JP4301026B2 - Data recording apparatus, data recording method, and recording / reproducing system - Google Patents

Description

  The present invention relates to a data recording apparatus and method for managing and recording various data such as AV data as files under the control of a host apparatus, and a recording / reproducing system including the host apparatus and the data recording apparatus. The present invention relates to a data recording apparatus and method having a recording medium such as a disk having a different data transfer rate depending on the access position, and a recording / reproducing system.

  In recent years, in a consumer device, a large-capacity storage (storage device), in particular, an HDD (Hard Disk Drive) or an optical disc device has been used as a device for recording moving images, sounds, or moving images. Until now, PCs (Personal Computers) that serve as host devices have requested the above storage to increase the number of command processes per unit time and the amount of data transfer (average value over a relatively long time). Less consideration is given to speed variations.

  On the other hand, the performance demanded by a consumer device for storage on a PC is not so high on average. For example, when high-definition recording is performed by MPEG (Moving Picture Experts Group) 2, the data rate is about 25 Mbit / sec, which is not so high in view of the transfer rate of the HDD exceeding 10 MB / sec.

  On the other hand, there is a strong demand for reducing variations in transfer speed, that is, real-time characteristics. In fact, if the transfer speed varies greatly and the real-time property is poor, problems such as stopping of images and sound during reproduction or inability to record during recording or recording occur. These problems are fatal for using storage as a consumer device.

  There are roughly two factors that cause such transfer speed variations. The first factor that slows down the transfer speed is that there is a seek error or an error in the read data, and this takes time to correct or retry. Another factor that slows down the transfer speed is that there are many seek operations and waiting for rotation and there is a lot of wasted time, or an area where the transfer speed is slow is used for a long time.

  The first factor can be solved temporarily by ignoring an error or setting an upper limit on the command processing time for AV data or the like whose data reliability may be low. For example, in ATA (AT Attachment) -7 Streaming Feature Set (commonly called AV command), the processing time of each command can be directly specified. However, there is a problem that how to execute it is completely up to the storage side, and it is not guaranteed whether the data can actually be read or written correctly. However, the frequency of occurrence of such problems is relatively small.

  Regarding the second factor, the frequency of occurrence is higher than that of the first factor, and the problem is more serious. Conventionally, two solutions have been proposed: command reordering (head scheduling) and device physical arrangement.

  Command reordering (head scheduling) is a technique for changing the execution order of a plurality of I / O requests requested by an application so that the processing time is reduced. Many algorithms have been studied so far, but now, a few to a hundred commands are queued, and the execution time is calculated as a table. It is normal to execute the smallest one compared to the execution time of the most recently entered command. The rotation waiting time is taken into account when calculating the execution time.

  However, this method is not suitable for handling AV data. This is because the amount of data transferred per I / O request is large, and therefore the number of I / O requests per unit time is small. In the above algorithm, if the number of I / O requests to be compared is small, the effect is weak. However, if waiting until a large number of I / O requests are obtained, the real-time property is impaired.

  On the other hand, there are many research and implementation methods for devising the physical layout of files. For example, in recent file systems, efforts are made on the logical block address (LBA) space by using the locality of data and placing related data in physical proximity. In order to guarantee the minimum value of the transfer rate, a method has been proposed in which a seek operation is prepared to increase, and a region where the transfer rate is intentionally combined with a region where the transfer rate is low is intentionally used.

  However, the host device cannot directly know information such as where the head currently exists in the HDD and where the data is arranged on the disk. For this reason, it is difficult to accurately know the time for seeking the head to a predetermined track, especially the rotation waiting time thereafter, and there is a limit to shortening it.

  On the other hand, the following Patent Document 1 discloses a recording disk access control method and apparatus for further optimizing the rotation waiting time by limiting the file arrangement. In the technique described in Patent Document 1, a skew indicating an angular difference in the circumferential direction between the heads of adjacent blocks on the disk and a gap indicating an angle difference between the head and the end in the same data block are appropriately used. By selecting the above and determining the data position on the disk of each block over the entire disk, the rotation waiting time at the average head movement distance when the head accesses the recording disk is shortened. Furthermore, by changing the size of the data block so that the gap indicating the angle difference between the beginning and end in the same data block is constant over the entire area from the outside to the inside of the recording disk, the real-time performance of the access (Guarantee of upper limit of processing time) can be further increased.

  That is, for example, a unit in which one piece of image data or the like is made into one data block is introduced, and the movement of adjacent data blocks is arranged on the disk so that the movement time is minimized in consideration of the rotation waiting time. The data is scheduled to be written in these blocks.

JP-A-9-185864

  However, Patent Document 1 has the following problems. That is, in the method described in Patent Document 1, in order to move to an adjacent block in a minimum time, the gap (angle difference between the head and the end in the same data block) must be constant. Therefore, since the number of sectors is different between the inner data block and the outer track, there is a side effect that the size of the data block must be changed. In order to avoid this, it is possible to divide the data block into sub-blocks and arrange them at different locations and make the sub-block size constant across the entire disk, but by dividing them into sub-blocks and arranging them at different locations There is a problem in that the seek operation is increased and the overall transfer rate is lowered.

  Also, since unused areas are generated, the use efficiency of the disk surface also decreases. Furthermore, when editing or the like is performed and there are random free areas, the initially assumed scheduling cannot be executed, and it is difficult to optimize the rotation waiting time.

