Magnetic disc device

Abstract

To provide a magnetic disc device capable of shortening a time required for write processing on a media cache area.SOLUTION: A magnetic disc device includes a disc DK, a head HD, a volatile buffer memory 90, a non-volatile memory 80, a main power source 5, and a control part. The control part has a write processing part 61a, a management part 62, a data protection processing part 63, a counter 64, and a determination part 65. Upon determination by the determination part 65 that a difference between a maximum value and a minimum value of a plurality of count values of a plurality of trucks of a media cache area M has reached a threshold value, the management part 62 returns, to a protection target, write data of the buffer memory 90 as original data of write data of the truck which is included in the plurality of trucks and whose count value is maximum.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to a magnetic disk drive.

Background Art

[0002] As magnetic disk drives, there are known a magnetic disk drive of a Conventional Magnetic Recording (CMR) type (or a conventional recording type) that writes a plurality of tracks at intervals in the radial direction of the disk, a Shingled Write Magnetic Recording (SMR) type (or Shingled Write Recording: SWR) magnetic disk drive that overwrites a plurality of tracks in the radial direction of the disk, and a hybrid recording type magnetic disk drive that selects and executes the conventional recording type and the shingled recording type.

[0003] The disk has a media cache area. Write data received by the magnetic disk drive from the host device is temporarily written to the media cache area. As an adverse effect on adjacent tracks when writing data to a track on the disk, Adjacent Track Interference (ATI) is known. It is difficult to read data on a track with a large adverse effect of ATI. Therefore, before it becomes difficult to read data, a refresh process is performed in which the data on the track is read, the data is rewritten to the track, and the data on the track is recovered.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0005] This embodiment provides a magnetic disk device capable of shortening the time required for write processing to a media cache area.

Means for Solving the Problems

[0006] A magnetic disk device according to an embodiment includes a disk having a media cache area including a plurality of tracks continuous in the radial direction on a recording layer, a head for writing data to the recording layer of the disk and reading data from the recording layer, a volatile buffer memory to which write data including a write command and user data corresponding to the write command is written, a non-volatile memory, a main power supply, and a control unit, the control unit including a write processing unit for controlling write processing of data to the recording layer, a management unit for including, as a protection target, write data before being written to the media cache area among the write data written in the buffer memory and excluding write data after being written to the media cache area from the protection target, a data protection processing unit for evacuating the write data managed by the management unit as the protection target to the non-volatile memory when the main power supply is lost, a counter capable of individually counting up a count value of each of the tracks in the media cache area, the counter being capable of counting up the count value of a track adjacent to the track to which the write data is written each time the write data is written to the media cache area, and a determination unit for determining whether a difference between a maximum value and a minimum value of a plurality of count values of the plurality of tracks in the media cache area has reached a threshold value, and when the determination unit determines that the difference has reached the threshold value, the management unit returns the write data in the buffer memory, which is the original data of the write data of the track having the maximum count value among the plurality of tracks, to the protection target.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

MODE FOR CARRYING OUT THE INVENTION

[0008] (One Embodiment) Hereinafter, a magnetic disk device 1 according to an embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the magnetic disk device 1 according to the present embodiment. In the present embodiment, the magnetic disk device 1 is a hybrid recording type magnetic disk device that selects and executes a normal recording type and a shingle recording type. However, the technology described later may be applied to a magnetic disk device of the normal recording type.

[0009] As shown in FIG. 1, the magnetic disk device 1 includes a plurality of, for example, 1 to 10 disks (magnetic disks) DK as recording media, a main power supply 5, a spindle motor (SPM) 12 as a drive motor, a head stack assembly (hereinafter referred to as HDA) 15, a driver IC 20, a head amplifier integrated circuit (hereinafter referred to as head amplifier IC or preamplifier) 30, a volatile memory 70, a non-volatile memory 80, a buffer memory (buffer) 90, and a system controller 130 which is a one-chip integrated circuit. Further, the magnetic disk device 1 is connected to a host device (hereinafter simply referred to as a host) 100.

[0010] Each disk DK is formed, for example, with a diameter of 97 mm (3.8 inches) and has a recording layer (magnetic recording layer) Y on both sides thereof. In the present embodiment, the magnetic disk device 1 includes 1 to 11 disks DK, but the number of disks DK is not limited to this.

[0011] The HDA 15 has a disk DK, a spindle motor (hereinafter referred to as SPM) 12, an arm 13 on which a head HD is mounted, and a voice coil motor (hereinafter referred to as VCM) 14. The disk DK is attached to the SPM 12 and rotates by the drive of the SPM 12. The arm 13 and the VCM 14 constitute an actuator. The actuator can control the movement of the head HD mounted on the arm 13 to a predetermined position on the disk DK by driving the VCM 14, that is, it can perform a seek. In the present embodiment, the magnetic disk device 1 may include a plurality of disks DK and a plurality of heads HD.

[0012] The disk DK has a writable area thereon, which is allocated with a user data area U that can be used by the user, a media cache area M (which may also be referred to as a media cache) that temporarily holds data (or commands) transferred from the host 100 or the like before writing the data to a predetermined area of the user data area U, and a system area S for writing information necessary for system management.

[0013] Hereinafter, the direction from the inner circumference to the outer circumference of the disk DK is referred to as the radial direction d1. In a direction parallel to the radial direction d1, the direction from the inner circumference to the outer circumference is referred to as the outer direction (outer side), and the direction from the outer circumference to the inner circumference is referred to as the inner direction (inner side). The direction orthogonal to the radial direction d1 of the disk DK is referred to as the circumferential direction or the peripheral direction. The circumferential direction corresponds to the direction along the circumference of the disk DK.

[0014] Also, a predetermined position in the radial direction d1 of the disk DK may be referred to as a radial position, and a predetermined position in the circumferential direction of the disk DK may be referred to as a circumferential position. The radial position and the circumferential position may be collectively simply referred to as a position. The radial position corresponds to the distance from the rotation center of the disk DK to a predetermined radial position, the distance from the innermost circumference of the disk DK to a predetermined radial position, or the distance from a predetermined radial position of the disk DK to another radial position, etc.

[0015] The head HD records and reproduces information with respect to the disk DK. The head HD has a slider as a main body and includes a write head WHD and a read head RHD mounted on the slider. The write head WHD writes data to the recording layer L of the disk DK. The read head RHD reads data from the data track of the recording layer L of the disk DK. Hereinafter, "writing data" may also be referred to as "writing", "data writing", "write processing", etc. "Reading data" may also be referred to as "reading", "data reading", "read processing", etc.

[0016] Note that the light head WHD may sometimes be simply referred to as the head HD, the read head RHD may sometimes be simply referred to as the head HD, and the light head WHD and the read head RHD may sometimes be collectively referred to as the head HD. The central part (center of gravity) of the head HD may sometimes be simply referred to as the head HD, the central part (center of gravity) of the light head WHD may sometimes be simply referred to as the light head WHD, and the central part (center of gravity) of the read head RHD may sometimes be simply referred to as the read head RHD.

[0017] "The central part (center of gravity) of the light head WHD" may sometimes be simply referred to as the "head HD", and "the central part (center of gravity) of the read head RHD" may sometimes be simply referred to as the "head HD". "Positioning the central part of the head HD at the track center of a predetermined track" may sometimes be expressed as "positioning the head HD on a predetermined track", "placing the head HD on a predetermined track", "positioning the head HD at a predetermined track", etc.

[0018] The system controller 130 includes a read / write (R / W) channel 40, a hard disk controller (HDC) 50, and a microprocessor (MPU) 60 as a control unit.

