JP2007334463A - Auxiliary storage device and data transferring method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To efficiently transfer the data of segments fragmented in the sector buffer of a magnetic disk device to a host device. <P>SOLUTION: Data from an LBA2000h to an LBA31FFh are stored in a sector buffer, and data from an LBA3000h to the LBA31FFh are fragmented. When receiving a read command to the data from the LBA2000h to the LBA31FFh from a host device, a magnetic disk device generates transfer information by connecting the fragmented segments, and transfers it to the host device by one time processing. As a result, it is possible to prevent the data from being reproduced or transferred from a magnetic disk, or the data from being transferred for every fragmented segment although the data are stored in the sector buffer. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a technology for transferring data from an auxiliary storage device equipped with a sector buffer to a host device, and more particularly to a technology for efficiently transferring data fragmented on a sector buffer to a host device.

  The computer system employs an auxiliary storage device that records data almost permanently in addition to a main storage device that stores a program executed by a CPU and provides a work area. The auxiliary storage device is generally called a mass storage device because it has a larger storage capacity than the main storage device. Moreover, it may be called an external storage device in the meaning of an external storage device other than the main storage device attached to the CPU. Examples of the auxiliary storage device include a magnetic disk device, a floppy disk device (floppy disk is a trademark), a magneto-optical disk device, a CD-RW drive, and a DVD-RW drive.

  These auxiliary storage devices are connected to a computer system as a host device through an interface circuit such as SCSI or IDE, and record data sent from the host device or send recorded data to the host device. Yes. In these auxiliary storage devices, a sector buffer is provided in order to absorb the difference between the data communication time with the host device and the internal read or write processing time or shorten the communication time.

  In a magnetic disk device that is one of typical auxiliary storage devices, a semiconductor memory such as SRAM or DRAM is used as a sector buffer. Some sector buffers include a read buffer and a write buffer. The sector buffer 1 shown in FIG. 6 includes a read buffer that temporarily stores read data requested from the host device and a write buffer that temporarily stores write data transferred from the host device. It is configured.

  Now, it is assumed that data of consecutive logical block addresses from n to m are stored in the read buffer. Here, the logical block address refers to the address of the data sector that is the smallest unit that can access the magnetic disk. Next, when a read command for logical block addresses from n to m is received from the host device, the processor reads the data block stored in the read buffer without reproducing the data from the magnetic disk. High-speed reading operation is realized by transferring. With data blocks of successive logical block addresses from n to m stored in the read buffer, for successive logical block addresses from n + x1 to n + x2 between n and m from the host device When a write command is received, the processor returns write processing completion status to the host device when it receives write data from the host device and stores it in the write buffer. Write operation is realized.

  At this time, since the data from n + x1 to n + x2 stored in the read buffer is updated with the data from n + x1 to n + x2 stored in the write buffer, the logical block addresses n + x1 to n + x2 of the read buffer are updated. Is disabled. In this state, when a read command for logical block addresses n to m is received from the host device, the processor reads data from n to n + x1-1 from the read buffer and transfers it to the host device. Thus, data from n + x1 to m is reproduced from the magnetic disk and transferred to the host device. Alternatively, after transferring the data from n to n + x1-1, it is further searched whether there is subsequent data in the read buffer or the write buffer and transferred. Either method consumes extra transfer time.

Japanese Patent Application Laid-Open No. 2004-133867 discloses a technique for detecting a fragmentation information such as the presence / absence of fragmentation, a free memory head address, and a region size and performing a concatenation operation of free regions in order to eliminate inconveniences associated with memory fragmentation. Disclosure. In this technique, countermeasures against fragmentation are realized by moving data on a memory. Patent Document 2 discloses a technique for reading data after being rearranged on the disk so that the data stored in the buffer does not become empty when fragmentation occurs in the data on the disk. Patent Document 3 discloses a technique for dynamically changing a buffer segment of an HDD by setting a segment table and preventing fragmentation of the buffer.
JP 2003-331239 A JP 2000-21086 A Japanese Patent Laid-Open No. 11-120690

  In this specification, the state in which data is stored without consecutive logical block address data being arranged in the logical address order of the sector buffer is referred to as fragmentation. A method of preventing fragmentation by overwriting the corresponding data in the read buffer with the updated data stored in the write buffer after the data from n + x1 to n + x2 is written in the write buffer is also conceivable. However, moving the data in the sector buffer requires a predetermined time and has a disadvantage of complicated control. Further, after transferring the data from n to n + x1, it is further searched whether or not the subsequent data is stored in the buffer, and if there is data in the sector buffer, the remaining data is stored in the sector buffer. It is also conceivable to transfer the data. However, even with this method, data transfer is repeated a plurality of times, and it is difficult to say that the speed has been sufficiently increased.