  The present invention has been proposed in view of such a conventional situation, and evenly uses the recording area on the disc, optimizes the rotation waiting time and guarantees the minimum transfer speed even if there are random empty areas. An object is to provide a data recording apparatus and method, and a recording / reproducing system.

In order to achieve the above-described object, a data recording apparatus according to the present invention is a data recording apparatus for recording transfer data transferred from a host device on a rotary recording medium having a recording area having a transfer speed that differs depending on a recording position. Control means for dividing the recording area into a plurality of partial areas having substantially the same capacity, and controlling the transfer data to be distributed and written in the divided partial areas. Are selected in a predetermined basic order so that the partial areas are used at substantially the same frequency, and the data transfer time is less than the predetermined time in the first scheduled partial area to be written next according to the basic order An empty area satisfying the above condition is searched, and control is performed so that the partial data constituting the transfer data is written in the corresponding empty area .

  In the present invention, the recording area is divided into a plurality of partial areas, and the transfer data from the host device is distributed and written in the plurality of partial areas, regardless of the transfer speed of the recording area. The area can be used evenly, for example, only an area having a high data transfer rate is not used.

  Further, the control means can divide the recording area into partial areas having substantially the same capacity, and can control writing of the transfer data so that each partial area is used at substantially the same frequency. By using them at substantially the same frequency, an empty area is not formed only in an area where the transfer rate is slow with the passage of time.

  Further, the control means can control to select the plurality of partial areas in a predetermined basic order, search for an empty area in the selected partial area, and write the partial data constituting the transfer data, By sequentially writing the partial data in the partial area according to the basic order, the transfer data can be distributed and written.

  Furthermore, the recording medium is a rotational recording medium, and the control means satisfies a condition that a data transfer time is less than a predetermined time in a first scheduled partial area to be written next according to the basic order. It is possible to control to search for an empty area and write the partial data in the corresponding empty area, and to reduce the transfer speed by writing data to an empty area whose data transfer time is less than a predetermined time.

  Further, the data transfer time can be a time obtained by combining the head seek operation and the disk rotation waiting time with the partial data writing time, and considers not only the seek time but also the disk rotation waiting time. By doing so, data writing can be controlled more accurately and efficiently.

  Further, the control means is arranged to follow the first scheduled partial area according to the first data transfer time and the basic order when the first partial data is written in the first scheduled partial area. The first and second empty areas satisfying the condition that the sum of the second data transfer time and the second data transfer time when the second partial data is written in the second scheduled partial area scheduled to be written to It can be controlled to search in the two planned partial areas and write the first and second partial data respectively. For example, when there is no planned partial area that satisfies the condition only in the first planned partial area, By searching for an empty area in consideration of the data transfer speed of the next scheduled partial area, it is possible to more reliably prevent the data transfer speed from decreasing.

  Furthermore, the control means has a transfer rate monitoring function for monitoring the transfer rate of the transfer data, and the transfer rate of the transfer data is faster than the minimum guaranteed rate for guaranteeing the minimum value, If there is a partial area with a slower transfer speed than the partial area in accordance with the basic order, the transfer data can be controlled to be written in the partial area with the slower transfer speed, and the data transfer speed is preferentially slow. By using this, it is possible to improve the data transfer rate as time passes, and to ensure the data transfer rate for a long time.

The data recording method according to the present invention is a data recording method for recording transfer data transferred from a host device on a rotary recording medium having a recording area having a different transfer speed depending on a recording position. A control step of dividing the plurality of partial areas into a plurality of divided partial areas and controlling the transfer data to be written in a distributed manner. In the control step, the plurality of partial areas are arranged at substantially the same frequency. Select a predetermined basic order to use, and search for a free area that satisfies the condition that the data transfer time is less than the predetermined time in the first scheduled partial area that is scheduled to be written next according to the basic order. Control is performed so that the partial data constituting the transfer data is written in the empty area .

A recording / reproducing system according to the present invention includes a host device and a data recording device for recording transfer data transferred from the host device on a rotary recording medium having a recording area having a transfer speed that differs depending on the recording position. The data recording apparatus includes a control unit that controls the recording area to be divided into a plurality of partial areas having substantially the same capacity, and the transfer data is distributed and written in the divided partial areas. The control means selects the plurality of partial areas in a predetermined basic order so as to be used at substantially the same frequency, and transfers data in the first predetermined partial area to be written next in accordance with the basic order. A search is made for an empty area that satisfies the condition that the time is less than the predetermined time, and control is performed so that the partial data constituting the transfer data is written in the corresponding empty area .

  According to the data recording apparatus and the data recording method of the present invention, the recording areas having different data transfer rates are divided into a plurality of pieces, and the transfer data from the host device is written so as to be distributed and arranged in the divided partial areas. By actively using an area where the data transfer speed is low in accordance with an area where the transfer speed is high, it is possible to guarantee the data transfer speed stably over a long period of time.

  In addition, according to the recording / reproducing system of the present invention, there is provided a system comprising the data recording apparatus as described above and a host apparatus for transferring data thereto, and guaranteeing a transfer speed of data transferred from the host apparatus. Can do.

  Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. In the present embodiment, the present invention comprises a host device and a data recording device having at least a rotating recording medium such as a hard disk or a rewritable optical disc, and seeks when accessing data recorded on the rotating recording medium. The present invention is applied to a recording / reproducing system capable of guaranteeing a data transfer speed even when there is a delay due to operation or rotation waiting time. Further, the recording / reproducing system in the present embodiment employs a file system that manages all data including AV data as files. Here, the data transfer time in the present embodiment includes a movement time composed of a seek operation of the head and a disk rotation waiting time, and a data write time for actually writing data, and the data transfer speed is the transfer data. Is divided by this data transfer time.

