18 results about "Shingled magnetic recording" patented technology

Non-sequential write commands in a shingled magnetic recording (SMR) drive are efficiently executed using a skip-bypass mode. When certain conditions are detected in the command history of the drive, the drive changes to the skip-bypass mode. In skip-bypass mode, data associated with the write commands are received into memory of the drive and written directly to a new SMR band in a sequential write operation, thereby bypassing storage in a media cache of the SMR drive. Prior to the sequential write operation, data associated with logical block addresses (LBAs) disposed between the LBAs referenced by the non-sequential write commands are read into the memory by a sequential read operation. The data associated with the non-sequential write commands can then be written, along with the data read in the sequential read operation, in a single sequential write operation to the new SMR band.

Controlling a shingled magnetic recording (SMR) hard drive involves attempting a sequential write to a first sector of a sequence of sectors and, responsive to encountering a write inhibit boundary corresponding to the first sector, continuing the write to the next available sector in the sequence of sectors for the write. Thus, instead of that write inhibit triggering a hard error, the data is adaptively written to the next down-track physical sector possible, i.e., “sliding” to the next sector. This does not require an additional disk revolution thus there is negligible performance penalty. The write may be continued to the next track if necessary, and may continue through the entire zone, to maintain all the data in sequential form for performance and large block protection purposes.

Data is written in tracks in a first sub-region of a region of a disk using Shingled Magnetic Recording (SMR). It is determined whether a predetermined data storage capacity for the region can be reached by adding a sub-region guard band and shingle writing throughout a remaining portion of the region using a lower limit of track overlap. The sub-region guard band does not store data and separates the first sub-region from a second sub-region in the region. In response to determining that the predetermined data storage capacity for the region can be reached by adding the sub-region guard band and shingle writing with the lower limit of track overlap throughout the remaining portion of the region, the sub-region guard band is added, and the second sub-region is shingle written with at least as much track overlap as the lower limit of track overlap.

The present technology enhances workload management of data storage systems by using an internal copy function and / or a zone-append technology. The internal copy function is used, e.g., in merge operations to move data between locations on a disk without using off-disk resources (e.g., processing or memory of a CPU). Zone-append technology uses nameless writes (e.g., write instruction without an assigned destination address on the disk) to combine IO units from different threads to be written to a common zone of a disk (e.g., a shingled magnetic recording (SMR) disk). Sequential addresses are assigned to IO units from different threads based on their order in the write queue, reducing the latency and seek time typically associated with random writes. The zone-append technology, e.g., uses sequential write operations within specified zones, allowing the disk to determine the actual write location and to report post-write logical block addresses (LBAs).

Write commands in a shingled magnetic recording (SMR) drive are efficiently executed when a write command and associated write data are received by an SMR HDD from a host while the target SMR band for storing the write data is undergoing a refresh operation. In response to the write command, the HDD suspends the refresh operation, stores the write data in nonvolatile memory, and informs the host that the write command has been completed. After the write data are stored in nonvolatile memory, the HDD resumes the refresh operation, and the remaining unrefreshed data in the target SMR band are refreshed by being rewritten to the spare SMR band. The nonvolatile memory can include the spare SMR band in some instances, the target SMR band in some instances, and in both the spare SMR band and the target SMR band in some instances.

The invention discloses a variable magnetic recording system and method, a server and a storage medium, and relates to the technical field of server data storage, the system comprises a memory, a read-write device of the memory, a display and a processor, and operation options of the memory are displayed through an interactive interface of the display. A user determines the target memory and the target magnetic recording mode based on the operation option, the target magnetic recording mode comprises a perpendicular magnetic recording mode or a shingled magnetic recording mode, the processor is connected with the read-write device and the display, the current magnetic recording mode of the target memory is modified based on the target magnetic recording mode, complex hardware modification is not needed, and the implementation is easy. According to the invention, the switching of the target magnetic recording mode can be realized through software configuration, the technical problem of high cost and design difficulty due to the fact that the switching of the target magnetic recording mode is realized through complex hardware transformation or an additional control circuit in the prior art is solved, and the technical effect of realizing flexible switching of the target magnetic recording mode at low cost is achieved.

An object storage data store may be implemented using storage devices providing multiple extents, where individual ones of the extents include multiple independently addressable, contiguous blocks and where updating an extent is performed by updating the respective independently addressable, contiguous blocks sequentially using a series of write operations. The storage devices may include shingled magnetic recording devices and may include conventional persistent storage devices. The key value data store may implement a superblock structure, index structure, and data store structure using respective portions of the multiple extents, where updates to each of the structures is performed sequentially using a series of write operations. The key value data store may further implement a cache for the index structure to minimize input-output (IO) density of the object storage data store.

According to one embodiment, a magnetic disk device includes a disk, a write head, an adjustment unit, and a write processing unit. The adjustment unit adjusts each of a first adjustment value, a second adjustment value, and a third adjustment value. The write processing unit can select shingled magnetic recording and perform write processing based on the first to third adjustment values. When the number of the plurality of tracks of the band is t+1 and the number of unused sectors among the plurality of sectors of the band is e. The adjustment unit adjusts the first to third adjustment values to establish e<t.