[0019] The driver IC 20 controls the driving of the SPM 12 and the VCM 14 according to the control of the system controller 130 (specifically, the MPU 60). The SPM 12 supports and rotates a plurality of disks DK.

[0020] The head amplifier IC (preamplifier) 30 includes a read amplifier and a write driver. The read amplifier amplifies the read signal read from the disk DK and outputs it to the system controller 130 (specifically, the R / W channel 40). The write driver outputs a write current corresponding to the signal output from the R / W channel 40 to the light head WHD.

[0021] The volatile memory 70 is a semiconductor memory in which the stored data is lost when the power supply is cut off. The volatile memory 70 stores data and the like necessary for processing in each part of the magnetic disk device 1. The volatile memory 70 is a random access memory (RAM: Random Access Memory). The volatile memory 70 is, for example, a DRAM (Dynamic Random Access Memory). However, the volatile memory 70 may be an SDRAM (Synchronous Dynamic Random Access Memory).

[0022] The non-volatile memory 80 is a semiconductor memory that records data stored even when the power supply is cut off. The non-volatile memory 80 is, for example, a NAND-type flash read-only memory (Flash Read Only Memory: FROM). However, the non-volatile memory 80 may be a NOR-type FROM.

[0023] The buffer memory 90 is a semiconductor memory that temporarily stores data and the like transmitted and received between the magnetic disk device 1 and the host 100. Note that the buffer memory 90 may be integrally configured with the volatile memory 70. The buffer memory 90 is a volatile RAM. By way of example, the buffer memory 90 is a DRAM, SRAM (Static Random Access Memory), SDRAM, FeRAM (Ferroelectric Random Access memory), MRAM (Magnetoresistive Random Access Memory), or the like.

[0024] The buffer memory 90 includes an area used as a write cache 91 and an area used as a read cache 92. Write data including a write command and user data corresponding to the write command is written to the write cache 91, and the write cache 91 temporarily stores the write data. A read command is written to the read cache 92, and the read cache 92 temporarily stores the read command.

[0025] The system controller (controller) 130 is realized using, for example, a large-scale integrated circuit (LSI) called a System-on-a-Chip (SoC) in which a plurality of elements are integrated on a single chip. The system controller 130 is electrically connected to, for example, the driver IC 20, the head amplifier IC 30, the volatile memory 70, the non-volatile memory 80, the buffer memory 90, and the host 100.

[0026] The R / W channel 40 executes signal processing, such as modulation processing, demodulation processing, encoding processing, and decoding processing, of read data transferred from the disk DK to the host 100 and write data transferred from the host 100 in response to an instruction from the MPU 60 described later. The R / W channel 40 has a circuit or function for measuring the signal quality of the read data. The R / W channel 40 is electrically connected to the head amplifier IC 30, the HDC 50, the MPU 60, etc.

[0027] The HDC 50 controls data transfer between the host 100 and the R / W channel 40 in response to an instruction from the MPU 60. The HDC 50 is electrically connected to, for example, the R / W channel 40, the MPU 60, the volatile memory 70, the non-volatile memory 80, the buffer memory 90, etc.

[0028] The main power supply 5, which is the power supply of the magnetic disk device 1, is connected to the driver IC 20, the head amplifier IC 30, the R / W channel 40, the HDC 50, the MPU 60, the volatile memory 70, the non-volatile memory 80, and the buffer memory 90. The driver IC 20, the head amplifier IC 30, the R / W channel 40, the HDC 50, the MPU 60, the volatile memory 70, the non-volatile memory 80, and the buffer memory 90 are driven by the power supplied from the main power supply 5. The SPM 12 and the VCM 14 are driven by the power supplied from the main power supply 5 via the driver IC 20.

[0029] The MPU60 is the main controller that controls each part of the magnetic disk device 1. The MPU60 controls the VCM14 via the driver IC20 and executes servo control for positioning the head HD. Also, the MPU60 controls the SPM12 via the driver IC20 to rotate the disk DK. The MPU60 controls the write operation of data to the disk DK and selects the storage destination of the write data. Also, the MPU60 controls the read operation of data from the disk DK and controls the processing of the read data. Also, the MPU60 manages the area for recording data. The MPU60 is connected to each part of the magnetic disk device 1. The MPU60 is electrically connected to the driver IC20, the R / W channel 40, the HDC50, etc.

[0030] The MPU60 includes a read / write processing unit 61, a management unit 62, a data protection processing unit 63, a counter 64, a determination unit 65, a write data selection processing unit 66, a write data integration processing unit 67, a command selection processing unit 68a, a command execution unit 68b, a command response processing unit 68c, etc. The MPU60 executes the processing of these units, for example, the read / write processing unit 61, the management unit 62, the data protection processing unit 63, the counter 64, the determination unit 65, the write data selection processing unit 66, the write data integration processing unit 67, the command selection processing unit 68a, the command execution unit 68b, the command response processing unit 68c, etc. on the firmware. Note that the MPU60 may include these units as circuits.

[0031] The read / write processing unit 61 has a write processing unit 61a and a read processing unit 61b. In accordance with commands from the host 100, the write processing unit 61a controls the write processing of data to the recording layer L, and the read processing unit 61b controls the read processing of data from the recording layer L. The write processing unit 61a is capable of executing write processing for writing data to the recording layer L of the disk DK. The read processing unit 61b is capable of executing read processing for reading data from the recording layer L. The read / write processing unit 61 controls the VCM 14 via the driver IC 20, positions the head HD at a target position (a predetermined radial position) on the disk DK, and executes read processing or write processing.

[0032] The management unit 62 can include, as protection targets, write data in the buffer memory 90 that is to be written to the media cache area M before being written to the media cache area M, and can exclude write data after being written to the media cache area M from the protection targets. When the main power supply 5 is lost, the data protection processing unit 63 can save the write data managed by the management unit 62 as protection targets to the non-volatile memory 80. The data protection processing unit 63 can perform power loss protection (PLP) processing to guarantee the write data to be protected in the buffer memory 90.

[0033] The counter 64 can individually count up the count value of each track in the media cache area M. The counter 64 can count up the count value of a track adjacent to the track where write data is written each time write data is written to the media cache area M. The counter 64 increases the count value by "1" each time it counts up. However, the counter 64 may increase the count value by "0.8" or "1.5" each time it counts up, and the value to be increased is not particularly limited.

[0034] Note that the non-volatile memory 80 has a management table TL that individually stores the count values of each track in the media cache area M. However, the management table TL may be provided in a storage medium or storage area other than the non-volatile memory 80.

[0035] The determination unit 65 can determine whether the difference between the maximum value and the minimum value among the count values of a plurality of tracks in the media cache area M has reached a threshold value. The write data selection processing unit 66 can perform a reordering process for rearranging the write data written to the buffer memory 90. The processing performed by the write data integration processing unit 67 will be described later.

[0036] The command selection processing unit 68a can perform a reordering process for rearranging a plurality of write commands of the write data written to the buffer memory 90. The command execution unit 68b can execute the write command selected by the command selection processing unit 68a. The processing performed by the command response processing unit 68c will be described later.

[0037] Next, the processing procedure when the determination unit 65 determines that the difference has reached the threshold value and the effects of the processing procedure will be described. When the determination unit 65 determines that the difference has reached the threshold value, the management unit 62 can perform the following processing. That is, the management unit 62 can return the write data in the buffer memory 90, which is the original data of the write data of the track with the maximum count value among the plurality of tracks in the media cache area M, to the protection target. Specifically, the status of the original data in the buffer memory 90 can be returned to the protection target.

