resources, such as disks, to be stored on each disk in a storage system, as well as to be stored in memory on each storage system node in the network. A further aspect of the invention is a disk homeness application program interface (API), which provides commands that can be utilized by an administrator at a host computer to set, modify and disco play ownership information about each disk in the cluster. Upon a takeover, any node in the network can takeover one or more disks by reading the ownership information stored on the disks or in the tables.

Method and system for maintaining disk location via homeness

The invention features a method for controlling storage of data in a plurality of storage devices each including storage blocks, for example, in a RAID array. The method includes receiving a plurality of write requests associated with data, and buffering the write requests. A file system defines a group of storage blocks, responsive to disk topology information. The group includes a plurality of storage blocks in each of the plurality of storage devices. Each data block of the data to be written is associated with a respective one of the storage blocks, for transmitting the association to the plurality of storage devices.

Growing community of inventors

Mountain View, CA, United States of America

Stephen H Strange