  In this embodiment, a case where a hard disk device (HDD) is applied as a recording medium and an MS-DOS compatible FAT file system is applied as a file system will be described. Any system can be applied without being limited to the DOS compatible FAT file system. Furthermore, in the present embodiment, the data recording apparatus is described as having a magnetic recording medium such as a hard disk. However, if the recording medium is a randomly accessible recording medium, the same processing can be applied to an optical disk such as a CD or DVD. It goes without saying that it is possible.

  Here, the FAT file system is, for example, a hard disk drive (HDD) in a host device such as a PC (Personal Computer), or a medium using a nonvolatile solid-state memory as a recording medium (manufactured by Sony: Memory Stick (registered trademark), Toshiba). (Manufactured by SmartMedia (registered trademark), SanDisk: compact flash (registered trademark), multimedia card, etc.)).

  FIG. 1 is a block diagram showing a recording / reproducing system according to the present embodiment. As shown in FIG. 1, a recording / reproducing system 1 includes a host device 2 such as a PC (Personal Computer) or AV equipment, an IDE (Integrated Drive Electronics), a SCSI (Small Computer System Interface), and an FC (Fibre Channel). And an HDD 4 as a data recording apparatus connected via an interface 3 such as a USB (Universal Serial Bus).

  The HDD 4 records various data output from the host device 2 on a disk 11 as a magnetic recording medium such as a hard disk. The HDD 4 rotates the disk 11, a spindle motor 12 that rotates the disk 11, and the disk 11. A voice coil motor 13 for feeding a magnetic head (not shown) for reading and writing signals in the radial direction of the disk 11, a servo control unit 14 for controlling the drive of the spindle motor 12 and the voice coil motor 13, and a disk And a read / write channel unit 15 for encoding data to be written to the disk 11 and decoding data read from the disk 11.

  Further, the HDD 4 transmits / receives data to / from the host device 2, a disk control unit 16 that manages data on the disk 11, a buffer memory 17 that buffers data read from the disk 11 and data to be written to the disk 11, and the host device 2. An interface control unit 18 constituting an input / output circuit for a control command, a memory 19 for storing the contents of the FAT area on the disk 11, and a CPU (Central Processing Unit) 20 for controlling these, Are connected via a bus 21.

  Further, a nonvolatile solid-state memory 22 may be further provided, and the recording area in the data recording device 4 may be a recording area composed of the disk 11 and the nonvolatile solid-state memory 22 to constitute a hybrid storage device. The nonvolatile solid-state memory 22 is used as a cache for temporarily storing data from the host device 2, stores a program used at startup, and is used as a part of a user area for storing user data. Can be. Since the nonvolatile solid-state memory 22 has fast access to data, for example, if data is written to or read from the nonvolatile solid-state memory 22 during a seek operation when data is written to or read from the disk 11, for example. The data transfer rate can be further improved.

  The HDD 4 receives a command issued from the host device 3 via the interface 3 by the interface control unit 18, and the interface control unit 18 understands the content and notifies the CPU 20 in the HDD 4. The CPU 20 sets necessary commands and parameters for the disk control unit 16, the read / write channel unit 15, and the servo control unit 14 based on the notification contents, and executes those operations. In addition, a replacement process of a defective sector in a disk cache area described later is performed.

  The servo control unit 14 performs drive control of the spindle motor 9 and the voice coil motor 11 to move the head with respect to predetermined tracks and sectors of the disk 11. The read / write channel section 15 encodes (modulates) the transmitted user data into a digital bit sequence suitable for the characteristics of the recording / reproducing system when writing to the disk 11. Also, at the time of reading, high frequency noise is removed from the reproduction signal read from the head, conversion from analog signal to digital signal is performed, data is estimated using maximum likelihood decoding, and then demodulation is performed. Play user data.

  The disk control unit 16 manages data exchange among the buffer memory 17, the read / write channel unit 15, and the interface control unit 18, and performs processing related to the data format. At this time, encoding processing using an error correction code, error detection, and error correction processing are also performed.

  Correspondingly, the host device 2 sends various commands to the HDD 4 in accordance with instructions from the host controller by processing of a central processing unit (CPU) 32 that secures a work area in the memory 31.

  In this process, the CPU 32 uploads data in the boot area, FAT area, and directory area, which are management data recorded in the system entry area of the disk 11, to the memory 31 by executing a predetermined processing procedure when the power is turned on. Various commands are sent out by setting parameters based on the uploaded data.

  Next, a data management method in this embodiment will be described. Data recorded on the disk 11 is managed in different address spaces in the host device 2 and the HDD 4. 2A is a diagram showing an LBA space P indicating an address space viewed from the host device 2 and a logical sector space Q indicating an address space viewed from the HDD 4, respectively.

  The minimum unit for recording data in the HDD 4 is called a sector, and its size is usually 512 bytes. In the HDD 4, the recording area of the disk 11 is managed in units of sectors, that is, a physical address, a physical sector number, and a logical sector number. The physical address is composed of a surface number, a track number, and a sector number. Here, the physical sector number is a number in which all sectors are numbered in order from the outside to the inside of the disk 11. The logical sector number is an address assigned by substitution processing to a defective sector that cannot be read or written.