[0038] In other words, when the determination unit 65 determines that there is data of a track with a large influence of ATI (Adjacent Track Interference) in the media cache area M, the data protection processing unit 63 can perform PLP processing on the write data of the buffer memory 90, which is the original data, together with the management unit 62. By performing the PLP processing, the write data (original data) of the buffer memory 90 can be guaranteed, and the write data can be guaranteed without additional write processing to the media cache area M. Therefore, the data protection processing unit 63 can quickly guarantee the write data together with the management unit 62. As a result, it can contribute to shortening the time required for the write processing to the media cache area M. Furthermore, since it is not necessary to forcibly write the original data of the track with a large influence of ATI to the user data area U, which is the place of origin, it is possible to obtain the effect of improving the processing efficiency such as the write processing.

[0039] When the determination unit 65 determines that the above difference has reached the above threshold, the counter 64 and the write processing unit 61a can perform the following processing. That is, the counter 64 resets the count value of the track whose count value has reached the maximum value to the initial value. The write processing unit 61a can regard the track whose count value has reached the maximum value as an empty track that can be overwritten. Note that the above initial value is, for example, "0". However, the above initial value may be a numerical value other than "0".

[0040] As described above, since the write data (original data) of the buffer memory 90 is guaranteed by performing the PLP processing, the data of the track with a large influence of ATI in the media cache area M is indirectly guaranteed. For example, it is not necessary to provide a write guard for the track with a large influence of ATI and the track adjacent to that track (prohibit writing to the track with a large influence of ATI and the track adjacent to that track).

[0041] Since it is possible to reduce the write prohibition area in the media cache area M, it is possible to increase the amount of newly writable data from the buffer memory 90 to the media cache area M. Furthermore, it is possible to increase the candidates for writable tracks among the plurality of tracks in the media cache area M. In other words, since the degree of freedom in selecting the write destination of the media cache area M can be increased, the restriction on the reordering process by the write data selection processing unit 66 can be relaxed. As a result, when the main power supply 5 is lost, it is possible to increase the amount of write data that can be guaranteed by the media cache area M and the non-volatile memory 80.

[0042] Next, the processing procedure and effects of the write processing unit 61a when the write data selection processing unit 66 performs the reordering process will be described. When the write data selection processing unit 66 performs the reordering process, the write processing unit 61a can write the write data selected by the write data selection processing unit 66 to the media cache area M. Since the write data can be written to the media cache area M after performing the reordering process, the overhead can be reduced.

[0043] Note that when the reordering process is performed, the adverse effect of ATI is more likely to occur in the media cache area M than when the reordering process is not performed (when writing sequentially). However, since the PLP process can be performed as described above, the problem of the adverse effect of ATI can be dealt with well.

[0044] Next, the timing of the write data selection processing unit 66 performing the reordering process and its effects will be described. Each time the write data transferred from the host 100 is newly written (stored) in the buffer memory 90 or the write data removed from the protection target by the management unit 62 is returned to the protection target, the management unit 62 can update the protection target. That is, the management unit 62 can update the protection target at any time.

[0045] Each time the management unit 62 updates the protection target, the write data selection processing unit 66 can perform reordering processing. Therefore, the write data selection processing unit 66 can always perform reordering processing.

[0046] Next, the processing procedures of the write data integration processing unit 67 and the write processing unit 61a when the determination unit 65 determines that the difference has reached the threshold, and the effects of the above processing procedures will be described. When the determination unit 65 determines that the difference has reached the threshold, the write data integration processing unit 67 can generate integrated write data obtained by integrating (merging) the head write data that the write data selection processing unit 66 will select next and the write data that is the original data. Further, the write processing unit 61a can write the integrated write data including the head write data selected by the write data selection processing unit 66 to the media cache area M.

[0047] Therefore, compared with the case where the write to the media cache area M of the head write data that the write data selection processing unit 66 will select next and the write to the media cache area M of the write data that is the original data are performed separately without generating the above integrated write data, the time required for the write processing to the media cache area M can be shortened. By repeating the above processing procedure, it becomes difficult for the writable area of the media cache area M to become saturated, and write data can be written to the optimal area (the area that can always be accessed at the highest speed) of the media cache area M. Therefore, it is possible to achieve both suppression of deterioration of write performance and guarantee of write data.

[0048] Next, the processing procedure of the command response processing unit 68c and the effects of the above processing procedure will be described. The magnetic disk device 1 has a write cache function that reports a status indicating that the execution of the write command has been completed when it receives write data including a write command and user data from the host 100. When the write cache function is enabled (Write Cache Enable), the command response processing unit 68c can report to the host 100 a status indicating that the execution of the write command has been completed when the write data is written to the buffer memory 90 (write cache 91).

[0049] On the other hand, when the write cache function is disabled (Write Cache Disable), the command response processing unit 68c can report to the host 100 a status indicating that the execution of the write command has been completed when the user data is written to the user data area U after the write data is written to the buffer memory 90 (write cache 91) and the user data is guaranteed.

[0050] However, in this embodiment, since the PLP process is performed before writing the user data to the user data area U which is the place of origin, the write data is guaranteed at the time when the PLP process is performed. Therefore, it is desirable to report to the host 100 a status indicating that the execution of the write command has been completed without waiting for the writing of the user data to the user data area U. That is, when the management unit 62 includes the write data in the protection target, it is desirable for the command response processing unit 68c to report to the host 100 a status indicating that the execution of the write command for the write data of the protection target has been completed. Thereby, the timing of reporting the above status to the host 100 can be advanced. The host 100 can recognize that the writing to the medium of the magnetic disk device 1 has been completed.

[0051] Next, the processing procedure for writing user data to the user data area U and the effects of the above processing procedure will be described. The write data written to the buffer memory 90 (write cache 91) includes first write data including a first write command and first user data corresponding to the first write command.

[0052] After the first write data read from the buffer memory 90 is written to the media cache area M, the command execution unit 68b, the write processing unit 61a, and the management unit 62 can perform the following processing. That is, the command execution unit 68b executes the first write command selected by the command selection processing unit 68a. The write processing unit 61a writes the first user data read from the buffer memory 90 to the user data area U, and then regards the area in the media cache area M where the first write data remains as an overwriteable empty area. The management unit 62 regards the area in the buffer memory 90 where the first write data remains as an overwriteable empty area.

[0053] As described above, by writing the first user data to the user data area U which is the place of origin, the free capacity of the media cache area M and the free capacity of the buffer memory 90 can be increased.

[0054] Subsequently, a processing procedure for regarding the track of the media cache area M as an empty track or resetting the count value, and the effect of the above processing procedure will be described. When performing the PLP process, as described above, the write processing unit 61a regards the track of the media cache area M as an empty track. Furthermore, the write processing unit 61a can also regard the track of the media cache area M as an empty track when writing user data to the user data area U which is the place of origin.

[0055] For example, when the write processing unit 61a regards the entire track in the media cache area M where the first write data remains as a free area, the counter 64 can reset the count value of the track where the first write data remains to the initial value. Also in this example, when the main power supply 5 is lost, the amount of write data that can be guaranteed by the media cache area M and the non-volatile memory 80 can be increased.

[0056] Next, the processing procedure for the counter 64 to increment the count value and the effects of the above processing procedure will be described. Each track in the media cache area M is an empty track where no write data has been written, an empty track where write data has been written and overwriting is permitted, or a valid track where write data has been written and overwriting is prohibited. The empty track where no write data has been written corresponds to an unused (initial) track where no write data has been written at all. The empty track where write data has been written and overwriting is permitted corresponds to a track that has only write data corresponding to either (1) the write data guaranteed by the PLP process or (2) the write data written in the user data area U. The valid track where write data has been written and overwriting is prohibited corresponds to a track that has write data that has not yet been written in the user data area U.