  SUMMARY OF THE INVENTION An object of the present invention is to provide a transfer method for transferring data stored in a fragmented state in a sector buffer in an auxiliary storage device to a host device at high speed. A further object of the present invention is to provide an auxiliary storage device that realizes such high-speed transfer.

  The principle of the present invention is that fragmentation is performed in order to transfer data in a single process in response to a read command from a host device that specifies an address for a data block stored in a fragmented segment in a sector buffer. Transfer information for making the segments continuous before data transfer is generated and rearranged logically. When a read command for the address of the data block stored in the fragmented segment is sent from the host device, the auxiliary storage device completes the data transfer in one process by transferring based on the transfer information be able to.

  In the aspect of the present invention, a read command specifying addresses of a plurality of data blocks to be read is received from the host device. Then, it is searched whether or not the head data block arranged at the head of the plurality of data blocks exists in the sector buffer. Subsequently, when either the first data block or the plurality of data blocks are present in different segments of the sector buffer, transfer information for generating continuous page addresses of the plurality of data blocks is generated. The transfer information is generated by the processor based on the address information in the buffer management table for each transfer. The transfer information is a table composed of a sector buffer page address and the number of pages generated for one read command. Finally, the data block whose address is specified based on the transfer information is read from the sector buffer and transferred to the host device.

  According to the present invention, it is possible to provide a method for transferring data stored in a fragmented state in a sector buffer in an auxiliary storage device to a host device at high speed. Furthermore, according to the present invention, an auxiliary storage device that realizes such high-speed transfer can be provided.

[Device configuration]
FIG. 1 is a block diagram showing an outline of a magnetic disk device 10 according to an embodiment of the present invention. The magnetic disk device 10 is connected to a host device 11 such as a computer or a music recording / reproducing device, and records data received from the host device 11 on the magnetic disk 25 or transfers data recorded on the magnetic disk 25 to the host device 11. To do. The host interface circuit 13 is an ATA standard circuit that controls data communication between the host device 11 and the magnetic disk device 10. Data, commands, control information, and the like are input / output between the host device 11 and the magnetic disk device 10 through the host interface circuit 13.

  The host device 11 accesses the address of the ATA register assigned on the host interface circuit 13 when writing data to the magnetic disk device 10 or reading data from the magnetic disk device 10. The ATA register includes a command register, a status register, a data register, a cylinder low / high register, a sector number register, and a sector count register.

  When the host device 11 transfers data to or from the magnetic disk device 10, the read command or write command is written to the command register, and the head is written to the cylinder low / high register and the sector / number register. Write the logical block address (hereinafter referred to as LBA) of the data sector. Furthermore, data transmission / reception is performed by designating the number of data sectors to be written to or read from the sector count register. When an error occurs in the execution process of the read command or the write command, the magnetic disk device 10 sets an error bit in the status register and reports it to the host device 11. When the data transfer with the host device 11 is completed, the magnetic disk device 10 sets a state in the status register, and the host device 11 reads it to recognize the completion of the data transfer.

  The sector buffer 31 is formed by an SDRAM which is an example of a volatile semiconductor memory. The sector buffer 31 realizes a read cache function and a write cache function in order to improve the performance by absorbing the difference between the processing speed inside the magnetic disk device 10 and the data transfer speed to the host device 11. The sector buffer 31 is functionally divided into a read buffer and a write buffer. However, the read buffer and the write buffer may be physically separated. The read buffer is an area for storing data read from the magnetic disk 25 for reading from the host apparatus 11, and the write buffer is an area for storing data related to writing from the host apparatus. Each of the read buffer and the write buffer stores data by a ring buffer method.

