Abstract: A plurality of storage nodes in a single chassis is provided. The plurality of storage nodes in the single chassis is configured to communicate together as a storage cluster. Each of the plurality of storage nodes includes nonvolatile solid-state memory for user data storage. The plurality of storage nodes is configured to distribute the user data and metadata associated with the user data throughout the plurality of storage nodes such that the plurality of storage nodes maintain the ability to read the user data, using erasure coding, despite a loss of two of the plurality of storage nodes. The chassis includes power distribution, a high speed communication bus and the ability to install one or more storage nodes which may use the power distribution and communication bus. A method for accessing user data in a plurality of storage nodes having nonvolatile solid-state memory is also provided.

Abstract: System and method for tracking statistics at the subfile level and transparently placing or migrating inactive or less active blocks of data to other storage devices. Embodiments may provide mechanisms to track statistics at the subfile level of files including, but not limited to, database files, and to transparently place or migrate inactive or less active blocks of data of the files from higher-performing, typically more expensive, storage to lower-performing, typically less expensive, storage, while placing or migrating active blocks of data of the files to higher-performing storage, based on the subfile-level statistics rather than on file-level timestamps. In some embodiments, knowledge of file structure (e.g., database file structure), for example knowledge of database partitions with header blocks and data blocks in databases using data partitioning, may be used to separate more active and less active blocks of data of files onto storage with different performance and/or other characteristics.

Abstract: A host of a multi-device file system may instruct an external data mover implementing a third party copy to move data from one storage device to another without the host reading or writing data as part of the move. The data being moved may remain accessible through the file system after being moved. A host may instruct an external data mover to write moved data to multiple mirrored devices. A host may instruct the data mover to move data between storage classes in a multi storage class file system. A journaling file system may utilize an external data mover implementing a third party copy to move data from a system log to another storage destination and may also instruct the data mover to move metadata as well as data.

Abstract: System and method for tracking statistics at the subfile level and transparently placing or migrating inactive or less active blocks of data to other storage devices. Embodiments may provide mechanisms to track statistics at the subfile level of files including, but not limited to, database files, and to transparently place or migrate inactive or less active blocks of data of the files from higher-performing, typically more expensive, storage to lower-performing, typically less expensive, storage, while placing or migrating active blocks of data of the files to higher-performing storage, based on the subfile-level statistics rather than on file-level timestamps. In some embodiments, knowledge of file structure (e.g., database file structure), for example knowledge of database partitions with header blocks and data blocks in databases using data partitioning, may be used to separate more active and less active blocks of data of files onto storage with different performance and/or other characteristics.

Abstract: System and method for performing optimized restores of a multi-class file system. More actively accessed data may be assigned to higher storage classes and less actively accessed data may be assigned to lower storage classes in the multi-class file system. In a restore, the higher storage class(es) including more actively accessed data may be restored first. The multi-class file system may then be brought online for access by application(s). The lower storage class(es) may then be restored. In one embodiment, if a request for data that have not been restored is received, the file system may obtain an estimated time until restore of the requested data from the restore mechanism. The file system may then notify the application of the estimated time until restore. The application may notify a user of the estimated time, and may generate another request for the data after the estimated time has elapsed.

Abstract: System and method for providing immutable data containers in tiered storage hierarchies. Embodiments may allow fulfillment of regulatory requirements for retaining certain data through management of a user-defined policy. The policy may specify what data in the file system needs to be stored as immutable data to the immutable data container in the file system. File system data may be tracked, and data specified by the policy may be transparently and automatically stored to the immutable data container within the file system. Updates to the data specified by the policy may also be stored to the immutable data container. This may be performed without overwriting or modifying the earlier version(s) of the data stored to the immutable data container, and thus every version of the data specified by the policy may be stored to and, if necessary, reconstructed from the immutable data container.

Abstract: Redirecting a data object such as a file block extent. The data object can be redirected from a first memory block to a second memory block, wherein the second memory block includes a copy of modified data of the first memory block. The redirection may occur in response to a request to modify data of the data object. Redirection preserves the prior version of the data object stored in the first memory block to enable restoration of the data object if needed. In one embodiment, a first data object is mapped to a first memory block. A copy of data contents of the first memory block is created. Thereafter, data contained within the copy is modified in accordance, for example, with a request to write data to the first data object. The modified copy is stored in a second memory block, and the first data object is mapped to the second memory block.

Abstract: A system or method for reestablishing data consistency between data volume P and its real time or near real time copy volume S. When volumes P and S enter a state of data inconsistency, data consistency can be restored through use of roll-back and/or roll-forward logs. The roll-forward log stores new data to be written to volume P. The roll-back log stores existing data of volume S before the existing data of volume S is overwritten with new data. As will be more fully described below, the roll-back log can be used to incrementally restore volume S to a prior data state in reverse chronological order, while a roll-forward log can be used to incrementally restore volume S in forward chronological to equal the data state of volume P.