[0057] The counter 64 includes the above valid tracks in the target for incrementing the count value and excludes the above empty tracks from the target for incrementing the count value. In other words, the counter 64 includes the tracks for which it is desired to avoid the occurrence of errors by ATI during reading in the target for incrementing the count value. Thereby, it is possible to accurately grasp the degree to which each track in the media cache area M is affected by ATI, and the PLP process can be performed at a desired timing.

[0058] Here, depending on the position of the first track in the media cache area M where write data is written, it is divided into a case where the count values of two tracks are incremented and a case where the count value of one track is incremented. A track adjacent to the first track in the media cache area M and located on the inner circumference side of the first track is defined as the inner circumference side track. A track adjacent to the first track in the media cache area M and located on the outer circumference side of the first track is defined as the outer circumference side track.

[0059] When the first track does not correspond to either the innermost track or the outermost track in the media cache area M, the media cache area M includes both the inner circumference side track and the outer circumference side track, and the counter 64 can increment the count value of the inner circumference side track and the count value of the outer circumference side track when write data is written to the first track.

[0060] When the first track corresponds to the innermost track in the media cache area M, the media cache area M includes the outer circumference side track, the inner circumference side track is a guard track, and the counter 64 can increment the count value of the outer circumference side track when write data is written to the first track.

[0061] Similarly, when the first track corresponds to the outermost track in the media cache area M, the media cache area M includes the inner circumference side track, the outer circumference side track is a guard track, and the counter 64 can increment the count value of the inner circumference side track when write data is written to the first track.

[0062] Next, the capacities of the non-volatile memory 80 and the buffer memory 90 will be described. The non-volatile memory 80 has a recording capacity of, for example, 4 MiB as several MiB. On the other hand, the buffer memory 90 has a recording capacity of, for example, 256 MiB as several hundreds of MiB. The recording capacity of the non-volatile memory 80 is smaller than that of the buffer memory 90. Therefore, it is difficult to evacuate all the write data of the buffer memory 90 to the non-volatile memory 80.

[0063] At any timing after write data is written to the buffer memory 90, the write data included in the protection target by the management unit 62 is within the range that can be evacuated to the non-volatile memory 80. Therefore, the management unit 62 can include only the amount of data that can be evacuated to the non-volatile memory 80 in the protection target.

[0064] Next, the processing procedure of the data protection processing unit 63 when the main power supply 5 is restored and the effect of the above processing procedure will be described. When the main power supply 5 is restored after the main power supply 5 is lost, the data protection processing unit 63 can process as follows. That is, the data protection processing unit 63 writes the write data evacuated to the non-volatile memory 80 and the write data written to the media cache area M to the buffer memory 90, and can restore the write data in the buffer memory 90. Thereby, the magnetic disk device 1 can continue processing using the write data restored in the buffer memory 90.

[0065] FIG. 2 is a perspective view showing a part of the magnetic disk device 1, and is a view showing a plurality of disks DK and a plurality of heads HD. In FIG. 2, the illustration of the media cache area M is omitted. As shown in FIG. 2, in the circumferential direction of the disk DK, the direction in which the disk DK rotates is referred to as the rotation direction d3. In the example shown in FIG. 2, the rotation direction is shown counterclockwise, but it may be in the opposite direction (clockwise). Also, the traveling direction d2 of the head HD with respect to the disk DK is opposite to the rotation direction d3. The traveling direction d2 is the direction in which the head HD sequentially writes and reads data with respect to the disk DK in the circumferential direction, that is, the direction in which the head HD travels with respect to the disk DK in the circumferential direction.

[0066] The magnetic disk device 1 includes i disks DK1 to DKi and j heads HD1 to HDj. In the present embodiment, the number of heads HD is twice the number of disks DK (j = 2 × i). The disks DK1 to DKi are coaxially provided and stacked with a space therebetween. The diameters of the disks DK1 to DKi are the same. Here, terms such as "the same", "identical", "coincident", "equivalent" include not only the meaning of being exactly the same but also the meaning of being different to the extent that they can be regarded as substantially the same. Note that the diameters of the disks DK1 to DKi may be different from each other.

[0067] Each disk DK has recording layers L on both sides. For example, the disk DK1 has a first recording layer La1 and a second recording layer Lb1 on the opposite side of the first recording layer La1. The disk DK2 has a first recording layer La2 and a second recording layer Lb2 on the opposite side of the first recording layer La2. The disk DKi has a first recording layer Lai and a second recording layer Lbi on the opposite side of the first recording layer Lai. Each first recording layer La may also be referred to as a surface or a recording surface. Each second recording layer Lb may also be referred to as a back surface or a recording surface.

[0068] Each recording layer L has a user data area U, a system area S, and the like. The first recording layer La1 has a user data area Ua1 and a system area Sa1. The second recording layer Lb1 has a user data area Ub1 and a system area Sb1. The first recording layer La2 has a user data area Ua2 and a system area Sa2. The second recording layer Lb2 has a user data area Ub2 and a system area Sb2. The first recording layer Lai has a user data area Uai and a system area Sai. The second recording layer Lbi has a user data area Ubi and a system area Sbi.

[0069] Among the user data area Ua1 (the first recording layer La1), the track sandwiched by double dashed lines in the figure is defined as track Ta1. Among the user data area Ub1 (the second recording layer Lb1), the track located on the opposite side of track Ta1 is defined as track Tb1. Among the user data area Ua2 (the first recording layer La2), the track sandwiched by double dashed lines in the figure is defined as track Tc1. Among the user data area Ub2 (the second recording layer Lb2), the track located on the opposite side of track Tc1 is defined as track Td1. Among the user data area Uai (the first recording layer Lai), the track sandwiched by double dashed lines in the figure is defined as track Te1. Among the user data area Ubi (the second recording layer Lbi), the track located on the opposite side of track Te1 is defined as track Tf1. In this embodiment, tracks Ta1, Tb1, Tc1, Td1, Te1, and Tf1 are located on the same cylinder.

[0070] The head HD faces the disk DK. In this embodiment, one head HD faces each recording layer L of the disk DK. For example, head HD1 faces the first recording layer La1 of disk DK1, writes data to the first recording layer La1, and reads data from the first recording layer La1. Head HD2 faces the second recording layer Lb1 of disk DK1, writes data to the second recording layer Lb1, and reads data from the second recording layer Lb1.

[0071] The head HD3 faces the first recording layer La2 of the disk DK2, writes data to the first recording layer La2, and reads data from the first recording layer La2. The head HD4 faces the second recording layer Lb2 of the disk DK2, writes data to the second recording layer Lb2, and reads data from the second recording layer Lb2. The head HDj-1 faces the first recording layer Lai of the disk DKi, writes data to the first recording layer Lai, and reads data from the first recording layer Lai. The head HDj faces the second recording layer Lbi of the disk DKi, writes data to the second recording layer Lbi, and reads data from the second recording layer Lbi.

[0072] FIG. 3 is a schematic diagram showing an example of the arrangement of a plurality of servo areas SV and a plurality of data areas DTR on one disk DK according to the present embodiment. As shown in FIG. 3, in the radial direction d1 of the disk DK, the direction toward the outer circumference of the disk DK is referred to as the outer direction (outer side), and the direction opposite to the outer direction is referred to as the inner direction (inner side). In FIG. 3, the user data area U is divided into an inner peripheral area IR located in the inner direction, an outer peripheral area OR located in the outer direction, and a middle peripheral area MR located between the inner peripheral area IR and the outer peripheral area OR.

