Netapp, Inc.

Network Appliance, Inc.

Wesley R Witte

Youyuan Wu

Gyanendra Pradhan

Sundeep Singh

Priya Thiruvasakan

Mark Muhlestein

Sachin Pandit

Abhishek Maurya

Mohammed Haroon Shareef

Gaurav Banga

Omprakaash C Thoppai

William Zumach

Raghavendra Chowdary Maddipatla

Amol Dixit

Ananthan Subramanian

Richard Parvin Jernigan, Iv

Tianyu Jiang

Garrett R Mueller

Bingxue Cai

Saji Kumar Vijaya Kuman Rajendran Nair Rajendran

Saji Vijaya Rajendran

Systems, methods, and machine-readable media are disclosed for isolating and reporting a volume placement error for a request to place a volume on a storage platform. A volume placement service requests information from a database using an optimized database query to determine an optimal location to place a new volume. The database returns no results. The volume placement service deconstructs the optimized database query to extract a plurality of queries. The volume placement service iterates over the plurality queries, combining queries in each iteration, to determine a cause for the database to return no results. The volume placement service determines based on the results of each iterative database request a cause the database to return an empty result. The volume placement service provides an indication of the cause for returning an empty result.

Volume placement failure isolation and reporting

Systems, methods, and machine-readable media are disclosed for determining an optimal location for creating a new volume (or volumes) on a storage platform and placing the volume at the determined location. A resource tracker collects resource use and/or limits data and stores it in a database. A volume placement service receives a volume deployment specification having constraints for creating a new volume, particularly including instructions relating to relationships between volumes to be created. The volume placement service retrieves the data from the database. The volume placement service identifies an optimal location for the volume based at least in part on given constraints from the specification and the resource usage data. The system places the requested volume at the determined location.

Multiple volume placement based on resource usage and scoring functions

Systems, methods, and machine-readable media are disclosed for collecting, maintaining, and retrieving use and limit data for connected resources, as well as determining an optimal location for creating a new volume (or volumes) on a storage platform and placing the volume at the determined location. A resource tracker collects resource use and/or limits data and stores it in a database. A volume placement service receives a volume deployment specification having constraints for creating a new volume. The volume placement service retrieves the data from the database. The volume placement service identifies an optimal location for the volume based at least in part on given constraints from the specification and the resource usage data. The system places the requested volume at the determined location.

Volume placement based on resource usage

Volume placement based on resource use and scoring functions

Decoupling volume deployment requirements and code implementation

Methods, non-transitory computer readable media, and computing devices are disclosed that facilitate efficient storage operations using variable length encoded segment maps for deduplicated objects. A key name and elements of a segment list are received with a request to store an object. Each of the elements corresponds to a segment associated with the object and comprises a segment hash. A segment map is generated for the object. The segment map includes a header and entries. Each of the entries includes at least an expanded offset, one of the segment hashes, and a start offset. The segment map is stored in an object store, as associated with the key name, along with segment data included in at least one of the elements.

Methods for facilitating efficient storage operations using variable length encoded segment maps for deduplicated objects and devices thereof

Techniques for notifying clients whose locks did not persist about a loss of lock state after a failover event are disclosed herein. According to one embodiment, a storage node of a high availability cluster constructs a lock data structure based on a mirrored lock data structure for a lock on a data container. The storage node receives a data operation request permitted by the lock from a client to operate on the data container. The storage node instructs to terminate a connection with the client if the lock data structure for the lock on the data container has been recently reconstructed. Accordingly, the client revokes the connection and refrains from committing the locally cached operations to the data container stored in the storage node. The client has an option to reconnect with the cluster and regain the data container privilege controlled by the lock.

Lock state reconstruction for non-disruptive persistent operation

The techniques introduced herein provide an efficient mechanism for reducing remote procedure requests to storage server nodes in a cluster of the storage servers to construct a directory path for a data container. According to one aspect of the invention, a new caching technique and an efficient organization of the cache memory are provided so that a cache memory on a storage server node is populated with individual path components of a directory structure. A novel cache invalidation mechanism is provided to maintain cache consistency at the cache so that when a path component changes, such as an identifier of a data container in the directory structure, and a path component is invalidated in the cache memory, the remaining path components can be retained and later reused.

Mechanism for distributed inode to path traversal in a striped volume system

Methods and/or systems for efficiently handling a request from a client for a target component (e.g., file) stored on a remote or secondary node in a clustered storage system are provided. In response to a request from the client for the target component, a first node to which the client is locally connected retrieves a list of one or more logical interfaces (LIFs) and generates a response comprising an indication that the requested target component is not covered by this first node and a list of one or more internet protocol (IP) addresses that correspond to the retrieved LIFs for accessing the secondary node. This allows the client to connect locally to the secondary node so that the target component can be retrieved locally and thus more efficiently regardless of where (e.g., upon which node) the file is stored within the cluster.

Efficient data access in clustered storage system

A technique supports Change Notify watches in virtualized storage systems. In particular, techniques of the present invention advantageously emulate Change Notify features (e.g., as documented by the CIFS protocol) on virtualized storage systems by leveraging virtualization mapping information (e.g., an inode-to-path or 'I2P' mapping) to walk a file system tree backwards from the data blocks to their ancestors to determine whether there are applicable watches on ancestor directories, and to obtain a pathname (e.g., relative) of the watched (changed) data. In particular, changes to data received from different protocols (e.g., CIFS, NFS, HTTP, etc.) can trigger watches to clients on the virtualized storage system. Also, performance may be enhanced using various caching techniques, and watch state may be retained while moving watched data across volumes of the virtualized storage system.

System and method for supporting change notify watches for virtualized storage systems

A technique efficiently creates and serves a backup data set on a backup filer located at a remote site from a primary filer by essentially moving an entire operating environment of a primary data set to the backup filer. The primary filer is organized into one or more virtual filers (vfilers), one of which (the primary vfiler) is configured to serve data, such as the primary data set, for a client. In the event that the primary filer or primary vfiler becomes unavailable, the technique may be implemented as a disaster recovery or data migration sequence to enable efficient instantiation of a backup vfiler to serve the backup data set for the client.

Remote disaster recovery and data migration using virtual appliance migration

A technique supports Change Notify watches in virtualized storage systems. In particular, techniques of the present invention advantageously emulate Change Notify features (e.g., as documented by the CIFS protocol) on virtualized storage systems by leveraging virtualization mapping information (e.g., an inode-to-path or 'IP' mapping) to walk a file system tree backwards from the data blocks to their ancestors to determine whether there are applicable watches on ancestor directories, and to obtain a pathname (e.g., relative) of the watched (changed) data. In particular, changes to data received from different protocols (e.g., CIFS, NFS, HTTP, etc.) can trigger watches to clients on the virtualized storage system. Also, performance may be enhanced using various caching techniques, and watch state may be retained while moving watched data across volumes of the virtualized storage system.

Growing community of inventors

Campbell, CA, United States of America

Wesley R Witte