Abstract: A data center control system includes a storage configured to maintain an emission usage value indicative of an estimated amount of greenhouse gas emission caused by consumption of power by resources within one or more data centers. The control system also includes a controller that may provide a signal to control an operation of at least one of the resources depending upon the indication of the estimated amount of greenhouse gas emission.

Abstract: A system or method for creating a point-in-time (PIT) or backup copy of one or more data volumes using a roll-back log. The backup copy can be created without employing hot backup mode. In one embodiment, the method includes copying data blocks of a volume to a backup memory configured to store a backup copy of the volume, wherein the data blocks are sequentially copied until all of the data blocks of the volume are copied to the backup memory. A first request is generated to overwrite existing data of a first data block of the volume with new data before all of the data blocks of the volume are copied to the backup memory. Before overwriting the existing data and before all of the data blocks of the volume are copied to the backup memory, the existing data is copied to a first memory (e.g., the roll-back log). Before all of the data blocks of the volume are copied to the backup memory, the existing data is overwritten with the new data.

Abstract: An application uses a set of resources, where the set of resources may include a variety of software and hardware resources, such as database management software, file systems, logical volumes, and physical disks. Configuration information, including various attributes of individual resources and dependencies among resources, is used to manage the set of resources. For example, tuning parameters for a database management system and information describing the dependency of the database management software on a set of logical volumes may be maintained as part of the configuration information. A subset of this configuration information is dynamically maintained in volatile storage. Recovery software is configured to retain a previous state of the dynamically maintained configuration information by storing the previous state in persistent storage.

Abstract: A file system may employ an enhanced or performance-adjusted allocation scheme when storing data to multiple storage devices. A file system may monitor one or more performance characteristics of storage devices. The file system may, in response to storage requests, select one or more of the storage devices for storing data associated storage requests based on differences among the respective monitored performance characteristics for the storage devices. Additionally, the file system may determine an allocation pattern for storing data to the storage devices and may modify the determined allocation pattern based on a detected change in the monitored performance characteristics of the storage devices. Further, the file system may store data based on both the allocation pattern and on data characteristics associated with a data storage request. The file system may also incorporate input specifying either new performance characteristics or a new allocation pattern.

Abstract: A roll-back memory can be used to incrementally restore one or more data volumes in reverse chronological order to the data state they occupied at some prior point in time without using a backup copy. After the one or more data volumes have been restored in reverse chronological order, a roll-forward memory can be used to incrementally restore the one or more data volumes in forward chronological order to the data state they occupied at some other point in time without using a backup copy. Incrementally restoring the one or more data volumes in reverse chronological order may follow an incremental restoration of the one or more data volumes in forward chronological order and vice versa until the one or more data volumes are in the data state they occupied just prior to, for example, a data corruption event.

Abstract: System and method for performing operations in a multi-class file system without requiring split mirrors. For one or more storage classes in the multi-class file system, operations that require stable copies of the storage classes may be performed without using split mirrors. In one embodiment, read-only data may be assigned and/or migrated to lower storage classes, and operations may be performed on the read-only storage classes without using split mirrors. In one embodiment, to perform an operation without using a split mirror, a write lock of a storage class may be examined to determine if the write-locked storage class has been written to during the operation on the storage class and, if so, the operation may be retried for the storage class. In one embodiment, the file system software may be blocked from enabling a storage class for writing for the duration of the operation on the storage class.

Abstract: System and method for implementing a file system across different storage classes in a storage system. Embodiments may define multiple classes of storage and automatically and transparently migrate data in the storage classes within the same file system to meet the usage needs of the business. Embodiments may transparently adapt the cost of storage to the usage patterns of data on the storage, thereby reducing the amount that customers need to spend for their storage. In embodiments, storage devices may be classified into different classes of storage to implement a multi-class file system. Embodiments may provide a multi-class storage mechanism for managing and implementing user-defined policies for assigning and migrating data within the multi-class file system. The multi-class storage mechanism may determine where to initially place data, and may transparently migrate data to other storage classes according to the policies. Migrated data remains online within the file system.

Abstract: System and method for performing backups of a multi-class file system are described. In one embodiment, more recently modified data may be assigned and/or migrated to higher storage classes and less recently modified data may be migrated at time intervals to lower storage classes in the multi-class file system. Backups of each of the storage classes may be performed at time intervals. In one embodiment, the backups may be image-based backups of the storage devices in the storage classes. In one embodiment, the lower storage classes may include one or more read-only storage classes including less-recently modified data that are backed up less frequently than higher storage classes including more-recently modified data. In one embodiment, files migrated to lower storage class(es) may be compressed.