[0073] The disk DK has a plurality of servo areas SV and a plurality of data areas DTR. The plurality of servo areas SV may be, for example, radially extending in the radial direction of the disk DK and discretely arranged at predetermined intervals in the circumferential direction. The plurality of servo areas SV may be, for example, linearly extending from the inner circumference to the outer circumference and discretely arranged at predetermined intervals in the circumferential direction. The plurality of servo areas SV may be, for example, spirally extending from the inner circumference to the outer circumference and discretely arranged at predetermined intervals in the circumferential direction. Also, the plurality of servo areas SV may be, for example, arranged in an island shape in the radial direction and discretely arranged at different predetermined intervals in the circumferential direction.

[0074] Hereinafter, one servo area SV in a predetermined track may be referred to as a "servo sector". Note that the "servo area SV" may also be referred to as a "servo sector SV". The servo sector contains servo data. Hereinafter, the "arrangement etc. of several servo data constituting the servo sector" may also be referred to as a "servo pattern". Note that the "servo data written to the servo sector" may also be referred to as a "servo sector".

[0075] The plurality of data areas DTR are respectively arranged between the plurality of servo areas SV. For example, the data area DTR corresponds to the area between two consecutive servo areas SV in the circumferential direction. Hereinafter, one data area DTR in a predetermined track may be referred to as a "data sector". Note that the "data area DTR" may also be referred to as a "data sector DTR". The data sector contains user data. Note that the "user data written to the data sector" may also be referred to as a "data sector". The "data sector" may also be referred to as "user data". Also, a "pattern composed of several data" may also be referred to as a "data pattern". In the example shown in FIG. 3, the data pattern of a predetermined track is composed of a plurality of servo data (servo sectors) and a plurality of user data (data sectors).

[0076] The servo area SV has a plurality of zone servo areas ZSV etc. Note that the servo area SV may, in addition to the zone servo area ZSV, include an area including a gap (circumferential position deviation between two zone servo areas), an area including servo data, and a data area DTR etc. The plurality of zone servo areas ZSV are discretely arranged along the radial direction d1. The plurality of zone servo areas ZSV respectively extend in the radial direction d1.

[0077] One zone servo area (servo area) ZSV in a predetermined track may be referred to as a "zone servo sector" or a "servo sector". Note that "zone servo area (servo area) ZSV" may also be referred to as "zone servo sector ZSV" or "servo sector ZSV". "Servo data written to the zone servo sector" may also be referred to as a "zone servo sector" or a "servo sector". Hereinafter, "the arrangement etc. of several servo data constituting the zone servo sector" may also be referred to as a "zone servo pattern" or a "servo pattern". Hereinafter, one servo area SV in a predetermined track may be referred to as a "zone pattern sector".

[0078] Note that "servo area SV" may also be referred to as a "zone pattern sector". "At least one data etc. written to the zone pattern sector" may also be referred to as a "zone pattern sector". The zone pattern sector includes at least one zone servo sector. Hereinafter, "the data pattern of the zone pattern sector" may also be referred to as a "zone data pattern".

[0079] In the example shown in FIG. 3, the servo area SV has zone servo areas ZSV0, ZSV1, and ZSV2. The zone servo areas ZSV0, ZSV1, and ZSV2 are arranged in a staggered pattern in the radial direction. The zone servo areas ZSV0, ZSV1, and ZSV2 may be arranged in a stepped pattern in the radial direction.

[0080] The zone servo region ZSV2 is located on the inner circumferential side of the zone servo region ZSV1. The zone servo region ZSV0 is located on the outer circumferential side of the zone servo region ZSV1. For example, the zone servo region ZSV2 is arranged from the inner circumferential region IR to the middle circumferential region MR, the zone servo region ZSV1 is arranged from the inner circumferential region IR to the outer circumferential region OR, and the zone servo region ZSV0 is arranged from the middle circumferential region MR to the outer circumferential region OR. Hereinafter, in a predetermined servo region SV, a predetermined region in the radial direction where a plurality of zone servo regions ZSV are arranged in the circumferential direction may also be referred to as a zone servo boundary region or a double servo region or a double zone servo region ZB.

[0081] In the example shown in FIG. 3, the main servo region SVO and the sub - servo region SVE are alternately arranged at intervals in the circumferential direction. For example, in the circumferential direction, one sub - servo region SVE is arranged between two main servo regions SVO that are continuously arranged at intervals. In other words, in the circumferential direction, one sub - servo region SVE is arranged between two main servo regions SVO that are continuously arranged at intervals. For example, when consecutive numbers are assigned to all the servo regions SV of the disk DK in order, the main servo region SVO corresponds to the odd - numbered servo regions SV, and the sub - servo region SVE corresponds to the even - numbered servo regions SV. Note that two or more sub - servo regions SVE may be arranged between two main servo regions SVO that are continuously arranged at intervals in the circumferential direction.

[0082] The main servo region SVO and the sub - servo region SVE may be composed of, for example, only a servo region (hereinafter, may also be referred to as a normal servo region) that reads and demodulates servo data as a whole. Hereinafter, "reading and demodulating servo data" may also be referred to as "servo - reading". The main servo region SVO and the sub - servo region SVE may be composed of, for example, a normal servo region and a servo region (hereinafter, may also be referred to as a short servo region) that servo - reads a circumferential range of servo data smaller than the circumferential range of the servo data servo - read in the normal servo region.

[0083] In the description of this embodiment, the case where the number of zones of the disk DK is three has been described as an example, but the number of zones of the disk DK can be variously changed. The number of zones of the disk DK may be 30 to 40. Also, each zone has a plurality of bands. For example, each zone has several hundred bands.

[0084] FIG. 4 is a schematic diagram showing three tracks STR of the user data area U where the tile recording process of the disk DK shown in FIG. 3 is performed, and the write head WHD. The user data area U is a tile recording area. In the user data area U, it is permitted to write data sequentially in band units, that is, tile recording is permitted. The track STR is a data track.

[0085] As shown in FIG. 4, the write head WHD can sequentially write data to the disk DK in the traveling direction d2. The read head RHD shown in FIG. 3 can also sequentially read the data written to the disk DK in the traveling direction d2.

[0086] In the direction parallel to the radial direction d1, the direction of continuously performing tile recording on a plurality of tracks STR, that is, the direction of overlapping the next track STR to be written with respect to the track STR written one before in the radial direction d1 is called the overwrite direction or the recording progress direction. In the band BAe shown in FIG. 4, the overwrite direction is the inner direction, but the overwrite direction may be the outer direction. For example, the overwrite direction applied to a plurality of bands BA (a plurality of zones Z) located on the outer peripheral side from a specific radius position and the overwrite direction applied to a plurality of bands BA (a plurality of zones Z) located on the inner peripheral side from a specific radius position may be opposite to each other.

[0087] Band BAe has a plurality of tracks STR including tracks STRe, STRe+1, and STRe+2. Tracks STRe, STRe+1, and STRe+2 are continuously overwritten in the overwrite direction in the order of these descriptions. Among tracks STRe, STRe+1, and STRe+2, track STRe corresponds to the track where data is first written, and track STRe+2 corresponds to the track where data is written last.

[0088] Track STRe has a track center STCe at the center in the radial direction d1 when no other tracks are overwritten. Track STRe+1 has a track center STCe+1 at the center in the radial direction d1 when no other tracks are overwritten. Track STRe+2 has a track center STCe+2 at the center in the radial direction d1 when no other tracks are overwritten.

[0089] In the example shown in FIG. 4, tracks STRe, STRe+1, and STRe+2 are written with a pitch (tile recording track pitch) STP. The track center STCe of track STRe and the track center STCe+1 of track STRe+1 are separated by a pitch STP in the radial direction d1. The track center STCe+1 of track STRe+1 and the track center STCe+2 of track STRe+2 are separated by a pitch STP in the radial direction d1. Tracks STRe to STRe+2 may be written with different pitches.