  On the other hand, the host device 2 accesses the disk 11 using a logical block address (LBA) instead of the logical sector number. The file system for managing files uses a plurality of sectors (N) as one cluster as a minimum unit for reading and writing. In the following description, N = 16 and one cluster is 8 KByte. The cluster address is simply LBA divided by N.

  In the present embodiment, a special access size is set particularly for AV data. Hereinafter, this is referred to as a super cluster. One super cluster is composed of a plurality of clusters (integer multiples of clusters). For example, 16 clusters (128 KBytes) can be set as one super cluster. In this case, the super cluster address is 1/16 of the cluster address, that is, the last one digit is deleted in hexadecimal notation.

  Here, the recording area of the disk 11 is usually divided into three areas: a system area SA, a user area UA, and a system area SA_h for the HDD 4, and only the system area SA and the user area UA are viewed from the host device 2. The LBA space P is allocated as shown in the left diagram of FIG. 2A.

  The system area SA includes an area MBR in which a master boot record is recorded, an area in which an IPL (Initial Program Loader) that is a program necessary for system boot (startup) is recorded, and a FAT area in which FAT is recorded. And have. The master boot record MBR is a sector having an LBA of 0 when viewed from the host device 2, and a bootstrap code and a partition table are recorded here.

  The FAT (File Allocation Table) is a table that records how files are stored in the cluster. A file system that is managed using the FAT is called a FAT file system. This FAT file system uses two data: a FAT (File Allocation Table) used to indicate where individual files are arranged on a recording medium, and a directory item having information on directories and information on files. To do.

  Normally, as shown in FIG. 2A, a FAT and a root directory area A are provided on the disk 11, and the host device 2 sends the information necessary for file access from the recording / playback device via the PC interface. (SCSI (Small Computer System Interface), IDE (Integrated Drive Electronics), IEEE 1394, USB (Universal Serial Bus), etc.) are received and recording / reproduction control is performed based on these.

  For example, when writing a file to the HDD 4, the data is written to an empty cluster, and when the writing is completed, information indicating which cluster is to be used next is written to the FAT item. When erasing a file, the written data is left as it is, and the FAT item corresponding to the used cluster is set as an empty cluster.

  Further, at the time of reading, the starting cluster address of the file is searched from the directory item, the FAT item corresponding to the file is read to know which cluster has the file data to be read, and reading is performed from the disk 11 based on this information. FIG. 2B shows an example of FAT. For example, the HDD 4 acquires the start cluster address (12340h) of File 1 from the directory information and refers to the FAT, so that, for example, the first super cluster from the first super cluster to the second super cluster shown in FIG. Even in the case of jumping from 1234h to 3235h, the cluster address (up to EOF) at which the file ends can be obtained from the start cluster address and, for example, File1 consisting of the first super cluster to the sixth super cluster can be read out. .

  The user area UA includes a directory area UA1 for managing file information and an actual data area UA2. In the FAT file system before FAT32, the root directory belongs to the system area SA. In the directory area UA1, the file name, extension, attribute, latest update time, start cluster address, file size, and the like are stored as directory items for each directory (each file).

  The system area SA_h for the HDD 4 is used by the CPU 20 in the HDD 4 for storing boot codes and various tables or as an area for alternative processing. In the logical sector space P shown in the left diagram of FIG. The area (256 MByte) from 000000h to 07FFFFh in the logical sector number corresponds to it. Therefore, unlike the LBA space viewed from the host device 2, in the logical sector space, the logical sector number of the master boot record MBR is 080000h. Since the normal host device 2 does not directly access this area, it is omitted in the LBA space P shown in the right diagram of FIG. 2A.

  Next, a data writing method in the present embodiment will be described. First, the recording area of the disk 11 will be described. Super clusters for writing data are arranged in order from the top of the user area UA without a gap except for the root directory area and the like. As a result, the heads of the individual superclusters are arranged substantially evenly when viewed in the circumferential direction. This is because, in recent HDDs, the disk is divided into a plurality of zones such as 10 to 20, for example, and zone bit recording using the same writing frequency and recording / reproducing parameters (coefficients of waveform equivalent filter, etc.) is generally used in each zone. This is because the number of sectors included in the inner track and the outer track of the disk is different.

  An example is shown in FIG. 3 (Hitachi 4GB Micro drive 3K-4, Hard Disk Drive Specifications). It should be noted that if the super cluster size and the track size have too large greatest common divisors, the top of the super cluster will not be arranged separately when viewed in the circumferential direction.

  In this embodiment, the disk on which the super cluster is arranged as described above is further divided into a plurality of partial areas having substantially the same capacity. FIG. 4 is a diagram illustrating an example in which the number of areas is four. Since the capacity of each area is divided so as to be substantially the same based on the continuous data transfer rate, the width of each area becomes narrower toward the outer peripheral side of the disk. In FIG. 4, the total capacity is 4 GB, each area is 1 GB, LBA is 000000h to 1FFFFFh, area E1, LBA is 200000h to 3FFFFFh, area E2, LBA is 400000h to 5FFFFFh, area E3, and LBA is 600000h to 7FFFFFh. A case where the area is E4 is shown.

