Netapp, Inc.

Vmware, Inc.

Network Appliance, Inc.

Pawan Saxena

Roger Keith Stager

Yafen Peggy Chang

Craig Anthony Johnston

Rico Blaser

Donald Alvin Trimmer

Randall C Johnson

Atul Ramesh Pandit

Vijay Mohan Deshmukh

Ameet Pyati

Anant Agarwal

Satish Singhal

Vivek Gupta

Paul Lockwood

Preethi Gopaulakrishnan

Gabriel Tarasuk-Levin

Rithin Kumar Shetty

Don Alvin Trimmer

Aalap Desai

Rahul Chandrasekaran

Ravi Kant Cherukupalli

Vikram Nair

Vishwajith Shivappa

Piyush Parmar

Alaa Shaabana

Ala Shaabana

Arvind Mohan

Umesha Margi

Dhaval Shah

Gregory Jean-Baptiste

A system and method for efficiently restoring one or more data containers is provided. A common persistent consistency point image (PCPI) is identified between a source and a destination storage systems prior to the destination storage system performing a rollback operation to the commonly identified PCPI. Differential data is then transmitted from the source storage system in a line efficient manner to the destination storage system.

System and method for efficient block level granular replication

Data is replicated on a backup node, where the granularity of the replication can be less than a full volume. A data consistency group comprising a subset of data for a volume is defined for a primary node. A set of differences for the data consistency group is sent to a backup node. The backup node creates change logs in response to receiving the set of differences. In response to receiving a request to access a file having data in the data consistency group, the backup node creates a clone of the file. The backup node determines whether an update to a data block of the file exists in the change logs. In response to determining that the update to the data block exists in the change logs, the backup node updates a copy of the data block for the cloned file with data in the change logs.

Granular replication of volume subsets

Systems and methods for analyzing the usage of a set of workloads in a hyper-converged infrastructure are disclosed. A neural network model is trained based upon historical usage data of the set of workloads. The neural network model can make usage predictions of future demands on the set of workloads to minimize over-allocation or under-allocation of resources to the workloads.

Neural network model for predicting usage in a hyper-converged infrastructure

System and computer-implemented method for managing multi-availability zone (AZ) clusters of host computers in a cloud computing environment automatically detects a degraded state of a first AZ in the cloud computing environment based on host failure events for host computers in a first cluster section of a multi-AZ cluster of host computers located in the first AZ and a recovered state of the first AZ based a successful scale-in operation of another multi-AZ cluster located partially in the first AZ. In response to the detection of the degraded state of the first AZ, a second cluster section of the multi-AZ cluster of host computers located in a second AZ is scaled out. In response to the detection of the recovered state of the first AZ, the second cluster section of the multi-AZ cluster of host computers located in the second AZ is scaled in.

Degraded availability zone remediation for multi-availability zone clusters of host computers

A system and method for automatically generating recurrent neural networks for log anomaly detection uses a controller recurrent neural network that generates an output set of hyperparameters when an input set of controller parameters is applied to the controller recurrent neural network. The output set of hyperparameters is applied to a target recurrent neural network to produce a child recurrent neural network with an architecture that is defined by the output set of hyperparameters. The child recurrent neural network is then trained, and a log classification accuracy of the child recurrent neural network is computed. Using the log classification accuracy, at least one of the controller parameters used to generate the child recurrent neural network is adjusted to produce a different input set of controller parameters to be applied to the controller recurrent neural network so that a different child recurrent neural network for log anomaly detection can be generated.

System and method for automatically generating neural networks for anomaly detection in log data from distributed systems

Restoration process to restore corrupted data of a volume

A hardware and/or software facility to enable emulated storage devices to share data stored on physical storage resources of a storage system. The facility may be implemented on a virtual tape library (VTL) system configured to back up data sets that have a high level of redundancy on multiple virtual tapes. The facility organizes all or a portion of the physical storage resources according to a common store data layout. By enabling emulated storage devices to share data stored on physical storage resources, the facility enables deduplication across the emulated storage devices irrespective of the emulated storage device to which the data is or was originally written, thereby eliminating duplicate data on the physical storage resources and improving the storage consumption of the emulated storage devices on the physical storage resources.

Eliminating duplicate data by sharing file system extents

A technique for determining an amount of storage space that would be recovered in a storage system by deleting a list of logical containers of data is provided. In one embodiment, data blocks referenced by the list of files are first identified. The data blocks (e.g., deduplicated data blocks) may be referenced by two or more files. A number of references made by the identified list of files to each data block is compared against a number of references made by all files stored in a dataset of the storage system. A total amount of storage space is then calculated based on a sum of storage spaces utilized by each data block for which the two reference numbers match. This total amount of storage space is the storage space that would be reclaimed through deletion of the identified list of files.

Predicting space reclamation in deduplicated datasets

A system for synchronizing a secondary volume with a primary volume in a continuous data protection system includes scanning means for scanning a region of the primary volume; comparing means for comparing the scanned region with a corresponding region of the secondary volume; storing means for storing an identification of the scanned region in a compare delta map when the comparing means returns a discrepancy between the scanned region and the corresponding region; copying means for copying data from the primary volume to the secondary volume, using the compare delta map as a guide to locate the data to copy; and revising means for revising the compare delta map by removing any changes made to the primary volume during a scan interval, which is a period of time required to scan the primary volume.

Method and system for restoring a volume in a continuous data protection system

A method and apparatus for managing backup data is disclosed. A data backup system defines a plurality of time windows for creating and maintaining backup data in accordance with a data backup policy. Each of the time windows is assigned a predetermined amount of storage space. When the data backup system creates backup data, the system determines whether a storage space assigned to a time window is large enough to accommodate new backup data. If the storage space is large enough, the new backup data is stored. However, if the storage space is not large enough, the system deletes the oldest backup data until enough storage space is obtained.

Method and apparatus for managing backup data

A method for tracking changes on a primary volume in a continuous data protection system writes data to the primary volume. A copy of the data is written to a secondary volume, the secondary volume including all writes made to the primary volume. Each write made to the secondary volume is mapped in a data structure, such that the data structure tracks changes on the primary volume between two different points in time.

Method and system for storing data using a continuous data protection system

A method for browsing objects on a protected volume in a continuous data protection system begins by displaying a list of top-level objects to a user who selects a top-level object to browse. A snapshot is selected from the selected top-level object and is decoded. A list of objects in the selected snapshot is displayed and the user selects an object to browse. The selected object is decoded and operations are performed on the selected object. The user can browse the protected volume by snapshots in the top-level object or by a range of time of coverage of the top-level object.

Method and system for browsing objects on a protected volume in a continuous data protection system

Growing community of inventors

Pleasanton, CA, United States of America

Pawan Saxena