Netapp, Inc.

Yong Cho

Prachi Deshmukh

Ananthan Subramanian

John K Edwards

Parag Sarfare

Sriram Venketaraman

Chaitanya V Patel

Anuja Jaiswal

Kumaran Nagappan

David A Grunwald

Linda Ann Riedle

Andy Kahn

Harihara Kadayam

Hrishikesh Keremane

Vaiapuri Ramasubramaniam

Szu-Wen Kuo

Sandeep Nirmale

Deepan Natesan Seeralan

Bhoovaraghan Subramanian

Vignesh Sukumar

Fani Jenkins

Maya Palem

Ling Zheng

Robert M English

Susan M Coatney

Stephen Lee Manley

Sandeep Yadav

Jason Ansel Lango

Don Alvin Trimmer

Paul Christopher Eastham

Tabriz Holtz

Andrew Eric Dunn

Vani Vully

Emmanuel Ackaouy

Techniques are provided for compacting indirect blocks. For example, an object is represented as a structure comprising data blocks within which data of the object is stored and indirect blocks comprising block numbers of where the data blocks are located in storage. Block numbers within a set of indirect blocks are compacted into a compacted indirect block comprising a base block number, a count of additional block numbers after the base block number in the compacted indirect block, and a pattern of the block numbers in the compacted indirect block. The compacted indirect block is stored into memory for processing access operations to the object. Storing compacted indirect blocks into memory allows for more block numbers to be stored within memory. In this way, the block numbers are read from memory is faster than loading the block numbers from disk.

Metadata compaction

Methods, systems, and computer program products for preventing non-detectable data loss during site switchover are disclosed. A computer-implemented method may include receiving a request to perform a switchover from a first node to a second node, determining whether to place a storage volume involved in the switchover in a suspended state, setting the storage volume in the suspended state based on determining that the storage volume is to be placed in the suspended state, and maintaining the storage volume in the suspended state after completing the switchover. In an example, the storage volume may be placed in a suspended state based on examining a volume-specific attribute indicating whether the storage volume is to be suspended when involved in a switchover. In one example, each storage volume involved in a switchover may be placed in a suspended state when indicated as part of a switchover request.

Preventing non-detectable data loss during site switchover

Techniques are provided for compacting indirect blocks. For example, an object is represented as a structure comprising data blocks within which data of the object is stored and indirect blocks comprising block numbers of where the data blocks are located in storage. Block numbers within a set of indirect blocks are compacted into a compacted indirect block comprising a base block number, a count of additional block numbers after the base block number in the compacted indirect block, and a pattern of the block numbers in the compacted indirect block. The compacted indirect block is stored into memory for processing access operations to the object.

Techniques are provided for compacting indirect blocks. For example, an object is represented as a structure comprising data blocks within which data of the object is stored and indirect blocks comprising block numbers of where the data blocks are located in storage. Block numbers within a set of indirect blocks are compacted into a compacted indirect block comprising a base block number, a count of additional block numbers after the base block number in the compacted indirect block, and a pattern of the block numbers in the compacted indirect block. The compacted indirect block is stored into memory for processing access operations to the object. Storing compacted indirect blocks into memory allows for more block numbers to be stored within memory.

A system and method for handling multi-node failures in a disaster recovery cluster is provided. In the event of an error condition, a switchover operation occurs from the failed nodes to one or more surviving nodes. Data stored in non-volatile random access memory is recovered by the surviving nodes to bring storage objects, e.g., disks, aggregates and/or volumes into a consistent state.

System and method for handling multi-node failures in a disaster recovery cluster

In one aspect of the disclosure, progress identifiers (e.g., a plurality of flags) and/or generation numbers are utilized to determine a 'correct' non-volatile random access memory (NVRAM) replay source to use during a retried switchover or early switchback. Initially, a switchover sequence is initiated. The switchover sequence includes a replay of logged information to storage devices of an aggregate to ensure data consistency of the aggregate. Progress of the switchover sequence is tracked using the progress identifiers and/or generation numbers. After an interruption during the switchover sequence, switchover is retried or an early switchback is performed. The retried switchover or early switchback decides whether to replay logged information, and, if so, determines an NVRAM replay source to replay logged information from based on states of the progress identifiers and/or comparison of the generation numbers.

Providing data integrity in a non-reliable storage behavior

A system and method for avoiding object identifier collisions in a cluster environment is provided. Upon creation of the cluster, volume location databases negotiate ranges for data set identifiers (DSIDs) between a first site and a second site of the cluster. Any pre-existing objects are remapped into an object identifier range associated with the particular site hosting the object.

System and method for avoiding object identifier collisions in a peered cluster environment

Techniques for recovering from a failure at a disaster recovery site are disclosed. An example method includes receiving an indication to shift control of a set of volumes of a plurality of volumes. The set of volumes is originally owned by a second storage node. The first storage node is a disaster recovery partner of the second storage node. The method includes shifting control of the set of volumes. The method further includes during the shifting, changing a status of a flag corresponding to a progress of the shifting. The method also includes during a reboot of the first storage node, determining the status of the flag and determining, based on the status of the flag, whether to mount the set of volumes during reboot at the first storage node.

Method and system for handling failures by tracking status of switchover or switchback

Methods, systems, and computer program products for providing deferred replication of recovery information at site switchover are disclosed. A computer-implemented method may include receiving a first copy of logged data for storage volumes of a disaster recovery (DR) partner at a remote site from the DR partner, receiving a request to perform a site switchover from the remote site to the local site, receiving a second copy of logged data for the storage volumes from a local high availability (HA) partner in response to the switchover, and recovering the storage volumes locally by applying one or more of the copies of logged data to corresponding mirrored storage volumes at the local site.

Deferred replication of recovery information at site switchover

A network storage server includes a tool for detecting and fixing errors while the network storage server remains online (available for servicing client requests), which includes enabling a user to approve or disapprove remedial changes before the changes are committed. The technique bypasses the usual consistency point process for new or modified data blocks representing potential remedial changes. At a consistency point, dirty data blocks representing the potential remedial changes are written to a change log file residing outside the volume. The modified data blocks are written in sequential order to logical blocks of the change log file. In response to a user input indicating that a potential change should be committed, the corresponding modified data blocks are read from the change log file in the order in which they were written to the change log file, and they are written to persistent storage in that order.

Online data consistency checking in a network storage system with optional committal of remedial changes

Growing community of inventors

Saratoga, CA, United States of America

Yong Cho