  Next, an operation for writing data in such a recording area will be described. Normally, management of address information for managing files on the disk 11 is performed by the host device 2 (hereinafter referred to as PC mode), but in this embodiment, the HDD 4 obtains permission from the host device 2. Is provided with an operation mode capable of executing FAT and its management. Hereinafter, this operation mode is referred to as an AV mode. If the HDD 4 is in the AV mode, the HDD 4 itself can perform FAT and its management. Here, the FAT and its management in the AV mode in the HDD 4 are performed by reading the FAT area data recorded in the system area SA into the memory 19 in the HDD 4 shown in FIG. 1 and updating the FAT on the memory 19. The HDD 4 is managed by updating the FAT on the system area SA as necessary, and writing the FAT updated on the memory 19 back to the FAT area of the system area SA when shifting to the PC mode. The host device 2 shares the FAT and its management exclusively.

  That is, in order to manage the address information for managing the file, it is necessary to manage the FAT on the system area SA and its management, and the directory information and its management. By switching, the host device 2 and the HDD 4 are exclusively shared. In the latter case, the HDD 4 is not managed, and a dedicated command is set so that the host apparatus 2 can directly access and manage the system area SA at any time, that is, in the PC mode or the AV mode. Shall.

  In the present embodiment, data writing is performed in the AV mode in which management of address information for managing files is performed in the HDD 4. As described above, the recording / reproducing system 1 shares the FAT information between the host device 2 and the HDD 4, but leaves the FAT and its management to the HDD 4. Accordingly, in order to write data, the AV mode is first shifted to. In order to shift to the AV mode, as shown in FIG. 5, the host apparatus 2 updates the FAT existing in the system area SA of the HDD 4, that is, the FAT area FA shown in FIG. A command for shifting from the PC mode to the AV mode is issued (step S1). The CPU 20 in the HDD 4 knows the content via the interface control unit 18, reads the FAT on the system area SA on the memory 19 (step S2), sets a flag indicating the AV mode, and sets the flag on the host device 2. It is notified that the mode has been changed to the AV mode (step S3).

  Next, a case where the host apparatus 2 performs writing after shifting to the AV mode will be described. Here, a case will be described as an example in which an operation for requesting writing of the content data is performed from the host device 2 when, for example, images are continuously shot by a digital camera. The host device 2 determines the file name (File1) of the content data, creates a new directory item, and writes the directory item to the HDD 4 (step S4). The directory item at this time is incomplete because the start cluster address and the latest update time are unknown.

  Next, the host device 2 sets parameters necessary for writing content data. Specifically, the start cluster address of the file and the access size of the file are determined. Although the host device 2 entrusts the management of the cluster address to the HDD 4, it is at least necessary to share the start cluster address in order to identify the file. FIG. 6A and FIG. 6B are diagrams showing an example of a command (Set Write File Parameter) for executing the command, and the register contents at the time of command issuance and the register contents at the end of the command, respectively. FIG. The command is defined as an AT vendor unique command and is executed only once before writing a file.

  The HDD 4 receiving the command performs writing based on a predetermined order indicating a predetermined basic order (basic sequence). Here, the basic sequence is set as area E1, area E2, area E3, area E4, area E4, area E3,..., For example, and the order is to access each area equally. The basic sequence is not limited to this order, and may be an order in which access from the area E1 to the area E4 is repeated, for example, area E1 →... → area E4 → area E1 →. That is, the order may be set so that each area can be accessed equally.

The HDD 4 refers to the FAT read into the memory 19, searches for a free super cluster from the area E1 according to the basic sequence, and notifies the host device 2 of the found free super cluster as a recording start cluster address (step S5). Then, it writes the address in the register at the end of a command as shown in Figure 6 (b). 2A shows an example in which the recording start cluster address of File1 is 12340h.

  Receiving the recording start cluster address, the host apparatus 2 writes the first super cluster SC1 of the file 1 as shown in FIG. Thereafter, the host device 2 sends data to the HDD 4 in units of super clusters. On the other hand, the HDD 4 writes to the notified recording start cluster address in the first super cluster, but thereafter searches for a free cluster and writes to the disk 11. In this way, it is determined whether or not the data transferred from the host device 2 is the last data of the file (end of file: EOF) (step S6), and the data is recorded in sequence and stored in the memory 19 in units of super clusters. The FAT is updated (step S7). If it is the final data of the file, the FAT processing on the memory 19 is written back to the FAT area of the disk 11 and the processing ends.

  Here, in the data writing method according to the present embodiment in step S7, as described above, the recording area (user area) is divided into a plurality of areas having substantially the same capacity based on the continuous data transfer rate, and the plurality of areas are divided. On the other hand, data is written according to the basic sequence set for the transfer data from the host device in a distributed manner on the disk 11.

  As a basic data writing method, there is a method of sequentially selecting areas and writing data according to a basic sequence. That is, after a super cluster is written in the first area, an empty super cluster in the next area is searched according to the basic sequence, and data is written in the searched empty super cluster. When there are a plurality of searched empty superclusters, for example, the one with the shortest access time can be selected.

  That is, when writing the second super cluster of File1, the HDD 4 searches for the FAT in the memory 19 and searches for an empty super cluster from the area E2 that is the next writing area. In most cases, multiple empty superclusters will be found, and you must choose an appropriate one according to the following method. A method for selecting an appropriate empty super cluster will be described.