  The CRC circuit 27 uses the generator polynomial based on the cyclic redundancy check (CRC) method on the user data sent from the host interface circuit 13 to the buffer controller 15 to generate an error check code (redundant byte). Hereinafter, CRCC is calculated and sent to the buffer controller 15. In this embodiment, the CRCC is calculated for each 512-byte user data corresponding to a data sector unit, and is composed of 4 bytes. The buffer controller 15 controls input / output of data to the sector buffer 31 and the CRC circuit 27. The buffer controller 15 controls the sector buffer 31 in order to store a 516-byte data set consisting of 512-byte user data and 4-byte CRCC at a predetermined address of the sector buffer 31. The buffer controller 15 includes an address management table for controlling the data storing operation for the sector buffer 31 in a ring buffer method.

  The CRC circuit 27 uses a generator polynomial for the data set read from the sector buffer 31 to the buffer controller 15 before sending data to the host device 11 and before writing data to the magnetic disk 25. Check for bit reversal errors. The CRC circuit 27 notifies the MPU unit 33 of the error detected from the data set.

  The channel interface circuit 17 controls data input / output operations with respect to the buffer controller 15, the read channel 19, the write channel 21, and the ECC circuit 29. The ECC circuit 29 calculates an error correction code (hereinafter referred to as ECC) by a Reed-Solomon method from a data set for recording sent from the buffer controller 15 to the channel interface circuit 17 at the time of recording operation. Send to interface circuit 17 The ECC is generated about 20 to 40 bytes for each 516-byte data set.

  The ECC circuit 29 calculates an error syndrome from the data set and ECC sent from the read channel 19 to the channel interface circuit 17 in the reproduction operation, and checks whether or not there is a bit inversion error in the data set. To do. If the bit inversion error is within a predetermined number, the ECC circuit 29 corrects the data set to a correct value and sends it to the buffer controller 15. The read channel 19 processes user data read from the magnetic disk 25 and sends it to the channel interface circuit 17. The read channel 19 processes servo data read from the magnetic disk 25 and sends it to the servo controller 35.

  The write channel 21 processes data sector information relating to recording received from the channel interface circuit 17 and sends it to the head mechanism 23. In addition to the data set and ECC, the data sector information includes a preamble, a postamble, address information and the like generated and added by a known method. The head mechanism 23 includes a magnetic head and a carriage mechanism that positions the magnetic head at a predetermined position on the magnetic disk 23. The magnetic disk 25 records user data in units of data sectors. Each data sector is composed of a preamble for synchronizing reproduction data, a 512-byte data block, CRCC, ECC, and the like. LBAs are assigned in order to all data sectors defined on the magnetic disk.

  The MPU unit 33 includes a processor, a RAM, an EEPROM, a ROM that stores firmware, and the like, and executes the firmware to control the entire operation of the magnetic disk device 10. The MPU unit 33 interprets a command written from the host device 11 to the ATA register of the host interface circuit 13 and controls the operation of the magnetic disk device 10. When an error occurs when executing a command sent from the host apparatus 11, the MPU 33 sets an error bit in the status register of the host interface circuit 13 and reports it to the host apparatus 11. Furthermore, the MPU 33 searches for data stored in the sector buffer 31 and reads data from the sector buffer to control data transfer operations with the host device. The data transfer method according to the present embodiment is realized by firm air.

  The servo controller 35 processes the servo information received from the read channel 19 and sends the magnetic head position information to the MPU unit 33. Based on the position information sent from the servo controller 35, the MPU 33 generates control information for the head mechanism 23 and sends it to the driver 37. The driver 37 generates a control current for positioning the head mechanism 23 at the position instructed by the MPU unit 33 and sends the control current to the head mechanism 23. In order to configure the magnetic disk device 10, many other well-known elements are necessary. However, the description is omitted because it is not particularly relevant to the present invention. Further, the functional blocks shown in FIG. 1 are shown as examples, and those skilled in the art can freely integrate or divide these functions into one semiconductor device.

[Sector buffer and buffer management table]
FIG. 2 is a diagram for explaining the data structures of the sector buffer and the buffer management table. As shown in FIG. 2A, the sector buffer 31 includes a read buffer 101 and a write buffer 103, and each stores data in a ring buffer system. As shown in FIG. 2B, the sector buffer 31 stores a data set composed of 512-byte user data and 4-byte CRCC in units of 516-byte pages 105. As shown in FIG. 2A, in the present embodiment, the read buffer 101 has 16384 continuous page addresses from 0000h to 3FFFh, and the write buffer 103 is continuous from 4000h to 7FFFh. Have the same number of page addresses.

