Abstract:
A technique to name data is disclosed to allow preservation of storage efficiency over a link between a source and a destination in a replication relationship as well as in storage at the destination. The technique allows the source to send named data to the destination once and refer to it by name multiple times in the future, without having to resend the data. The technique also allows the transmission of data extents to be decoupled from the logical containers that refer to the data extents. Additionally, the technique allows a replication system to accommodate different extent sizes between replication source and destination while preserving storage efficiency.
Abstract:
A storage system provides highly flexible data layouts that can be tailored to various different applications and use cases. The system defines several types of data containers, including “regions”, “logical extents” and “slabs”. Each region includes one or more logical extents. Allocated to each logical extent is at least part of one or more slabs allocated to the region that includes the extent. Each slab is a set of blocks of storage from one or more physical storage devices. The slabs can be defined from a heterogeneous pool of physical storage. The system also maintains multiple “volumes” above the region layer. Each volume includes one or more logical extents from one or more regions. A foreign LUN can be assimilated into the system by defining slabs as separate portions of the foreign LUN. Layouts of the extents within the regions are not visible to any of the volumes.
Abstract:
A plurality of storage devices is organized into a physical volume called an aggregate, and the aggregate is organized into a global storage space, and a data block is resident on one of the storage devices of the plurality of storage devices. A plurality of virtual volumes is organized within the aggregate and he data block is allocated to a virtual volume. A physical volume block number (pvbn) is selected for the data block from a pvbn space of the aggregate, and virtual volume block number (vvbn) for the data block is selected from a vvbn space of the selected vvol. Both the selected pvbn and the selected vvbn are inserted in a parent block as block pointers to point to the allocated data block on the storage device.
Abstract:
A plurality of types of volumes are maintained, a volume being a logical arrangement of storage space on one or more data storage devices. A volume type field is used to designate the type of a particular volume, and a flexible volume paradigm is selected by the volume type field for interpreting data within a data structure written to a data storage device of the one or more data storage devices. A physical volume block number to virtual volume block number mapping pair (pvbn/vvbn pair) is designated by the volume type field, the pvbn/vvbn pair is used to translate a physical volume block number to a virtual volume block number. A request to write a data to a first block of the particular volume is received, a pvbn/vvbn pair is determined. The data is written to the physical block designated by the pvbn/vvbn pair.
Abstract:
A write allocation technique extends a conventional write allocation procedure employed by a write anywhere file system of a storage system. A write allocator of the file system implements the extended write allocation technique in response to an event in the file system. The extended write allocation technique efficiently allocates blocks, and frees blocks, to and from a virtual volume (vvol) of an aggregate. The aggregate is a physical volume comprising one or more groups of disks, such as RAID groups, underlying one or more vvols of the storage system. The aggregate has its own physical volume block number (pvbn) space and maintains metadata, such as block allocation structures, within that pvbn space. Each vvol also has its own virtual volume block number (vvbn) space and maintains metadata, such as block allocation structures, within that vvbn space. The inventive technique extends input/output efficiencies of the conventional write allocation procedure to comport with an extended file system layout of the storage system.
Abstract:
A file folding technique reduces the number of duplicate data blocks of a file consumed on a storage device of a file server configured to generate a persistent image of its active file system at a point in time. According to the file folding technique, if “old” data blocks of the file are over-written with “new” data and that new data is identical to the data of the persistent file image, the old data blocks are “freed” and the file is directed to refer to the persistent image for its data. The invention reduces disk space consumption in a file server configured to generate persistent images of its active file system and, in particular, reduces overall persistent image disk usage.
Abstract:
An on-disk storage arrangement increases the number of persistent consistency point images (PCPIs) that may be maintained for a volume of a storage system. The on-disk storage arrangement comprises a novel volume information (volinfo) block representing a root of the volume; the volinfo block is stored at predefined locations on disk and comprises various system wide configuration data. The volinfo block further comprises a data structure configured to provide a level of indirection that increases the number of PCPIs maintainable by a file system executing on the storage system. To that end, the data structure may be organized as an array of pointers, wherein each pointer references a block containing a snapshot root, thereby enabling efficient access to each PCPI maintained by the file system.
Abstract:
A technique to name data is disclosed to allow preservation of storage efficiency over a link between a source and a destination in a replication relationship as well as in storage at the destination. The technique allows the source to send named data to the destination once and refer to it by name multiple times in the future, without having to resend the data. The technique also allows the transmission of data extents to be decoupled from the logical containers that refer to the data extents. Additionally, the technique allows a replication system to accommodate different extent sizes between replication source and destination while preserving storage efficiency.
Abstract:
A technique is disclosed for restoring data of sparse volumes, where one or more block pointers within the file system structure are marked as ABSENT, and fetching the appropriate data from an alternate location on demand. Client data access requests to the local storage system initiate a restoration of the data from a backing store as required. A demand generator can also be used to restore the data as a background process by walking through the sparse volume and restoring the data of absent blocks. A pump module is also disclosed to regulate the access of the demand generator. Once all the data has been restored, the volume contains all data locally, and is no longer a sparse volume.
Abstract:
A technique is disclosed for restoring data of sparse volumes, where one or more block pointers within the file system structure are marked as ABSENT, and fetching the appropriate data from an alternate location on demand. Client data access requests to the local storage system initiate a restoration of the data from a backing store as required. A demand generator can also be used to restore the data as a background process by walking through the sparse volume and restoring the data of absent blocks. A pump module is also disclosed to regulate the access of the demand generator. Once all the data has been restored, the volume contains all data locally, and is no longer a sparse volume.