Here, for simplicity, a case where two such empty superclusters are found will be described. As shown in FIG. 7, it is assumed that an empty supercluster SC2 and an empty supercluster SC2 ′ exist in the area E2. At this time, the angles from the end of the supercluster SC1 to the beginning of the empty superclusters SC2 and SC2 ′ are θ ₁ and θ ₂ , and the number of tracks (seek distance) between them is ΔTrk ₁ and ΔTrk ₂ , respectively. At this time, the time required to move from the end of the supercluster SC1 to the beginning of the empty superclusters SC2 and SC2 ′ is given as follows.

Travel time (last of SC1 → first of SC2)
= For {N = 0, N <infinity, N ++,
if (rotation waiting time (N, θ ₁ )> seek profile function (ΔTrk ₁ ))
Return [Rotation waiting time (N, θ ₁ )] Break [];
End if
}
Travel time (last of SC1 → first of SC2 ')
= For {N = 0, N <infinity, N ++,
if (rotation waiting time (N, θ ₂ )> seek profile function (ΔTrk ₂ ))
Return [Rotation waiting time (N, θ ₂ )] Break [];
End if
}

  Here, the movement time is a time generated when moving from the super cluster where the data is arranged to the beginning of the super cluster where the data is next arranged, that is, a time combining the seek time and the disk rotation time. The seek profile function is a function that outputs the time required to move by the number of tracks ΔTrk, and the rotation waiting time is a value obtained by adding the time required to rotate by an angle θ and the time required to rotate N (integer) rounds. Function. For the sake of simplicity, the part related to the head of the physical address is ignored.

In the present embodiment, in the case described above, the HDD 4 performs writing by selecting the smaller of the movement times to these two empty superclusters SC2 and SC2 ′. In the example shown in FIG. 2A, the super cluster address 3235h is selected, and data is written in this super cluster to become the second super cluster of File1. Hereinafter, the sum of the movement time to the Kth super cluster and the time taken for writing is referred to as a writing processing time T _K-1 . For simplicity, the first super cluster is ignored and K is set to 2 or more.

  In the present embodiment, the case where there are two empty superclusters has been described. Even when more empty superclusters can be selected, the seek operation and moving time are similarly calculated to select the smallest one. Can do. As the number of empty superclusters increases, the average value of the rotation waiting time is distributed uniformly on the circumference of the start address, and the average value of the rotation waiting time is (one rotation time). / (2 × number of empty superclusters in the area).

Similarly, as shown in FIG. 2A, the third super cluster, the fourth super cluster, and the fifth super cluster are respectively arranged in the super cluster addresses 5236h, 7237h, and 7250h of the areas E3, E4, and E4 according to the basic sequence. To do. Also, the time required until the third super cluster, the fourth super cluster, and the fifth super cluster are arranged, that is, the write processing time, which is the sum of the movement time to the super cluster + the write time, is expressed as T ₂ , T _3, and _{T 4.}

  Next, the sixth super cluster is written. In the present embodiment, there are two methods for writing the sixth super cluster. The first method is a first method of selecting an empty super cluster that satisfies the time limit from the area E3 that is the next sequential area of the area E4 according to the basic sequence as described above. In this case, as described above, an empty super cluster is searched in the area E3, and data is arranged in the empty super cluster with the shortest write processing time.

The other is a method that uses as much as possible the area on the inner circumference side where the data transfer rate is low, and is a second method that selects again the super cluster that satisfies the time limit from the area E4. This second method will be described with reference to FIG. FIG. 8A and FIG. 8B are flowcharts showing a writing method in the case of preferentially using the area on the inner circumference side where the data transfer rate is low. In order to apply the second method, the reference time T ₀ is used in the present embodiment. The reference time T ₀ is a time calculated from the minimum guaranteed transfer rate, specifically, the super cluster size divided by the minimum guaranteed transfer rate. HDD4 chose a super-cluster that is free from the area E4, to calculate the write processing time T ₅ in the same formula as described above. When there are a plurality of empty superclusters, the condition given by the following formula (1), that is, the average time of the write processing time (movement time + write time) required for the data write processing is the reference time from among them. Search for a condition that satisfies T ₀ or less. It should be noted that the parameter m is introduced into the equation (1) so that the value can be calculated at an arbitrary time. In this example, m = 0.

  In this case, since the empty super cluster candidate for writing the sixth super cluster is searched in the same area E4, the seek operation is short and the rotation waiting time becomes dominant. Therefore, it is only necessary to find a super cluster with a short rotation waiting time, and the probability of finding an empty super cluster that can satisfy the above formula (1) is increased by considering the rotation waiting time.

  Here, in the above formula (1), it is an average of the write processing time required for arranging the four super clusters in a predetermined area. The number of superclusters to be averaged over the write processing time required for data transfer is determined by the following two factors, for example. That is, one is the number of areas, and the other is the length of time (unit of time) when obtaining the minimum guaranteed transfer rate. For example, when the number of zones of the HDD 4 is around 10 and AV contents are handled, considering that the time for obtaining the minimum guaranteed transfer rate is about several seconds, the super cluster for obtaining the average time is as follows. The number is suitably about 5-10. For example, when the number of areas is four, it is preferable that the number of superclusters used when obtaining the average time is four or more, which is equal to or greater than the number of areas. This is because if it is less than the number of areas, the average time when super clusters are arranged in all areas cannot be obtained.

In this way, using the reference time T ₀ and writing data to the inner peripheral area where the data transfer rate is low, the areas E1, E2, E3, E4 are assigned to the first to fifth superclusters according to the basic sequence. , E4. Then, as shown in FIG. 8A, an empty super cluster in which the next sixth super cluster SC6 is arranged is searched in the area E4 (step S11).

