Abstract: Data in a nonvolatile memory included in a data storage device is rewritten with higher security. According to one embodiment of the present invention, if an error is included in data stored in a nonvolatile semiconductor memory, the HDD rewrites correct data to the nonvolatile semiconductor memory. In particular, during the execution sequence of a write command, the HDD executes rewrite processing of control data stored in the nonvolatile semiconductor memory. More specifically, data is rewritten during a specified period of time that falls within a period of time starting from a start notification of write-data transfer processing that is sent from the HDD to the host, until a command completion notification. Since there is a very small possibility that the power of the host may be interrupted during this specified period of time, it is possible to securely rewrite data.

Abstract: Embodiments of the present invention help to improve accuracy in data and maintain data rate in a disk drive device which sends data at a reassignment source address to a host in response to a specific command. According to one embodiment, a hard disk drive (HDD) performs data write operations to a reassignment source data sector in addition to a reassignment destination source data sector if a reassigned data sector is present. Writing data to the reassignment source data sector improves accuracy in data to be transferred in a continuous read. The number of execution steps registered in an error recovery procedure (ERP) table in a write operation to the reassignment source data sector is smaller than the number of execution steps registered in an ERP table to the reassignment destination data sector.

Abstract: Data in a nonvolatile memory included in a data storage device is rewritten with higher security. According to one embodiment of the present invention, if an error is included in data stored in a nonvolatile semiconductor memory, the HDD rewrites correct data to the nonvolatile semiconductor memory. In particular, during the execution sequence of a write command, the HDD executes rewrite processing of control data stored in the nonvolatile semiconductor memory. More specifically, data is rewritten during a specified period of time that falls within a period of time starting from a start notification of write-data transfer processing that is sent from the HDD to the host, until a command completion notification. Since there is a very small possibility that the power of the host may be interrupted during this specified period of time, it is possible to securely rewrite data.

Abstract: Embodiments of the invention realize a power-save mode which prevents reduction in performance of a data storage device. The HDD as an embodiment of the present invention, upon receiving a request for switching to a power-save mode (PMREQ) from the host, judges whether the serial interface should be switched to the power-save mode based on the execution status of the command. When the HDD has determined not to switch the serial interface to the power-save mode, the HDD transmits a negative response (PMNACK) to the host and keep the serial interface in the active mode. By denying switching to a power-save mode when data transfer is executed within a short period of time, etc., it is possible to prevent reduction in performance of the data storage device.

Abstract: An error recovery procedure (ERP) in a storage device such as a rotating magnetic hard disk drive is executed to the last step regardless of the established time-out period for an instruction, thereby more reliably recovering from errors. In accordance with one embodiment of the invention, when a disk drive receives a reset instruction from a host during the execution of an ERP, it executes the ERP until the error is recovered, or to the last step without interrupting the ERP. Further, in accordance with another embodiment of the invention, when a disk drive receives a reset instruction during the execution of an ERP, it stops execution of the ERP and holds the number K of the step which was completed immediately before stopping, and when receiving a retry instruction after that, sequentially executes the ERP from the K+1-th error recovery step.