[0090] The width in the radial direction d1 of the region of track STRe where track STRe+1 is not overwritten and the width in the radial direction d1 of the region of track STRe+1 where track STRe+2 is not overwritten are the same. Note that the width in the radial direction d1 of the region of track STRe where track STRe+1 is not overwritten and the width in the radial direction d1 of the region of track STRe+1 where track STRe+2 is not overwritten may be different.

[0091] In FIG. 4, for the sake of convenience of explanation, each track STR is shown in a rectangular shape, but in reality, each track STR is curved along the circumferential direction. Further, each track STR may be wavy, extending in the circumferential direction while varying in the radial direction d1. Note that in FIG. 4, three tracks STR are overlaid, but more than three tracks STR may be overlaid. It is only necessary that a plurality of track STRs are overlaid in units of the band BAe.

[0092] The write processing unit 61a can select a tile recording format in which data is written to a plurality of tracks STR overlaid in the radial direction d1 of the disk DK and execute write processing. In the example shown in FIG. 4, the write processing unit 61a sequentially performs tile recording on tracks STRe to STRe+2 in the band BAe at a pitch STP toward the inner direction (overlay direction).

[0093] The write processing unit 61a writes track STRe+1 at a pitch STP in the inner direction of track STRe and overlays a part of track STRe+1 on a part of the inner circumferential side of track STRe. The write processing unit 61a writes track STRe+2 at a pitch STP in the inner direction of track STRe+1 and overlays a part of track STRe+2 on a part of the inner circumferential side of track STRe+1.

[0094] FIG. 5 is a schematic diagram showing three tracks CTR in the media cache area M where the normal recording process of the disk DK shown in FIG. 3 is performed, and the write head WHD. The media cache area M and the system area S shown in FIG. 3 are normal recording areas. In the media cache area M and the system area S, random data writing is permitted, that is, normal recording is permitted. The track CTR is a data track.

[0095] As shown in FIG. 5, the media cache area M has a plurality of tracks CTR including tracks CTRe, CTRe+1, and CTRe+2. For example, the widths (track widths) in the radial direction d1 of tracks CTRe, CTRe+1, and CTRe+2 are the same. Note that the track widths of tracks CTRe to CTRe+2 may be different from each other.

[0096] Track CTRe has a track center CTCe at the center in the radial direction d1, track CTRe+1 has a track center CTCe+1 at the center in the radial direction d1, and track CTRe+2 has a track center CTCe+2 at the center in the radial direction d1. In the example shown in FIG. 4, tracks CTRe, CTRe+1, and CTRe+2 are written with a pitch (normal recording track pitch) CTP. The track center CTCe of track CTRe and the track center CTCe+1 of track CTRe+1 are separated by a pitch CTP. The track center CTCe+1 of track CTRe+1 and the track center CTCe+2 of track CTRe+2 are separated by a pitch CTP.

[0097] Track CTRe and track CTRe+1 are separated with a gap GP therebetween. Track CTRe+1 and track CTRe+2 are separated with a gap GP therebetween. Note that tracks CTRe to CTRe+2 may be written with different pitches. In FIG. 5, for convenience of explanation, each track CTR is shown in a rectangular shape, but actually, each track CTR is curved along the circumferential direction. Also, each track CTR may be wavy, extending in the circumferential direction while varying in the radial direction d1.

[0098] The write processing unit 61a can select a normal recording format in which data is written to a plurality of tracks CTR at intervals in the radial direction d1 of the disk DK and execute write processing. In the example shown in FIG. 4, in a predetermined area of the disk DK, the write processing unit 61a positions the write head WHD at the track center CTCe and normally records track CTRe or a predetermined sector of track CTRe.

[0099] The light processing unit 61a positions the light head WHD at a track center CTCe+1 that is separated from the track center CTCe of the track CTRe by a pitch CTP inward, and normally records the track CTRe+1 or a predetermined sector of the track CTRe+1. The light processing unit 62 positions the light head WHD at a track center CTCe+2 that is separated from the track center CTCe+1 of the track CTRe+1 by a pitch CTP inward, and normally records the track CTRe+2 or a predetermined sector of the track CTRe+2.

[0100] The light processing unit 61a may sequentially and normally record the tracks CTRe, CTRe+1, and CTRe+2 in a predetermined area of the disk DK, or may randomly and normally record a predetermined sector of the track CTRe, a predetermined sector of the track CTRe+1, and a predetermined sector of the track CTRe+2.

[0101] FIG. 6 is an enlarged plan view showing the disk DK shown in FIG. 3, and shows four media cache areas M and four user data areas U, etc. As shown in FIG. 6, the disk DK includes media cache areas M0, M1, M2, M3 and user data areas U0, U1, U2, U3 in the recording layer L. The media cache areas M0, M1, M2, M3 are provided inward in this order. In order to volatilize the operation of receiving write data in the nonvolatile memory 80 by the PLP, the media cache areas M0 to M3 serve as a temporary storage location for the write data of the buffer memory 90. The user data areas U0, U1, U2, U3 are provided inward in this order. The media cache areas M and the user data areas U are alternately provided in the radial direction d1.

[0102] One guard track GTR is provided between the media cache area M and the user data area U adjacent to each other in the radial direction d1. However, two or more guard tracks GTR may be provided between the media cache area M and the user data area U. In the present embodiment, a system area S is provided on the outermost peripheral side of the recording layer L. The system area S and the media cache area M0 are adjacent to each other in the radial direction d1, and one or more guard tracks GTR are also provided between the system area S and the media cache area M0. In the figure, the guard track GTR is marked with a dot pattern.

[0103] Note that the respective numbers of the media cache area M and the user data area U provided in the recording layer L and the layouts of the media cache area M and the user data area U are not limited to the example of FIG. 6 and can be variously deformed. The disk DK only needs to include at least one media cache area M and at least one user data area U in the recording layer L.

[0104] FIG. 7 is a plan view showing the disk DK shown in FIG. 6 and is a view showing an enlargement of a plurality of tracks CTR of one media cache area M0. As shown in FIG. 7, the media cache area M0 includes eight tracks CTR0, CTR1, CTR2,..., CTR7. The tracks CTR0, CTR1, CTR2,..., CTR7 are provided inward in this order and are continuous in the radial direction d1. In the figure, the tracks CTR0, CTR2, CTR4, CTR6 are marked with a dot pattern, and the tracks CTR1, CTR3, CTR5, CTR7 are not marked with a pattern. Each track CTR has a plurality of sectors. Note that the number of tracks CTR included in the media cache area M is not limited to eight and can be variously changed.

[0105] Next, a case where the write processing unit 61a writes write data to the media cache area M without reordering by the write data selection processing unit 66 and a case where the write processing unit 61a writes write data to the media cache area M using reordering by the write data selection processing unit 66 will be described.

[0106] FIG. 8 is a plan view showing the disk DK shown in FIG. 7, and is a diagram for explaining an example in which, when write data 1, write data 2, and write data 3 are received in order, the write data 1, write data 2, and write data 3 are written in order without reordering. FIG. 9 is a plan view showing the disk DK shown in FIG. 7, and is a diagram for explaining an example in which, when write data 1, write data 2, and write data 3 are received in order, the data is reordered and the write data 1, write data 3, and write data 2 are written in order.

[0107] In FIGS. 8 and 9, the dashed-dotted arrow indicates a seek, which is an operation of moving from the current track to the target track. The dashed arrow indicates a rotation wait operation from when the movement of the head to the target track is completed until the target sector comes around.