  If there is no empty supercluster that satisfies the above formula (1) in the area E4, an empty supercluster is selected from the area E3 that is the next area according to the basic sequence (step S12). If there is nothing that satisfies the conditions even when considering the area E3, the area E4 and the area E3 having the shortest write processing time is selected (step S13), and the sixth super cluster is arranged in this area. Good.

  As a method for further shortening the data write processing time, not only the write processing time of the sixth super cluster but also the write processing time of the seventh super cluster which is the next write data can be considered. In the present embodiment, this is referred to as advance scheduling of an empty area.

That is, as shown in FIG. 8B, similarly area E4, if not found empty superclusters meeting the criteria time _{T 0} and search for empty supercluster area E3 (Step S21 and S22), the area E3, E4 Among them, the one with the shortest write processing time is selected. Here, the write processing time is calculated on the assumption that the seventh super cluster as the next data is written in the next area E2. As this case was also described above, for example, in the formula (1), m = 1 obtains an average of four super cluster writing processing time as it may become less than the reference time T _0. Here, when prior scheduling is performed, if an empty super cluster satisfying both the areas E4 and E3 is searched, the data may be written with priority over the area E4 on the inner circumference side where the data transfer speed is low. Good. Further, after step S21, the sixth super cluster SC6 is written in the area E4 and the write processing time is calculated when the seventh super cluster is written in the area E3 (preceding scheduling). Only when there is not, you may make it progress to step S22.

  In the above, an example of a method for arranging data in units of super clusters has been described. However, there are also other methods for preferentially using a region having a low transfer rate in view of processing time for the basic sequence. That is, in the present embodiment, the basic sequence is to sequentially select the area from the outer periphery side to the inner periphery side, and from the inner periphery side to the outer periphery side, but as described above, from the outer periphery side to the inner periphery side. You may make it repeat selecting sequentially. Further, the start area of the basic sequence is not limited to the outer peripheral side, and may be started from any area.

Further, with respect to a method of preferentially using an area having a low transfer rate, an area E4 having a low data transfer rate is added to the basic sequence as shown in FIG. 8A, or an empty area is used as shown in FIG. 8B. In addition to the method of pre-scheduling the area E4 so that the area E4 is used more preferentially, it is possible to use an area with a low data transfer rate efficiently by combining these to dynamically determine the area to be written. it can. Also, how to obtain the reference time T _0, by appropriately selecting the such as the number of superclusters for obtaining the average of the write processing time can be achieved write processing time recording and reproduction systems require.

Next, the effect in this Embodiment is demonstrated. FIG. 9 shows the result of calculating the data write processing time for each area when the reference time T ₀ is 60 ms and the rotation speed is 3600 rpm (rotation time 16.7 ms).

In FIG. 9, the time unit is ms, and N indicates the number of super clusters that can be selected in the area. The transfer time (T1) is the data write time, and the total time (T3) is the sum of the transfer time (T1), the maximum seek time (T2) across the area, and the average rotation waiting time (T3). And corresponds to the above-described write processing time. There are four areas E1 to E4.

If the four areas E1 to E4 are equally used, the transfer time is 63.33 ms when N = 1, 57.08 ms when N = 4, and less than the reference time T ₀ when N = 4. The restriction (condition) of being able to be satisfied. Further, if the basic sequence is followed after the data is arranged in the area E4, the data is originally arranged in the area E3. At this time, when there is a margin in the average of the total time, the empty super cluster in the area E4 can be used again by the function of preferentially arranging the data in the area where the data transfer rate is low. As already described, the time required for moving the head in the area is dominated by the rotation waiting time, so even if it is about several ms, there is a high possibility that it will fall within the reference time on average.

  In this embodiment, although there is a restriction on the addresses that can be taken as the recording start cluster address, the recording start cluster is arranged almost randomly on the disk 11, and the location of the super cluster to be used is the writing at that time. By dynamically determining according to a plurality of conditions such as processing time, reference time and average time of writing processing time, it is possible to optimize the waiting time between rotations and guarantee the transfer speed. In this way, the rotation waiting time is controlled stochastically, and the data writing processing time consisting of the data writing time (transfer time) + seek time + rotation waiting time, that is, the time actually required for data transfer is reduced. The arrangement can be changed dynamically, and a highly accurate speed can be ensured.

  Even if the initial orderly data arrangement is broken due to editing or the like, and the empty area is fragmented, the performance is hardly affected by the above-described writing method.

  In addition, since it has a function that preferentially uses the inner area when placing data, an area with a high transfer rate remains with the passage of time, and as a result, the average transfer rate increases. .

  As described above, it is difficult to use a region having a low transfer rate by using the region having a high transfer rate, or to repeatedly obtain a continuous free region by repeatedly writing and erasing data. Thus, the problem in the conventional data recording apparatus that the transfer speed is greatly reduced due to the fact that one file is divided and recorded in many non-consecutive clusters (usually fragmentation) is solved, and the data is By writing, the transfer speed can be improved, and real-time performance can be reliably ensured for a long time.

  It should be noted that the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the scope of the present invention.