  In the ring buffer method, a continuous LBA data set is sequentially stored from page address 0000h. Then, a new continuous LBA data set is stored from the next page of the last stored page. Then, after page address 3FFFh, it returns to page address 0000h and overwrites the already stored data set. The same is stored in the write buffer 103 as well.

  A unit of a storage area in which page addresses in which consecutive LBA data sets are stored is called a segment. In the example of FIG. 2B, eight pages from page addresses 0005h to 000Ch store data sets from LBA11 to LBA18 to form one segment. Seven pages from page addresses 000Dh to 0012h store the data set from LBA35 to LBA41 to form another segment. When the MPU 33 receives a read command in which an address for a data set that is not stored in the read buffer 101 is received from the host device 11, the MPU 33 stores consecutive data sets in the LBA for which the address is specified on the magnetic disk 25. Is read out and stored in the read buffer 101. At this time, the data set stored in the read buffer 101 forms one segment.

  FIG. 2C shows the configuration of the buffer management table 107 for the buffer controller 15 to manage the address of the sector buffer 31. In the buffer management table 107, an entry is formed for each segment. One entry includes a page address, the last LBA of the data set stored at the page address, and the page number (length) of the page. In the example of FIG. 2B, in 000Ch, a segment formed by a data set in which eight LBAs having the LBA 18 data set as the final address is registered is registered as an entry. Similarly, segment information is registered in the page address 0012h.

[Segment fragmentation]
FIG. 3 is a diagram for explaining a state in which fragmentation has occurred in the segment in the sector buffer 31. In FIG. 3A, the data set from LBA2000h to LBA3FFFh stored from the page address 1000h to 2FFFh of the sector buffer 31 forms one segment, and the segment entry is registered in the buffer management table 107. ing. Thereafter, the host device 11 sends the LBA 3000h, which is the start address of the write data, and 511 data blocks following it to the magnetic disk device 10 together with the write command. Before actually writing data to the data sector of the magnetic disk 25, the magnetic disk device 10 stores the data set in the write buffer 103 and writes to the status register as shown in FIG. 3B. Set the completion status and notify the host device.

  Since it takes some time for the magnetic disk device 10 to write data to the magnetic disk 25, the write processing completion status is notified to the host device when the write data is stored in the write buffer 103. The host device 11 can be released from the write operation at an early stage. The buffer controller 15 stores a data set composed of a data block and CRCC transferred from the host device in a predetermined page of the write buffer 103. Then, the page address where the data set is stored, the final LBA, and the number of pages are stored in the buffer management table 107. FIG. 3B shows a state where the MPU 33 has written data blocks from LBA 3000h to LBA 31FFh to pages of the write buffer 103 having page addresses from 5000h to 51FFh. Accordingly, since the data blocks from LBA 3000h to LBA 31FFh stored in the page addresses 2000h to 21FFh of the sector buffer 31 have been updated, the data is processed to be invalid in the buffer management table 107.

  In the buffer management table 107 in FIG. 3B, the segments of the data set stored in the pages from the page addresses 1000h to 2FFFh are updated from the segments from the page addresses 1000h to 1FFFh and the page address 2200h. It is divided into two segments up to 2FFFh. The buffer controller 15 recognizes that the segment is divided based on the buffer management table 107. Therefore, when a read command is next sent from the host apparatus 11 to the data blocks from LBA 3000h to LBA 31FFh, the buffer controller 15 stores the data stored in the page addresses 5000h to 51FFh. It is determined that the data is valid, and the address of the sector buffer 31 is designated to be sent to the host device 11.

  Therefore, the data set stored in the page address from 2000h to 21FFh becomes invalid. As described above, the size of the segment when it is first formed becomes a variable size according to the number of LBAs commanded from the host device, and the number of segments is increased by being divided by updating user data. Data blocks stored in the storage area with page addresses 2000h to 21FFh are not read out until the next new data set is stored in the order of the ring buffer method. In this embodiment, the read buffer 101 can hold 128 segments, and the write buffer 103 can hold 64 segments.