An information processing apparatus includes a nonvolatile memory and circuitry. The nonvolatile memory stores data written using shingled magnetic recording, in which tracks are partially arranged one over another in a radial direction. The circuitry is to instruct the nonvolatile memory to write the data in units of sectors, additionally write the data to a data writing area of the nonvolatile memory, create, on a volatile memory, a buffer for delayed writing in which the data to be written to the data writing area is temporarily held, and write the data in the buffer for delayed writing to the nonvolatile memory in a case that a total amount of data accumulated in the buffer for delayed writing exceeds a threshold value.

Controlling a shingled magnetic recording (SMR) hard drive involves writing, to a first track of a zone pre-sized based on a nominal track width based on an expected mean track width across an entire zone, a portion of a write operation according to the nominal track width. Then, based on the positional accuracy of the first track writing, determining a second track position for an adjacent second track, and writing the second track another portion of the write operation according to the determined second track position. Thus, the determination and position of a given track is determined by the positional accuracy of a previously written track, considering for example the position error signal corresponding to the writing of the previously written track. Thus, the track pitch is effectively defined by the average positional error across a zone rather than by a worst-case scenario positional error across the zone.

According to one embodiment, a magnetic disk device includes a disk, a write head, a write processing unit selecting a shingled magnetic recording, a determination unit, and a refresh processing unit. The determination unit determines whether a quality-degraded recording sector exists in all recording sectors in each of the bands. If it is determined that a target band including the quality-degraded recording sector exists in the bands, the refresh processing unit refreshes target recording sectors. The target recording sectors include the quality-degraded recording sector. In the target band, the number of the target recording sectors is less than the number of all recording sectors.

The present technology enhances workload management of data storage systems by using an internal copy function and / or a zone-append technology. The internal copy function is used, e.g., in merge operations to move data between locations on a disk without using off-disk resources (e.g., processing or memory of a CPU). Zone-append technology uses nameless writes (e.g., write instruction without an assigned destination address on the disk) to combine IO units from different threads to be written to a common zone of a disk (e.g., a shingled magnetic recording (SMR) disk). Sequential addresses are assigned to IO units from different threads based on their order in the write queue, reducing the latency and seek time typically associated with random writes. The zone-append technology, e.g., uses sequential write operations within specified zones, allowing the disk to determine the actual write location and to report post-write logical block addresses (LBAs).

A Data Storage Device (DSD) includes a disk for storing user data in tracks including sectors. Adjacent Track Interference (ATI) values are determined for annular locations along a guard band location designated to not store user data and to separate a first region of tracks from a second region of tracks. Based on the ATI values determined for the annular locations, guard band sectors are assigned from one or more adjacent tracks of the second region corresponding to one or more locations where the one or more adjacent tracks are deemed more susceptible to data corruption based on the determined ATI values. The assigned guard band sectors form part of the guard band. According to one aspect, the ATI values are determined based on at least one Magnetic Recording Metric (MRM) and a track pitch.

According to one embodiment, a magnetic disk device includes a disk, a write head, a write processing unit selecting a shingled magnetic recording, a determination unit, and a refresh processing unit. The determination unit determines whether a quality-degraded recording sector exists in all recording sectors in each of the bands. If it is determined that a target band including the quality-degraded recording sector exists in the bands, the refresh processing unit refreshes target recording sectors. The target recording sectors include the quality-degraded recording sector. In the target band, the number of the target recording sectors is less than the number of all recording sectors.

Systems and methods for data storage in a storage device are provided in the present disclosure. The method may include dividing the storage device into a recording region and a shingled magnetic recording (SMR) region. The SMR region may be configured to store data, and the recording region may be configured to store storage information associated with the storage device. The storage information may include at least a corresponding relationship between an index of the data and a storage location of the data. The method may also include obtaining target data to be stored. The method may further include determining, based on the target data and the storage information, a target position in the SMR region for storing the target data.

According to one embodiment, an adjustment method of a heat-assisted magnetic recording and reproduction device including a magnetic recording head and a heat-assisted magnetic recording medium, in which write characteristics are improved in a start area of a shingled magnetic recording band and in each area storing information other than user data.

Embodiments of the present application disclose a hard disk testing method and device, electronic equipment and medium. The method comprises: creating a disk array for a shingled magnetic recording (SMR) area and a conventional magnetic recording (CMR) area in a shingled hard disk; issuing data blocks to the disk array and / or reading data blocks; wherein the way of issuing data blocks to the disk array corresponding to the SMR area does not include a random way; and performing performance testing on the disk array issuing data blocks and / or reading data blocks. The technical solution can adaptively create a disk array for different areas of a shingled hard disk, and then perform testing respectively, thereby improving the accuracy and stability of shingled hard disk performance testing through a scheme suitable for shingled hard disk testing.

Write commands in a shingled magnetic recording (SMR) drive are efficiently executed when a write command and associated write data are received by an SMR HDD from a host while the target SMR band for storing the write data is undergoing a refresh operation. In response to the write command, the HDD suspends the refresh operation, stores the write data in nonvolatile memory, and informs the host that the write command has been completed. After the write data are stored in nonvolatile memory, the HDD resumes the refresh operation, and the remaining unrefreshed data in the target SMR band are refreshed by being rewritten to the spare SMR band. The nonvolatile memory can include the spare SMR band in some instances, the target SMR band in some instances, and in both the spare SMR band and the target SMR band in some instances.