摘要:
Embodiments in accordance with the present invention provide methods to record, in a rotating disk storage device, a data block in the unit of a logical sector on a recording medium on which a physical sector including a plurality of logical sectors is formatted. Extra addresses are acquired in a buffer to record write data blocks transferred from a host device. Data blocks are read from the recording medium in the unit of a physical sector. A skip read section discards data blocks having the same data blocks as the write data blocks by removing them from the read data blocks, and sends the remaining data blocks to the buffer. The buffer stores the data blocks in the order of recording in a physical sector.
摘要:
Embodiments of the invention raise the performance of a HDD by controlling the timing of notifying of command completion. In one embodiment, transmission of command completion notifications to a host is managed by a host interface manager. If two data write addresses respectively for two queued commands are adjacent or near to each other, that is, these addresses on the magnetic disk can be accessed without rotational latency, the host interface manager postpones the transmission of a command completion notification (X) concerning the first write command (X). Two command completion notifications (X) and (Y) are performed at a time after the write data (Y) for the next command is transmitted and its write to the medium is completed.
摘要:
A method and apparatus for minimizing performance degradation resulting from reassignment of data to alternate sectors as a result of a defect within the original sector. For example, when a request for writing data “a” into a sector A is made but the data is written into an alternative sector A′ in an alternative sector area X because the sector A is defective. Therefore, when a write request for writing data “b” into a sector B is made subsequently, re-assignment is performed to a sector B′ subsequent to the alternative sector A′. Similarly, a defective sector C for which a request for writing data “c” is made is re-assigned an alternative sector C′. Thus, the successive data a, b, and c are written into the successive sectors A′, B′, and C′ in the same alternative sector area X, minimizing performance degradation.
摘要:
The present invention includes a method of reading and writing data on a recording medium, and a system including a disk drive apparatus and a disk drive apparatus controller. According to the method of the present invention, data can be read in the middle of a plurality of write commands provided that the addresses of the read/write data locations do not overlap. This method and system results in improved read/write times.
摘要:
A disk storage device is disclosed for avoiding the instantaneous performance degradation as much as possible, and a method for processing a defective sector in such a disk storage device. There is executed a predetermined check related to a function of the disk storage device, preferably at least one of a read test, a write servo test, or a write test, when the disk storage device is in a waiting state where the disk storage device has no access from a host. The read test and write servo test are used to search for a defective sector on a disk and reassign the defective sector. The write test is used to indicate an abnormal condition of a head. Furthermore, the disk storage device includes a detector for detecting the waiting state, and a check logic for executing a predetermined check.
摘要:
A method and system are disclosed to prevent significant degradation of a data transfer rate in write cache transfer, thereby keeping the minimum data transfer rate high. The initial value Ti of the virtual buffer full capacity T(tx) is set to F/N (where F is a data capacity of the buffer, and N>1) and it is determined if the amount of write cached data S(tx) reaches the virtual buffer full capacity T(tx) so that write cache transfer is enabled during an S(tx)