732 results about "Block number" patented technology

A system and method for mapping file block numbers (FBNs) to logical block addresses (LBAs) is provided. The system and method performs the mapping of FBNs to LBAs in a file system layer of a storage operating system, thereby enabling the use of clients in a storage environment that have not been modified to incorporate mapping tables. As a result, a client may send data access requests to the storage system utilizing FBNs and have the storage system perform the appropriate mapping to LBAs.

A system and method for remote asynchronous replication or mirroring of changes in a source file system snapshot in a destination replica file system using a scan (via a scanner) of the blocks that make up two versions of a snapshot of the source file system, which identifies changed blocks in the respective snapshot files based upon differences in volume block numbers identified in a scan of the logical file block index of each snapshot. Trees of blocks associated with the files are traversed, bypassing unchanged pointers between versions and walking down to identify the changes in the hierarchy of the tree. These changes are transmitted to the destination mirror or replicated snapshot. This technique allows regular files, directories, inodes and any other hierarchical structure to be efficiently scanned to determine differences between versions thereof. The changes in the files and directories are transmitted over the network for update of the replicated destination snapshot in an asynchronous (lazy write) manner. The changes are described in an extensible, system-independent data stream format layered under a network transport protocol. At the destination, source changes are used to update the destination snapshot. Any deleted or modified inodes already on the destination are moved to a temporary or “purgatory” directory and, if reused, are relinked to the rebuilt replicated snapshot directory. The source file system snapshots can be representative of a volume sub-organization, such as a qtree.

A file system layout apportions an underlying physical volume into one or more virtual volumes (vvols) of a storage system. The underlying physical volume is an aggregate comprising one or more groups of disks, such as RAID groups, 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 has its own virtual volume block number (vvbn) space and maintains metadata, such as block allocation structures, within that vvbn space. Notably, the block allocation structures of a vvol are sized to the vvol, and not to the underlying aggregate, to thereby allow operations that manage data served by the storage system (e.g., snapshot operations) to efficiently work over the vvols. The file system layout extends the file system layout of a conventional write anywhere file layout system implementation, yet maintains performance properties of the conventional implementation.

A system and method for remote asynchronous replication or mirroring of changes in a source file system snapshot in a destination replica file system using a scan (via a scanner) of the blocks that make up two versions of a snapshot of the source file system, which identifies changed blocks in the respective snapshot files based upon differences in volume block numbers identified in a scan of the logical file block index of each snapshot. Trees of blocks associated with the files are traversed, bypassing unchanged pointers between versions and walking down to identify the changes in the hierarchy of the tree. These changes are transmitted to the destination mirror or replicated snapshot. This technique allows regular files, directories, inodes and any other hierarchical structure to be efficiently scanned to determine differences between versions thereof. The changes in the files and directories are transmitted over the network for update of the replicated destination snapshot in an asynchronous (lazy write) manner. The changes are described in an extensible, system-independent data stream format layered under a network transport protocol. At the destination, source changes are used to update the destination snapshot. Any deleted or modified inodes already on the destination are moved to a temporary or “purgatory” directory and, if reused, are relinked to the rebuilt replicated snapshot directory. The source file system snapshots can be representative of a volume sub-organization, such as a qtree.

A hybrid-padding approach for arranging variable size data packets for error correction encoding and decoding is disclosed. The approach can involve arranging the data packets in columns and rows and selecting the row size to minimize the amount of padding required. If data packet is smaller than the number of rows the data packet is inserted into the column and the remaining rows are padded. If the data packet is larger than the number of rows, the data packet is allowed to span multiple columns with the last column being padded if necessary. The data packets can include parameters, such as a source block number, packet length, and starting column number, and the error correction packets can include parameters, such as, a source block number an N, a K, the starting column number, and the number of row, to signal the hybrid-padding message.

Described embodiments provide logical-to-physical address translation for data stored on a storage device having sectors organized into blocks and superblocks. A flash translation layer maps a physical address in the storage device to a logical sector address. The logical sector address corresponds to mapping data that includes i) a page index, ii) a block index, and iii) a superblock number. The mapping data is stored in at least one summary page corresponding to the superblock containing the physical address. A block index and a page index of a next empty page in the superblock are stored in a page global directory corresponding to the superblock. A block index and a page index of the at least one summary page and the at least one active block table for each superblock are stored in at least one active block table of the storage device.