  In FIG. 3B, the continuous LBA data set from LBA2000h to LBA3FFFh is stored in the storage area where the page address is discontinuous on the sector buffer 31, and the segment is in a fragmented state. Yes. Conventionally, when a read command is sent for data corresponding to a segment fragmented in this way, the MPU unit 33 causes the data of the head LBA specified by the read command on the sector buffer 31. A search is made as to whether or not there is a segment including the set. If there is a segment, the data blocks up to the last LBA of the segment are once transferred to the host device 11 and the remaining data blocks are reproduced from the magnetic disk 25. And sent. Alternatively, search and transfer were repeated for each segment. Note that segment fragmentation does not occur only between the read buffer 101 and the write buffer 103 but also occurs only within the read buffer 101.

[Data transfer procedure]
FIG. 4 is a flowchart showing a transfer procedure when a read command for an LBA data block included in a segment segmented as shown in FIG. 3B is sent. A program describing the transfer procedure is incorporated in the firmware of the MPU unit 33. In block 201, the host device 11 reads the ATA register of the host interface circuit 13 by designating the LBA2000h of the first data block to be read stored in the magnetic disk 25 and the number of data blocks to be read 8192.・ Send a command. In block 203, the MPU unit 33 interprets the read command and sends the head LBA and the number of data blocks to the buffer controller 15. The buffer controller 15 searches the entry of the buffer management table 107 to search whether the first data set of the LBA specified by the read command exists in the sector buffer 31.

  When the first data block does not exist in the sector buffer 31 in block 203, the MPU unit 33 reproduces data from the magnetic disk 25 by a normal reproduction operation (block 205) and stores it in the read buffer 101. (Block 207), the data is transferred to the host device (block 209). When the host device 11 requests data of the same LBA from the next time, the MPU unit 33 reads from the read buffer 101 and transfers it. This procedure is the same as the conventional transfer procedure.

  If the first data block is present in the sector buffer 31 in block 203, the MPU unit 33 checks in block 211 whether fragmentation has occurred for the segment storing the designated LBA. As shown in FIG. 3A, when the entire data block of the designated LBA is stored in one segment and no fragmentation occurs, the MPU unit 33 transfers the transfer information according to this embodiment. The data is read from the read buffer 101 without being generated and transferred to the host device 11. If it is determined in the block 211 that fragmentation has occurred, the MPU unit 33 generates transfer information according to the present embodiment in the block 213.

  The transfer information is address information of the sector buffer 31 for transferring the data block stored in the segment fragmented by the MPU unit 33 in one data transfer procedure. FIG. 5 is a diagram illustrating a data structure of transfer information. When the MPU unit 33 receives one read command from the host device 11, the transfer information is stored in the host device 11 when it is determined that the corresponding data block is fragmented in the sector buffer 31. This is a table generated by the MPU unit 31 executing firmware every time data is transferred. The MPU unit 31 can transfer the segment data segmented using the transfer information to the host device 11 by a single transfer operation.

  As shown in FIG. 5A, the transfer information is composed of the page address of the sector buffer and the number of pages. The LBA data blocks included in the fragmented segment shown in FIG. 3B are arranged so that the page address of the last LBA of each segment is arranged in the order of 1FFFh, 51FFh, and 2FFFh in FIG. 5A. Arranged. Each final LBA is associated with the number of pages of the corresponding segment. Then, in block 215, the MPU unit 33 reads out the sector block page address in the order of 1000h-1FFFh, 5000h-51FFh, 2200h-2FFFh based on the transfer information at a time. Transfer to host device.

  The transfer information in the case where the last LBA of the data block specified by the read command is not the last LBA (3FFFh) of the segment, for example, 3FF5h, is as shown in FIG. In this case, the data block of LBA3FF5h is stored at the page address of 2FF5h of the sector buffer. Therefore, transfer information is generated as shown in FIG. 5B, and the sector buffer is transferred by the MPU unit 33 in the order of the page addresses of 1000h-1FFFh, 5000h-51FFh, 2200h-2FF5h based on the transfer information. The

  In this embodiment, every time a read command is processed, the MPU unit 33 generates transfer information based on the address information in the buffer management table 107. The transfer information can be generated, for example, by adding information indicating the transfer order to the buffer management table 107. It is burdensome on the MPU unit 33 to calculate and update the state of the buffer management table 107 every time a read or write operation that causes fragmentation is performed. Further, when fragmentation occurs, it is possible to actually change the data arrangement itself of the sector buffer to remove the fragmentation, but this also increases the burden on the MPU unit 33 for data movement. It is better to generate the transfer information every time the data is transferred as in the present embodiment.