It is a block diagram which shows the recording / reproducing system in embodiment of this invention. 3 is a diagram showing an LBA space P indicating an address space viewed from the host device 2 and a logical sector space Q indicating an address space viewed from the HDD 4. FIG. It is a figure which shows an example of FAT. It is a figure explaining an example of the number of sectors contained in the track of a disk. It is a schematic diagram which shows the example which divided the recording area of the disc into four areas. It is a flowchart which shows the write-in operation | movement of the data in the recording / reproducing system in embodiment of this invention. (A) And (b) is a figure which shows one example (Set Write File Parameter) of the command which performs it. FIG. 3 is a schematic diagram showing a first super cluster SC1 and second super clusters SC1, SC2 'of file 1. It is a flowchart which shows the writing method in the case of using preferentially the area | region of the inner peripheral side with a slow data transfer speed. 12 is a flowchart showing another example of a writing method when an inner peripheral area with a low data transfer rate is used preferentially. Reference time 60ms to _{T 0,} when the rotational speed was 3600 rpm (rotation time 16.7 ms), is a diagram illustrating the results of calculating the data write processing time for each area.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Recording / reproducing system, 2 Host apparatus, 3 Interface, 4 HDD, 11 Disc, 12 Spindle motor, 13 Voice coil motor, 14 Servo control part, 15 Read / write channel part, 16 Hard disk control part, 17 Buffer memory, 18 Interface control Part, 19, 21 memory, 20, 22 CPU, 21 bus

Claims (11)

In a data recording apparatus for recording transfer data transferred from a host device on a rotating recording medium having a recording area with different transfer speeds depending on recording positions,
Control means for dividing the recording area into a plurality of partial areas having substantially the same capacity, and controlling the transfer data to be distributed and written in the divided partial areas;
The control means selects the plurality of partial areas in a predetermined basic order so as to be used at substantially the same frequency, and the data transfer time in the first predetermined partial area to be written next in accordance with the basic order A data recording device that controls to search for an empty area that satisfies a condition that is less than a predetermined time and to write partial data constituting the transfer data in the corresponding empty area . When satisfying the empty area in which the data transfer time is less than the predetermined time it is found more, the data recording apparatus according to claim 1, wherein selecting an empty area where the data transfer time is minimized. The data recording apparatus according to claim 2 , wherein the data transfer time is a time obtained by combining a seek operation of the head and a rotation waiting time of the disk and a writing time of the partial data. The control means is configured to perform writing next to the first scheduled partial area according to the first data transfer time and the basic order when the first partial data is written in the first scheduled partial area. Search the first and second scheduled partial areas for empty areas that satisfy the condition that the sum of the second data transfer time and the second data transfer time when the second partial data is written in the two scheduled partial areas is less than a predetermined time. and, the data recording apparatus of the respective claim 1 for controlling to write the first and second partial data. The control means has a transfer rate monitoring function for monitoring the transfer rate of the transfer data, and the transfer rate of the transfer data is faster than the minimum guaranteed rate for guaranteeing the minimum value, and the basic order 2. The data recording apparatus according to claim 1, wherein when there is a partial area having a slower transfer speed than the partial area in accordance with the data transfer, the transfer data is controlled to be written in the partial area having a slower transfer speed. A memory for storing a table for managing transfer data transferred from the host device as a file;
The table is recorded in a predetermined area of the recording area,
The control unit reads the table into the memory in response to a predetermined mode switching command from the host device, and searches for an empty area in the recording area with reference to the read table. Data recording device. The data recording apparatus according to claim 6 , wherein the file includes a plurality of super clusters, and each super cluster has a size that is an integral multiple of a cluster that is an access unit of the host apparatus. In a data recording method for recording transfer data transferred from a host device on a rotating recording medium having a recording area with different transfer speeds depending on recording positions,
A control step of dividing the recording area into a plurality of partial areas having substantially the same capacity and controlling the transfer data to be distributed and written in the divided partial areas;
In the control step, the plurality of partial areas are selected in a predetermined basic order so as to be used at substantially the same frequency, and the data transfer time in the first predetermined partial area to be written next in accordance with the basic order A data recording method for controlling to search for an empty area that satisfies a condition that is less than a predetermined time and to write partial data constituting the transfer data in the corresponding empty area . In the control step, the first scheduled data is written next to the first scheduled partial area according to the first data transfer time and the basic order when the first partial data is written in the first scheduled partial area. Search the first and second scheduled partial areas for empty areas that satisfy the condition that the sum of the second data transfer time and the second data transfer time when the second partial data is written in the two scheduled partial areas is less than a predetermined time. The data recording method according to claim 8 , wherein each of the first and second partial data is controlled to be written. In the control step, the transfer rate of the transfer data is monitored by a transfer rate monitoring function, and the transfer rate of the transfer data is faster than the minimum guaranteed rate for guaranteeing the minimum value, and the basic order is followed. The data recording method according to claim 8 , wherein when there is a partial area having a slower transfer speed than the partial area, the transfer data is controlled to be written in the partial area having the slower transfer speed. In a recording / reproducing system having a host device and a data recording device for recording transfer data transferred from the host device on a rotary recording medium having a recording area having a transfer speed different depending on a recording position.
The data recording device is
Control means for dividing the recording area into a plurality of partial areas having substantially the same capacity, and controlling the transfer data to be distributed and written in the divided partial areas;
The control means selects the plurality of partial areas in a predetermined basic order so as to be used at substantially the same frequency, and the data transfer time in the first predetermined partial area to be written next in accordance with the basic order A recording / reproducing system that searches for an empty area that satisfies a condition that is less than a predetermined time and writes the partial data constituting the transfer data in the corresponding empty area .

Images