[0108] As shown in FIG. 8, when the host 100 issues a plurality of write data and the magnetic disk device 1 receives write data including a plurality of write commands at once, the magnetic disk device 1 processes the write data in the order in which it arrives. For example, when the magnetic disk device 1 receives write data 1, write data 2, and write data 3 in order, it writes the write data 1, write data 2, and write data 3 in order without reordering.

[0109] First, the write processing unit 61a writes the write data 1 to the execution area CTR0a of the track CTR0. Subsequently, it performs a seek and rotation wait operation, and writes the write data 2 to the execution area CTR1a of the track CTR1. Next, it performs a seek and rotation wait operation, and writes the write data to the execution area CTR2a of the track CTR2. Note that the execution area CTR0a, the execution area CTR1a, and the execution area CTR2a each include one or more sectors. Also, in the radial direction d1, the execution area CTR1a is located on the inner circumference side of the execution area CTR0a, and the execution area CTR2a is located inside the execution area CTR1a.

[0110] In the example of FIG. 8, the distance from the current execution area to the next execution area becomes long. Specifically, in the traveling direction d2, the distance from the end of the last sector of the current execution area to the start of the first sector of the next execution area becomes long. And the rotation wait time becomes long. In the example of FIG. 8, it is difficult to shorten the overhead.

[0111] On the other hand, as shown in FIG. 9, the write data selection processing unit 66 rearranges and processes the write data in a reasonable order. For example, when the magnetic disk device 1 receives the write data 1, the write data 2, and the write data 3 in this order, the write data selection processing unit 66 determines that it is possible to access the execution area CTR1a following the execution area CTR0a. The write data selection processing unit 66 performs reordering, and the write processing unit 61a writes the write data 1, the write data 3, and the write data 2 in this order.

[0112] First, write the write data 1 to the execution area CTR0a of the track CTR0. Subsequently, perform a seek and rotation wait operation, and write the write data 3 to the execution area CTR2a of the track CTR2. Next, perform a seek and rotation wait operation, and write the write data 2 to the execution area CTR1a of the track CTR1.

[0113] In the example of FIG. 9, the distance from the current execution area to the next execution area can be minimized. That is, the rotation waiting time can be shortened. And the write processes of write data 1, write data 2, and write data 3 to the media cache area M can be completed at the highest speed. Therefore, in the example of FIG. 9, the overhead can be reduced.

[0114] Next, the management table TL will be described. FIG. 10 is a diagram showing a part of the management table TL shown in FIG. 1, and is a diagram showing a plurality of count values and the like of the media cache areas M0 to M3 of the first recording layer La1. The head HD1 faces the first recording layer La1. As shown in FIG. 10, among the usage states of the track CTR, "empty" means that the track CTR is the above-mentioned empty track, and "data present" means that the track CTR is the above-mentioned valid track. Differences calculated in units of the media cache area M can be recorded in the management table TL. The determination unit 65 can determine whether or not the difference has reached the threshold value for each media cache area M. The determination unit 65 does not determine whether or not the difference in the count value of ATI has reached the threshold value between adjacent track CTRs. It is desirable that the determination unit 65 makes such a determination because it does not cause overhead.

[0115] Focusing on the media cache area M0 of the first recording layer La1 (head HD1), there is a difference that has reached the threshold value. In the track CTR4, the difference has reached the threshold value. Therefore, the data protection processing unit 63 can determine that it is necessary to perform the PLP process on the original data of the write data of the track CTR4. On the other hand, focusing on the media cache areas M1 to M3 of the first recording layer La1, there is no difference that has reached the threshold value. Therefore, the data protection processing unit 63 can determine that it is not necessary to perform the PLP process on the original data of the write data of the media cache areas M1 to M3.

[0116] In this embodiment, the threshold value is common (e.g., "10") for all media cache areas M of all recording layers L (heads HD). However, the threshold value may be made different for each recording layer L or for each media cache area M.

[0117] Next, a case where the determination unit 65 does not determine whether the difference has reached the threshold value will be described, which is an undesirable processing example of the MPU 60. FIG. 11 is a diagram showing a plurality of count values and the like of one media cache area MO in the management table TL shown in FIG. 10, and is a diagram reflecting the result of continuously writing write data to the fourth track without determining whether the difference has reached the threshold value.

[0118] As shown in FIG. 11, the track CTR3 is the fourth track. Write data is continuously and excessively written to the track CTR3. The count values of the tracks CTR2 and CTR4 adjacent to the track CTR3 exceed "10". Since the adverse effect of the ATI on the tracks CTR2 and CTR4 increases, an error is likely to occur when reading the write data of the tracks CTR2 and CTR4. For example, the write data of the tracks CTR2 and CTR4 is damaged. In that case, it becomes difficult for the media cache area M0 to guarantee the write data.

[0119] Next, a desirable processing example of the MPU 60 will be described with reference to FIGS. 12 to 16. FIG. 12 is a diagram showing a plurality of count values and the like of one media cache area M0 in the management table TL shown in FIG. 10, and is a diagram reflecting the result of writing write data to the fourth track (track CTR3). FIG. 13 is a diagram showing the state after a lapse of time from the state of the management table TL shown in FIG. 12, and is a diagram reflecting up to the result of writing write data to the fourth track (track CTR3). FIG. 14 is a diagram reflecting that, after a lapse of time from the state of the management table TL shown in FIG. 13 and the original data of the write data of the fifth track (track CTR4) is returned to the protection target, the fifth track is regarded as an empty track.

[0120] FIG. 15 is a diagram reflecting that after time has elapsed from the state of the management table TL shown in FIG. 14 and the original data of the write data on the seventh track (track CTR6) has been written to the user data area U, the seventh track is regarded as an empty track. FIG. 16 is a diagram showing an example different from FIG. 15, and after time has elapsed from the state of the management table TL shown in FIG. 14 and the integrated write data generated using the original data of the write data on the seventh track (track CTR6) by garbage collection has been written to the third track (track CTR2), the seventh track is regarded as an empty track.

[0121] As shown in FIG. 12, when all the tracks CTR0 to CTR7 in the media cache area M0 of the first recording layer La1 are in the state of empty tracks, thereafter, write data is written to track CTR4, and subsequently, write data is written to track CTR5. When the write data is written to track CTR5, the counter 64 increments the count value of track CTR4, which is an effective track. As a result, the count value of track CTR4 becomes "1", and the difference between the count value of track CTR4 and the count values (minimum value) of the other track CTRs becomes "1".

[0122] As shown in FIG. 13, thereafter, write data is written to the media cache area M0 of the first recording layer La1 a plurality of times, and finally, write data is written to track CTR3. When the write data is written to track CTR3, the counter 64 increments the count value of track CTR4, which is an effective track. As a result, the count value of track CTR4 becomes "10", and the difference between the count value of track CTR4 and the count values (minimum value) of the other track CTRs becomes "10". Thereby, the determination unit 65 can determine that the difference has reached the threshold value.

[0123] As shown in FIG. 14, then, the data protection processing unit 63 performs PLP processing on the write data of the buffer memory 90, which is the original data of the write data of the track CTR4, together with the management unit 62. As a result, the write processing unit 61a can regard the track CTR4, which was an effective track, as an empty track that can be overwritten, and the counter 64 can reset the count value of the track CTR4 to the initial value. Then, the track CTR4, which is an empty track, can be newly added to the writable area that can be selected during reordering, making it difficult for the writable area to run out, and enabling the writable area to be freely selected for write processing.