A storage operating system is configured to assign volume block numbers (VBNs) to a volume. The system has a plurality of disks, and each disk of the plurality of disks is assigned disk block numbers (DBNs). A raidmap is configured to map the VBNs to the DBNs of the plurality of physical disks, the mapping for a particular disk stored in a disk label for the particular disk. The disk label for the particular disk is then written to the particular disk.

The present invention demonstrates an improved CNC Control system, which integrates operator-induced changes into the pre-programmed CNC machining process. The improved CNC Control system develops a Human Activity Storage Program (HASP), which is used for subsequent production in conjunction with and simultaneously with the Numerical Control Program thereby enhancing the production process by integrating the skilled machinist's input into the production process. The numerical control program of a CNC machine is interfaced with an IBM compatible personal computer (PC) to make information relative to the block number, feed-rate and / or spindle speed over-ride values available at the personal computer. If the CNC Control has been re-configured properly (with regard to the ladder interface and operating system) a PC computer is not required. During the machining of a part the machine operator will manually over-ride the feed-rate and / or the spindle speed to optimize machining performance. Through the use of VISUAL BASIC OR C++programming modules and routines, the spindle speed and feed-rate controls (located at the CNC Control) are polled at frequent or 5OO ms intervals. The status or over-ridden values of these controls are correlated to the active block number in use during each polled sequence and this information is written to an "event file". After the subject part has been completed, one of two options can be used. An "edit phase" is initiated which utilizes the information in the "event file" to reconstruct the MCD file. After the edit phase is complete, the resultant output "Optimized MCD" can be used to produce like parts with confidence that all motion is running at peak performance and all programmed trajectories are maintained. The cycle can be repeated again (if desired) to ensure even greater efficiency while cutting. In the alternative, the event file can be employed to "command" the CNC Control with respect to feed-rate and / or spindle speed over-ride settings.

An on-disk structure of a file system has the capability to efficiently manage and organize data containers, such as snapshots, stored on a storage system. A multi-bit, monotonically increasing, snapshot identifier (“snapid”) is provided that represents a snapshot and that increases every time a snapshot is generated for a volume of the storage system. The snapid facilitates organization of snapshot metadata within, e.g., a data structure used to organize metadata associated with snapshot data. In the illustrative embodiment, the data structure is a balanced tree structure configured to index the copy-out snapshot data blocks. The snapid is also used to determine which blocks belong to which snapshots. To that end, every block that is used in a snapshot has an associated “valid-to” snapid denoting the newest snapshot for which the block is valid. The oldest snapshot for which the block is valid is one greater than the valid-to field of the next older block at the same file block number.

Broadly speaking, a method and an apparatus is provided for processing access commands directed to a striped configuration of disks. More specifically, the method and apparatus determines a physical block address corresponding to a logical address in a redundant array of independent disks level 0 (RAID 0) system. Bit-level operations are incorporated to determine a disk in the RAID 0 system and a block number on the disk that corresponds to a particular logical address. Since the bit-level operations replace traditionally required division and modulo operations, the method and apparatus provides for more efficient processing of access commands directed to the RAID 0 system.

The invention discloses a snapshot storage and data recovery method of a continuous data protection system. In a block-level continuous data protection (CDP) system, each write operation of a disk data block has a CDP metadata for recording the write operation. The CDP metadata is taken as a chain table node, and besides a block number containing the data block, the node also sets up three fields of forward link, uplink and downlink. On the basis, a binary tree is constructed to record the table head of each key chain table node, thereby forming a key node set, and the chain table starting from the table heads can reflect the mapping relation from each block address of the disk of the current time to the log data block. The invention can store the mapping relation of the snapshot time by using less storage space, thereby supporting more intensive data snapshot and being beneficial to shortening the data recovery time.

The invention relates to the field of deep neural networks and provides a blocked convolution optimization method and a device for a convolution neural network, so as to solve the bottleneck problem of convolution operation in a hardware processing system in the neural network. The optimization method comprises steps: a to-be-blocked convolution layer is selected, and the upper limit of the block size is determined; according to the upper limit of the block size, a block number and the block size of an input feature map are determined; based on the block number, the block size, the size of a convolution kernel, the size of the input feature map and the filling size of an input feature map boundary, the block boundary filling size of a block feature map is calculated; and based on the block number, the block size and the block boundary filling size, a convolution based on the block boundary filling is built to replace the original convolution. The resource constraint problem of the convolution neural network during operation of an embedded hardware platform is greatly alleviated, the burst length is improved maximally when a memory is read and written, the throughput is improved, the time delay is reduced, and the efficiency is improved.