  In the present embodiment, the method in which the sector buffer stores data by the ring buffer method has been described as an example. However, the present invention is not limited to this, and an LRU (Least Recently Used) algorithm or FIFO is used. (First-In First-Out) Even when storing by the algorithm, it can be applied when fragmentation occurs.

  Although the present invention has been described with the specific embodiments shown in the drawings, the present invention is not limited to the embodiments shown in the drawings, and is known so far as long as the effects of the present invention are achieved. It goes without saying that any configuration can be adopted.

1 is a block diagram showing a configuration of a magnetic disk device according to an embodiment of the present invention. It is a figure which shows the data structure of a sector buffer and a buffer management table. It is a figure which shows the state of the segment fragmented by the sector buffer. It is a flowchart which shows the procedure which transfers the data of the fragmented segment. It is a figure which shows the data structure of transfer information. It is a figure explaining the subject of the fragmentation which generate | occur | produces in a sector buffer.

Explanation of symbols

101 ... Read buffer 103 ... Write buffer 105 ... Page 107 ... Buffer management table

Claims (13)

A method of transferring data from an auxiliary storage device equipped with a nonvolatile recording medium and a sector buffer to a host device,
Receiving a read command specifying addresses of a plurality of data blocks to be read from the host device;
Searching for a head data block arranged at the head of the plurality of data blocks in the sector buffer; and
When the first data block and at least one data block other than the first data block are present in different segments of the sector buffer, the page addresses of the plurality of data blocks are continuously transferred. Generating information;
And a step of reading the plurality of data blocks from the sector buffer based on the transfer information and transferring them to the host device.   The transfer method according to claim 1, wherein the transfer information is generated for each processing of the read command.   2. The transfer method according to claim 1, wherein the transfer information includes a page address of the sector buffer and the number of pages.   If the entire plurality of data blocks are present in one segment of the sector buffer, the plurality of data blocks are read from the sector buffer and transferred to the host device without generating the address information. The transfer method according to claim 1, further comprising steps.   If some of the plurality of data blocks do not exist in the sector buffer, the data blocks existing in the sector buffer are transferred to the host device continuously from the first page, and then the nonvolatile device The transfer method according to claim 1, wherein the remaining data blocks are transferred from the recording medium to the host device.   2. The transfer method according to claim 1, further comprising a step of reading the entire data block from the nonvolatile recording medium when the head data block does not exist in the sector buffer. An auxiliary storage device,
A non-volatile recording medium;
An interface circuit for controlling data transfer with the host device;
A sector buffer for storing data blocks for writing and data blocks for reading;
A control unit for controlling data transfer performed between the host device and the interface circuit;
The control unit receives a read command specifying addresses of a plurality of data blocks to be read from the host device, and a head data block arranged at the head of the plurality of data blocks is the sector data block. Whether the first data block and at least one data block other than the first data block exist in different segments of the sector buffer. An auxiliary storage device that generates transfer information that makes page addresses of the entire block continuous, reads the plurality of data blocks from the sector buffer based on the transfer information, and transfers them to the host device.   8. The auxiliary storage device according to claim 7, wherein the sector buffer includes a read buffer and a write buffer, and the read buffer and the write buffer are ring buffers.   9. The auxiliary storage device according to claim 8, wherein the data block to be read is included in a segment existing in the write buffer and a segment existing in the read buffer.   9. The auxiliary storage device according to claim 8, wherein the data block to be read is included in a different segment existing in the read buffer.   8. The auxiliary storage device according to claim 7, wherein the control unit generates the transfer information based on address information of a buffer management table that manages a page address of the sector buffer.   The auxiliary storage device according to claim 7, wherein the auxiliary storage device is a magnetic disk device. A magnetic disk drive,
A magnetic disk;
An interface circuit for controlling data transfer with the host device;
A sector buffer for storing data blocks for writing and data blocks for reading;
A processor for controlling the magnetic disk device;
Receiving a read command designating addresses of a plurality of data blocks to be read from the host device from the host device; and a head data block arranged at the head of the plurality of data blocks is the sector data A step of searching whether or not the buffer is present in the buffer, and when the first data block and at least one data block other than the first data block exist in different segments of the sector buffer, Generating transfer information for contiguous page addresses of the entire data block; and reading the plurality of data blocks from the sector buffer based on the transfer information and transferring them to the host device. Magnetic disk having firmware Location.

Images