[0124] As shown in FIG. 15, thereafter, the write processing unit 61a writes the write data of the buffer memory 90, which is the original data of the write data of the track CTR6, to the user data area U. Therefore, the write processing unit 61a can regard the track CTR6, which was an effective track, as an empty track that can be overwritten, and the counter 64 can reset the count value of the track CTR6 to the initial value. Then, the track CTR6, which is an empty track, can be newly added to the above writable area.

[0125] As shown in FIG. 16, or, by garbage collection, the write data integration processing unit 67 generates integrated write data by integrating the write data of the buffer memory 90, which is the original data of the write data of the track CTR6, and the first write data to be selected next by the write data selection processing unit 66, and the write processing unit 61a may write the integrated write data to the track CTR2.

[0126] Therefore, the write processing unit 61a can regard the track CTR6, which was an effective track, as an empty track that can be overwritten, and the counter 64 can reset the count value of the track CTR6 to the initial value. On the one hand, when integrated write data is written to the track CTR2, the counter 64 increments the count value of the track CTR3, which is a valid track. As a result, the count value of the track CTR3 becomes "1".

[0127] According to the magnetic disk device 1 according to the present embodiment configured as described above, the magnetic disk device 1 includes a disk DK, a head HD, a buffer memory 90, a non-volatile memory 80, a main power supply 5, and an MPU 60. The MPU 60 has a write processing unit 61a, a management unit 62, a data protection processing unit 63, a counter 64, and a determination unit 65. When the determination unit 65 determines that the difference between the maximum value and the minimum value among the count values of the plurality of track CTRs in the media cache area M has reached the threshold value, the management unit 62 can perform the following processing. That is, the management unit 62 can return the write data in the buffer memory 90, which is the original data of the write data of the track CTR with the maximum count value among the plurality of track CTRs, to the protection target.

[0128] Since the PLP process can be performed on the above original data, the write data (original data) in the buffer memory 90 can be quickly guaranteed. And the write data of the above track CTR can be guaranteed without additional write processing to the media cache area M. From the above description, a magnetic disk device 1 that can shorten the time required for write processing to the media cache area M can be obtained. Also, according to the magnetic disk device 1 according to the present embodiment, since the system for guaranteeing the write data in the media cache area M is in place, the write processing to the media cache area M can be safely performed.

[0129] Although embodiments of the present invention have been described, the above embodiments are presented as examples and are not intended to limit the scope of the invention. The above novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. The above embodiments and their modifications are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalent scope thereof.

Explanation of Reference Numerals

[0130] 1... magnetic disk device, 5... main power supply, 20... driver IC, 30... head amplifier IC, 70... volatile memory, 80... non-volatile memory, 90... buffer memory, 91... write cache, 92... read cache, DK... disk, L... recording layer, M... media cache area, CTR... track, U... user data area, 130... system controller, 40... R / W channel, 50... HDC, 60... MPU, 61... read / write processing unit, 61a... write processing unit, 61b... read processing unit, 62... write processing unit, 62... management unit, 63... data protection processing unit, 64... counter, 65... determination unit, 66... write data selection processing unit, 67... write data integration processing unit, 68a... command selection processing unit, 68b... command execution unit, 68c... command response processing unit, HD... head, WHD... write head, RHD... read head, TL... management table, d1... radial direction, d2... traveling direction, d3... rotational direction.

Claims

1. A disk having a media cache area including a plurality of tracks continuous in the radial direction in a recording layer; A head for writing data to and reading data from the recording layer of the disk; A volatile buffer memory in which write data including a write command and user data corresponding to the write command is written; A non-volatile memory; A main power supply; A control unit, comprising: The control unit includes: A write processing unit for controlling the write processing of data to the recording layer; A management unit that includes, as a protection target, the write data before being written to the media cache area among the write data written in the buffer memory, and excludes the write data after being written to the media cache area from the protection target; A data protection processing unit for evacuating the write data managed by the management unit as the protection target to the non-volatile memory when the main power supply is lost; A counter capable of individually counting up the count value of each of the tracks in the media cache area, and capable of counting up the count value of the track adjacent to the track where the write data is written every time write data is written to the media cache area; A determination unit for determining whether or not the difference between the maximum value and the minimum value of the plurality of count values of the plurality of tracks in the media cache area has reached a threshold value; When the determination unit determines that the difference has reached the threshold value, The management unit returns the write data in the buffer memory, which is the original data of the write data of the track whose count value has become the maximum value among the plurality of tracks, to the protection target; A magnetic disk device.

2. When the determination unit determines that the difference has reached the threshold value, The counter resets the count value of the track whose count value has become the maximum value to an initial value, The write processing unit regards the track whose count value has become the maximum value as an empty track that can be overwritten; The magnetic disk device according to claim 1.

3. The control unit further includes a write data selection processing unit that performs a reordering process of rearranging the write data written in the buffer memory; The write processing unit writes the write data selected by the write data selection processing unit to the media cache area. The magnetic disk device according to claim 1.

4. Each time the management unit updates the protection target, The write data selection processing unit performs the reordering process. The magnetic disk device according to claim 3.

5. The control unit further includes a write data integration processing unit. When the determination unit determines that the difference has reached the threshold value, The write data integration processing unit generates integrated write data obtained by integrating the leading write data to be selected next by the write data selection processing unit and the write data that is the original data, The write processing unit writes the integrated write data including the leading write data selected by the write data selection processing unit to the media cache area. The magnetic disk device according to claim 3.

6. The control unit, When the management unit includes the write data in the protection target, further includes a command response processing unit that reports a status indicating that execution of the write command for the write data in the protection target has been completed. The magnetic disk device according to claim 1.

7. The disk further has a user data area in the recording layer. The control unit, A command selection processing unit that performs a reordering process of arranging a plurality of write commands of the write data written in the buffer memory, A command execution unit that executes the write command selected by the command selection processing unit, The write data written in the buffer memory includes first write data including a first write command and first user data corresponding to the first write command. After the first write data read from the buffer memory is written to the media cache area, The command execution unit executes the first write command selected by the command selection processing unit. The write processing unit, Writes the first user data read from the buffer memory to the user data area. Subsequently, the area of the media cache area where the first write data remains is regarded as an overwriteable empty area. The management unit regards the area of the buffer memory where the first write data remains as an overwriteable empty area. The magnetic disk device according to claim 1.

8. When the write processing unit regards the entire track in the media cache area where the first write data remains as the free area, the counter resets the count value of the track where the first write data remains to the initial value. The magnetic disk device according to claim 7.

9. Each track in the media cache area is an empty track where the write data has not been written, an empty track where the write data has been written and overwriting is permitted, or a valid track where the write data has been written and overwriting is prohibited. The counter includes the valid track in the target for incrementing the count value and excludes the empty track from the target for incrementing the count value. The magnetic disk device according to claim 1.

10. At an arbitrary timing after the write data is written to the buffer memory, the write data included in the protection target by the management unit is within the range that can be saved to the non-volatile memory. The magnetic disk device according to claim 1.

11. In the media cache area, when a track adjacent to the first track among a plurality of tracks and located on the inner circumference side of the first track is defined as the inner circumference side track, and a track adjacent to the first track and located on the outer circumference side of the first track is defined as the outer circumference side track, the counter increments the count value of the inner circumference side track and the count value of the outer circumference side track when the write data is written to the first track. The magnetic disk device according to claim 1.

12. The non-volatile memory has a management table that stores the count value of each track in the media cache area individually. The magnetic disk device according to claim 1.

13. When the main power supply is restored after the main power supply is lost, the data protection processing unit writes the write data saved to the non-volatile memory and the write data written to the media cache area to the buffer memory and restores the write data in the buffer memory. The magnetic disk device according to claim 1.

14. The non-volatile memory is a flash read-only memory. The magnetic disk device according to claim 1.

Images