摘要:
A disc storage system having a host computer interface adapted to coupled to a host computer, a disc storage medium having a disc surface and a spindle motor coupled to the disc adapted to rotate the disc. A transducer is positioned for reading and writing data on the disc surface. The system further includes a volatile memory write cache and a non-volatile memory write cache adapted to store data during a power loss. A method is also provided for storing data prior to writing the data in a non-volatile memory cache in a disc storage system.
摘要:
A magnetic disc storage system includes a magnetic storage disc and a transducing head. During periods of inactivity the transducing head is dithered whereby the head is moved to tracks on the disc according to a number of criteria. The criteria includes wear reduction, power reduction, avoidance of textured zones, head cycling, increased fly height and clearing of debris carried on the head.
摘要:
In general, this disclosure is directed to techniques for adjusting the timing of operations for a storage device. According to one aspect of the disclosure, a method includes receiving, with at least one device, a workload indicator. The method further includes adjusting, with the at least one device, an operation execution time for the storage device responsive to at least the workload indicator. In some examples, the workload indicator may include a host demand indicator. In additional examples, the workload indicator may include a resource utilization indicator. In further examples, the operation execution time may be one of a write operation execution time or a read operation execution time.
摘要:
A method formats disc surfaces in a disc drive for storage of data in a group of tracks on the disc surfaces. The disc drive performs seek operations to seek among cylinders on the disc surfaces as a function of time according to an actual seek profile. An approximation of the actual seek profile is determined such that the actual seek profile falls within the approximation. The disc surfaces are formatted according to the approximation of the actual seek profile.
摘要:
Method and apparatus for transferring speculative data in lieu of requested data in a data transfer operation. First data are transferred in response to an execution of a first pending command. Speculative data are transferred instead of second data associated with a second pending command during a next available latency period for the second data, preferably when the speculative data are adjudged as having a utility greater than a utility of the second data. The first and second commands are preferably received in a queue and a command execution algorithm identifies the second command as a next best command to be executed after execution of the first command. The above steps are preferably carried out by a controller of a data storage device.
摘要:
Methods and control systems for delaying a seek once a command is received to further load a buffer with read look ahead data are described. The methods involve calculating when or at what point the prefetching should cease and a seek should be initiated so that the actuator arm arrives at a new track just in time to begin reading the target data. The control systems include a processor that instructs a servo control to hold the actuator on a track while data is prefetched and loaded into a buffer until a seek must be initiated to allow the actuator to arrive at the new track just in time to begin reading the new target data.
摘要:
The disclosure is related to systems and methods of managing data storage in a memory device. In a particular embodiment, a method is disclosed that includes receiving, in a data storage device, at least one data packet that has a size that is different from an allocated storage capacity of at least one physical destination location on a data storage medium in the data storage device for the at least one data packet. The method also includes storing the at least one received data packet in a non-volatile cache memory prior to transferring the at least one received data packet to the at least one physical destination location.
摘要:
A first data set is written to first memory units identified as having a higher data reliability and a second data set is written to second memory units identified as having a lower data reliability than the first memory units. In some cases, the second data set may include metadata or redundancy information that is useful to aid in reading and/or decoding the first data set. The act of writing the second data set increases the data reliability of the first data set. The second data set may be a null pattern, such as all erased bits.
摘要:
A data storage system and method of scheduling commands in such a data storage system are provided in which commands are stored in a command sort queue and a scheduled command queue. Commands in the command sort queue are sorted and assigned a priority. Eventually, commands in the command sort queue are transferred to the scheduled command queue. Commands in the scheduled command queue are executed without further sorting. The desired queue depth or size of the scheduled command queue is determined as a function of both the queue depth of the command sort queue and a command execution rate value which is indicative of the rate at which commands in the scheduled command queue are executed. The desired queue depth may be dynamically determined using the queue depth of the command sort queue and the command execution rate value as inputs to a look-up table. The data storage system may include a small computer system interface (SCSI) disc (or “disk”) drive which executes commands from a host system.
摘要:
A unified debug system with multiple user-configurable trace volumes is disclosed, including embodiments as a system, a method, and a computer-readable medium. Embodiments of the present invention provide more robust and flexible solutions for introducing configurable trace volumes to firmware, allowing a user to specify firmware system configurations for trace buffers, trace frames, and trace volumes, and offer other advantages over the prior art. One embodiment of the present invention pertains to a system that includes a firmware component comprising firmware, and a firmware interface communicatively connected to the firmware component. The firmware includes a plurality of trace volumes for storing a plurality of trace entries. The trace volumes are user-configurable through the firmware interface. The plurality of trace volumes includes first, second and third trace volumes. The first trace volume includes storing at least some of the trace entries to a trace buffer in a first volatile memory component. The second trace volume includes storing at least some of the trace entries to one or more trace buffers in one or more trace frames in a second volatile memory component. The third trace volume includes storing at least some of the trace entries to one or more trace buffers in one or more trace frames in a non-volatile memory component.